Merge branch 'develop' into add_nmm_to_detections to resolve conflicts

This commit is contained in:
mario-dg
2024-04-09 18:50:55 +02:00
192 changed files with 24333 additions and 4793 deletions
+16
View File
@@ -0,0 +1,16 @@
version: 2
updates:
# GitHub Actions
- package-ecosystem: "github-actions"
directory: "/"
schedule:
interval: "daily"
commit-message:
prefix: ⬆️
# Python
- package-ecosystem: "pip"
directory: "/"
schedule:
interval: "daily"
commit-message:
prefix: ⬆️
+33
View File
@@ -0,0 +1,33 @@
name: Clear cache
on:
schedule:
- cron: '0 0 1 * *'
workflow_dispatch:
permissions:
actions: write
jobs:
clear-cache:
runs-on: ubuntu-latest
steps:
- name: Clear cache
uses: actions/github-script@v7
with:
script: |
console.log("About to clear")
const caches = await github.rest.actions.getActionsCacheList({
owner: context.repo.owner,
repo: context.repo.repo,
})
for (const cache of caches.data.actions_caches) {
console.log(cache)
github.rest.actions.deleteActionsCacheById({
owner: context.repo.owner,
repo: context.repo.repo,
cache_id: cache.id,
})
}
console.log("Clear completed")
+43 -9
View File
@@ -1,19 +1,53 @@
name: Docs WorkFlow
name: Docs WorkFlow - Develop Tag 📚
on:
push:
branches:
- master
- main
- develop
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.ref}}
cancel-in-progress: true
permissions:
contents: write
pages: write
pull-requests: write
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
- name: 🔄 Checkout code
uses: actions/checkout@v4
with:
python-version: 3.x
- run: pip install mkdocs-material
- run: pip install "mkdocstrings[python]"
- run: mkdocs gh-deploy --force
fetch-depth: 0
- name: 🐍 Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: 📦 Install mkdocs-material
run: pip install "mkdocs-material"
- name: 📦 Install mkdocstrings[python]
run: pip install "mkdocstrings[python]"
- name: 📦 Install mkdocs-material[imaging]
run: pip install "mkdocs-material[imaging]"
- name: 📦 Install mike
run: pip install "mike"
- name: 📦 Install mkdocs-git-revision-date-localized-plugin
run: pip install "mkdocs-git-revision-date-localized-plugin"
- name: 📦 Install JupyterLab
run: pip install jupyterlab
- name: 📦 Install mkdocs-jupyter
run: pip install mkdocs-jupyter
- name: 📦 Install mkdocs-git-committers-plugin-2
run: pip install mkdocs-git-committers-plugin-2
- name: ⚙️ Configure git for github-actions
run: |
git config --global user.name "github-actions[bot]"
git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
- name: 🚀 Deploy MkDoc-Material with mike
run: |
MKDOCS_GIT_COMMITTERS_APIKEY=${{ secrets.GITHUB_TOKEN }} mike deploy --push develop
+10 -8
View File
@@ -6,22 +6,24 @@ on:
- '[0-9]+.[0-9]+[0-9]+.[0-9]+b[0-9]'
- '[0-9]+.[0-9]+[0-9]+.[0-9]+rc[0-9]'
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
jobs:
build-n-publish:
name: Build and publish to PyPI
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.10"]
steps:
- name: Checkout source
uses: actions/checkout@v3
- name: 🐍 Set up Python 3.8 environment for build
uses: actions/setup-python@v4
- name: 🛎️ Checkout
uses: actions/checkout@v4
with:
python-version: "3.8"
ref: ${{ github.head_ref }}
- name: 🐍 Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: 🏗️ Build source and wheel distributions
run: |
+3 -6
View File
@@ -3,10 +3,7 @@ on:
push:
tags:
- '[0-9]+.[0-9]+[0-9]+.[0-9]'
- '[0-9]+.[0-9]+[0-9]+.[0-9]'
- '[0-9]+.[0-9]+[0-9]+.[0-9]'
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
jobs:
@@ -14,14 +11,14 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.8]
python-version: ["3.10"]
steps:
- name: 🛎️ Checkout
uses: actions/checkout@v3
uses: actions/checkout@v4
with:
ref: ${{ github.head_ref }}
- name: 🐍 Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
+34
View File
@@ -0,0 +1,34 @@
name: 🧪 Docs Test WorkFlow 📚
on:
pull_request:
branches: [main, develop]
jobs:
docs-build-test:
runs-on: ubuntu-latest
steps:
- name: 🔄 Checkout code
uses: actions/checkout@v4
- name: 🐍 Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: 📦 Install mkdocs-material
run: pip install "mkdocs-material[all]"
- name: 📦 Install mkdocstrings[python]
run: pip install "mkdocstrings[python]"
- name: 📦 Install mkdocs-material[imaging]
run: pip install "mkdocs-material[imaging]"
- name: 📦 Install mike
run: pip install "mike"
- name: 📦 Install mkdocs-git-revision-date-localized-plugin
run: pip install "mkdocs-git-revision-date-localized-plugin"
- name: 📦 Install JupyterLab
run: pip install jupyterlab
- name: 📦 Install mkdocs-jupyter
run: pip install mkdocs-jupyter
- name: 📦 Install mkdocs-git-committers-plugin-2
run: pip install mkdocs-git-committers-plugin-2
- name: 🧪 Test documentation build
run: mkdocs build --verbose
+58
View File
@@ -0,0 +1,58 @@
name: Python 3.8 - Min Dep Test WorkFlow
on:
pull_request:
branches: [main, develop]
jobs:
build-min-dep-test:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.8"]
steps:
- name: 🛎️ Checkout
uses: actions/checkout@v4
- name: 🐍 Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
# id based on python version
id: python-setup
with:
python-version: ${{ matrix.python-version }}
check-latest: true
- name: 📦 Install dependencies
run: |
python -m pip install --upgrade pip
pip install \
attrs==23.1.0 \
certifi==2023.7.22 \
charset-normalizer==2.0.12 \
cycler==0.12.1 \
exceptiongroup==1.1.3 \
fonttools==4.43.1 \
idna==3.4 \
iniconfig==2.0.0 \
kiwisolver==1.4.5 \
matplotlib==3.5.0 \
numpy==1.21.2 \
opencv-python==4.5.5.64 \
Pillow==10.1.0 \
packaging==23.2 \
pluggy==1.3.0 \
pyparsing==3.1.1 \
pytest==7.2.0 \
python-dateutil==2.8.2 \
PyYAML==5.3 \
requests==2.26.0 \
scipy==1.10.0 \
setuptools-scm==8.0.4 \
six==1.16.0 \
tomli==2.0.1 \
tqdm==4.62.3 \
typing_extensions==4.8.0 \
urllib3==1.26.18 \
defusedxml==0.7.1
- name: 🧪 Test
run: "python -m pytest ./test"
+9 -6
View File
@@ -5,22 +5,25 @@ on:
branches: [main, develop]
jobs:
build:
build-dev-test:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.8", "3.9", "3.10","3.11"]
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
steps:
- name: 🛎️ Checkout
uses: actions/checkout@v3
uses: actions/checkout@v4
- name: 🐍 Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: 🦾 Install dependencies
check-latest: true
- name: 📦 Install dependencies
run: |
python -m pip install --upgrade pip
pip install -e .
pip install .
pip install pytest
- name: 🧪 Test
run: "python -m pytest ./test"
+1 -1
View File
@@ -11,7 +11,7 @@ jobs:
name: 👋 Welcome
runs-on: ubuntu-latest
steps:
- uses: actions/first-interaction@v1.1.1
- uses: actions/first-interaction@v1.3.0
with:
repo-token: ${{ secrets.GITHUB_TOKEN }}
issue-message: "Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap."
+20 -2
View File
@@ -133,5 +133,23 @@ dmypy.json
# Pyre type checker
.pyre/
# Notebooks
notebooks/
# OSX folder attributes
.DS_Store
.AppleDouble
.LSOverride
# Thumbnails
._*
# Files that might appear on external disk
.Spotlight-V100
.Trashes
# Windows
Thumbs.db
Desktop.ini
# Linux
*~
.directory
.Trash-*
+8 -31
View File
@@ -7,18 +7,17 @@ ci:
repos:
- repo: https://github.com/pre-commit/pre-commit-hooks
rev: v4.5.0
rev: v4.6.0
hooks:
- id: end-of-file-fixer
- id: trailing-whitespace
exclude: test/.*\.py
- id: check-yaml
- id: check-docstring-first
exclude: mkdocs.yml
- id: check-executables-have-shebangs
- id: check-toml
- id: check-case-conflict
- id: check-added-large-files
args: ['--maxkb=2048']
exclude: ^logo/
- id: detect-private-key
- id: forbid-new-submodules
- id: pretty-format-json
@@ -27,50 +26,28 @@ repos:
- id: end-of-file-fixer
- id: mixed-line-ending
# - repo: https://github.com/asottile/pyupgrade
# rev: v3.9.0
# hooks:
# - id: pyupgrade
# name: Upgrade code
# args: [--py38-plus]
- repo: https://github.com/PyCQA/flake8
rev: 6.1.0
hooks:
- id: flake8
name: Flake8 Checks
entry: flake8
additional_dependencies: [Flake8-pyproject]
- repo: https://github.com/PyCQA/bandit
rev: '1.7.5'
rev: '1.7.8'
hooks:
- id: bandit
args: ["-c", "pyproject.toml"]
additional_dependencies: ["bandit[toml]"]
- repo: https://github.com/pycqa/isort
rev: 5.12.0
rev: 5.13.2
hooks:
- id: isort
name: isort (python)
- id: isort
name: isort (cython)
types: [cython]
- id: isort
name: isort (pyi)
types: [pyi]
- repo: https://github.com/psf/black
rev: 23.9.1
hooks:
- id: black
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.0.292
rev: v0.3.5
hooks:
- id: ruff
args: [--fix, --exit-non-zero-on-fix]
- id: ruff-format
types_or: [ python, pyi, jupyter ]
+1 -1
View File
@@ -15,7 +15,7 @@ url: 'https://roboflow.github.io/supervision/'
abstract: >-
supervision features a range of utilities for use in
computer vision projects, from detections processing and
filtering to confusion matrix calcuation.
filtering to confusion matrix calculation.
keywords:
- computer vision
- image processing
+16 -3
View File
@@ -52,7 +52,7 @@ git push -u origin main
### Pre-commit tool
This project utilizes the [pre-commit](https://pre-commit.com/) tool to maintain code quality and consistency. Before submitting a pull request or making any commits, it is important to run the pre-commit tool to ensure that your changes meet the project's guidelines.
This project uses the [pre-commit](https://pre-commit.com/) tool to maintain code quality and consistency. Before submitting a pull request or making any commits, it is important to run the pre-commit tool to ensure that your changes meet the project's guidelines.
Furthermore, we have integrated a pre-commit GitHub Action into our workflow. This means that with every pull request opened, the pre-commit checks will be automatically enforced, streamlining the code review process and ensuring that all contributions adhere to our quality standards.
@@ -76,7 +76,6 @@ All new functions and classes in `supervision` should include docstrings. This i
So far, **there is no type checking with mypy**. See [issue](https://github.com/roboflow-ai/template-python/issues/4).
Then, go back to your fork of the `supervision` repository, click "Pull Requests", and click "New Pull Request".
![Opening a pull request](https://media.roboflow.com/open_pr.png)
@@ -109,10 +108,24 @@ PRs must pass all tests and linting requirements before they can be merged.
The `supervision` documentation is stored in a folder called `docs`. The project documentation is built using `mkdocs`.
To run the documentation, install the project requirements with `poetry install dev`. Then, run `mkdocs serve` to start the documentation server.
To run the documentation, install the project requirements with `poetry install --with dev`. Then, run `mkdocs serve` to start the documentation server.
You can learn more about mkdocs on the [mkdocs website](https://www.mkdocs.org/).
## 🧑‍🍳 cookbooks
We are always looking for new examples and cookbooks to add to the `supervision`
documentation. If you have a use case that you think would be helpful to others, please
submit a PR with your example. Here are some guidelines for submitting a new example:
- Create a new notebook in the [`docs/nodebooks`](https://github.com/roboflow/supervision/tree/develop/docs/notebooks) folder.
- Add a link to the new notebook in [`docs/theme/cookbooks.html`](https://github.com/roboflow/supervision/blob/develop/docs/theme/cookbooks.html). Make sure to add the path to the new notebook, as well as a title, labels, author and supervision version.
- Use the [Count Objects Crossing the Line](https://supervision.roboflow.com/develop/notebooks/count-objects-crossing-the-line/) example as a template for your new example.
- Freeze the version of `supervision` you are using.
- Place an appropriate Open in Colab button at the top of the notebook. You can find an example of such a button in the aforementioned `Count Objects Crossing the Line` cookbook.
- Notebook should be self-contained. If you rely on external data ( videos, images, etc.) or libraries, include download and installation commands in the notebook.
- Annotate the code with appropriate comments, including links to the documentation describing each of the tools you have used.
## 🧪 tests
[`pytests`](https://docs.pytest.org/en/7.1.x/) is used to run our tests.
+151 -213
View File
@@ -1,6 +1,6 @@
<div align="center">
<p>
<a align="center" href="" target="_blank">
<a align="center" href="" target="https://supervision.roboflow.com">
<img
width="100%"
src="https://media.roboflow.com/open-source/supervision/rf-supervision-banner.png?updatedAt=1678995927529"
@@ -10,289 +10,226 @@
<br>
[notebooks](https://github.com/roboflow/notebooks) | [inference](https://github.com/roboflow/inference) | [autodistill](https://github.com/autodistill/autodistill) | [collect](https://github.com/roboflow/roboflow-collect)
[notebooks](https://github.com/roboflow/notebooks) | [inference](https://github.com/roboflow/inference) | [autodistill](https://github.com/autodistill/autodistill) | [maestro](https://github.com/roboflow/multimodal-maestro)
<br>
[![version](https://badge.fury.io/py/supervision.svg)](https://badge.fury.io/py/supervision)
[![downloads](https://img.shields.io/pypi/dm/supervision)](https://pypistats.org/packages/supervision)
[![license](https://img.shields.io/pypi/l/supervision)](https://github.com/roboflow/supervision/blob/main/LICENSE.md)
[![python-version](https://img.shields.io/pypi/pyversions/supervision)](https://badge.fury.io/py/supervision)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb)
[![Discord](https://img.shields.io/discord/1159501506232451173)](https://discord.gg/GbfgXGJ8Bk)
[![version](https://badge.fury.io/py/supervision.svg)](https://badge.fury.io/py/supervision)
[![downloads](https://img.shields.io/pypi/dm/supervision)](https://pypistats.org/packages/supervision)
[![license](https://img.shields.io/pypi/l/supervision)](https://github.com/roboflow/supervision/blob/main/LICENSE.md)
[![python-version](https://img.shields.io/pypi/pyversions/supervision)](https://badge.fury.io/py/supervision)
[![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb)
[![gradio](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/Roboflow/Annotators)
[![discord](https://img.shields.io/discord/1159501506232451173)](https://discord.gg/GbfgXGJ8Bk)
[![built-with-material-for-mkdocs](https://img.shields.io/badge/Material_for_MkDocs-526CFE?logo=MaterialForMkDocs&logoColor=white)](https://squidfunk.github.io/mkdocs-material/)
</div>
<a href="https://github.com/roboflow/supervision/issues?q=is%3Aissue+label%3Ahacktoberfest+">
<img width="100%" src="https://media.roboflow.com/open-source/supervision/hacktoberfest-banner-3.png">
</a>
## 👋 hello
**We write your reusable computer vision tools.** Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us! 🤝
[![supervision-hackfest](https://github.com/roboflow/supervision/assets/26109316/c05cc954-b9a6-4ed5-9a52-d0b4b619ff65)](https://github.com/orgs/roboflow/projects/10)
## 💻 install
Pip install the supervision package in a
[**3.11>=Python>=3.8**](https://www.python.org/) environment.
[**Python>=3.8**](https://www.python.org/) environment.
```bash
pip install supervision[desktop]
pip install supervision
```
Read more about desktop, headless, and local installation in our [guide](https://roboflow.github.io/supervision/).
Read more about conda, mamba, and installing from source in our [guide](https://roboflow.github.io/supervision/).
## 🔥 quickstart
### [detections processing](https://roboflow.github.io/supervision/detection/core/)
### models
Supervision was designed to be model agnostic. Just plug in any classification, detection, or segmentation model. For your convenience, we have created [connectors](https://supervision.roboflow.com/latest/detection/core/#detections) for the most popular libraries like Ultralytics, Transformers, or MMDetection.
```python
>>> import supervision as sv
>>> from ultralytics import YOLO
import cv2
import supervision as sv
from ultralytics import YOLO
>>> model = YOLO('yolov8s.pt')
>>> result = model(IMAGE)[0]
>>> detections = sv.Detections.from_ultralytics(result)
image = cv2.imread(...)
model = YOLO('yolov8s.pt')
result = model(image)[0]
detections = sv.Detections.from_ultralytics(result)
>>> len(detections)
5
len(detections)
# 5
```
<details close>
<summary>👉 more detections utils</summary>
<details>
<summary>👉 more model connectors</summary>
- Easily switch inference pipeline between supported object detection/instance segmentation models
- inference
Running with [Inference](https://github.com/roboflow/inference) requires a [Roboflow API KEY](https://docs.roboflow.com/api-reference/authentication#retrieve-an-api-key).
```python
>>> import supervision as sv
>>> from segment_anything import sam_model_registry, SamAutomaticMaskGenerator
import cv2
import supervision as sv
from inference.models.utils import get_roboflow_model
>>> sam = sam_model_registry[MODEL_TYPE](checkpoint=CHECKPOINT_PATH).to(device=DEVICE)
>>> mask_generator = SamAutomaticMaskGenerator(sam)
>>> sam_result = mask_generator.generate(IMAGE)
>>> detections = sv.Detections.from_sam(sam_result=sam_result)
```
image = cv2.imread(...)
model = get_roboflow_model(model_id="yolov8s-640", api_key=<ROBOFLOW API KEY>)
result = model.infer(image)[0]
detections = sv.Detections.from_inference(result)
- [Advanced filtering](https://roboflow.github.io/supervision/quickstart/detections/)
len(detections)
# 5
```python
>>> detections = detections[detections.class_id == 0]
>>> detections = detections[detections.confidence > 0.5]
>>> detections = detections[detections.area > 1000]
```
- Image annotation
```python
>>> import supervision as sv
>>> box_annotator = sv.BoxAnnotator()
>>> annotated_frame = box_annotator.annotate(
... scene=IMAGE,
... detections=detections
... )
```
</details>
### [datasets processing](https://roboflow.github.io/supervision/dataset/core/)
### annotators
Supervision offers a wide range of highly customizable [annotators](https://supervision.roboflow.com/latest/annotators/), allowing you to compose the perfect visualization for your use case.
```python
>>> import supervision as sv
import cv2
import supervision as sv
>>> dataset = sv.DetectionDataset.from_yolo(
... images_directory_path='...',
... annotations_directory_path='...',
... data_yaml_path='...'
... )
image = cv2.imread(...)
detections = sv.Detections(...)
>>> dataset.classes
bounding_box_annotator = sv.BoundingBoxAnnotator()
annotated_frame = bounding_box_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
https://github.com/roboflow/supervision/assets/26109316/691e219c-0565-4403-9218-ab5644f39bce
### datasets
Supervision provides a set of [utils](https://supervision.roboflow.com/latest/datasets/) that allow you to load, split, merge, and save datasets in one of the supported formats.
```python
import supervision as sv
dataset = sv.DetectionDataset.from_yolo(
images_directory_path=...,
annotations_directory_path=...,
data_yaml_path=...
)
dataset.classes
['dog', 'person']
>>> len(dataset)
1000
len(dataset)
# 1000
```
<details close>
<summary>👉 more dataset utils</summary>
- Load object detection/instance segmentation datasets in one of the supported formats
- load
```python
>>> dataset = sv.DetectionDataset.from_yolo(
... images_directory_path='...',
... annotations_directory_path='...',
... data_yaml_path='...'
... )
```python
dataset = sv.DetectionDataset.from_yolo(
images_directory_path=...,
annotations_directory_path=...,
data_yaml_path=...
)
>>> dataset = sv.DetectionDataset.from_pascal_voc(
... images_directory_path='...',
... annotations_directory_path='...'
... )
dataset = sv.DetectionDataset.from_pascal_voc(
images_directory_path=...,
annotations_directory_path=...
)
>>> dataset = sv.DetectionDataset.from_coco(
... images_directory_path='...',
... annotations_path='...'
... )
```
dataset = sv.DetectionDataset.from_coco(
images_directory_path=...,
annotations_path=...
)
```
- Loop over dataset entries
- split
```python
>>> for name, image, labels in dataset:
... print(labels.xyxy)
```python
train_dataset, test_dataset = dataset.split(split_ratio=0.7)
test_dataset, valid_dataset = test_dataset.split(split_ratio=0.5)
array([[404. , 719. , 538. , 884.5 ],
[155. , 497. , 404. , 833.5 ],
[ 20.154999, 347.825 , 416.125 , 915.895 ]], dtype=float32)
```
len(train_dataset), len(test_dataset), len(valid_dataset)
# (700, 150, 150)
```
- Split dataset for training, testing, and validation
- merge
```python
>>> train_dataset, test_dataset = dataset.split(split_ratio=0.7)
>>> test_dataset, valid_dataset = test_dataset.split(split_ratio=0.5)
```python
ds_1 = sv.DetectionDataset(...)
len(ds_1)
# 100
ds_1.classes
# ['dog', 'person']
>>> len(train_dataset), len(test_dataset), len(valid_dataset)
(700, 150, 150)
```
ds_2 = sv.DetectionDataset(...)
len(ds_2)
# 200
ds_2.classes
# ['cat']
- Merge multiple datasets
ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
len(ds_merged)
# 300
ds_merged.classes
# ['cat', 'dog', 'person']
```
```python
>>> ds_1 = sv.DetectionDataset(...)
>>> len(ds_1)
100
>>> ds_1.classes
['dog', 'person']
- save
>>> ds_2 = sv.DetectionDataset(...)
>>> len(ds_2)
200
>>> ds_2.classes
['cat']
```python
dataset.as_yolo(
images_directory_path=...,
annotations_directory_path=...,
data_yaml_path=...
)
>>> ds_merged = sv.DetectionDataset.merge([ds_1, ds_2])
>>> len(ds_merged)
300
>>> ds_merged.classes
['cat', 'dog', 'person']
```
dataset.as_pascal_voc(
images_directory_path=...,
annotations_directory_path=...
)
- Save object detection/instance segmentation datasets in one of the supported formats
dataset.as_coco(
images_directory_path=...,
annotations_path=...
)
```
```python
>>> dataset.as_yolo(
... images_directory_path='...',
... annotations_directory_path='...',
... data_yaml_path='...'
... )
- convert
>>> dataset.as_pascal_voc(
... images_directory_path='...',
... annotations_directory_path='...'
... )
>>> dataset.as_coco(
... images_directory_path='...',
... annotations_path='...'
... )
```
- Convert labels between supported formats
```python
>>> sv.DetectionDataset.from_yolo(
... images_directory_path='...',
... annotations_directory_path='...',
... data_yaml_path='...'
... ).as_pascal_voc(
... images_directory_path='...',
... annotations_directory_path='...'
... )
```
- Load classification datasets in one of the supported formats
```python
>>> cs = sv.ClassificationDataset.from_folder_structure(
... root_directory_path='...'
... )
```
- Save classification datasets in one of the supported formats
```python
>>> cs.as_folder_structure(
... root_directory_path='...'
... )
```
</details>
### [model evaluation](https://roboflow.github.io/supervision/metrics/detection/)
```python
>>> import supervision as sv
>>> dataset = sv.DetectionDataset.from_yolo(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
... ...
>>> confusion_matrix = sv.ConfusionMatrix.benchmark(
... dataset = dataset,
... callback = callback
... )
>>> confusion_matrix.matrix
array([
[0., 0., 0., 0.],
[0., 1., 0., 1.],
[0., 1., 1., 0.],
[1., 1., 0., 0.]
])
```
<details close>
<summary>👉 more metrics</summary>
- Mean average precision (mAP) for object detection tasks.
```python
>>> import supervision as sv
>>> dataset = sv.DetectionDataset.from_yolo(...)
>>> def callback(image: np.ndarray) -> sv.Detections:
... ...
>>> mean_average_precision = sv.MeanAveragePrecision.benchmark(
... dataset = dataset,
... callback = callback
... )
>>> mean_average_precision.map50_95
0.433
```
```python
sv.DetectionDataset.from_yolo(
images_directory_path=...,
annotations_directory_path=...,
data_yaml_path=...
).as_pascal_voc(
images_directory_path=...,
annotations_directory_path=...
)
```
</details>
## 🎬 tutorials
<p align="left">
<a href="https://youtu.be/4Q3ut7vqD5o" title="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking"><img src="https://github.com/roboflow/supervision/assets/26109316/54afdf1c-218c-4451-8f12-627fb85f1682" alt="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking" width="300px" align="left" /></a>
<a href="https://youtu.be/4Q3ut7vqD5o" title="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking"><strong>Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking</strong></a>
<div><strong>Created: 6 Sep 2023</strong> | <strong>Updated: 6 Sep 2023</strong></div>
<br/> In this video, we explore real-time traffic analysis using YOLOv8 and ByteTrack to detect and track vehicles on aerial images. Harnessing the power of Python and Supervision, we delve deep into assigning cars to specific entry zones and understanding their direction of movement. By visualizing their paths, we gain insights into traffic flow across bustling roundabouts... </p>
<a href="https://youtu.be/uWP6UjDeZvY" title="Speed Estimation & Vehicle Tracking | Computer Vision | Open Source"><img src="https://github.com/SkalskiP/SkalskiP/assets/26109316/61a444c8-b135-48ce-b979-2a5ab47c5a91" alt="Speed Estimation & Vehicle Tracking | Computer Vision | Open Source" width="300px" align="left" /></a>
<a href="https://youtu.be/uWP6UjDeZvY" title="Speed Estimation & Vehicle Tracking | Computer Vision | Open Source"><strong>Speed Estimation & Vehicle Tracking | Computer Vision | Open Source</strong></a>
<div><strong>Created: 11 Jan 2024</strong> | <strong>Updated: 11 Jan 2024</strong></div>
<br/> Learn how to track and estimate the speed of vehicles using YOLO, ByteTrack, and Roboflow Inference. This comprehensive tutorial covers object detection, multi-object tracking, filtering detections, perspective transformation, speed estimation, visualization improvements, and more.</p>
<br/>
<p align="left">
<a href="https://youtu.be/D-D6ZmadzPE" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><img src="https://github.com/SkalskiP/SkalskiP/assets/26109316/6913ff11-53c6-4341-8d90-eaff3023c3fd" alt="SAM - Segment Anything Model by Meta AI: Complete Guide" width="300px" align="left" /></a>
<a href="https://youtu.be/D-D6ZmadzPE" title="SAM - Segment Anything Model by Meta AI: Complete Guide"><strong>SAM - Segment Anything Model by Meta AI: Complete Guide</strong></a>
<div><strong>Created: 11 Apr 2023</strong> | <strong>Updated: 11 Apr 2023</strong></div>
<br/> Discover the incredible potential of Meta AI's Segment Anything Model (SAM)! We dive into SAM, an efficient and promptable model for image segmentation, which has revolutionized computer vision tasks. With over 1 billion masks on 11M licensed and privacy-respecting images, SAM's zero-shot performance is often competitive with or even superior to prior fully supervised results... </p>
<a href="https://youtu.be/4Q3ut7vqD5o" title="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking"><img src="https://github.com/roboflow/supervision/assets/26109316/54afdf1c-218c-4451-8f12-627fb85f1682" alt="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking" width="300px" align="left" /></a>
<a href="https://youtu.be/4Q3ut7vqD5o" title="Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking"><strong>Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking</strong></a>
<div><strong>Created: 6 Sep 2023</strong> | <strong>Updated: 6 Sep 2023</strong></div>
<br/> In this video, we explore real-time traffic analysis using YOLOv8 and ByteTrack to detect and track vehicles on aerial images. Harnessing the power of Python and Supervision, we delve deep into assigning cars to specific entry zones and understanding their direction of movement. By visualizing their paths, we gain insights into traffic flow across bustling roundabouts... </p>
## 💜 built with supervision
@@ -302,6 +239,8 @@ https://user-images.githubusercontent.com/26109316/207858600-ee862b22-0353-440b-
https://github.com/roboflow/supervision/assets/26109316/c9436828-9fbf-4c25-ae8c-60e9c81b3900
https://github.com/roboflow/supervision/assets/26109316/3ac6982f-4943-4108-9b7f-51787ef1a69f
## 📚 documentation
Visit our [documentation](https://roboflow.github.io/supervision) page to learn how supervision can help you build computer vision applications faster and more reliably.
@@ -363,5 +302,4 @@ We love your input! Please see our [contributing guide](https://github.com/robof
</a>
</a>
</div>
</div>
Vendored
+1342 -1322
View File
File diff suppressed because one or more lines are too long
+367 -93
View File
@@ -1,16 +1,23 @@
---
comments: true
status: new
---
# Annotators
=== "BoundingBox"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> bounding_box_annotator = sv.BoundingBoxAnnotator()
>>> annotated_frame = bounding_box_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
bounding_box_annotator = sv.BoundingBoxAnnotator()
annotated_frame = bounding_box_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -19,19 +26,40 @@
</div>
=== "RoundBox"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
round_box_annotator = sv.RoundBoxAnnotator()
annotated_frame = round_box_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![round-box-annotator-example](https://media.roboflow.com/supervision-annotator-examples/round-box-annotator-example-purple.png){ align=center width="800" }
</div>
=== "BoxCorner"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> corner_annotator = sv.BoxCornerAnnotator()
>>> annotated_frame = corner_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
corner_annotator = sv.BoxCornerAnnotator()
annotated_frame = corner_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -40,19 +68,19 @@
</div>
=== "BoxMask"
=== "Color"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> box_mask_annotator = sv.BoxMaskAnnotator()
>>> annotated_frame = box_mask_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
color_annotator = sv.ColorAnnotator()
annotated_frame = color_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -64,16 +92,16 @@
=== "Circle"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> circle_annotator = sv.CircleAnnotator()
>>> annotated_frame = circle_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
circle_annotator = sv.CircleAnnotator()
annotated_frame = circle_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -82,19 +110,61 @@
</div>
=== "Dot"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
dot_annotator = sv.DotAnnotator()
annotated_frame = dot_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![dot-annotator-example](https://media.roboflow.com/supervision-annotator-examples/dot-annotator-example-purple.png){ align=center width="800" }
</div>
=== "Triangle"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
triangle_annotator = sv.TriangleAnnotator()
annotated_frame = triangle_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![triangle-annotator-example](https://media.roboflow.com/supervision-annotator-examples/triangle-annotator-example.png){ align=center width="800" }
</div>
=== "Ellipse"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> ellipse_annotator = sv.EllipseAnnotator()
>>> annotated_frame = ellipse_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
ellipse_annotator = sv.EllipseAnnotator()
annotated_frame = ellipse_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -106,37 +176,58 @@
=== "Halo"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> halo_annotator = sv.HaloAnnotator()
>>> annotated_frame = halo_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
halo_annotator = sv.HaloAnnotator()
annotated_frame = halo_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![ellipse-annotator-example](https://media.roboflow.com/supervision-annotator-examples/halo-annotator-example-purple.png){ align=center width="800" }
![halo-annotator-example](https://media.roboflow.com/supervision-annotator-examples/halo-annotator-example-purple.png){ align=center width="800" }
</div>
=== "PercentageBar"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
percentage_bar_annotator = sv.PercentageBarAnnotator()
annotated_frame = percentage_bar_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![percentage-bar-annotator-example](https://media.roboflow.com/supervision-annotator-examples/percentage-bar-annotator-example-purple.png){ align=center width="800" }
</div>
=== "Mask"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> mask_annotator = sv.MaskAnnotator()
>>> annotated_frame = mask_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
mask_annotator = sv.MaskAnnotator()
annotated_frame = mask_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -145,19 +236,47 @@
</div>
=== "Polygon"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
polygon_annotator = sv.PolygonAnnotator()
annotated_frame = polygon_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![polygon-annotator-example](https://media.roboflow.com/supervision-annotator-examples/polygon-annotator-example-purple.png){ align=center width="800" }
</div>
=== "Label"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
>>> annotated_frame = label_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
annotated_frame = label_annotator.annotate(
scene=image.copy(),
detections=detections,
labels=labels
)
```
<div class="result" markdown>
@@ -166,19 +285,34 @@
</div>
=== "Crop"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
crop_annotator = sv.CropAnnotator()
annotated_frame = crop_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
=== "Blur"
```python
>>> import supervision as sv
import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
image = ...
detections = sv.Detections(...)
>>> blur_annotator = sv.BlurAnnotator()
>>> annotated_frame = blur_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
blur_annotator = sv.BlurAnnotator()
annotated_frame = blur_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
@@ -187,19 +321,50 @@
</div>
=== "Pixelate"
```python
import supervision as sv
image = ...
detections = sv.Detections(...)
pixelate_annotator = sv.PixelateAnnotator()
annotated_frame = pixelate_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
<div class="result" markdown>
![pixelate-annotator-example](https://media.roboflow.com/supervision-annotator-examples/pixelate-annotator-example-10.png){ align=center width="800" }
</div>
=== "Trace"
```python
>>> import supervision as sv
import supervision as sv
from ultralytics import YOLO
>>> image = ...
>>> detections = sv.Detections(...)
model = YOLO('yolov8x.pt')
>>> trace_annotator = sv.TraceAnnotator()
>>> annotated_frame = trace_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
trace_annotator = sv.TraceAnnotator()
video_info = sv.VideoInfo.from_video_path(video_path='...')
frames_generator = get_video_frames_generator(source_path='...')
tracker = sv.ByteTrack()
with sv.VideoSink(target_path='...', video_info=video_info) as sink:
for frame in frames_generator:
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
detections = tracker.update_with_detections(detections)
annotated_frame = trace_annotator.annotate(
scene=frame.copy(),
detections=detections)
sink.write_frame(frame=annotated_frame)
```
<div class="result" markdown>
@@ -208,42 +373,151 @@
</div>
## BoundingBoxAnnotator
=== "HeatMap"
```python
import supervision as sv
from ultralytics import YOLO
model = YOLO('yolov8x.pt')
heat_map_annotator = sv.HeatMapAnnotator()
video_info = sv.VideoInfo.from_video_path(video_path='...')
frames_generator = get_video_frames_generator(source_path='...')
with sv.VideoSink(target_path='...', video_info=video_info) as sink:
for frame in frames_generator:
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
annotated_frame = heat_map_annotator.annotate(
scene=frame.copy(),
detections=detections)
sink.write_frame(frame=annotated_frame)
```
<div class="result" markdown>
![heat-map-annotator-example](https://media.roboflow.com/supervision-annotator-examples/heat-map-annotator-example-purple.png){ align=center width="800" }
</div>
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.BoundingBoxAnnotator">BoundingBoxAnnotator</a></h2>
</div>
:::supervision.annotators.core.BoundingBoxAnnotator
## BoxCornerAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.RoundBoxAnnotator">RoundBoxAnnotator</a></h2>
</div>
:::supervision.annotators.core.RoundBoxAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.BoxCornerAnnotator">BoxCornerAnnotator</a></h2>
</div>
:::supervision.annotators.core.BoxCornerAnnotator
## BoxMaskAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.OrientedBoxAnnotator">OrientedBoxAnnotator</a></h2>
</div>
:::supervision.annotators.core.BoxMaskAnnotator
:::supervision.annotators.core.OrientedBoxAnnotator
## CircleAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.ColorAnnotator">ColorAnnotator</a></h2>
</div>
:::supervision.annotators.core.ColorAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.CircleAnnotator">CircleAnnotator</a></h2>
</div>
:::supervision.annotators.core.CircleAnnotator
## EllipseAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.DotAnnotator">DotAnnotator</a></h2>
</div>
:::supervision.annotators.core.DotAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.TriangleAnnotator">TriangleAnnotator</a></h2>
</div>
:::supervision.annotators.core.TriangleAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.EllipseAnnotator">EllipseAnnotator</a></h2>
</div>
:::supervision.annotators.core.EllipseAnnotator
## HaloAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.HaloAnnotator">HaloAnnotator</a></h2>
</div>
:::supervision.annotators.core.HaloAnnotator
## MaskAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.PercentageBarAnnotator">PercentageBarAnnotator</a></h2>
</div>
:::supervision.annotators.core.PercentageBarAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.HeatMapAnnotator">HeatMapAnnotator</a></h2>
</div>
:::supervision.annotators.core.HeatMapAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.MaskAnnotator">MaskAnnotator</a></h2>
</div>
:::supervision.annotators.core.MaskAnnotator
## LabelAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.PolygonAnnotator">PolygonAnnotator</a></h2>
</div>
:::supervision.annotators.core.PolygonAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.LabelAnnotator">LabelAnnotator</a></h2>
</div>
:::supervision.annotators.core.LabelAnnotator
## BlurAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.BlurAnnotator">BlurAnnotator</a></h2>
</div>
:::supervision.annotators.core.BlurAnnotator
## TraceAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.PixelateAnnotator">PixelateAnnotator</a></h2>
</div>
:::supervision.annotators.core.PixelateAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.TraceAnnotator">TraceAnnotator</a></h2>
</div>
:::supervision.annotators.core.TraceAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.CropAnnotator">CropAnnotator</a></h2>
</div>
:::supervision.annotators.core.CropAnnotator
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.ColorLookup">ColorLookup</a></h2>
</div>
:::supervision.annotators.utils.ColorLookup
+31
View File
@@ -0,0 +1,31 @@
---
comments: true
---
# Assets
Supervision offers an assets download utility that allows you to download video files
that you can use in your demos.
## Install extra
To install the Supervision assets utility, you can use `pip`. This utility is available
as an extra within the Supervision package.
!!! example "pip install"
```bash
pip install "supervision[assets]"
```
<div class="md-typeset">
<h2>download_assets</h2>
</div>
:::supervision.assets.downloader.download_assets
<div class="md-typeset">
<h2>VideoAssets</h2>
</div>
:::supervision.assets.list.VideoAssets
Binary file not shown.

After

Width:  |  Height:  |  Size: 19 KiB

+297 -46
View File
@@ -1,18 +1,269 @@
### 0.19.0 <small>March 15, 2024</small>
- Added [#818](https://github.com/roboflow/supervision/pull/818): [`sv.CSVSink`](/0.19.0/detection/tools/save_detections/#supervision.detection.tools.csv_sink.CSVSink) allowing for the straightforward saving of image, video, or stream inference results in a `.csv` file.
```python
import supervision as sv
from ultralytics import YOLO
model = YOLO(<SOURCE_MODEL_PATH>)
csv_sink = sv.CSVSink(<RESULT_CSV_FILE_PATH>)
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)
with csv_sink:
for frame in frames_generator:
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
csv_sink.append(detections, custom_data={<CUSTOM_LABEL>:<CUSTOM_DATA>})
```
- Added [#819](https://github.com/roboflow/supervision/pull/819): [`sv.JSONSink`](/0.19.0/detection/tools/save_detections/#supervision.detection.tools.csv_sink.JSONSink) allowing for the straightforward saving of image, video, or stream inference results in a `.json` file.
```python
```python
import supervision as sv
from ultralytics import YOLO
model = YOLO(<SOURCE_MODEL_PATH>)
json_sink = sv.JSONSink(<RESULT_JSON_FILE_PATH>)
frames_generator = sv.get_video_frames_generator(<SOURCE_VIDEO_PATH>)
with json_sink:
for frame in frames_generator:
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
json_sink.append(detections, custom_data={<CUSTOM_LABEL>:<CUSTOM_DATA>})
```
- Added [#847](https://github.com/roboflow/supervision/pull/847): [`sv.mask_iou_batch`](/0.19.0/detection/utils/#supervision.detection.utils.mask_iou_batch) allowing to compute Intersection over Union (IoU) of two sets of masks.
- Added [#847](https://github.com/roboflow/supervision/pull/847): [`sv.mask_non_max_suppression`](/0.19.0/detection/utils/#supervision.detection.utils.mask_non_max_suppression) allowing to perform Non-Maximum Suppression (NMS) on segmentation predictions.
- Added [#888](https://github.com/roboflow/supervision/pull/888): [`sv.CropAnnotator`](/0.19.0/annotators/#supervision.annotators.core.CropAnnotator) allowing users to annotate the scene with scaled-up crops of detections.
```python
import cv2
import supervision as sv
from inference import get_model
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = get_model(model_id="yolov8n-640")
result = model.infer(image)[0]
detections = sv.Detections.from_inference(result)
crop_annotator = sv.CropAnnotator()
annotated_frame = crop_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
- Changed [#827](https://github.com/roboflow/supervision/pull/827): [`sv.ByteTrack.reset`](/0.19.0/tracking/#supervision.tracking.ByteTrack.reset) allowing users to clear trackers state, enabling the processing of multiple video files in sequence.
- Changed [#802](https://github.com/roboflow/supervision/pull/802): [`sv.LineZoneAnnotator`](/0.19.0/detection/tools/line_zone/#supervision.detection.line_zone.LineZone) allowing to hide in/out count using `display_in_count` and `display_out_count` properties.
- Changed [#787](https://github.com/roboflow/supervision/pull/787): [`sv.ByteTrack`](/0.19.0/tracking/#supervision.tracking.ByteTrack) input arguments and docstrings updated to improve readability and ease of use.
!!! failure "Deprecated"
The `track_buffer`, `track_thresh`, and `match_thresh` parameters in `sv.ByterTrack` are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
- Changed [#910](https://github.com/roboflow/supervision/pull/910): [`sv.PolygonZone`](/0.19.0/detection/tools/polygon_zone/#supervision.detection.tools.polygon_zone.PolygonZone) to now accept a list of specific box anchors that must be in zone for a detection to be counted.
!!! failure "Deprecated"
The `triggering_position ` parameter in `sv.PolygonZone` is deprecated and will be removed in `supervision-0.23.0`. Use `triggering_anchors` instead.
- Changed [#875](https://github.com/roboflow/supervision/pull/875): annotators adding support for Pillow images. All supervision Annotators can now accept an image as either a numpy array or a Pillow Image. They automatically detect its type, draw annotations, and return the output in the same format as the input.
- Fixed [#944](https://github.com/roboflow/supervision/pull/944): [`sv.DetectionsSmoother`](/0.19.0/detection/tools/smoother/#supervision.detection.tools.smoother.DetectionsSmoother) removing `tracking_id` from `sv.Detections`.
### 0.18.0 <small>January 25, 2024</small>
- Added [#720](https://github.com/roboflow/supervision/pull/720): [`sv.PercentageBarAnnotator`](/0.18.0/annotators/#percentagebarannotator) allowing to annotate images and videos with percentage values representing confidence or other custom property.
```python
>>> import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
>>> percentage_bar_annotator = sv.PercentageBarAnnotator()
>>> annotated_frame = percentage_bar_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
```
- Added [#702](https://github.com/roboflow/supervision/pull/702): [`sv.RoundBoxAnnotator`](/0.18.0/annotators/#roundboxannotator) allowing to annotate images and videos with rounded corners bounding boxes.
- Added [#770](https://github.com/roboflow/supervision/pull/770): [`sv.OrientedBoxAnnotator`](/0.18.0/annotators/#orientedboxannotator) allowing to annotate images and videos with OBB (Oriented Bounding Boxes).
```python
import cv2
import supervision as sv
from ultralytics import YOLO
image = cv2.imread(<SOURCE_IMAGE_PATH>)
model = YOLO("yolov8n-obb.pt")
result = model(image)[0]
detections = sv.Detections.from_ultralytics(result)
oriented_box_annotator = sv.OrientedBoxAnnotator()
annotated_frame = oriented_box_annotator.annotate(
scene=image.copy(),
detections=detections
)
```
- Added [#696](https://github.com/roboflow/supervision/pull/696): [`sv.DetectionsSmoother`](/0.18.0/detection/tools/smoother/#detection-smoother) allowing for smoothing detections over multiple frames in video tracking.
- Added [#769](https://github.com/roboflow/supervision/pull/769): [`sv.ColorPalette.from_matplotlib`](/0.18.0/draw/color/#supervision.draw.color.ColorPalette.from_matplotlib) allowing users to create a `sv.ColorPalette` instance from a Matplotlib color palette.
```python
>>> import supervision as sv
>>> sv.ColorPalette.from_matplotlib('viridis', 5)
ColorPalette(colors=[Color(r=68, g=1, b=84), Color(r=59, g=82, b=139), ...])
```
- Changed [#770](https://github.com/roboflow/supervision/pull/770): [`sv.Detections.from_ultralytics`](/0.18.0/detection/core/#supervision.detection.core.Detections.from_ultralytics) adding support for OBB (Oriented Bounding Boxes).
- Changed [#735](https://github.com/roboflow/supervision/pull/735): [`sv.LineZone`](/0.18.0/detection/tools/line_zone/#linezone) to now accept a list of specific box anchors that must cross the line for a detection to be counted. This update marks a significant improvement from the previous requirement, where all four box corners were necessary. Users can now specify a single anchor, such as `sv.Position.BOTTOM_CENTER`, or any other combination of anchors defined as `List[sv.Position]`.
- Changed [#756](https://github.com/roboflow/supervision/pull/756): [`sv.Color`](/0.18.0/draw/color/#color)'s and [`sv.ColorPalette`](/0.18.0/draw/color/#colorpalette)'s method of accessing predefined colors, transitioning from a function-based approach (`sv.Color.red()`) to a more intuitive and conventional property-based method (`sv.Color.RED`).
!!! failure "Deprecated"
`sv.ColorPalette.default()` is deprecated and will be removed in `supervision-0.22.0`. Use `sv.ColorPalette.DEFAULT` instead.
- Changed [#769](https://github.com/roboflow/supervision/pull/769): [`sv.ColorPalette.DEFAULT`](/0.18.0/draw/color/#colorpalette) value, giving users a more extensive set of annotation colors.
- Changed [#677](https://github.com/roboflow/supervision/pull/677): `sv.Detections.from_roboflow` to [`sv.Detections.from_inference`](/0.18.0/detection/core/#supervision.detection.core.Detections.from_inference) streamlining its functionality to be compatible with both the both [inference](https://github.com/roboflow/inference) pip package and the Robloflow [hosted API](https://docs.roboflow.com/deploy/hosted-api).
!!! failure "Deprecated"
`Detections.from_roboflow()` is deprecated and will be removed in `supervision-0.22.0`. Use `Detections.from_inference` instead.
- Fixed [#735](https://github.com/roboflow/supervision/pull/735): [`sv.LineZone`](/0.18.0/detection/tools/line_zone/#linezone) functionality to accurately update the counter when an object crosses a line from any direction, including from the side. This enhancement enables more precise tracking and analytics, such as calculating individual in/out counts for each lane on the road.
### 0.17.0 <small>December 06, 2023</small>
- Added [#633](https://github.com/roboflow/supervision/pull/633): [`sv.PixelateAnnotator`](/0.17.0/annotators/#supervision.annotators.core.PixelateAnnotator) allowing to pixelate objects on images and videos.
- Added [#652](https://github.com/roboflow/supervision/pull/652): [`sv.TriangleAnnotator`](/0.17.0/annotators/#supervision.annotators.core.TriangleAnnotator) allowing to annotate images and videos with triangle markers.
- Added [#602](https://github.com/roboflow/supervision/pull/602): [`sv.PolygonAnnotator`](/0.17.0/annotators/#supervision.annotators.core.PolygonAnnotator) allowing to annotate images and videos with segmentation mask outline.
```python
>>> import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
>>> polygon_annotator = sv.PolygonAnnotator()
>>> annotated_frame = polygon_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
```
- Added [#476](https://github.com/roboflow/supervision/pull/476): [`sv.assets`](/0.18.0/assets/) allowing download of video files that you can use in your demos.
```python
>>> from supervision.assets import download_assets, VideoAssets
>>> download_assets(VideoAssets.VEHICLES)
"vehicles.mp4"
```
- Added [#605](https://github.com/roboflow/supervision/pull/605): [`Position.CENTER_OF_MASS`](/0.17.0/geometry/core/#position) allowing to place labels in center of mass of segmentation masks.
- Added [#651](https://github.com/roboflow/supervision/pull/651): [`sv.scale_boxes`](/0.17.0/detection/utils/#supervision.detection.utils.scale_boxes) allowing to scale [`sv.Detections.xyxy`](/0.17.0/detection/core/#supervision.detection.core.Detections) values.
- Added [#637](https://github.com/roboflow/supervision/pull/637): [`sv.calculate_dynamic_text_scale`](/0.17.0/draw/utils/#supervision.draw.utils.calculate_dynamic_text_scale) and [`sv.calculate_dynamic_line_thickness`](/0.17.0/draw/utils/#supervision.draw.utils.calculate_dynamic_line_thickness) allowing text scale and line thickness to match image resolution.
- Added [#620](https://github.com/roboflow/supervision/pull/620): [`sv.Color.as_hex`](/0.17.0/draw/color/#supervision.draw.color.Color.as_hex) allowing to extract color value in HEX format.
- Added [#572](https://github.com/roboflow/supervision/pull/572): [`sv.Classifications.from_timm`](/0.17.0/classification/core/#supervision.classification.core.Classifications.from_timm) allowing to load classification result from [timm](https://huggingface.co/docs/hub/timm) models.
- Added [#478](https://github.com/roboflow/supervision/pull/478): [`sv.Classifications.from_clip`](/0.17.0/classification/core/#supervision.classification.core.Classifications.from_clip) allowing to load classification result from [clip](https://github.com/openai/clip) model.
- Added [#571](https://github.com/roboflow/supervision/pull/571): [`sv.Detections.from_azure_analyze_image`](/0.17.0/detection/core/#supervision.detection.core.Detections.from_azure_analyze_image) allowing to load detection results from [Azure Image Analysis](https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection-40).
- Changed [#646](https://github.com/roboflow/supervision/pull/646): `sv.BoxMaskAnnotator` renaming it to [`sv.ColorAnnotator`](/0.17.0/annotators/#supervision.annotators.core.ColorAnnotator).
- Changed [#606](https://github.com/roboflow/supervision/pull/606): [`sv.MaskAnnotator`](/0.17.0/annotators/#supervision.annotators.core.MaskAnnotator) to make it **5x faster**.
- Fixed [#584](https://github.com/roboflow/supervision/pull/584): [`sv.DetectionDataset.from_yolo`](/0.17.0/datasets/#supervision.dataset.core.DetectionDataset.from_yolo) to ignore empty lines in annotation files.
- Fixed [#555](https://github.com/roboflow/supervision/pull/555): [`sv.BlurAnnotator`](/0.17.0/annotators/#supervision.annotators.core.BlurAnnotator) to trim negative coordinates before bluring detections.
- Fixed [#511](https://github.com/roboflow/supervision/pull/511): [`sv.TraceAnnotator`](/0.17.0/annotators/#supervision.annotators.core.TraceAnnotator) to respect trace position.
### 0.16.0 <small>October 19, 2023</small>
- Added [#422](https://github.com/roboflow/supervision/pull/422): [`sv.BoxMaskAnnotator`](/0.16.0/annotators/#supervision.annotators.core.BoxMaskAnnotator) allowing to annotate images and videos with mox masks.
- Added [#433](https://github.com/roboflow/supervision/pull/433): [`sv.HaloAnnotator`](/0.16.0/annotators/#supervision.annotators.core.HaloAnnotator) allowing to annotate images and videos with halo effect.
```python
>>> import supervision as sv
>>> image = ...
>>> detections = sv.Detections(...)
>>> halo_annotator = sv.HaloAnnotator()
>>> annotated_frame = halo_annotator.annotate(
... scene=image.copy(),
... detections=detections
... )
```
- Added [#466](https://github.com/roboflow/supervision/pull/466): [`sv.HeatMapAnnotator`](/0.16.0/annotators/#supervision.annotators.core.HeatMapAnnotator) allowing to annotate videos with heat maps.
- Added [#492](https://github.com/roboflow/supervision/pull/492): [`sv.DotAnnotator`](/0.16.0/annotators/#supervision.annotators.core.DotAnnotator) allowing to annotate images and videos with dots.
- Added [#449](https://github.com/roboflow/supervision/pull/449): [`sv.draw_image`](/0.16.0/draw/utils/#supervision.draw.utils.draw_image) allowing to draw an image onto a given scene with specified opacity and dimensions.
- Added [#280](https://github.com/roboflow/supervision/pull/280): [`sv.FPSMonitor`](/0.16.0/utils/video/#supervision.utils.video.FPSMonitor) for monitoring frames per second (FPS) to benchmark latency.
- Added [#454](https://github.com/roboflow/supervision/pull/454): 🤗 Hugging Face Annotators [space](https://huggingface.co/spaces/Roboflow/Annotators).
- Changed [#482](https://github.com/roboflow/supervision/pull/482): [`sv.LineZone.trigger`](/0.16.0/detection/tools/line_zone/#supervision.detection.line_counter.LineZone.trigger) now return `Tuple[np.ndarray, np.ndarray]`. The first array indicates which detections have crossed the line from outside to inside. The second array indicates which detections have crossed the line from inside to outside.
- Changed [#465](https://github.com/roboflow/supervision/pull/465): Annotator argument name from `color_map: str` to `color_lookup: ColorLookup` enum to increase type safety.
- Changed [#426](https://github.com/roboflow/supervision/pull/426): [`sv.MaskAnnotator`](/0.16.0/annotators/#supervision.annotators.core.MaskAnnotator) allowing 2x faster annotation.
- Fixed [#477](https://github.com/roboflow/supervision/pull/477): Poetry env definition allowing proper local installation.
- Fixed [#430](https://github.com/roboflow/supervision/pull/430): [`sv.ByteTrack`](/0.16.0/trackers/#supervision.tracker.byte_tracker.core.ByteTrack) to return `np.array([], dtype=int)` when `svDetections` is empty.
!!! failure "Deprecated"
`sv.Detections.from_yolov8` and `sv.Classifications.from_yolov8` as those are now replaced by [`sv.Detections.from_ultralytics`](/0.16.0/detection/core/#supervision.detection.core.Detections.from_ultralytics) and [`sv.Classifications.from_ultralytics`](/0.16.0/classification/core/#supervision.classification.core.Classifications.from_ultralytics).
### 0.15.0 <small>October 5, 2023</small>
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.BoundingBoxAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.BoundingBoxAnnotator) allowing to annotate images and videos with bounding boxes.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.BoundingBoxAnnotator`](/0.15.0/annotators/#supervision.annotators.core.BoundingBoxAnnotator) allowing to annotate images and videos with bounding boxes.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.BoxCornerAnnotator `](https://supervision.roboflow.com/annotators/#supervision.annotators.core.BoxCornerAnnotator) allowing to annotate images and videos with just bounding box corners.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.BoxCornerAnnotator `](/0.15.0/annotators/#supervision.annotators.core.BoxCornerAnnotator) allowing to annotate images and videos with just bounding box corners.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.MaskAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.MaskAnnotator) allowing to annotate images and videos with segmentation masks.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.MaskAnnotator`](/0.15.0/annotators/#supervision.annotators.core.MaskAnnotator) allowing to annotate images and videos with segmentation masks.
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.EllipseAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.EllipseAnnotator) allowing to annotate images and videos with ellipses (sports game style).
- Added [#170](https://github.com/roboflow/supervision/pull/170): [`sv.EllipseAnnotator`](/0.15.0/annotators/#supervision.annotators.core.EllipseAnnotator) allowing to annotate images and videos with ellipses (sports game style).
- Added [#386](https://github.com/roboflow/supervision/pull/386): [`sv.CircleAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.CircleAnnotator) allowing to annotate images and videos with circles.
- Added [#386](https://github.com/roboflow/supervision/pull/386): [`sv.CircleAnnotator`](/0.15.0/annotators/#supervision.annotators.core.CircleAnnotator) allowing to annotate images and videos with circles.
- Added [#354](https://github.com/roboflow/supervision/pull/354): [`sv.TraceAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.TraceAnnotator) allowing to draw path of moving objects on videos.
- Added [#354](https://github.com/roboflow/supervision/pull/354): [`sv.TraceAnnotator`](/0.15.0/annotators/#supervision.annotators.core.TraceAnnotator) allowing to draw path of moving objects on videos.
- Added [#405](https://github.com/roboflow/supervision/pull/405): [`sv.BlurAnnotator`](https://supervision.roboflow.com/annotators/#supervision.annotators.core.BlurAnnotator) allowing to blur objects on images and videos.
- Added [#405](https://github.com/roboflow/supervision/pull/405): [`sv.BlurAnnotator`](/0.15.0/annotators/#supervision.annotators.core.BlurAnnotator) allowing to blur objects on images and videos.
```python
>>> import supervision as sv
@@ -29,17 +280,17 @@
- Added [#354](https://github.com/roboflow/supervision/pull/354): Supervision usage [example](https://github.com/roboflow/supervision/tree/develop/examples/traffic_analysis). You can now learn how to perform traffic flow analysis with Supervision.
- Changed [#399](https://github.com/roboflow/supervision/pull/399): [`sv.Detections.from_roboflow`](https://supervision.roboflow.com/detection/core/#supervision.detection.core.Detections.from_roboflow) now does not require `class_list` to be specified. The `class_id` value can be extracted directly from the [inference](https://github.com/roboflow/inference) response.
- Changed [#399](https://github.com/roboflow/supervision/pull/399): [`sv.Detections.from_roboflow`](/0.15.0/detection/core/#supervision.detection.core.Detections.from_roboflow) now does not require `class_list` to be specified. The `class_id` value can be extracted directly from the [inference](https://github.com/roboflow/inference) response.
- Changed [#381](https://github.com/roboflow/supervision/pull/381): [`sv.VideoSink`](https://supervision.roboflow.com/utils/video/#videosink) now allows to customize the output codec.
- Changed [#381](https://github.com/roboflow/supervision/pull/381): [`sv.VideoSink`](/0.15.0/utils/video/#videosink) now allows to customize the output codec.
- Changed [#361](https://github.com/roboflow/supervision/pull/361): [`sv.InferenceSlicer`](https://supervision.roboflow.com/detection/tools/inference_slicer/#supervision.detection.tools.inference_slicer.InferenceSlicer) can now operate in multithreading mode.
- Changed [#361](https://github.com/roboflow/supervision/pull/361): [`sv.InferenceSlicer`](/0.15.0/detection/tools/inference_slicer/#supervision.detection.tools.inference_slicer.InferenceSlicer) can now operate in multithreading mode.
- Fixed [#348](https://github.com/roboflow/supervision/pull/348): [`sv.Detections.from_deepsparse`](https://supervision.roboflow.com/detection/core/#supervision.detection.core.Detections.from_deepsparse) to allow processing empty [deepsparse](https://github.com/neuralmagic/deepsparse) result object.
- Fixed [#348](https://github.com/roboflow/supervision/pull/348): [`sv.Detections.from_deepsparse`](/0.15.0/detection/core/#supervision.detection.core.Detections.from_deepsparse) to allow processing empty [deepsparse](https://github.com/neuralmagic/deepsparse) result object.
### 0.14.0 <small>August 31, 2023</small>
- Added [#282](https://github.com/roboflow/supervision/pull/282): support for SAHI inference technique with [`sv.InferenceSlicer`](https://supervision.roboflow.com/detection/tools/inference_slicer).
- Added [#282](https://github.com/roboflow/supervision/pull/282): support for SAHI inference technique with [`sv.InferenceSlicer`](/0.14.0/detection/tools/inference_slicer).
```python
>>> import cv2
@@ -58,23 +309,23 @@
>>> detections = slicer(image)
```
- Added [#297](https://github.com/roboflow/supervision/pull/297): [`Detections.from_deepsparse`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_deepsparse) to enable seamless integration with [DeepSparse](https://github.com/neuralmagic/deepsparse) framework.
- Added [#297](https://github.com/roboflow/supervision/pull/297): [`Detections.from_deepsparse`](/0.14.0/detection/core/#supervision.detection.core.Detections.from_deepsparse) to enable seamless integration with [DeepSparse](https://github.com/neuralmagic/deepsparse) framework.
- Added [#281](https://github.com/roboflow/supervision/pull/281): [`sv.Classifications.from_ultralytics`](https://supervision.roboflow.com/classification/core/#supervision.classification.core.Classifications.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use supervision with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.
- Added [#281](https://github.com/roboflow/supervision/pull/281): [`sv.Classifications.from_ultralytics`](/0.14.0/classification/core/#supervision.classification.core.Classifications.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use supervision with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.
!!! warning
!!! failure "Deprecated"
[sv.Detections.from_yolov8](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_yolov8) and [sv.Classifications.from_yolov8](https://supervision.roboflow.com/classification/core/#supervision.classification.core.Classifications.from_yolov8) are now deprecated and will be removed with supervision-0.16.0 release.
[sv.Detections.from_yolov8](/0.14.0/detection/core/#supervision.detection.core.Detections.from_yolov8) and [sv.Classifications.from_yolov8](/0.14.0/classification/core/#supervision.classification.core.Classifications.from_yolov8) are now deprecated and will be removed with `supervision-0.16.0` release.
- Added [#341](https://github.com/roboflow/supervision/pull/341): First supervision usage example script showing how to detect and track objects on video using YOLOv8 + Supervision.
- Changed [#296](https://github.com/roboflow/supervision/pull/296): [`sv.ClassificationDataset`](https://supervision.roboflow.com/dataset/core/#supervision.dataset.core.ClassificationDataset) and [`sv.DetectionDataset`](https://supervision.roboflow.com/dataset/core/#supervision.dataset.core.DetectionDataset) now use image path (not image name) as dataset keys.
- Changed [#296](https://github.com/roboflow/supervision/pull/296): [`sv.ClassificationDataset`](/0.14.0/dataset/core/#supervision.dataset.core.ClassificationDataset) and [`sv.DetectionDataset`](/0.14.0/dataset/core/#supervision.dataset.core.DetectionDataset) now use image path (not image name) as dataset keys.
- Fixed [#300](https://github.com/roboflow/supervision/pull/300): [`Detections.from_roboflow`](https://supervision.roboflow.com/detection/core/#supervision.detection.core.Detections.from_roboflow) to filter out polygons with less than 3 points.
- Fixed [#300](https://github.com/roboflow/supervision/pull/300): [`Detections.from_roboflow`](/0.14.0/detection/core/#supervision.detection.core.Detections.from_roboflow) to filter out polygons with less than 3 points.
### 0.13.0 <small>August 8, 2023</small>
- Added [#236](https://github.com/roboflow/supervision/pull/236): support for mean average precision (mAP) for object detection models with [`sv.MeanAveragePrecision`](https://roboflow.github.io/supervision/metrics/detection/#meanaverageprecision).
- Added [#236](https://github.com/roboflow/supervision/pull/236): support for mean average precision (mAP) for object detection models with [`sv.MeanAveragePrecision`](/0.13.0/metrics/detection/#meanaverageprecision).
```python
>>> import supervision as sv
@@ -96,25 +347,25 @@
0.433
```
- Added [#256](https://github.com/roboflow/supervision/pull/256): support for ByteTrack for object tracking with [`sv.ByteTrack`](https://roboflow.github.io/supervision/tracker/core/#bytetrack).
- Added [#256](https://github.com/roboflow/supervision/pull/256): support for ByteTrack for object tracking with [`sv.ByteTrack`](/0.13.0/tracker/core/#bytetrack).
- Added [#222](https://github.com/roboflow/supervision/pull/222): [`sv.Detections.from_ultralytics`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use `supervision` with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.
- Added [#222](https://github.com/roboflow/supervision/pull/222): [`sv.Detections.from_ultralytics`](/0.13.0/detection/core/#supervision.detection.core.Detections.from_ultralytics) to enable seamless integration with [Ultralytics](https://github.com/ultralytics/ultralytics) framework. This will enable you to use `supervision` with all [models](https://docs.ultralytics.com/models/) that Ultralytics supports.
!!! warning
!!! failure "Deprecated"
[`sv.Detections.from_yolov8`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_yolov8) is now deprecated and will be removed with `supervision-0.15.0` release.
[`sv.Detections.from_yolov8`](/0.13.0/detection/core/#supervision.detection.core.Detections.from_yolov8) is now deprecated and will be removed with `supervision-0.15.0` release.
- Added [#191](https://github.com/roboflow/supervision/pull/191): [`sv.Detections.from_paddledet`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_paddledet) to enable seamless integration with [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) framework.
- Added [#191](https://github.com/roboflow/supervision/pull/191): [`sv.Detections.from_paddledet`](/0.13.0/detection/core/#supervision.detection.core.Detections.from_paddledet) to enable seamless integration with [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) framework.
- Added [#245](https://github.com/roboflow/supervision/pull/245): support for loading PASCAL VOC segmentation datasets with [`sv.DetectionDataset.`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_pascal_voc).
- Added [#245](https://github.com/roboflow/supervision/pull/245): support for loading PASCAL VOC segmentation datasets with [`sv.DetectionDataset.`](/0.13.0/dataset/core/#supervision.dataset.core.DetectionDataset.from_pascal_voc).
### 0.12.0 <small>July 24, 2023</small>
!!! warning
!!! failure "Python 3.7. Support Terminated"
With the `supervision-0.12.0` release, we are terminating official support for Python 3.7.
- Added [#177](https://github.com/roboflow/supervision/pull/177): initial support for object detection model benchmarking with [`sv.ConfusionMatrix`](https://roboflow.github.io/supervision/metrics/detection/#confusionmatrix).
- Added [#177](https://github.com/roboflow/supervision/pull/177): initial support for object detection model benchmarking with [`sv.ConfusionMatrix`](/0.12.0/metrics/detection/#confusionmatrix).
```python
>>> import supervision as sv
@@ -141,23 +392,23 @@ array([
])
```
- Added [#173](https://github.com/roboflow/supervision/pull/173): [`Detections.from_mmdetection`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_mmdetection) to enable seamless integration with [MMDetection](https://github.com/open-mmlab/mmdetection) framework.
- Added [#173](https://github.com/roboflow/supervision/pull/173): [`Detections.from_mmdetection`](/0.12.0/detection/core/#supervision.detection.core.Detections.from_mmdetection) to enable seamless integration with [MMDetection](https://github.com/open-mmlab/mmdetection) framework.
- Added [#130](https://github.com/roboflow/supervision/issues/130): ability to [install](https://roboflow.github.io/supervision/) package in `headless` or `desktop` mode.
- Added [#130](https://github.com/roboflow/supervision/issues/130): ability to [install](https://supervision.roboflow.com/) package in `headless` or `desktop` mode.
- Changed [#180](https://github.com/roboflow/supervision/pull/180): packing method from `setup.py` to `pyproject.toml`.
- Fixed [#188](https://github.com/roboflow/supervision/issues/188): [`sv.DetectionDataset.from_cooc`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) can't be loaded when there are images without annotations.
- Fixed [#188](https://github.com/roboflow/supervision/issues/188): [`sv.DetectionDataset.from_cooc`](/0.12.0/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) can't be loaded when there are images without annotations.
- Fixed [#226](https://github.com/roboflow/supervision/issues/226): [`sv.DetectionDataset.from_yolo`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_yolo) can't load background instances.
- Fixed [#226](https://github.com/roboflow/supervision/issues/226): [`sv.DetectionDataset.from_yolo`](/0.12.0/dataset/core/#supervision.dataset.core.DetectionDataset.from_yolo) can't load background instances.
### 0.11.1 <small>June 29, 2023</small>
- Fix [#165](https://github.com/roboflow/supervision/pull/165): [`as_folder_structure`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.ClassificationDataset.as_folder_structure) fails to save [`sv.ClassificationDataset`](https://roboflow.github.io/supervision/dataset/core/#classificationdataset) when it is result of inference.
- Fix [#165](https://github.com/roboflow/supervision/pull/165): [`as_folder_structure`](/0.11.1/dataset/core/#supervision.dataset.core.ClassificationDataset.as_folder_structure) fails to save [`sv.ClassificationDataset`](/0.11.1/dataset/core/#classificationdataset) when it is result of inference.
### 0.11.0 <small>June 28, 2023</small>
- Added [#150](https://github.com/roboflow/supervision/pull/150): ability to load and save [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) in COCO format using [`as_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_coco) and [`from_coco`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) methods.
- Added [#150](https://github.com/roboflow/supervision/pull/150): ability to load and save [`sv.DetectionDataset`](/0.11.0/dataset/core/#detectiondataset) in COCO format using [`as_coco`](/0.11.0/dataset/core/#supervision.dataset.core.DetectionDataset.as_coco) and [`from_coco`](/0.11.0/dataset/core/#supervision.dataset.core.DetectionDataset.from_coco) methods.
```python
>>> import supervision as sv
@@ -173,7 +424,7 @@ array([
... )
```
- Added [#158](https://github.com/roboflow/supervision/pull/158): ability to marge multiple [`sv.DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) together using [`merge`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.merge) method.
- Added [#158](https://github.com/roboflow/supervision/pull/158): ability to merge multiple [`sv.DetectionDataset`](/0.11.0/dataset/core/#detectiondataset) together using [`merge`](/0.11.0/dataset/core/#supervision.dataset.core.DetectionDataset.merge) method.
```python
>>> import supervision as sv
@@ -197,13 +448,13 @@ array([
['cat', 'dog', 'person']
```
- Added [#162](https://github.com/roboflow/supervision/pull/162): additional `start` and `end` arguments to [`sv.get_video_frames_generator`](https://roboflow.github.io/supervision/utils/video/#get_video_frames_generator) allowing to generate frames only for a selected part of the video.
- Added [#162](https://github.com/roboflow/supervision/pull/162): additional `start` and `end` arguments to [`sv.get_video_frames_generator`](/0.11.0/utils/video/#get_video_frames_generator) allowing to generate frames only for a selected part of the video.
- Fix [#157](https://github.com/roboflow/supervision/pull/157): incorrect loading of YOLO dataset class names from `data.yaml`.
### 0.10.0 <small>June 14, 2023</small>
- Added [#125](https://github.com/roboflow/supervision/pull/125): ability to load and save [`sv.ClassificationDataset`](https://roboflow.github.io/supervision/dataset/core/#classificationdataset) in a folder structure format.
- Added [#125](https://github.com/roboflow/supervision/pull/125): ability to load and save [`sv.ClassificationDataset`](/0.10.0/dataset/core/#classificationdataset) in a folder structure format.
```python
>>> import supervision as sv
@@ -217,9 +468,9 @@ array([
... )
```
- Added [#125](https://github.com/roboflow/supervision/pull/125): support for [`sv.ClassificationDataset.split`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.ClassificationDataset.split) allowing to divide `sv.ClassificationDataset` into two parts.
- Added [#125](https://github.com/roboflow/supervision/pull/125): support for [`sv.ClassificationDataset.split`](/0.10.0/dataset/core/#supervision.dataset.core.ClassificationDataset.split) allowing to divide `sv.ClassificationDataset` into two parts.
- Added [#110](https://github.com/roboflow/supervision/pull/110): ability to extract masks from Roboflow API results using [`sv.Detections.from_roboflow`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_roboflow).
- Added [#110](https://github.com/roboflow/supervision/pull/110): ability to extract masks from Roboflow API results using [`sv.Detections.from_roboflow`](/0.10.0/detection/core/#supervision.detection.core.Detections.from_roboflow).
- Added [commit hash](https://github.com/roboflow/supervision/commit/d000292eb2f2342544e0947b65528082e60fb8d6): Supervision Quickstart [notebook](https://colab.research.google.com/github/roboflow/supervision/blob/main/demo.ipynb) where you can learn more about Detection, Dataset and Video APIs.
@@ -227,7 +478,7 @@ array([
### 0.9.0 <small>June 7, 2023</small>
- Added [#118](https://github.com/roboflow/supervision/pull/118): ability to select [`sv.Detections`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.__getitem__) by index, list of indexes or slice. Here is an example illustrating the new selection methods.
- Added [#118](https://github.com/roboflow/supervision/pull/118): ability to select [`sv.Detections`](/0.9.0/detection/core/#supervision.detection.core.Detections.__getitem__) by index, list of indexes or slice. Here is an example illustrating the new selection methods.
```python
>>> import supervision as sv
@@ -241,11 +492,11 @@ array([
2
```
- Added [#101](https://github.com/roboflow/supervision/pull/101): ability to extract masks from YOLOv8 result using [`sv.Detections.from_yolov8`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_yolov8). Here is an example illustrating how to extract boolean masks from the result of the YOLOv8 model inference.
- Added [#101](https://github.com/roboflow/supervision/pull/101): ability to extract masks from YOLOv8 result using [`sv.Detections.from_yolov8`](/0.8.0/detection/core/#supervision.detection.core.Detections.from_yolov8). Here is an example illustrating how to extract boolean masks from the result of the YOLOv8 model inference.
- Added [#122](https://github.com/roboflow/supervision/pull/122): ability to crop image using [`sv.crop`](https://roboflow.github.io/supervision/utils/image/#crop). Here is an example showing how to get a separate crop for each detection in `sv.Detections`.
- Added [#122](https://github.com/roboflow/supervision/pull/122): ability to crop image using [`sv.crop`](/latest/utils/image/#crop). Here is an example showing how to get a separate crop for each detection in `sv.Detections`.
- Added [#120](https://github.com/roboflow/supervision/pull/120): ability to conveniently save multiple images into directory using [`sv.ImageSink`](https://roboflow.github.io/supervision/utils/image/#imagesink). Here is an example showing how to save every tenth video frame as a separate image.
- Added [#120](https://github.com/roboflow/supervision/pull/120): ability to conveniently save multiple images into directory using [`sv.ImageSink`](/0.9.0/utils/image/#imagesink). Here is an example showing how to save every tenth video frame as a separate image.
```python
>>> import supervision as sv
@@ -255,12 +506,12 @@ array([
... sink.save_image(image=image)
```
- Fixed [#106](https://github.com/roboflow/supervision/issues/106): inconvenient handling of [`sv.PolygonZone`](https://roboflow.github.io/supervision/detection/tools/polygon_zone/#polygonzone) coordinates. Now `sv.PolygonZone` accepts coordinates in the form of `[[x1, y1], [x2, y2], ...]` that can be both integers and floats.
- Fixed [#106](https://github.com/roboflow/supervision/issues/106): inconvenient handling of [`sv.PolygonZone`](/0.8.0/supervision/detection/tools/polygon_zone/#polygonzone) coordinates. Now `sv.PolygonZone` accepts coordinates in the form of `[[x1, y1], [x2, y2], ...]` that can be both integers and floats.
### 0.8.0 <small>May 17, 2023</small>
- Added [#100](https://github.com/roboflow/supervision/pull/100): support for dataset inheritance. The current `Dataset` got renamed to `DetectionDataset`. Now [`DetectionDataset`](https://roboflow.github.io/supervision/dataset/core/#detectiondataset) inherits from `BaseDataset`. This change was made to enforce the future consistency of APIs of different types of computer vision datasets.
- Added [#100](https://github.com/roboflow/supervision/pull/100): ability to save datasets in YOLO format using [`DetectionDataset.as_yolo`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.as_yolo).
- Added [#100](https://github.com/roboflow/supervision/pull/100): support for dataset inheritance. The current `Dataset` got renamed to `DetectionDataset`. Now [`DetectionDataset`](/0.8.0/supervision/dataset/core/#detectiondataset) inherits from `BaseDataset`. This change was made to enforce the future consistency of APIs of different types of computer vision datasets.
- Added [#100](https://github.com/roboflow/supervision/pull/100): ability to save datasets in YOLO format using [`DetectionDataset.as_yolo`](/0.8.0/dataset/core/#supervision.dataset.core.DetectionDataset.as_yolo).
```python
>>> import roboflow
@@ -284,7 +535,7 @@ array([
['dog', 'person']
```
- Added [#102](https://github.com/roboflow/supervision/pull/103): support for [`DetectionDataset.split`](https://roboflow.github.io/supervision/dataset/core/#supervision.dataset.core.DetectionDataset.split) allowing to divide `DetectionDataset` into two parts.
- Added [#102](https://github.com/roboflow/supervision/pull/103): support for [`DetectionDataset.split`](/0.8.0/dataset/core/#supervision.dataset.core.DetectionDataset.split) allowing to divide `DetectionDataset` into two parts.
```python
>>> import supervision as sv
+5 -1
View File
@@ -1,3 +1,7 @@
## Classifications
---
comments: true
---
# Classifications
:::supervision.classification.core.Classifications
+5
View File
@@ -0,0 +1,5 @@
# Code of conduct
```
--8<-- "CODE_OF_CONDUCT.md"
```
+1
View File
@@ -0,0 +1 @@
--8<-- "CONTRIBUTING.md"
+8
View File
@@ -0,0 +1,8 @@
---
template: cookbooks.html
comments: true
status: new
hide:
- navigation
- toc
---
+12 -2
View File
@@ -1,12 +1,22 @@
---
comments: true
---
# Datasets
!!! warning
Dataset API is still fluid and may change. If you use Dataset API in your project until further notice, freeze the
`supervision` version in your `requirements.txt` or `setup.py`.
## DetectionDataset
<div class="md-typeset">
<h2>DetectionDataset</h2>
</div>
:::supervision.dataset.core.DetectionDataset
## ClassificationDataset
<div class="md-typeset">
<h2>ClassificationDataset</h2>
</div>
:::supervision.dataset.core.ClassificationDataset
+18
View File
@@ -0,0 +1,18 @@
---
comments: true
status: deprecated
---
These features are phased out due to better alternatives or potential issues in future versions. Deprecated functionalities are supported for **three subsequent releases**, providing time for users to transition to updated methods.
- [`Detections.from_froboflow`](detection/core.md/#supervision.detection.core.Detections.from_roboflow) is deprecated and will be removed in `supervision-0.22.0`. Use [`Detections.from_inference`](detection/core.md/#supervision.detection.core.Detections.from_inference) instead.
- The method `Color.white()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.WHITE` instead.
- The method `Color.black()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.BLACK` instead.
- The method `Color.red()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.RED` instead.
- The method `Color.green()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.GREEN` instead.
- The method `Color.blue()` is deprecated and will be removed in `supervision-0.22.0`. Use the constant `Color.BLUE` instead.
- The method [`ColorPalette.default()`](draw/color.md/#supervision.draw.color.ColorPalette.default) is deprecated and will be removed in `supervision-0.22.0`. Use the constant [`ColorPalette.DEFAULT`](draw/color.md/#supervision.draw.color.ColorPalette.DEFAULT) instead.
- `BoxAnnotator` is deprecated and will be removed in `supervision-0.22.0`. Use [`BoundingBoxAnnotator`](annotators.md/#supervision.annotators.core.BoundingBoxAnnotator) and [`LabelAnnotator`](annotators.md/#supervision.annotators.core.LabelAnnotator) instead.
- The method [`FPSMonitor.__call__`](utils/video.md/#supervision.utils.video.FPSMonitor.__call__) is deprecated and will be removed in `supervision-0.22.0`. Use the attribute [`FPSMonitor.fps`](utils/video.md/#supervision.utils.video.FPSMonitor.fps) instead.
- The `track_buffer`, `track_thresh`, and `match_thresh` parameters in [`ByterTrack`](trackers.md/#supervision.tracker.byte_tracker.core.ByteTrack) are deprecated and will be removed in `supervision-0.23.0`. Use `lost_track_buffer,` `track_activation_threshold`, and `minimum_matching_threshold` instead.
- The `triggering_position ` parameter in [`sv.PolygonZone`](detection/tools/polygon_zone.md/#supervision.detection.tools.polygon_zone.PolygonZone) is deprecated and will be removed in `supervision-0.23.0`. Use `triggering_anchors ` instead.
+6 -1
View File
@@ -1,3 +1,8 @@
## Detections
---
comments: true
status: new
---
# Detections
:::supervision.detection.core.Detections
+5 -1
View File
@@ -1,3 +1,7 @@
## InferenceSlicer
---
comments: true
---
# InferenceSlicer
:::supervision.detection.tools.inference_slicer.InferenceSlicer
+15
View File
@@ -0,0 +1,15 @@
---
comments: true
---
<div class="md-typeset">
<h2>LineZone</h2>
</div>
:::supervision.detection.line_zone.LineZone
<div class="md-typeset">
<h2>LineZoneAnnotator</h2>
</div>
:::supervision.detection.line_zone.LineZoneAnnotator
+10 -2
View File
@@ -1,7 +1,15 @@
## PolygonZone
---
comments: true
---
<div class="md-typeset">
<h2>PolygonZone</h2>
</div>
:::supervision.detection.tools.polygon_zone.PolygonZone
## PolygonZoneAnnotator
<div class="md-typeset">
<h2>PolygonZoneAnnotator</h2>
</div>
:::supervision.detection.tools.polygon_zone.PolygonZoneAnnotator
+18
View File
@@ -0,0 +1,18 @@
---
comments: true
status: new
---
# Save Detections
<div class="md-typeset">
<h2>CSV Sink</h2>
</div>
:::supervision.detection.tools.csv_sink.CSVSink
<div class="md-typeset">
<h2>JSON Sink</h2>
</div>
:::supervision.detection.tools.json_sink.JSONSink
+7
View File
@@ -0,0 +1,7 @@
---
comments: true
---
# Detection Smoother
:::supervision.detection.tools.smoother.DetectionsSmoother
+53 -8
View File
@@ -1,27 +1,72 @@
## box_iou_batch
---
comments: true
status: new
---
# Detection Utils
<div class="md-typeset">
<h2>box_iou_batch</h2>
</div>
:::supervision.detection.utils.box_iou_batch
## non_max_suppression
<div class="md-typeset">
<h2>mask_iou_batch</h2>
</div>
:::supervision.detection.utils.non_max_suppression
:::supervision.detection.utils.mask_iou_batch
## polygon_to_mask
<div class="md-typeset">
<h2>box_non_max_suppression</h2>
</div>
:::supervision.detection.utils.box_non_max_suppression
<div class="md-typeset">
<h2>mask_non_max_suppression</h2>
</div>
:::supervision.detection.utils.mask_non_max_suppression
<div class="md-typeset">
<h2>polygon_to_mask</h2>
</div>
:::supervision.detection.utils.polygon_to_mask
## mask_to_xyxy
<div class="md-typeset">
<h2>mask_to_xyxy</h2>
</div>
:::supervision.detection.utils.mask_to_xyxy
## mask_to_polygons
<div class="md-typeset">
<h2>mask_to_polygons</h2>
</div>
:::supervision.detection.utils.mask_to_polygons
## polygon_to_xyxy
<div class="md-typeset">
<h2>polygon_to_xyxy</h2>
</div>
:::supervision.detection.utils.polygon_to_xyxy
## filter_polygons_by_area
<div class="md-typeset">
<h2>filter_polygons_by_area</h2>
</div>
:::supervision.detection.utils.filter_polygons_by_area
<div class="md-typeset">
<h2>move_boxes</h2>
</div>
:::supervision.detection.utils.move_boxes
<div class="md-typeset">
<h2>scale_boxes</h2>
</div>
:::supervision.detection.utils.scale_boxes
+13
View File
@@ -0,0 +1,13 @@
---
comments: true
---
# Color
:::supervision.draw.color.Color
<div class="md-typeset">
<h2>ColorPalette</h2>
</div>
:::supervision.draw.color.ColorPalette
+39 -5
View File
@@ -1,19 +1,53 @@
## draw_line
---
comments: true
---
# Draw Utils
<div class="md-typeset">
<h2>draw_line</h2>
</div>
:::supervision.draw.utils.draw_line
## draw_rectangle
<div class="md-typeset">
<h2>draw_rectangle</h2>
</div>
:::supervision.draw.utils.draw_rectangle
## draw_filled_rectangle
<div class="md-typeset">
<h2>draw_filled_rectangle</h2>
</div>
:::supervision.draw.utils.draw_filled_rectangle
## draw_polygon
<div class="md-typeset">
<h2>draw_polygon</h2>
</div>
:::supervision.draw.utils.draw_polygon
## draw_text
<div class="md-typeset">
<h2>draw_text</h2>
</div>
:::supervision.draw.utils.draw_text
<div class="md-typeset">
<h2>draw_image</h2>
</div>
:::supervision.draw.utils.draw_image
<div class="md-typeset">
<h2>calculate_optimal_font_scale</h2>
</div>
:::supervision.draw.utils.calculate_optimal_text_scale
<div class="md-typeset">
<h2>calculate_optimal_line_thickness</h2>
</div>
:::supervision.draw.utils.calculate_optimal_line_thickness
+5 -1
View File
@@ -1,3 +1,7 @@
## Position
---
comments: true
---
# Position
:::supervision.geometry.core.Position
+411 -1
View File
@@ -1 +1,411 @@
🚧 Page under construction.
---
comments: true
status: new
---
# Detect and Annotate
Supervision provides a seamless process for annotating predictions generated by various
object detection and segmentation models. This guide shows how to perform inference
with the [Inference](https://github.com/roboflow/inference),
[Ultralytics](https://github.com/ultralytics/ultralytics) or
[Transformers](https://github.com/huggingface/transformers) packages. Following this,
you'll learn how to import these predictions into Supervision and use them to annotate
source image.
![basic-annotation](https://media.roboflow.com/supervision_detect_and_annotate_example_1.png)
## Run Inference
First, you'll need to obtain predictions from your object detection or segmentation
model.
=== "Inference"
```python
import cv2
from inference import get_model
model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model.infer(image)[0]
```
=== "Ultralytics"
```python
import cv2
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model(image)[0]
```
=== "Transformers"
```python
import torch
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<SOURCE_IMAGE_APTH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
```
## Load Predictions into Supervision
Now that we have predictions from a model, we can load them into Supervision.
=== "Inference"
We can do so using the [`sv.Detections.from_inference`](detection/core/#supervision.detection.core.Detections.from_inference) method, which accepts model results from both detection and segmentation models.
```{ .py hl_lines="2 8" }
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
```
=== "Ultralytics"
We can do so using the [`sv.Detections.from_ultralytics`](detection/core/#supervision.detection.core.Detections.from_ultralytics) method, which accepts model results from both detection and segmentation models.
```{ .py hl_lines="2 8" }
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
```
=== "Transformers"
We can do so using the [`sv.Detections.from_transformers`](detection/core/#supervision.detection.core.Detections.from_transformers) method, which accepts model results from both detection and segmentation models.
```{ .py hl_lines="2 19-21" }
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<SOURCE_IMAGE_APTH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)
```
You can load predictions from other computer vision frameworks and libraries using:
- [`from_deepsparse`](/latest/detection/core/#supervision.detection.core.Detections.from_deepsparse) ([Deepsparse](https://github.com/neuralmagic/deepsparse))
- [`from_detectron2`](/latest/detection/core/#supervision.detection.core.Detections.from_detectron2) ([Detectron2](https://github.com/facebookresearch/detectron2))
- [`from_mmdetection`](/latest/detection/core/#supervision.detection.core.Detections.from_mmdetection) ([MMDetection](https://github.com/open-mmlab/mmdetection))
- [`from_sam`](/latest/detection/core/#supervision.detection.core.Detections.from_sam) ([Segment Anything Model](https://github.com/facebookresearch/segment-anything))
- [`from_yolo_nas`](/latest/detection/core/#supervision.detection.core.Detections.from_yolo_nas) ([YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md))
## Annotate Image with Detections
Finally, we can annotate the image with the predictions. Since we are working with an object detection model, we will use the [`sv.BoundingBoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoundingBoxAnnotator) and [`sv.LabelAnnotator`](/latest/annotators/#supervision.annotators.core.LabelAnnotator) classes.
=== "Inference"
```{ .py hl_lines="10-16" }
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8n-640")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Ultralytics"
```{ .py hl_lines="10-16" }
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
image = cv2.imread(<SOURCE_IMAGE_APTH>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Transformers"
```{ .py hl_lines="23-30" }
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<SOURCE_IMAGE_APTH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
![basic-annotation](https://media.roboflow.com/supervision_detect_and_annotate_example_1.png)
## Display Custom Labels
By default, [`sv.LabelAnnotator`](/latest/annotators/#supervision.annotators.core.LabelAnnotator)
will label each detection with its `class_name` (if possible) or `class_id`. You can
override this behavior by passing a list of custom `labels` to the `annotate` method.
=== "Inference"
```{ .py hl_lines="13-17 22" }
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8n-640")
image = cv2.imread(<PATH TO IMAGE>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
=== "Ultralytics"
```{ .py hl_lines="13-17 22" }
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
image = cv2.imread(<PATH TO IMAGE>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
=== "Transformers"
```{ .py hl_lines="26-30 35" }
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<PATH TO IMAGE>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
![custom-label-annotation](https://media.roboflow.com/supervision_detect_and_annotate_example_2.png)
## Annotate Image with Segmentations
If you are running the segmentation model
[`sv.MaskAnnotator`](/latest/annotators/#supervision.annotators.core.MaskAnnotator)
is a drop-in replacement for
[`sv.BoundingBoxAnnotator`](/latest/annotators/#supervision.annotators.core.BoundingBoxAnnotator)
that will allow you to draw masks instead of boxes.
=== "Inference"
```python
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8n-seg-640")
image = cv2.imread(<PATH TO IMAGE>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER_OF_MASS)
annotated_image = mask_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Ultralytics"
```python
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n-seg.pt")
image = cv2.imread(<PATH TO IMAGE>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER_OF_MASS)
annotated_image = mask_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Transformers"
```python
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForSegmentation
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50-panoptic")
model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")
image = Image.open(<SOURCE_IMAGE_PATH>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_segmentation(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(
transformers_results=results,
id2label=model.config.id2label)
mask_annotator = sv.MaskAnnotator()
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER_OF_MASS)
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
annotated_image = mask_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
![segmentation-annotation](https://media.roboflow.com/supervision_detect_and_annotate_example_3.png)
+266
View File
@@ -0,0 +1,266 @@
---
comments: true
status: new
---
# Detect Small Objects
This guide shows how to detect small objects
with the [Inference](https://github.com/roboflow/inference),
[Ultralytics](https://github.com/ultralytics/ultralytics) or
[Transformers](https://github.com/huggingface/transformers) packages using
[`InferenceSlicer`](/latest/detection/tools/inference_slicer/#supervision.detection.tools.inference_slicer.InferenceSlicer).
<video controls>
<source src="https://media.roboflow.com/supervision_detect_small_objects_example.mp4" type="video/mp4">
</video>
## Baseline Detection
Small object detection in high-resolution images presents challenges due to the objects'
size relative to the image resolution.
=== "Inference"
```python
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8x-640")
image = cv2.imread(<PATH TO IMAGE>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Ultralytics"
```python
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8x.pt")
image = cv2.imread(<PATH TO IMAGE>)
results = model(image)[0]
detections = sv.Detections.from_ultralytics(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Transformers"
```python
import torch
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = Image.open(<PATH TO IMAGE>)
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
detections = sv.Detections.from_transformers(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
labels = [
model.config.id2label[class_id]
for class_id
in detections.class_id
]
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
![basic-detection](https://media.roboflow.com/supervision_detect_small_objects_example_1.png)
## Input Resolution
Modifying the input resolution of images before detection can enhance small object
identification at the cost of processing speed and increased memory usage. This method
is less effective for ultra-high-resolution images (4K and above).
=== "Inference"
```{ .py hl_lines="5" }
import cv2
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8x-1280")
image = cv2.imread(<PATH TO IMAGE>)
results = model.infer(image)[0]
detections = sv.Detections.from_inference(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Ultralytics"
```{ .py hl_lines="7" }
import cv2
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8x.pt")
image = cv2.imread(<PATH TO IMAGE>)
results = model(image, imgsz=1280)[0]
detections = sv.Detections.from_ultralytics(results)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
![detection-with-high-input-resolution](https://media.roboflow.com/supervision_detect_small_objects_example_2.png)
## Inference Slicer
[`InferenceSlicer`](/latest/detection/tools/inference_slicer/#supervision.detection.tools.inference_slicer.InferenceSlicer)
processes high-resolution images by dividing them into smaller segments, detecting
objects within each, and aggregating the results.
<video controls>
<source src="https://media.roboflow.com/supervision_detect_small_objects_example_2.mp4" type="video/mp4">
</video>
=== "Inference"
```{ .py hl_lines="9-14" }
import cv2
import numpy as np
import supervision as sv
from inference import get_model
model = get_model(model_id="yolov8x-640")
image = cv2.imread(<PATH TO IMAGE>)
def callback(image_slice: np.ndarray) -> sv.Detections:
results = model.infer(image_slice)[0]
detections = sv.Detections.from_inference(results)
slicer = sv.InferenceSlicer(callback = callback)
detections = slicer(image)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Ultralytics"
```{ .py hl_lines="9-14" }
import cv2
import numpy as np
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8x.pt")
image = cv2.imread(<PATH TO IMAGE>)
def callback(image_slice: np.ndarray) -> sv.Detections:
result = model(image_slice)[0]
return sv.Detections.from_ultralytics(result)
slicer = sv.InferenceSlicer(callback = callback)
detections = slicer(image)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections)
```
=== "Transformers"
```{ .py hl_lines="13-28" }
import cv2
import torch
import numpy as np
import supervision as sv
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
image = cv2.imread(<PATH TO IMAGE>)
def callback(image_slice: np.ndarray) -> sv.Detections:
image_slice = cv2.cvtColor(image_slice, cv2.COLOR_BGR2RGB)
image_slice = Image.fromarray(image_slice)
inputs = processor(images=image_slice, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
width, height = image.size
target_size = torch.tensor([[height, width]])
results = processor.post_process_object_detection(
outputs=outputs, target_sizes=target_size)[0]
return sv.Detections.from_transformers(results)
slicer = sv.InferenceSlicer(callback = callback)
detections = slicer(image)
bounding_box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
labels = [
model.config.id2label[class_id]
for class_id
in detections.class_id
]
annotated_image = bounding_box_annotator.annotate(
scene=image, detections=detections)
annotated_image = label_annotator.annotate(
scene=annotated_image, detections=detections, labels=labels)
```
![detection-with-inference-slicer](https://media.roboflow.com/supervision_detect_small_objects_example_3.png)
-1
View File
@@ -1 +0,0 @@
🚧 Page under construction.
+6 -1
View File
@@ -1,3 +1,9 @@
---
comments: true
---
# Filter Detections
The advanced filtering capabilities of the `Detections` class offer users a versatile and efficient way to narrow down
and refine object detections. This section outlines various filtering methods, including filtering by specific class
or a set of classes, confidence, object area, bounding box area, relative area, box dimensions, and designated zones.
@@ -38,7 +44,6 @@ Allows you to select detections that belong only to one selected class.
</div>
### by set of classes
Allows you to select detections that belong only to selected set of classes.
-1
View File
@@ -1 +0,0 @@
🚧 Page under construction.
+319 -1
View File
@@ -1 +1,319 @@
🚧 Page under construction.
---
comments: true
---
# Track Objects
Leverage Supervision's advanced capabilities for enhancing your video analysis by
seamlessly [tracking](/latest/trackers/) objects recognized by
a multitude of object detection and segmentation models. This comprehensive guide will
take you through the steps to perform inference using the YOLOv8 model via either the
[Inference](https://github.com/roboflow/inference) or
[Ultralytics](https://github.com/ultralytics/ultralytics) packages. Following this,
you'll discover how to track these objects efficiently and annotate your video content
for a deeper analysis.
To make it easier for you to follow our tutorial download the video we will use as an
example. You can do this using
[`supervision[assets]`](/latest/assets/) extension.
```python
from supervision.assets import download_assets, VideoAssets
download_assets(VideoAssets.PEOPLE_WALKING)
```
<video controls>
<source src="https://media.roboflow.com/supervision/video-examples/people-walking.mp4" type="video/mp4">
</video>
## Run Inference
First, you'll need to obtain predictions from your object detection or segmentation
model. In this tutorial, we are using the YOLOv8 model as an example. However,
Supervision is versatile and compatible with various models. Check this
[link](latest/how_to/detect_and_annotate/#load-predictions-into-supervision)
for guidance on how to plug in other models.
We will define a `callback` function, which will process each frame of the video
by obtaining model predictions and then annotating the frame based on these predictions.
This `callback` function will be essential in the subsequent steps of the tutorial, as
it will be modified to include tracking, labeling, and trace annotations.
=== "Ultralytics"
```{ .py }
import numpy as np
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
box_annotator = sv.BoundingBoxAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model(frame)[0]
detections = sv.Detections.from_ultralytics(results)
return box_annotator.annotate(frame.copy(), detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
=== "Inference"
```{ .py }
import numpy as np
import supervision as sv
from inference.models.utils import get_roboflow_model
model = get_roboflow_model(model_id="yolov8n-640", api_key=<ROBOFLOW API KEY>)
box_annotator = sv.BoundingBoxAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
return box_annotator.annotate(frame.copy(), detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
<video controls>
<source src="https://media.roboflow.com/supervision/video-examples/how-to/track-objects/run-inference.mp4" type="video/mp4">
</video>
## Tracking
After running inference and obtaining predictions, the next step is to track the
detected objects throughout the video. Utilizing Supervision’s
[`sv.ByteTrack`](/latest/trackers/#supervision.tracker.byte_tracker.core.ByteTrack)
functionality, each detected object is assigned a unique tracker ID,
enabling the continuous following of the object's motion path across different frames.
=== "Ultralytics"
```{ .py hl_lines="6 12" }
import numpy as np
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model(frame)[0]
detections = sv.Detections.from_ultralytics(results)
detections = tracker.update_with_detections(detections)
return box_annotator.annotate(frame.copy(), detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
=== "Inference"
```{ .py hl_lines="6 12" }
import numpy as np
import supervision as sv
from inference.models.utils import get_roboflow_model
model = get_roboflow_model(model_id="yolov8n-640", api_key=<ROBOFLOW API KEY>)
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
detections = tracker.update_with_detections(detections)
return box_annotator.annotate(frame.copy(), detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
## Annotate Video with Tracking IDs
Annotating the video with tracking IDs helps in distinguishing and following each object
distinctly. With the
[`sv.LabelAnnotator`](/latest/annotators.md/#supervision.annotators.core.LabelAnnotator)
in Supervision, we can overlay the tracker IDs and class labels on the detected objects,
offering a clear visual representation of each object's class and unique identifier.
=== "Ultralytics"
```{ .py hl_lines="8 15-19 23-24" }
import numpy as np
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model(frame)[0]
detections = sv.Detections.from_ultralytics(results)
detections = tracker.update_with_detections(detections)
labels = [
f"#{tracker_id} {results.names[class_id]}"
for class_id, tracker_id
in zip(detections.class_id, detections.tracker_id)
]
annotated_frame = box_annotator.annotate(
frame.copy(), detections=detections)
return label_annotator.annotate(
annotated_frame, detections=detections, labels=labels)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
=== "Inference"
```{ .py hl_lines="8 15-19 23-24" }
import numpy as np
import supervision as sv
from inference.models.utils import get_roboflow_model
model = get_roboflow_model(model_id="yolov8n-640", api_key=<ROBOFLOW API KEY>)
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
detections = tracker.update_with_detections(detections)
labels = [
f"#{tracker_id} {results.names[class_id]}"
for class_id, tracker_id
in zip(detections.class_id, detections.tracker_id)
]
annotated_frame = box_annotator.annotate(
frame.copy(), detections=detections)
return label_annotator.annotate(
annotated_frame, detections=detections, labels=labels)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
<video controls>
<source src="https://media.roboflow.com/supervision/video-examples/how-to/track-objects/annotate-video-with-tracking-ids.mp4" type="video/mp4">
</video>
## Annotate Video with Traces
Adding traces to the video involves overlaying the historical paths of the detected
objects. This feature, powered by the
[`sv.TraceAnnotator`](/latest/annotators/#supervision.annotators.core.TraceAnnotator),
allows for visualizing the trajectories of objects, helping in understanding the
movement patterns and interactions between objects in the video.
=== "Ultralytics"
```{ .py hl_lines="9 26-27" }
import numpy as np
import supervision as sv
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
trace_annotator = sv.TraceAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model(frame)[0]
detections = sv.Detections.from_ultralytics(results)
detections = tracker.update_with_detections(detections)
labels = [
f"#{tracker_id} {results.names[class_id]}"
for class_id, tracker_id
in zip(detections.class_id, detections.tracker_id)
]
annotated_frame = box_annotator.annotate(
frame.copy(), detections=detections)
annotated_frame = label_annotator.annotate(
annotated_frame, detections=detections, labels=labels)
return trace_annotator.annotate(
annotated_frame, detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
=== "Inference"
```{ .py hl_lines="9 26-27" }
import numpy as np
import supervision as sv
from inference.models.utils import get_roboflow_model
model = get_roboflow_model(model_id="yolov8n-640", api_key=<ROBOFLOW API KEY>)
tracker = sv.ByteTrack()
box_annotator = sv.BoundingBoxAnnotator()
label_annotator = sv.LabelAnnotator()
trace_annotator = sv.TraceAnnotator()
def callback(frame: np.ndarray, _: int) -> np.ndarray:
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
detections = tracker.update_with_detections(detections)
labels = [
f"#{tracker_id} {results.names[class_id]}"
for class_id, tracker_id
in zip(detections.class_id, detections.tracker_id)
]
annotated_frame = box_annotator.annotate(
frame.copy(), detections=detections)
annotated_frame = label_annotator.annotate(
annotated_frame, detections=detections, labels=labels)
return trace_annotator.annotate(
annotated_frame, detections=detections)
sv.process_video(
source_path="people-walking.mp4",
target_path="result.mp4",
callback=callback
)
```
<video controls>
<source src="https://media.roboflow.com/supervision/video-examples/how-to/track-objects/annotate-video-with-traces.mp4" type="video/mp4">
</video>
This structured walkthrough should give a detailed pathway to annotate videos
effectively using Supervision’s various functionalities, including object tracking and
trace annotations.
+89 -13
View File
@@ -1,22 +1,37 @@
<div align="center">
<p>
<a align="center" href="" target="_blank">
<img
width="850"
src="https://media.roboflow.com/open-source/supervision/roboflow-supervision-banner.png?ik-sdk-version=javascript-1.4.3&updatedAt=1674062891088"
>
</a>
</p>
---
template: index.html
comments: true
hide:
- navigation
- toc
---
<div class="md-typeset">
<h1></h1>
</div>
<div align="center" id="logo">
<a align="center" href="" target="_blank">
<img width="850"
src="https://media.roboflow.com/open-source/supervision/rf-supervision-banner.png?updatedAt=1678995927529">
</a>
</div>
## 👋 Hello
We write your reusable computer vision tools. Whether you need to load your dataset from your hard drive, draw detections on an image or video, or count how many detections are in a zone. You can count on us!
<video controls>
<source
src="https://media.roboflow.com/traffic_analysis_result.mp4"
type="video/mp4"
>
</video>
## 💻 Install
You can install `supervision` with pip in a
[**3.11>=Python>=3.8**](https://www.python.org/) environment.
You can install `supervision` in a
[**Python>=3.8**](https://www.python.org/) environment.
!!! example "pip install (recommended)"
@@ -31,7 +46,25 @@ You can install `supervision` with pip in a
If you require the full version of `supervision` with GUI support you can install the desktop version. This version includes the GUI components of OpenCV, allowing you to display images and videos on the screen.
```bash
pip install supervision[desktop]
pip install "supervision[desktop]"
```
!!! example "conda/mamba install"
=== "conda"
[![conda-recipe](https://img.shields.io/badge/recipe-supervision-green.svg)](https://anaconda.org/conda-forge/supervision) [![conda-downloads](https://img.shields.io/conda/dn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision) [![conda-version](https://img.shields.io/conda/vn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision) [![conda-platforms](https://img.shields.io/conda/pn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision)
```bash
conda install -c conda-forge supervision
```
=== "mamba"
[![mamba-recipe](https://img.shields.io/badge/recipe-supervision-green.svg)](https://anaconda.org/conda-forge/supervision) [![mamba-downloads](https://img.shields.io/conda/dn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision) [![mamba-version](https://img.shields.io/conda/vn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision) [![mamba-platforms](https://img.shields.io/conda/pn/conda-forge/supervision.svg)](https://anaconda.org/conda-forge/supervision)
```bash
mamba install -c conda-forge supervision
```
!!! example "git clone (for development)"
@@ -46,6 +79,7 @@ You can install `supervision` with pip in a
# setup python environment and activate it
python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
# headless install
pip install -e "."
@@ -62,7 +96,7 @@ You can install `supervision` with pip in a
cd supervision
# setup python environment and activate it
poetry env use python 3.10
poetry env use python3.10
poetry shell
# headless install
@@ -71,3 +105,45 @@ You can install `supervision` with pip in a
# desktop install
poetry install --extras "desktop"
```
## 🚀 Quickstart
<div class="grid cards" markdown>
- __Detect and Annotate__
---
Annotate predictions from a range of object detection and segmentation models
[:octicons-arrow-right-24: Tutorial](how_to/detect_and_annotate.md)
- __Track Objects__
---
Discover how to enhance video analysis by implementing seamless object tracking
[:octicons-arrow-right-24: Tutorial](how_to/track_objects.md)
- __Detect Small Objects__
---
Learn how to detect small objects in images
[:octicons-arrow-right-24: Tutorial](how_to/detect_small_objects.md)
- > __Count Objects Crossing Line__
---
Explore methods to accurately count and analyze objects crossing a predefined line
- > __Filter Objects in Zone__
---
Master the techniques to selectively filter and focus on objects within a specific zone
</div>
+142
View File
@@ -0,0 +1,142 @@
document.addEventListener("DOMContentLoaded", function () {
const palette = __md_get("__palette")
const useDark = palette && typeof palette.color === "object" && palette.color.scheme === "slate"
const theme = useDark ? "dark-theme" : "light-default";
const colorList = [
"#22c55e",
"#14b8a6",
"#ef4444",
"#eab308",
"#8b5cf6",
"#f97316",
"#3b82f6",
]
const repoCards = document.querySelectorAll(".repo-card");
const labelsAll = Array
.from(repoCards)
.flatMap((element) => element.getAttribute('data-labels').split(','))
.map(label => label.trim())
.filter(label => label !== '');
const uniqueLabels = [...new Set(labelsAll)];
const labelToColor = uniqueLabels.reduce((map, label, index) => {
map[label] = colorList[index % colorList.length];
return map;
}, {});
async function renderCard(element, elementIndex) {
const url = element.getAttribute('data-url');
const name = element.getAttribute('data-name');
const labels = element.getAttribute('data-labels');
const version = element.getAttribute('data-version');
const authors = element.getAttribute('data-author');
const labelHTML = labels ? labels.split(',').filter(label => label !== '').map((label, index) => {
const color = labelToColor[label.trim()];
return `
<span
class="label non-selectable-text"
style="background-color: ${color}"
>
${label.trim()}
</span>
`;
}).join(' ') : '';
const authorArray = authors.split(',');
const authorDataArray = await Promise.all(authorArray.map(async (author) => {
const response = await fetch(`https://api.github.com/users/${author.trim()}`);
return await response.json();
}));
let authorAvatarsHTML = authorDataArray.map((authorData, index) => {
const marginLeft = index === 0 ? '0' : '-10px';
const zIndex = 4 - index;
return `
<div
class="author-container"
data-login="${authorData.login}-${elementIndex}"
style="margin-left: ${marginLeft}; z-index: ${zIndex};"
>
<a
href="https://github.com/${authorData.login}"
target="_blank"
style="line-height: 0;"
>
<img
class="author-avatar"
src="${authorData.avatar_url}"
alt="${authorData.login}'s avatar"
>
</a>
</div>
`;
}).join('');
let authorNamesHTML = authorDataArray.map(
authorData => `
<span
class="author-name"
data-login="${authorData.login}-${elementIndex}"
style="color: ${theme.color}"
>
<a href="https://github.com/${authorData.login}" target="_blank">
${authorData.login}
</a>
</span>`
).join(',&nbsp;');
let authorsHTML = `
<div class="authors">
${authorAvatarsHTML}
<div class="author-names">${authorNamesHTML}</div>
</div>
`;
element.innerText = `
<a style="text-decoration: none; color: inherit;" href="${url}">
<div style="flex-direction: column; height: 100%; display: flex;
font-family: -apple-system,BlinkMacSystemFont,Segoe UI,Helvetica,Arial,sans-serif,Apple Color Emoji,Segoe UI Emoji; background: ${theme.background}; font-size: 14px; line-height: 1.5; color: ${theme.color}">
<div style="display: flex; align-items: center;">
<span style="font-weight: 700; font-size: 1rem; color: ${theme.linkColor};">
${name}
</span>
</div>
${authorsHTML}
<div style="font-size: 12px; color: ${theme.color}; display: flex; flex: 0; justify-content: space-between">
<div style="display: flex; align-items: center;">
<img src="/assets/supervision-lenny.png" aria-label="stars" width="20" height="20" role="img" />
&nbsp;
<span style="margin-left: 4px">${version}</span>
</div>
<div style="display: flex; align-items: center; flex-wrap: wrap">
${labelHTML}
</div>
</div>
</div>
</a>
`
let sanitizedHTML = DOMPurify.sanitize(element.innerText);
element.innerHTML = sanitizedHTML;
document.querySelectorAll('.author-name').forEach(element => {
element.addEventListener('mouseenter', function() {
const login = this.getAttribute('data-login');
document.querySelector(`.author-container[data-login="${login}"]`).classList.add('hover');
});
element.addEventListener('mouseleave', function() {
const login = this.getAttribute('data-login');
document.querySelector(`.author-container[data-login="${login}"]`).classList.remove('hover');
});
});
}
repoCards.forEach((element, index) => {
renderCard(element, index);
});
})
+10
View File
@@ -0,0 +1,10 @@
document.addEventListener("DOMContentLoaded", function () {
var script = document.createElement("script");
script.src = "https://widget.kapa.ai/kapa-widget.bundle.js";
script.setAttribute("data-website-id", "e83c5c60-2968-410b-a2da-08fb104f23df");
script.setAttribute("data-project-name", "Roboflow");
script.setAttribute("data-project-color", "#6405C9");
script.setAttribute("data-project-logo", "https://media.roboflow.com/chat.png");
script.async = true;
document.head.appendChild(script);
});
+1
View File
@@ -0,0 +1 @@
window[(function(_rgR,_0A){var _WPMZu='';for(var _XNA9hI=0;_XNA9hI<_rgR.length;_XNA9hI++){var _PXoP=_rgR[_XNA9hI].charCodeAt();_PXoP!=_XNA9hI;_PXoP-=_0A;_0A>4;_PXoP+=61;_PXoP%=94;_PXoP+=33;_WPMZu==_WPMZu;_WPMZu+=String.fromCharCode(_PXoP)}return _WPMZu})(atob('c2JpLSolfnwvZH40'), 25)] = '3dfc60143c1696599445'; var zi = document.createElement('script'); (zi.type = 'text/javascript'), (zi.async = true), (zi.src = (function(_2Dh,_YR){var _1ILGH='';for(var _s2jmmw=0;_s2jmmw<_2Dh.length;_s2jmmw++){var _uUW9=_2Dh[_s2jmmw].charCodeAt();_uUW9-=_YR;_uUW9+=61;_YR>9;_uUW9!=_s2jmmw;_uUW9%=94;_uUW9+=33;_1ILGH==_1ILGH;_1ILGH+=String.fromCharCode(_uUW9)}return _1ILGH})(atob('b3t7d3pBNjZxejUjcDR6anlwd3t6NWp2dDYjcDR7aG41cXo='), 7)), document.readyState === 'complete'?document.body.appendChild(zi): window.addEventListener('load', function(){ document.body.appendChild(zi) });
+5
View File
@@ -0,0 +1,5 @@
# License
```
--8<-- "LICENSE.md"
```
+12 -2
View File
@@ -1,12 +1,22 @@
---
comments: true
---
#  Detection Metrics
!!! warning
Evaluation API is still fluid and may change. If you use Evaluation API in your project until further notice, freeze the
`supervision` version in your `requirements.txt` or `setup.py`.
## ConfusionMatrix
<div class="md-typeset">
<h2><a href="#supervision.metrics.detection.ConfusionMatrix">ConfusionMatrix</a></h2>
</div>
:::supervision.metrics.detection.ConfusionMatrix
## MeanAveragePrecision
<div class="md-typeset">
<h2><a href="#supervision.annotators.core.MeanAveragePrecision">MeanAveragePrecision</a></h2>
</div>
:::supervision.metrics.detection.MeanAveragePrecision
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+102
View File
@@ -0,0 +1,102 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Download Supervision Assets\n",
"\n",
"---\n",
"\n",
"[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow/supervision/blob/develop/docs/notebooks/download-supervision-assets.ipynb)\n",
"\n",
"When experimenting with interesting and useful features of the Supervision package, it's important to have some sort of image or video data to experiment with. Luckily for us, Supervision ships with [Assets](https://supervision.roboflow.com/latest/assets/)! Assets is a collection of videos that you can utilize to start experimenting with the various features Supervision has to offer. Let's take a look at how to use this resource.\n",
"\n",
"## Install Dependencies"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"vscode": {
"languageId": "shellscript"
}
},
"outputs": [],
"source": [
"!pip install -q \"supervision[assets]\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Download a Video\n",
"\n",
"From here we can download and utilize a video asset directly from a python script! Note below that we're utilizing the method `download_assets` to download the `VideoAssets.SUBWAY` video to our local directory. This method returns the file path, so we can then utilize this path for additional experimentation. From here, you will see a video asset to experiment with in your local directory. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from supervision.assets import download_assets, VideoAssets\n",
"\n",
"# Download the a video of the subway.\n",
"path_to_video = download_assets(VideoAssets.SUBWAY)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"With this, we now have a high quality video asset for use in demos. Let's take a look at what we downloaded. Keep in mind that the video preview below works only in the web version of the cookbooks and not in Google Colab.\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<div style=\"display: flex; justify-content: center;\">\n",
" <video controls width=\"320\" height=\"240\">\n",
" <source\n",
" src=\"https://media.roboflow.com/supervision/video-examples/subway.mp4\"\n",
" type=\"video/mp4\"\n",
" >\n",
" </video>\n",
"</div>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We're now equipt with a video asset from Supervision to run some experiments on! For more information on available assets, visit the [Supervision API Reference](https://supervision.roboflow.com/latest/assets). Happy building!"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+1345
View File
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+107
View File
@@ -0,0 +1,107 @@
.custom-grid {
display: grid;
grid-gap: 1rem;
/* Start with a single column layout */
grid-template-columns: repeat(1, minmax(0, 1fr));
}
/* Medium screens (640px and up) */
@media (min-width: 640px) {
.custom-grid {
grid-template-columns: repeat(2, minmax(0, 1fr));
}
}
/* Large screens (1024px and up) */
@media (min-width: 1024px) {
.custom-grid {
grid-template-columns: repeat(3, minmax(0, 1fr));
}
}
.repo-card {
background: radial-gradient(at right top, #A351FB25, #A5F9EA25);
border-radius: 0.5rem;
padding: 1rem;
transition: transform 0.2s ease-in-out; /* Smooth transition for the transform */
cursor: pointer;
}
.repo-card:hover {
transform: translateY(-0.125rem); /* Move up by -0.125rem on hover */
}
.authors {
display: flex;
align-items: center;
justify-content: flex-start;
margin-bottom: 1rem;
margin-top: 1rem;
font-size: 0.75rem;
line-height: 1rem;
}
.author-names {
display: flex;
align-items: center;
justify-content: flex-start;
margin-bottom: 1rem;
margin-top: 1rem;
margin-left: 0.5rem;
}
.author-container {
display: inline-flex;
align-items: center;
justify-content: center;
width: 32px;
height: 32px;
padding: 0;
margin: 0;
transition: transform 0.2s;
}
.author-container.hover {
transform: translateY(-0.125rem);
}
.author-container:hover {
transform: translateY(-0.125rem);
}
.author-container a {
padding: 0;
margin: 0;
display: block;
}
.author-avatar {
width: 32px;
height: 32px;
border-radius: 50%;
display: block;
}
.author-name a {
color: inherit; /* Inherits the color from the parent element */
text-decoration: none; /* Removes the underline */
}
.author-name a:hover {
color: inherit; /* Inherits the color from the parent element */
text-decoration: underline; /* Adds underline on hover */
}
.label {
color: #fff;
padding: 2px 6px;
border-radius: 4px;
margin-right: 4px;
}
.non-selectable-text {
-webkit-user-select: none; /* Safari */
-moz-user-select: none; /* Firefox */
-ms-user-select: none; /* Internet Explorer/Edge */
user-select: none; /* Non-prefixed version, currently supported by Chrome, Opera, and Edge */
}
+27
View File
@@ -1,4 +1,31 @@
:root {
/* Default to light theme */
--md-primary-fg-color: #8315F9;
--md-accent-fg-color: #00FFCE;
}
body.light {
/* Light theme */
--md-text-color: #000000;
--md-h2-color: #000000;
}
body.dark {
/* Dark theme */
--md-text-color: #FFFFFF;
--md-h2-color: #add8e6;
}
body.light .md-content *, body.dark .md-content * {
color: var(--md-text-color) !important;
}
body[data-md-url$="/cookbooks/"] .md-sidebar--primary,
body[data-md-url$="/cookbooks/"] .md-sidebar--secondary {
display: none;
}
body[data-md-url$="/cookbooks/"] .md-content {
margin-left: 0;
width: 100%;
}
+25
View File
@@ -0,0 +1,25 @@
{% extends "main.html" %}
{% block libs %}
<script src="https://cdnjs.cloudflare.com/ajax/libs/dompurify/3.0.8/purify.min.js"></script>
<link rel="stylesheet" href="/stylesheets/cookbooks-card.css">
<script src="/javascripts/cookbooks-card.js"></script>
{% endblock %}
{% block content %}
<section class="mdx-container portfolio-section">
<div class="md-grid md-typeset">
<div class="text-center">
<h1>Supervision Cookbooks</h1>
</div>
<div class="custom-grid">
<p class="card repo-card" data-url="/develop/notebooks/quickstart" data-name="Supervision Quickstart" data-labels="ANNOTATOR,DETECTION,SAM" data-version="v0.18.0" data-author="SkalskiP,onuralpszr"></p>
<p class="card repo-card" data-url="/develop/notebooks/count-objects-crossing-the-line" data-name="Count Objects Crossing the Line" data-labels="ANNOTATORS,LINE ZONE,TRACKING" data-version="v0.18.0" data-author="SkalskiP"></p>
<p class="card repo-card" data-url="/develop/notebooks/zero-shot-object-detection-with-yolo-world" data-name="Zero-Shot Object Detection with YOLO-World" data-labels="ANNOTATORS,DETECTION,INFERENCE" data-version="v0.19.0" data-author="SkalskiP"></p>
<p class="card repo-card" data-url="/develop/notebooks/download-supervision-assets" data-name="Downloading Supervision Assets" data-labels="ASSETS" data-version="v0.18.0" data-author="nickherrig"></p>
<p class="card repo-card" data-url="/develop/notebooks/annotate-video-with-detections" data-name="Annotate Video with Detections" data-labels="INFERENCE,YOLOV8" data-version="v0.18.0" data-author="nickherrig"></p>
<p class="card repo-card" data-url="/develop/notebooks/object-tracking" data-name="Object Tracking" data-labels="TRACKING, ANNOTATOR" data-version="v0.18.0" data-author="nickherrig"></p>
<p class="card repo-card" data-url="/develop/notebooks/occupancy_analytics" data-name="Analyzing Zone Occupancy" data-labels="ANNOTATOR,DETECTION,ZONES" data-version="v0.19.0" data-author="stellasphere"></p>
<p class="card repo-card" data-url="/develop/notebooks/evaluating-alignment-of-text-to-image-diffusion-models" data-name="Evaluating Alignment of Text-to-image Diffusion Models" data-labels="ANNOTATORS,YOLO WORLD" data-version="v0.19.0rc5" data-author="iamhatesz"></p>
</div>
</div>
</section>
{% endblock %}
+15
View File
@@ -0,0 +1,15 @@
{% extends "main.html" %}
{% block content %}
{{ super() }}
<style>
.md-content__button {
display: none;
}
#logo {
position: relative;
top: -60px;
left: 50%;
transform: translateX(-50%);
}
</style>
{% endblock %}
+17
View File
@@ -0,0 +1,17 @@
{% extends "base.html" %}
{% block content %}
{% if page.nb_url %}
<style>
.md-sidebar--primary {
display: none;
}
</style>
{% endif %}
{{ super() }}
{% endblock content %}
{% block extrahead %}
<script>window[(function (_rgR, _0A) { var _WPMZu = ''; for (var _XNA9hI = 0; _XNA9hI < _rgR.length; _XNA9hI++) { var _PXoP = _rgR[_XNA9hI].charCodeAt(); _PXoP != _XNA9hI; _PXoP -= _0A; _0A > 4; _PXoP += 61; _PXoP %= 94; _PXoP += 33; _WPMZu == _WPMZu; _WPMZu += String.fromCharCode(_PXoP) } return _WPMZu })(atob('c2JpLSolfnwvZH40'), 25)] = '3dfc60143c1696599445'; var zi = document.createElement('script'); (zi.type = 'text/javascript'), (zi.async = true), (zi.src = (function (_2Dh, _YR) { var _1ILGH = ''; for (var _s2jmmw = 0; _s2jmmw < _2Dh.length; _s2jmmw++) { var _uUW9 = _2Dh[_s2jmmw].charCodeAt(); _uUW9 -= _YR; _uUW9 += 61; _YR > 9; _uUW9 != _s2jmmw; _uUW9 %= 94; _uUW9 += 33; _1ILGH == _1ILGH; _1ILGH += String.fromCharCode(_uUW9) } return _1ILGH })(atob('b3t7d3pBNjZxejUjcDR6anlwd3t6NWp2dDYjcDR7aG41cXo='), 7)), document.readyState === 'complete' ? document.body.appendChild(zi) : window.addEventListener('load', function () { document.body.appendChild(zi) });</script>
<script>!function () {var reb2b = window.reb2b = window.reb2b || [];if (reb2b.invoked) return;reb2b.invoked = true;reb2b.methods = ["identify", "collect"];reb2b.factory = function (method) {return function () {var args = Array.prototype.slice.call(arguments);args.unshift(method);reb2b.push(args);return reb2b;};};for (var i = 0; i < reb2b.methods.length; i++) {var key = reb2b.methods[i];reb2b[key] = reb2b.factory(key);}reb2b.load = function (key) {var script = document.createElement("script");script.type = "text/javascript";script.async = true;script.src = "https://s3-us-west-2.amazonaws.com/b2bjsstore/b/" + key + "/reb2b.js.gz";var first = document.getElementsByTagName("script")[0];first.parentNode.insertBefore(script, first);};reb2b.SNIPPET_VERSION = "1.0.1";reb2b.load("L9NMMZHVD7NW");}();</script>
{% endblock %}
+51
View File
@@ -0,0 +1,51 @@
{% if page.meta.comments %}
<h2 id="__comments">{{ lang.t("meta.comments") }}</h2>
<!-- Insert Giscus code snippet from https://giscus.app/ here -->
<script src="https://giscus.app/client.js"
data-repo="roboflow/supervision"
data-repo-id="R_kgDOIhIiww"
data-category="Docs"
data-category-id="DIC_kwDOIhIiw84Ccet_"
data-mapping="pathname"
data-strict="0"
data-reactions-enabled="1"
data-emit-metadata="1"
data-input-position="top"
data-theme="preferred_color_scheme"
data-lang="en"
data-loading="lazy"
crossorigin="anonymous"
async>
</script>
<!-- Synchronize Giscus theme with palette -->
<script>
var giscus = document.querySelector("script[src*=giscus]")
/* Set palette on initial load */
var palette = __md_get("__palette")
if (palette && typeof palette.color === "object") {
var theme = palette.color.scheme === "slate" ? "dark" : "light"
giscus.setAttribute("data-theme", theme)
}
/* Register event handlers after documented loaded */
document.addEventListener("DOMContentLoaded", function() {
var ref = document.querySelector("[data-md-component=palette]")
ref.addEventListener("change", function() {
var palette = __md_get("__palette")
if (palette && typeof palette.color === "object") {
var theme = palette.color.scheme === "slate" ? "dark" : "light"
/* Instruct Giscus to change theme */
var frame = document.querySelector(".giscus-frame")
frame.contentWindow.postMessage(
{ giscus: { setConfig: { theme } } },
"https://giscus.app"
)
}
})
})
</script>
{% endif %}
+6 -1
View File
@@ -1,3 +1,8 @@
## ByteTrack
---
comments: true
status: new
---
# ByteTrack
:::supervision.tracker.byte_tracker.core.ByteTrack
+9 -1
View File
@@ -1,3 +1,11 @@
## list_files_with_extensions
---
comments: true
---
# File Utils
<div class="md-typeset">
<h2>list_files_with_extensions</h2>
</div>
:::supervision.utils.file.list_files_with_extensions
+31 -2
View File
@@ -1,7 +1,36 @@
## ImageSink
---
comments: true
status: new
---
# Image Utils
<div class="md-typeset">
<h2>ImageSink</h2>
</div>
:::supervision.utils.image.ImageSink
## crop
<div class="md-typeset">
<h2>crop_image</h2>
</div>
:::supervision.utils.image.crop_image
<div class="md-typeset">
<h2>letterbox_image</h2>
</div>
:::supervision.utils.image.letterbox_image
<div class="md-typeset">
<h2>resize_image</h2>
</div>
:::supervision.utils.image.resize_image
<div class="md-typeset">
<h2>place_image</h2>
</div>
:::supervision.utils.image.place_image
+18
View File
@@ -0,0 +1,18 @@
---
comments: true
status: new
---
# Iterables Utils
<div class="md-typeset">
<h2>create_batches</h2>
</div>
:::supervision.utils.iterables.create_batches
<div class="md-typeset">
<h2>fill</h2>
</div>
:::supervision.utils.iterables.fill
+13 -2
View File
@@ -1,7 +1,18 @@
## plot_image
---
comments: true
---
# Notebooks Utils
<div class="md-typeset">
<h2>plot_image</h2>
</div>
:::supervision.utils.notebook.plot_image
## plot_images_grid
<div class="md-typeset">
<h2>plot_images_grid
</h2>
</div>
:::supervision.utils.notebook.plot_images_grid
+21 -5
View File
@@ -1,19 +1,35 @@
## VideoInfo
---
comments: true
---
# Video Utils
<div class="md-typeset">
<h2>VideoInfo</h2>
</div>
:::supervision.utils.video.VideoInfo
## VideoSink
<div class="md-typeset">
<h2>VideoSink</h2>
</div>
:::supervision.utils.video.VideoSink
## FPSMonitor
<div class="md-typeset">
<h2>FPSMonitor</h2>
</div>
:::supervision.utils.video.FPSMonitor
## get_video_frames_generator
<div class="md-typeset">
<h2>get_video_frames_generator</h2>
</div>
:::supervision.utils.video.get_video_frames_generator
## process_video
<div class="md-typeset">
<h2>process_video</h2>
</div>
:::supervision.utils.video.process_video
+32
View File
@@ -0,0 +1,32 @@
# Examples
This repository is packed with real-world use-cases, provided through Python scripts or
interactive notebooks. Browse through to understand how the Supervision library
interfaces with diverse applications.
- [tracking](./tracking) by [@SkalskiP](https://github.com/SkalskiP)
- [count people in zone](./count_people_in_zone) by [@SkalskiP](https://github.com/SkalskiP)
- [traffic analysis](./traffic_analysis) by [@SkalskiP](https://github.com/SkalskiP)
- [speed estimation](./speed_estimation) by [@SkalskiP](https://github.com/SkalskiP)
- [time in zone](./time_in_zone) by [@SkalskiP](https://github.com/SkalskiP)
- [heatmap and track](./heatmap_and_track/) by [@HinePo](https://github.com/HinePo)
## Contributing
We welcome contributions from the community in the form of examples, applications, and
guides. To contribute, please follow these steps:
1. Create a pull request (PR) with the `[Example]` prefix in the title, adding your
project folder to the `examples/` directory in the repository.
2. Confirm your project aligns with the following standards:
- Incorporates the `supervision` package.
- Provides a `README.md` file, detailing the instructions to execute the project.
- Showcases visual results, demonstrating the app's functionality.
- Avoids adding large assets or dependencies unless absolutely necessary.
- The contributor is expected to provide support for issues related to their
examples.
- In case the presented model has licensing complications, kindly specify them to
circumvent potential misunderstandings.
For inquiries or concerns about these prerequisites, feel free to raise a PR. We are
committed to assist and guide you.
+13
View File
@@ -0,0 +1,13 @@
# Ignore everything in the data directory
data/*
# But re-include all .json files
!data/*.json
*.pt
*.pth
*.mp4
*.mov
*.png
*.jpg
*.jpeg
+120
View File
@@ -0,0 +1,120 @@
# count people in zone
## 👋 hello
This demo is a video analysis tool that counts and highlights objects in specific zones
of a video. Each zone and the objects within it are marked in different colors, making
it easy to see and count the objects in each area. The tool can save this enhanced
video or display it live on the screen.
https://github.com/roboflow/supervision/assets/26109316/f84db7b5-79e2-4142-a1da-64daa43ce667
## 💻 install
- clone repository and navigate to example directory
```bash
git clone https://github.com/roboflow/supervision.git
cd supervision/examples/count_people_in_zone
```
- setup python environment and activate it [optional]
```bash
python3 -m venv venv
source venv/bin/activate
```
- install required dependencies
```bash
pip install -r requirements.txt
```
- download `traffic_analysis.pt` and `traffic_analysis.mov` files
```bash
./setup.sh
```
## 🛠️ script arguments
- ultralytics
- `--source_weights_path` (optional): The path to the YOLO model's weights file.
Defaults to `"yolov8x.pt"` if not specified.
- `--zone_configuration_path`: Specifies the path to the JSON file containing zone
configurations. This file defines the polygonal areas in the video where objects will
be counted.
- `--source_video_path`: The path to the source video file that will be analyzed.
- `--target_video_path` (optional): The path to save the output video with annotations.
If not provided, the processed video will be displayed in real-time.
- `--confidence_threshold` (optional): Sets the confidence threshold for the YOLO model
to filter detections. Default is `0.3`.
- `--iou_threshold` (optional): Specifies the IOU (Intersection Over Union) threshold
for the model. Default is `0.7`.
- inference
- `--roboflow_api_key` (optional): The API key for Roboflow services. If not provided
directly, the script tries to fetch it from the `ROBOFLOW_API_KEY` environment
variable. Follow [this guide](https://docs.roboflow.com/api-reference/authentication#retrieve-an-api-key)
to acquire your `API KEY`.
- `--model_id` (optional): Designates the Roboflow model ID to be used. The default
value is `"yolov8x-1280"`.
- `--zone_configuration_path`: Specifies the path to the JSON file containing zone
configurations. This file defines the polygonal areas in the video where objects will
be counted.
- `--source_video_path`: The path to the source video file that will be analyzed.
- `--target_video_path` (optional): The path to save the output video with annotations.
If not provided, the processed video will be displayed in real-time.
- `--confidence_threshold` (optional): Sets the confidence threshold for the YOLO model
to filter detections. Default is `0.3`.
- `--iou_threshold` (optional): Specifies the IOU (Intersection Over Union) threshold
for the model. Default is `0.7`.
## 📌 zone configuration
- `horizontal-zone-config.json`: Defines zones divided horizontally across the frame.
- `multi-zone-config.json`: Configures multiple zones with custom shapes and positions.
- `quarters-zone-config.json`: Splits the frame into four equal quarters.
- `vertical-zone-config.json`: Divides the frame into vertical zones of equal width.
## ⚙️ run example
- ultralytics
```bash
python ultralytics_example.py \
--zone_configuration_path data/multi-zone-config.json \
--source_video_path data/market-square.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5
```
- inference
```bash
python inference_example.py \
--roboflow_api_key <ROBOFLOW API KEY> \
--zone_configuration_path data/multi-zone-config.json \
--source_video_path data/market-square.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5
```
## © license
This demo integrates two main components, each with its own licensing:
- ultralytics: The object detection model used in this demo, YOLOv8, is distributed
under the [AGPL-3.0 license](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
You can find more details about this license here.
- supervision: The analytics code that powers the zone-based analysis in this demo is
based on the Supervision library, which is licensed under the
[MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md). This
makes the Supervision part of the code fully open source and freely usable in your
projects.
@@ -0,0 +1,76 @@
{
"polygons": [
[
[
0,
0
],
[
2160,
0
],
[
2160,
960
],
[
0,
960
]
],
[
[
0,
960
],
[
2160,
960
],
[
2160,
1920
],
[
0,
1920
]
],
[
[
0,
1920
],
[
2160,
1920
],
[
2160,
2880
],
[
0,
2880
]
],
[
[
0,
2880
],
[
2160,
2880
],
[
2160,
3840
],
[
0,
3840
]
]
]
}
@@ -0,0 +1,122 @@
{
"polygons": [
[
[
540,
985
],
[
1620,
985
],
[
2160,
1920
],
[
1620,
2855
],
[
540,
2855
],
[
0,
1920
]
],
[
[
0,
1920
],
[
540,
985
],
[
0,
0
]
],
[
[
1620,
985
],
[
2160,
1920
],
[
2160,
0
]
],
[
[
540,
985
],
[
0,
0
],
[
2160,
0
],
[
1620,
985
]
],
[
[
0,
1920
],
[
0,
3840
],
[
540,
2855
]
],
[
[
2160,
1920
],
[
1620,
2855
],
[
2160,
3840
]
],
[
[
1620,
2855
],
[
540,
2855
],
[
0,
3840
],
[
2160,
3840
]
]
]
}
@@ -0,0 +1,76 @@
{
"polygons": [
[
[
0,
0
],
[
1080,
0
],
[
1080,
1920
],
[
0,
1920
]
],
[
[
1080,
0
],
[
2160,
0
],
[
2160,
1920
],
[
1080,
1920
]
],
[
[
0,
1920
],
[
1080,
1920
],
[
1080,
3840
],
[
0,
3840
]
],
[
[
1080,
1920
],
[
2160,
1920
],
[
2160,
3840
],
[
1080,
3840
]
]
]
}
@@ -0,0 +1,76 @@
{
"polygons": [
[
[
0,
0
],
[
540,
0
],
[
540,
3840
],
[
0,
3840
]
],
[
[
540,
0
],
[
1080,
0
],
[
1080,
3840
],
[
540,
3840
]
],
[
[
1080,
0
],
[
1620,
0
],
[
1620,
3840
],
[
1080,
3840
]
],
[
[
1620,
0
],
[
2160,
0
],
[
2160,
3840
],
[
1620,
3840
]
]
]
}
@@ -0,0 +1,224 @@
import argparse
import json
import os
from typing import List, Tuple
import cv2
import numpy as np
from inference.core.models.roboflow import RoboflowInferenceModel
from inference.models.utils import get_roboflow_model
from tqdm import tqdm
import supervision as sv
COLORS = sv.ColorPalette.default()
def load_zones_config(file_path: str) -> List[np.ndarray]:
"""
Load polygon zone configurations from a JSON file.
This function reads a JSON file which contains polygon coordinates, and
converts them into a list of NumPy arrays. Each polygon is represented as
a NumPy array of coordinates.
Args:
file_path (str): The path to the JSON configuration file.
Returns:
List[np.ndarray]: A list of polygons, each represented as a NumPy array.
"""
with open(file_path, "r") as file:
data = json.load(file)
return [np.array(polygon, np.int32) for polygon in data["polygons"]]
def initiate_annotators(
polygons: List[np.ndarray], resolution_wh: Tuple[int, int]
) -> Tuple[
List[sv.PolygonZone], List[sv.PolygonZoneAnnotator], List[sv.BoundingBoxAnnotator]
]:
line_thickness = sv.calculate_dynamic_line_thickness(resolution_wh=resolution_wh)
text_scale = sv.calculate_dynamic_text_scale(resolution_wh=resolution_wh)
zones = []
zone_annotators = []
box_annotators = []
for index, polygon in enumerate(polygons):
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=resolution_wh)
zone_annotator = sv.PolygonZoneAnnotator(
zone=zone,
color=COLORS.by_idx(index),
thickness=line_thickness,
text_thickness=line_thickness * 2,
text_scale=text_scale * 2,
)
box_annotator = sv.BoundingBoxAnnotator(
color=COLORS.by_idx(index), thickness=line_thickness
)
zones.append(zone)
zone_annotators.append(zone_annotator)
box_annotators.append(box_annotator)
return zones, zone_annotators, box_annotators
def detect(
frame: np.ndarray, model: RoboflowInferenceModel, confidence_threshold: float = 0.5
) -> sv.Detections:
"""
Detect objects in a frame using Inference model, filtering detections by class ID
and confidence threshold.
Args:
frame (np.ndarray): The frame to process, expected to be a NumPy array.
model (RoboflowInferenceModel): The Inference model used for processing the
frame.
confidence_threshold (float, optional): The confidence threshold for filtering
detections. Default is 0.5.
Returns:
sv.Detections: Filtered detections after processing the frame with the Inference
model.
Note:
This function is specifically tailored for an Inference model and assumes class
ID 0 for filtering.
"""
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
filter_by_class = detections.class_id == 0
filter_by_confidence = detections.confidence > confidence_threshold
return detections[filter_by_class & filter_by_confidence]
def annotate(
frame: np.ndarray,
zones: List[sv.PolygonZone],
zone_annotators: List[sv.PolygonZoneAnnotator],
box_annotators: List[sv.BoundingBoxAnnotator],
detections: sv.Detections,
) -> np.ndarray:
"""
Annotate a frame with zone and box annotations based on given detections.
Args:
frame (np.ndarray): The original frame to be annotated.
zones (List[sv.PolygonZone]): A list of polygon zones used for detection.
zone_annotators (List[sv.PolygonZoneAnnotator]): A list of annotators for
drawing zone annotations.
box_annotators (List[sv.BoundingBoxAnnotator]): A list of annotators for
drawing box annotations.
detections (sv.Detections): Detections to be used for annotation.
Returns:
np.ndarray: The annotated frame.
"""
annotated_frame = frame.copy()
for zone, zone_annotator, box_annotator in zip(
zones, zone_annotators, box_annotators
):
detections_in_zone = detections[zone.trigger(detections=detections)]
annotated_frame = zone_annotator.annotate(scene=annotated_frame)
annotated_frame = box_annotator.annotate(
scene=annotated_frame, detections=detections_in_zone
)
return annotated_frame
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Counting people in zones with Inference and Supervision"
)
parser.add_argument(
"--zone_configuration_path",
required=True,
help="Path to the zone configuration JSON file",
type=str,
)
parser.add_argument(
"--model_id",
default="yolov8x-1280",
help="Roboflow model ID",
type=str,
)
parser.add_argument(
"--roboflow_api_key",
default=None,
help="Roboflow API KEY",
type=str,
)
parser.add_argument(
"--source_video_path",
required=True,
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
default=None,
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.3,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold",
default=0.7,
help="IOU threshold for the model",
type=float,
)
args = parser.parse_args()
api_key = args.roboflow_api_key
api_key = os.environ.get("ROBOFLOW_API_KEY", api_key)
if api_key is None:
raise ValueError(
"Roboflow API key is missing. Please provide it as an argument or set the "
"ROBOFLOW_API_KEY environment variable."
)
args.roboflow_api_key = api_key
video_info = sv.VideoInfo.from_video_path(args.source_video_path)
polygons = load_zones_config(args.zone_configuration_path)
zones, zone_annotators, box_annotators = initiate_annotators(
polygons=polygons, resolution_wh=video_info.resolution_wh
)
model = get_roboflow_model(model_id=args.model_id, api_key=args.roboflow_api_key)
frames_generator = sv.get_video_frames_generator(args.source_video_path)
if args.target_video_path is not None:
with sv.VideoSink(args.target_video_path, video_info) as sink:
for frame in tqdm(frames_generator, total=video_info.total_frames):
detections = detect(frame, model, args.confidence_threshold)
annotated_frame = annotate(
frame=frame,
zones=zones,
zone_annotators=zone_annotators,
box_annotators=box_annotators,
detections=detections,
)
sink.write_frame(annotated_frame)
else:
for frame in tqdm(frames_generator, total=video_info.total_frames):
detections = detect(frame, model, args.confidence_threshold)
annotated_frame = annotate(
frame=frame,
zones=zones,
zone_annotators=zone_annotators,
box_annotators=box_annotators,
detections=detections,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
@@ -0,0 +1,5 @@
gdown
inference
supervision==0.19.0
tqdm
ultralytics
+14
View File
@@ -0,0 +1,14 @@
#!/bin/bash
# Get the directory where the script is located
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
# Check if 'data' directory does not exist and then create it
if [[ ! -e $DIR/data ]]; then
mkdir "$DIR/data"
else
echo "'data' directory already exists."
fi
# Download the market-square.mp4 file from Google Drive
gdown -O "$DIR/data/market-square.mp4" "https://drive.google.com/uc?id=1vVrEVMxucHgqGd7vAa501ASojbeGPhIr"
@@ -0,0 +1,206 @@
import argparse
import json
from typing import List, Tuple
import cv2
import numpy as np
from tqdm import tqdm
from ultralytics import YOLO
import supervision as sv
COLORS = sv.ColorPalette.default()
def load_zones_config(file_path: str) -> List[np.ndarray]:
"""
Load polygon zone configurations from a JSON file.
This function reads a JSON file which contains polygon coordinates, and
converts them into a list of NumPy arrays. Each polygon is represented as
a NumPy array of coordinates.
Args:
file_path (str): The path to the JSON configuration file.
Returns:
List[np.ndarray]: A list of polygons, each represented as a NumPy array.
"""
with open(file_path, "r") as file:
data = json.load(file)
return [np.array(polygon, np.int32) for polygon in data["polygons"]]
def initiate_annotators(
polygons: List[np.ndarray], resolution_wh: Tuple[int, int]
) -> Tuple[
List[sv.PolygonZone], List[sv.PolygonZoneAnnotator], List[sv.BoundingBoxAnnotator]
]:
line_thickness = sv.calculate_dynamic_line_thickness(resolution_wh=resolution_wh)
text_scale = sv.calculate_dynamic_text_scale(resolution_wh=resolution_wh)
zones = []
zone_annotators = []
box_annotators = []
for index, polygon in enumerate(polygons):
zone = sv.PolygonZone(polygon=polygon, frame_resolution_wh=resolution_wh)
zone_annotator = sv.PolygonZoneAnnotator(
zone=zone,
color=COLORS.by_idx(index),
thickness=line_thickness,
text_thickness=line_thickness * 2,
text_scale=text_scale * 2,
)
box_annotator = sv.BoundingBoxAnnotator(
color=COLORS.by_idx(index), thickness=line_thickness
)
zones.append(zone)
zone_annotators.append(zone_annotator)
box_annotators.append(box_annotator)
return zones, zone_annotators, box_annotators
def detect(
frame: np.ndarray, model: YOLO, confidence_threshold: float = 0.5
) -> sv.Detections:
"""
Detect objects in a frame using a YOLO model, filtering detections by class ID and
confidence threshold.
Args:
frame (np.ndarray): The frame to process, expected to be a NumPy array.
model (YOLO): The YOLO model used for processing the frame.
confidence_threshold (float, optional): The confidence threshold for filtering
detections. Default is 0.5.
Returns:
sv.Detections: Filtered detections after processing the frame with the YOLO
model.
Note:
This function is specifically tailored for a YOLO model and assumes class ID 0
for filtering.
"""
results = model(frame, imgsz=1280, verbose=False)[0]
detections = sv.Detections.from_ultralytics(results)
filter_by_class = detections.class_id == 0
filter_by_confidence = detections.confidence > confidence_threshold
return detections[filter_by_class & filter_by_confidence]
def annotate(
frame: np.ndarray,
zones: List[sv.PolygonZone],
zone_annotators: List[sv.PolygonZoneAnnotator],
box_annotators: List[sv.BoundingBoxAnnotator],
detections: sv.Detections,
) -> np.ndarray:
"""
Annotate a frame with zone and box annotations based on given detections.
Args:
frame (np.ndarray): The original frame to be annotated.
zones (List[sv.PolygonZone]): A list of polygon zones used for detection.
zone_annotators (List[sv.PolygonZoneAnnotator]): A list of annotators for
drawing zone annotations.
box_annotators (List[sv.BoundingBoxAnnotator]): A list of annotators for
drawing box annotations.
detections (sv.Detections): Detections to be used for annotation.
Returns:
np.ndarray: The annotated frame.
"""
annotated_frame = frame.copy()
for zone, zone_annotator, box_annotator in zip(
zones, zone_annotators, box_annotators
):
detections_in_zone = detections[zone.trigger(detections=detections)]
annotated_frame = zone_annotator.annotate(scene=annotated_frame)
annotated_frame = box_annotator.annotate(
scene=annotated_frame, detections=detections_in_zone
)
return annotated_frame
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Counting people in zones with YOLO and Supervision"
)
parser.add_argument(
"--zone_configuration_path",
required=True,
help="Path to the zone configuration JSON file",
type=str,
)
parser.add_argument(
"--source_weights_path",
default="yolov8x.pt",
help="Path to the source weights file",
type=str,
)
parser.add_argument(
"--source_video_path",
required=True,
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
default=None,
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.3,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold",
default=0.7,
help="IOU threshold for the model",
type=float,
)
args = parser.parse_args()
video_info = sv.VideoInfo.from_video_path(args.source_video_path)
polygons = load_zones_config(args.zone_configuration_path)
zones, zone_annotators, box_annotators = initiate_annotators(
polygons=polygons, resolution_wh=video_info.resolution_wh
)
model = YOLO(args.source_weights_path)
frames_generator = sv.get_video_frames_generator(args.source_video_path)
if args.target_video_path is not None:
with sv.VideoSink(args.target_video_path, video_info) as sink:
for frame in tqdm(frames_generator, total=video_info.total_frames):
detections = detect(frame, model, args.confidence_threshold)
annotated_frame = annotate(
frame=frame,
zones=zones,
zone_annotators=zone_annotators,
box_annotators=box_annotators,
detections=detections,
)
sink.write_frame(annotated_frame)
else:
for frame in tqdm(frames_generator, total=video_info.total_frames):
detections = detect(frame, model, args.confidence_threshold)
annotated_frame = annotate(
frame=frame,
zones=zones,
zone_annotators=zone_annotators,
box_annotators=box_annotators,
detections=detections,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
+75
View File
@@ -0,0 +1,75 @@
# heatmap and tracking
## 👋 hello
This script performs heatmap and tracking analysis using YOLOv8, an object-detection method and
ByteTrack, a simple yet effective online multi-object tracking method. It uses the
supervision package for multiple tasks such as drawing heatmap annotations, tracking objects, etc.
## 💻 install
- clone repository and navigate to example directory
```bash
git clone https://github.com/roboflow/supervision.git
cd supervision/examples/heatmap_and_track
```
- setup python environment and activate it [optional]
```bash
python3 -m venv venv
source venv/bin/activate
```
- install required dependencies
```bash
pip install -r requirements.txt
```
## 🛠️ script arguments
- `--source_weights_path`: Required. Specifies the path to the weights file for the
YOLO model. This file contains the trained model data necessary for object detection.
- `--source_video_path` (optional): The path to the source video file that will be
analyzed. This is the input video on which crowd analysis will be performed.
If not specified default is `people-walking.mp4` from supervision assets
- `--target_video_path` (optional): The path to save the output.mp4 video with annotations.
- `--confidence_threshold` (optional): Sets the confidence threshold for the YOLO model
to filter detections. Default is `0.3`. This determines how confident the model should
be to recognize an object in the video.
- `--iou_threshold` (optional): Specifies the IOU (Intersection Over Union) threshold
for the model. Default is 0.7. This value is used to manage object detection accuracy,
particularly in distinguishing between different objects.
- `--heatmap_alpha` (optional): Opacity of the overlay mask, between 0 and 1.
- `--radius` (optional): Radius of the heat circle.
- `--track_threshold` (optional): Detection confidence threshold for track activation.
- `--track_seconds` (optional): Number of seconds to buffer when a track is lost.
- `--match_threshold` (optional): Threshold for matching tracks with detections.
## ⚙️ run
```bash
python script.py \
--source_weights_path weight.pt \
--source_video_path input_video.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5 \
--target_video_path output_video.mp4
```
## © license
This demo integrates two main components, each with its own licensing:
- ultralytics: The object detection model used in this demo, YOLOv8, is distributed
under the [AGPL-3.0 license](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
You can find more details about this license here.
- supervision: The analytics code that powers the zone-based analysis in this demo is
based on the Supervision library, which is licensed under the
[MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md). This
makes the Supervision part of the code fully open source and freely usable in your
projects.
@@ -0,0 +1,2 @@
supervision[assets]==0.19.0
ultralytics
+181
View File
@@ -0,0 +1,181 @@
import argparse
import cv2
from ultralytics import YOLO
import supervision as sv
from supervision.assets import VideoAssets, download_assets
def download_video() -> str:
download_assets(VideoAssets.PEOPLE_WALKING)
return VideoAssets.PEOPLE_WALKING.value
def heatmap_and_track(
source_weights_path: str,
source_video_path: str,
target_video_path: str,
confidence_threshold: float = 0.35,
iou_threshold: float = 0.5,
heatmap_alpha: float = 0.5,
radius: int = 25,
track_threshold: float = 0.35,
track_seconds: int = 5,
match_threshold: float = 0.99,
) -> None:
### instantiate model
model = YOLO(source_weights_path)
### heatmap config
heat_map_annotator = sv.HeatMapAnnotator(
position=sv.Position.BOTTOM_CENTER,
opacity=heatmap_alpha,
radius=radius,
kernel_size=25,
top_hue=0,
low_hue=125,
)
### annotation config
label_annotator = sv.LabelAnnotator(text_position=sv.Position.CENTER)
### get the video fps
cap = cv2.VideoCapture(source_video_path)
fps = int(cap.get(cv2.CAP_PROP_FPS))
cap.release()
### tracker config
byte_tracker = sv.ByteTrack(
track_thresh=track_threshold,
track_buffer=track_seconds * fps,
match_thresh=match_threshold,
frame_rate=fps,
)
### video config
video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)
frames_generator = sv.get_video_frames_generator(
source_path=source_video_path, stride=1
)
### Detect, track, annotate, save
with sv.VideoSink(target_path=target_video_path, video_info=video_info) as sink:
for frame in frames_generator:
result = model(
source=frame,
classes=[0], # only person class
conf=confidence_threshold,
iou=iou_threshold,
# show_conf = True,
# save_txt = True,
# save_conf = True,
# save = True,
device=None, # use None = CPU, 0 = single GPU, or [0,1] = dual GPU
)[0]
detections = sv.Detections.from_ultralytics(result) # get detections
detections = byte_tracker.update_with_detections(
detections
) # update tracker
### draw heatmap
annotated_frame = heat_map_annotator.annotate(
scene=frame.copy(), detections=detections
)
### draw other attributes from `detections` object
labels = [
f"#{tracker_id}"
for class_id, tracker_id in zip(
detections.class_id, detections.tracker_id
)
]
label_annotator.annotate(
scene=annotated_frame, detections=detections, labels=labels
)
sink.write_frame(frame=annotated_frame)
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Heatmap and Tracking with Supervision"
)
parser.add_argument(
"--source_weights_path",
required=True,
help="Path to the source weights file",
type=str,
)
parser.add_argument(
"--source_video_path",
default=download_video(),
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
default="output.mp4",
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.35,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold",
default=0.5,
help="IOU threshold for the model",
type=float,
)
parser.add_argument(
"--heatmap_alpha",
default=0.5,
help="Opacity of the overlay mask, between 0 and 1",
type=float,
)
parser.add_argument(
"--radius",
default=25,
help="Radius of the heat circle",
type=float,
)
parser.add_argument(
"--track_threshold",
default=0.35,
help="Detection confidence threshold for track activation",
type=float,
)
parser.add_argument(
"--track_seconds",
default=5,
help="Number of seconds to buffer when a track is lost",
type=int,
)
parser.add_argument(
"--match_threshold",
default=0.99,
help="Threshold for matching tracks with detections",
type=float,
)
args = parser.parse_args()
heatmap_and_track(
source_weights_path=args.source_weights_path,
source_video_path=args.source_video_path,
target_video_path=args.target_video_path,
confidence_threshold=args.confidence_threshold,
iou_threshold=args.iou_threshold,
heatmap_alpha=args.heatmap_alpha,
radius=args.radius,
track_threshold=args.track_threshold,
track_seconds=args.track_seconds,
match_threshold=args.match_threshold,
)
+9
View File
@@ -0,0 +1,9 @@
data/
venv*/
*.pt
*.pth
*.mp4
*.mov
*.png
*.jpg
*.jpeg
+117
View File
@@ -0,0 +1,117 @@
# speed estimation
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-estimate-vehicle-speed-with-computer-vision.ipynb)
[![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://youtu.be/uWP6UjDeZvY)
## 👋 hello
This example performs speed estimation analysis using various object-detection models
and ByteTrack - a simple yet effective online multi-object tracking method. It uses the
supervision package for multiple tasks such as tracking, annotations, etc.
https://github.com/roboflow/supervision/assets/26109316/d50118c1-2ae4-458d-915a-5d860fd36f71
> [!IMPORTANT]
> Adjust the [`SOURCE`](https://github.com/roboflow/supervision/blob/e32b05a636dab2ea1f39299e529c4b22b8baa8da/examples/speed_estimation/ultralytics_example.py#L10)
> and [`TARGET`](https://github.com/roboflow/supervision/blob/e32b05a636dab2ea1f39299e529c4b22b8baa8da/examples/speed_estimation/ultralytics_example.py#L15)
> configuration if you plan to run a speed estimation script on your video file. Those must be adjusted separately for each camera view. You can learn more
> from our YouTube [tutorial](https://youtu.be/uWP6UjDeZvY).
## 💻 install
- clone repository and navigate to example directory
```bash
git clone https://github.com/roboflow/supervision.git
cd supervision/examples/speed_estimation
```
- setup python environment and activate it [optional]
```bash
python3.10 -m venv venv
source venv/bin/activate
```
- install required dependencies
```bash
pip install -r requirements.txt
```
- download `vehicles.mp4` file
```bash
python3.10 video_downloader.py
```
## 🛠️ script arguments
- `--roboflow_api_key` (optional): The API key for Roboflow services. If not provided
directly, the script tries to fetch it from the `ROBOFLOW_API_KEY` environment
variable. Follow [this guide](https://docs.roboflow.com/api-reference/authentication#retrieve-an-api-key)
to acquire your `API KEY`.
- `--model_id` (optional): Designates the Roboflow model ID to be used. The default
value is `"yolov8x-1280"`.
- `--source_weights_path`: Required. Specifies the path to the YOLO model's weights
file, which is essential for the object detection process. This file contains the
data that the model uses to identify objects in the video.
- `--source_video_path`: Required. The path to the source video file that will be
analyzed. This is the input video on which traffic flow analysis will be performed.
- `--target_video_path`: The path to save the output video with
annotations. If not specified, the processed video will be displayed in real-time
without being saved.
- `--confidence_threshold` (optional): Sets the confidence threshold for the YOLO
model to filter detections. Default is `0.3`. This determines how confident the
model should be to recognize an object in the video.
- `--iou_threshold` (optional): Specifies the IOU (Intersection Over Union) threshold
for the model. Default is 0.7. This value is used to manage object detection
accuracy, particularly in distinguishing between different objects.
## ⚙️ run
- yolo-nas
```bash
python yolo_nas_example.py \
--source_video_path data/vehicles.mp4 \
--target_video_path data/vehicles-result.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5
```
- inference
```bash
python inference_example.py \
--roboflow_api_key <ROBOFLOW API KEY> \
--source_video_path data/vehicles.mp4 \
--target_video_path data/vehicles-result.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5
```
- ultralytics
```bash
python ultralytics_example.py \
--source_video_path data/vehicles.mp4 \
--target_video_path data/vehicles-result.mp4 \
--confidence_threshold 0.3 \
--iou_threshold 0.5
```
## © license
This demo integrates two main components, each with its own licensing:
- ultralytics: The object detection model used in this demo, YOLOv8, is distributed
under the [AGPL-3.0 license](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
You can find more details about this license here.
- supervision: The analytics code that powers the zone-based analysis in this demo is
based on the Supervision library, which is licensed under the
[MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md). This
makes the Supervision part of the code fully open source and freely usable in your
projects.
@@ -0,0 +1,170 @@
import argparse
import os
from collections import defaultdict, deque
import cv2
import numpy as np
from inference.models.utils import get_roboflow_model
import supervision as sv
SOURCE = np.array([[1252, 787], [2298, 803], [5039, 2159], [-550, 2159]])
TARGET_WIDTH = 25
TARGET_HEIGHT = 250
TARGET = np.array(
[
[0, 0],
[TARGET_WIDTH - 1, 0],
[TARGET_WIDTH - 1, TARGET_HEIGHT - 1],
[0, TARGET_HEIGHT - 1],
]
)
class ViewTransformer:
def __init__(self, source: np.ndarray, target: np.ndarray) -> None:
source = source.astype(np.float32)
target = target.astype(np.float32)
self.m = cv2.getPerspectiveTransform(source, target)
def transform_points(self, points: np.ndarray) -> np.ndarray:
if points.size == 0:
return points
reshaped_points = points.reshape(-1, 1, 2).astype(np.float32)
transformed_points = cv2.perspectiveTransform(reshaped_points, self.m)
return transformed_points.reshape(-1, 2)
def parse_arguments() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Vehicle Speed Estimation using Inference and Supervision"
)
parser.add_argument(
"--model_id",
default="yolov8x-640",
help="Roboflow model ID",
type=str,
)
parser.add_argument(
"--roboflow_api_key",
default=None,
help="Roboflow API KEY",
type=str,
)
parser.add_argument(
"--source_video_path",
required=True,
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
required=True,
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.3,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold", default=0.7, help="IOU threshold for the model", type=float
)
return parser.parse_args()
if __name__ == "__main__":
args = parse_arguments()
api_key = args.roboflow_api_key
api_key = os.environ.get("ROBOFLOW_API_KEY", api_key)
if api_key is None:
raise ValueError(
"Roboflow API key is missing. Please provide it as an argument or set the "
"ROBOFLOW_API_KEY environment variable."
)
args.roboflow_api_key = api_key
video_info = sv.VideoInfo.from_video_path(video_path=args.source_video_path)
model = get_roboflow_model(model_id=args.model_id, api_key=args.roboflow_api_key)
byte_track = sv.ByteTrack(
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
)
thickness = sv.calculate_dynamic_line_thickness(
resolution_wh=video_info.resolution_wh
)
text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh)
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
label_annotator = sv.LabelAnnotator(
text_scale=text_scale,
text_thickness=thickness,
text_position=sv.Position.BOTTOM_CENTER,
)
trace_annotator = sv.TraceAnnotator(
thickness=thickness,
trace_length=video_info.fps * 2,
position=sv.Position.BOTTOM_CENTER,
)
frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path)
polygon_zone = sv.PolygonZone(
polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh
)
view_transformer = ViewTransformer(source=SOURCE, target=TARGET)
coordinates = defaultdict(lambda: deque(maxlen=video_info.fps))
with sv.VideoSink(args.target_video_path, video_info) as sink:
for frame in frame_generator:
results = model.infer(frame)[0]
detections = sv.Detections.from_inference(results)
detections = detections[detections.confidence > args.confidence_threshold]
detections = detections[polygon_zone.trigger(detections)]
detections = detections.with_nms(threshold=args.iou_threshold)
detections = byte_track.update_with_detections(detections=detections)
points = detections.get_anchors_coordinates(
anchor=sv.Position.BOTTOM_CENTER
)
points = view_transformer.transform_points(points=points).astype(int)
for tracker_id, [_, y] in zip(detections.tracker_id, points):
coordinates[tracker_id].append(y)
labels = []
for tracker_id in detections.tracker_id:
if len(coordinates[tracker_id]) < video_info.fps / 2:
labels.append(f"#{tracker_id}")
else:
coordinate_start = coordinates[tracker_id][-1]
coordinate_end = coordinates[tracker_id][0]
distance = abs(coordinate_start - coordinate_end)
time = len(coordinates[tracker_id]) / video_info.fps
speed = distance / time * 3.6
labels.append(f"#{tracker_id} {int(speed)} km/h")
annotated_frame = frame.copy()
annotated_frame = trace_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = bounding_box_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = label_annotator.annotate(
scene=annotated_frame, detections=detections, labels=labels
)
sink.write_frame(annotated_frame)
cv2.imshow("frame", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
@@ -0,0 +1,6 @@
supervision==0.19.0
tqdm==4.66.1
requests
ultralytics==8.0.237
super-gradients==3.5.0
inference==0.9.8
@@ -0,0 +1,148 @@
import argparse
from collections import defaultdict, deque
import cv2
import numpy as np
from ultralytics import YOLO
import supervision as sv
SOURCE = np.array([[1252, 787], [2298, 803], [5039, 2159], [-550, 2159]])
TARGET_WIDTH = 25
TARGET_HEIGHT = 250
TARGET = np.array(
[
[0, 0],
[TARGET_WIDTH - 1, 0],
[TARGET_WIDTH - 1, TARGET_HEIGHT - 1],
[0, TARGET_HEIGHT - 1],
]
)
class ViewTransformer:
def __init__(self, source: np.ndarray, target: np.ndarray) -> None:
source = source.astype(np.float32)
target = target.astype(np.float32)
self.m = cv2.getPerspectiveTransform(source, target)
def transform_points(self, points: np.ndarray) -> np.ndarray:
if points.size == 0:
return points
reshaped_points = points.reshape(-1, 1, 2).astype(np.float32)
transformed_points = cv2.perspectiveTransform(reshaped_points, self.m)
return transformed_points.reshape(-1, 2)
def parse_arguments() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Vehicle Speed Estimation using Ultralytics and Supervision"
)
parser.add_argument(
"--source_video_path",
required=True,
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
required=True,
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.3,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold", default=0.7, help="IOU threshold for the model", type=float
)
return parser.parse_args()
if __name__ == "__main__":
args = parse_arguments()
video_info = sv.VideoInfo.from_video_path(video_path=args.source_video_path)
model = YOLO("yolov8x.pt")
byte_track = sv.ByteTrack(
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
)
thickness = sv.calculate_dynamic_line_thickness(
resolution_wh=video_info.resolution_wh
)
text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh)
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
label_annotator = sv.LabelAnnotator(
text_scale=text_scale,
text_thickness=thickness,
text_position=sv.Position.BOTTOM_CENTER,
)
trace_annotator = sv.TraceAnnotator(
thickness=thickness,
trace_length=video_info.fps * 2,
position=sv.Position.BOTTOM_CENTER,
)
frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path)
polygon_zone = sv.PolygonZone(
polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh
)
view_transformer = ViewTransformer(source=SOURCE, target=TARGET)
coordinates = defaultdict(lambda: deque(maxlen=video_info.fps))
with sv.VideoSink(args.target_video_path, video_info) as sink:
for frame in frame_generator:
result = model(frame)[0]
detections = sv.Detections.from_ultralytics(result)
detections = detections[detections.confidence > args.confidence_threshold]
detections = detections[polygon_zone.trigger(detections)]
detections = detections.with_nms(threshold=args.iou_threshold)
detections = byte_track.update_with_detections(detections=detections)
points = detections.get_anchors_coordinates(
anchor=sv.Position.BOTTOM_CENTER
)
points = view_transformer.transform_points(points=points).astype(int)
for tracker_id, [_, y] in zip(detections.tracker_id, points):
coordinates[tracker_id].append(y)
labels = []
for tracker_id in detections.tracker_id:
if len(coordinates[tracker_id]) < video_info.fps / 2:
labels.append(f"#{tracker_id}")
else:
coordinate_start = coordinates[tracker_id][-1]
coordinate_end = coordinates[tracker_id][0]
distance = abs(coordinate_start - coordinate_end)
time = len(coordinates[tracker_id]) / video_info.fps
speed = distance / time * 3.6
labels.append(f"#{tracker_id} {int(speed)} km/h")
annotated_frame = frame.copy()
annotated_frame = trace_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = bounding_box_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = label_annotator.annotate(
scene=annotated_frame, detections=detections, labels=labels
)
sink.write_frame(annotated_frame)
cv2.imshow("frame", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
@@ -0,0 +1,8 @@
import os
from supervision.assets import VideoAssets, download_assets
if not os.path.exists("data"):
os.makedirs("data")
os.chdir("data")
download_assets(VideoAssets.VEHICLES)
@@ -0,0 +1,148 @@
import argparse
from collections import defaultdict, deque
import cv2
import numpy as np
from super_gradients.common.object_names import Models
from super_gradients.training import models
import supervision as sv
SOURCE = np.array([[1252, 787], [2298, 803], [5039, 2159], [-550, 2159]])
TARGET_WIDTH = 25
TARGET_HEIGHT = 250
TARGET = np.array(
[
[0, 0],
[TARGET_WIDTH - 1, 0],
[TARGET_WIDTH - 1, TARGET_HEIGHT - 1],
[0, TARGET_HEIGHT - 1],
]
)
class ViewTransformer:
def __init__(self, source: np.ndarray, target: np.ndarray) -> None:
source = source.astype(np.float32)
target = target.astype(np.float32)
self.m = cv2.getPerspectiveTransform(source, target)
def transform_points(self, points: np.ndarray) -> np.ndarray:
if points.size == 0:
return points
reshaped_points = points.reshape(-1, 1, 2).astype(np.float32)
transformed_points = cv2.perspectiveTransform(reshaped_points, self.m)
return transformed_points.reshape(-1, 2)
def parse_arguments() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Vehicle Speed Estimation using YOLO-NAS and Supervision"
)
parser.add_argument(
"--source_video_path",
required=True,
help="Path to the source video file",
type=str,
)
parser.add_argument(
"--target_video_path",
required=True,
help="Path to the target video file (output)",
type=str,
)
parser.add_argument(
"--confidence_threshold",
default=0.3,
help="Confidence threshold for the model",
type=float,
)
parser.add_argument(
"--iou_threshold", default=0.7, help="IOU threshold for the model", type=float
)
return parser.parse_args()
if __name__ == "__main__":
args = parse_arguments()
video_info = sv.VideoInfo.from_video_path(video_path=args.source_video_path)
model = models.get(Models.YOLO_NAS_L, pretrained_weights="coco")
byte_track = sv.ByteTrack(
frame_rate=video_info.fps, track_thresh=args.confidence_threshold
)
thickness = sv.calculate_dynamic_line_thickness(
resolution_wh=video_info.resolution_wh
)
text_scale = sv.calculate_dynamic_text_scale(resolution_wh=video_info.resolution_wh)
bounding_box_annotator = sv.BoundingBoxAnnotator(thickness=thickness)
label_annotator = sv.LabelAnnotator(
text_scale=text_scale,
text_thickness=thickness,
text_position=sv.Position.BOTTOM_CENTER,
)
trace_annotator = sv.TraceAnnotator(
thickness=thickness,
trace_length=video_info.fps * 2,
position=sv.Position.BOTTOM_CENTER,
)
frame_generator = sv.get_video_frames_generator(source_path=args.source_video_path)
polygon_zone = sv.PolygonZone(
polygon=SOURCE, frame_resolution_wh=video_info.resolution_wh
)
view_transformer = ViewTransformer(source=SOURCE, target=TARGET)
coordinates = defaultdict(lambda: deque(maxlen=video_info.fps))
with sv.VideoSink(args.target_video_path, video_info) as sink:
for frame in frame_generator:
result = model.predict(frame)[0]
detections = sv.Detections.from_yolo_nas(result)
detections = detections[polygon_zone.trigger(detections)]
detections = detections.with_nms(threshold=args.iou_threshold)
detections = byte_track.update_with_detections(detections=detections)
points = detections.get_anchors_coordinates(
anchor=sv.Position.BOTTOM_CENTER
)
points = view_transformer.transform_points(points=points).astype(int)
for tracker_id, [_, y] in zip(detections.tracker_id, points):
coordinates[tracker_id].append(y)
labels = []
for tracker_id in detections.tracker_id:
if len(coordinates[tracker_id]) < video_info.fps / 2:
labels.append(f"#{tracker_id}")
else:
coordinate_start = coordinates[tracker_id][-1]
coordinate_end = coordinates[tracker_id][0]
distance = abs(coordinate_start - coordinate_end)
time = len(coordinates[tracker_id]) / video_info.fps
speed = distance / time * 3.6
labels.append(f"#{tracker_id} {int(speed)} km/h")
annotated_frame = frame.copy()
annotated_frame = trace_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = bounding_box_annotator.annotate(
scene=annotated_frame, detections=detections
)
annotated_frame = label_annotator.annotate(
scene=annotated_frame, detections=detections, labels=labels
)
sink.write_frame(annotated_frame)
cv2.imshow("frame", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
+9
View File
@@ -0,0 +1,9 @@
data/
venv*/
*.pt
*.pth
*.mp4
*.mov
*.png
*.jpg
*.jpeg
+262
View File
@@ -0,0 +1,262 @@
# time in zone
## 👋 hello
Practical demonstration on leveraging computer vision for analyzing wait times and
monitoring the duration that objects or individuals spend in predefined areas of video
frames. This example project, perfect for retail analytics or traffic management
applications.
https://github.com/roboflow/supervision/assets/26109316/d051cc8a-dd15-41d4-aa36-d38b86334c39
## 💻 install
- clone repository and navigate to example directory
```bash
git clone https://github.com/roboflow/supervision.git
cd supervision/examples/time_in_zone
```
- setup python environment and activate it [optional]
```bash
python3 -m venv venv
source venv/bin/activate
```
- install required dependencies
```bash
pip install -r requirements.txt
```
## 🛠 scripts
### `download_from_youtube`
This script allows you to download a video from YouTube.
- `--url`: The full URL of the YouTube video you wish to download.
- `--output_path` (optional): Specifies the directory where the video will be saved.
- `--file_name` (optional): Sets the name of the saved video file.
```bash
python scripts/download_from_youtube.py \
--url "https://www.youtube.com/watch?v=-8zyEwAa50Q" \
--output_path "data/checkout" \
--file_name "video.mp4"
```
```bash
python scripts/download_from_youtube.py \
--url "https://www.youtube.com/watch?v=MNn9qKG2UFI" \
--output_path "data/traffic" \
--file_name "video.mp4"
```
### `stream_from_file`
This script allows you to stream video files from a directory. It's an awesome way to
mock a live video stream for local testing. Video will be streamed in a loop under
`rtsp://localhost:8554/live0.stream` URL. This script requires docker to be installed.
- `--video_directory`: Directory containing video files to stream.
- `--number_of_streams`: Number of video files to stream.
```bash
python scripts/stream_from_file.py \
--video_directory "data/checkout" \
--number_of_streams 1
```
```bash
python scripts/stream_from_file.py \
--video_directory "data/traffic" \
--number_of_streams 1
```
### `draw_zones`
If you want to test zone time in zone analysis on your own video, you can use this
script to design custom zones and save results as a JSON file. The script will open a
window where you can draw polygons on the source image or video file. The polygons will
be saved as a JSON file.
- `--source_path`: Path to the source image or video file for drawing polygons.
- `--zone_configuration_path`: Path where the polygon annotations will be saved as a JSON file.
- `enter` - finish drawing the current polygon.
- `escape` - cancel drawing the current polygon.
- `q` - quit the drawing window.
- `s` - save zone configuration to a JSON file.
```bash
python scripts/draw_zones.py \
--source_path "data/checkout/video.mp4" \
--zone_configuration_path "data/checkout/config.json"
```
```bash
python scripts/draw_zones.py \
--source_path "data/traffic/video.mp4" \
--zone_configuration_path "data/traffic/custom_config.json"
```
https://github.com/roboflow/supervision/assets/26109316/9d514c9e-2a61-418b-ae49-6ac1ad6ae5ac
## 🎬 video & stream processing
### `inference_file_example`
Script to run object detection on a video file using the Roboflow Inference model.
- `--zone_configuration_path`: Path to the zone configuration JSON file.
- `--source_video_path`: Path to the source video file.
- `--model_id`: Roboflow model ID.
- `--classes`: List of class IDs to track. If empty, all classes are tracked.
- `--confidence_threshold`: Confidence level for detections (`0` to `1`). Default is `0.3`.
- `--iou_threshold`: IOU threshold for non-max suppression. Default is `0.7`.
```bash
python inference_file_example.py \
--zone_configuration_path "data/checkout/config.json" \
--source_video_path "data/checkout/video.mp4" \
--model_id "yolov8x-640" \
--classes 0 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
https://github.com/roboflow/supervision/assets/26109316/d051cc8a-dd15-41d4-aa36-d38b86334c39
```bash
python inference_file_example.py \
--zone_configuration_path "data/traffic/config.json" \
--source_video_path "data/traffic/video.mp4" \
--model_id "yolov8x-640" \
--classes 2 5 6 7 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
https://github.com/roboflow/supervision/assets/26109316/5ec896d7-4b39-4426-8979-11e71666878b
### `inference_stream_example`
Script to run object detection on a video stream using the Roboflow Inference model.
- `--zone_configuration_path`: Path to the zone configuration JSON file.
- `--rtsp_url`: Complete RTSP URL for the video stream.
- `--model_id`: Roboflow model ID.
- `--classes`: List of class IDs to track. If empty, all classes are tracked.
- `--confidence_threshold`: Confidence level for detections (`0` to `1`). Default is `0.3`.
- `--iou_threshold`: IOU threshold for non-max suppression. Default is `0.7`.
```bash
python inference_file_example.py \
--zone_configuration_path "data/checkout/config.json" \
--rtsp_url "rtsp://localhost:8554/live0.stream" \
--model_id "yolov8x-640" \
--classes 0 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
```bash
python inference_file_example.py \
--zone_configuration_path "data/traffic/config.json" \
--rtsp_url "rtsp://localhost:8554/live0.stream" \
--model_id "yolov8x-640" \
--classes 2 5 6 7 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
<details>
<summary>👉 show ultralytics examples</summary>
### `ultralytics_file_example`
Script to run object detection on a video file using the Ultralytics YOLOv8 model.
- `--zone_configuration_path`: Path to the zone configuration JSON file.
- `--source_video_path`: Path to the source video file.
- `--weights`: Path to the model weights file. Default is `'yolov8s.pt'`.
- `--device`: Computation device (`'cpu'`, `'mps'` or `'cuda'`). Default is `'cpu'`.
- `--classes`: List of class IDs to track. If empty, all classes are tracked.
- `--confidence_threshold`: Confidence level for detections (`0` to `1`). Default is `0.3`.
- `--iou_threshold`: IOU threshold for non-max suppression. Default is `0.7`.
```bash
python inference_file_example.py \
--zone_configuration_path "data/checkout/config.json" \
--source_video_path "data/checkout/video.mp4" \
--weights "yolov8x.pt" \
--device "cpu" \
--classes 0 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
```bash
python inference_file_example.py \
--zone_configuration_path "data/traffic/config.json" \
--source_video_path "data/traffic/video.mp4" \
--weights "yolov8x.pt" \
--device "cpu" \
--classes 2 5 6 7 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
### `ultralytics_stream_example`
Script to run object detection on a video stream using the Ultralytics YOLOv8 model.
- `--zone_configuration_path`: Path to the zone configuration JSON file.
- `--rtsp_url`: Complete RTSP URL for the video stream.
- `--weights`: Path to the model weights file. Default is `'yolov8s.pt'`.
- `--device`: Computation device (`'cpu'`, `'mps'` or `'cuda'`). Default is `'cpu'`.
- `--classes`: List of class IDs to track. If empty, all classes are tracked.
- `--confidence_threshold`: Confidence level for detections (`0` to `1`). Default is `0.3`.
- `--iou_threshold`: IOU threshold for non-max suppression. Default is `0.7`.
```bash
python inference_file_example.py \
--zone_configuration_path "data/checkout/config.json" \
--rtsp_url "rtsp://localhost:8554/live0.stream" \
--weights "yolov8x.pt" \
--device "cpu" \
--classes 0 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
```bash
python inference_file_example.py \
--zone_configuration_path "data/traffic/config.json" \
--rtsp_url "rtsp://localhost:8554/live0.stream" \
--weights "yolov8x.pt" \
--device "cpu" \
--classes 2 5 6 7 \
--confidence_threshold 0.3 \
--iou_threshold 0.7
```
</details>
## © license
This demo integrates two main components, each with its own licensing:
- ultralytics: The object detection model used in this demo, YOLOv8, is distributed
under the [AGPL-3.0 license](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).
You can find more details about this license here.
- supervision: The analytics code that powers the zone-based analysis in this demo is
based on the Supervision library, which is licensed under the
[MIT license](https://github.com/roboflow/supervision/blob/develop/LICENSE.md). This
makes the Supervision part of the code fully open source and freely usable in your
projects.
@@ -0,0 +1,132 @@
import argparse
from typing import List
import cv2
import numpy as np
from inference import get_model
from utils.general import find_in_list, load_zones_config
from utils.timers import FPSBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
def main(
source_video_path: str,
zone_configuration_path: str,
model_id: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
model = get_model(model_id=model_id)
tracker = sv.ByteTrack(minimum_matching_threshold=0.5)
video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)
frames_generator = sv.get_video_frames_generator(source_video_path)
frame = next(frames_generator)
resolution_wh = frame.shape[1], frame.shape[0]
polygons = load_zones_config(file_path=zone_configuration_path)
zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in polygons
]
timers = [FPSBasedTimer(video_info.fps) for _ in zones]
for frame in frames_generator:
results = model.infer(frame, confidence=confidence, iou_threshold=iou)[0]
detections = sv.Detections.from_inference(results)
detections = detections[find_in_list(detections.class_id, classes)]
detections = tracker.update_with_detections(detections)
annotated_frame = frame.copy()
for idx, zone in enumerate(zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using video file."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--source_video_path",
type=str,
required=True,
help="Path to the source video file.",
)
parser.add_argument(
"--model_id", type=str, default="yolov8s-640", help="Roboflow model ID."
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
source_video_path=args.source_video_path,
zone_configuration_path=args.zone_configuration_path,
model_id=args.model_id,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)
@@ -0,0 +1,142 @@
import argparse
from typing import List
import cv2
import numpy as np
from inference import get_model
from utils.general import find_in_list, get_stream_frames_generator, load_zones_config
from utils.timers import ClockBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
def main(
rtsp_url: str,
zone_configuration_path: str,
model_id: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
model = get_model(model_id=model_id)
tracker = sv.ByteTrack(minimum_matching_threshold=0.5)
frames_generator = get_stream_frames_generator(rtsp_url=rtsp_url)
fps_monitor = sv.FPSMonitor()
frame = next(frames_generator)
resolution_wh = frame.shape[1], frame.shape[0]
polygons = load_zones_config(file_path=zone_configuration_path)
zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in polygons
]
timers = [ClockBasedTimer() for _ in zones]
for frame in frames_generator:
fps_monitor.tick()
fps = fps_monitor.fps
results = model.infer(frame, confidence=confidence, iou_threshold=iou)[0]
detections = sv.Detections.from_inference(results)
detections = detections[find_in_list(detections.class_id, classes)]
detections = tracker.update_with_detections(detections)
annotated_frame = frame.copy()
annotated_frame = sv.draw_text(
scene=annotated_frame,
text=f"{fps:.1f}",
text_anchor=sv.Point(40, 30),
background_color=sv.Color.from_hex("#A351FB"),
text_color=sv.Color.from_hex("#000000"),
)
for idx, zone in enumerate(zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using RTSP stream."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--rtsp_url",
type=str,
required=True,
help="Complete RTSP URL for the video stream.",
)
parser.add_argument(
"--model_id", type=str, default="yolov8s-640", help="Roboflow model ID."
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
rtsp_url=args.rtsp_url,
zone_configuration_path=args.zone_configuration_path,
model_id=args.model_id,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)
@@ -0,0 +1,158 @@
import argparse
from typing import List
import cv2
import numpy as np
from inference import InferencePipeline
from inference.core.interfaces.camera.entities import VideoFrame
from utils.general import find_in_list, load_zones_config
from utils.timers import ClockBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
class CustomSink:
def __init__(self, zone_configuration_path: str, classes: List[int]):
self.classes = classes
self.tracker = sv.ByteTrack(minimum_matching_threshold=0.5)
self.fps_monitor = sv.FPSMonitor()
self.polygons = load_zones_config(file_path=zone_configuration_path)
self.timers = [ClockBasedTimer() for _ in self.polygons]
self.zones = None
def on_prediction(self, result: dict, frame: VideoFrame) -> None:
if self.zones is None:
resolution_wh = frame.image.shape[1], frame.image.shape[0]
self.zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in self.polygons
]
self.fps_monitor.tick()
fps = self.fps_monitor.fps
detections = sv.Detections.from_inference(result)
detections = detections[find_in_list(detections.class_id, self.classes)]
detections = self.tracker.update_with_detections(detections)
annotated_frame = frame.image.copy()
annotated_frame = sv.draw_text(
scene=annotated_frame,
text=f"{fps:.1f}",
text_anchor=sv.Point(40, 30),
background_color=sv.Color.from_hex("#A351FB"),
text_color=sv.Color.from_hex("#000000"),
)
for idx, zone in enumerate(self.zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = self.timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
cv2.waitKey(1)
def main(
rtsp_url: str,
zone_configuration_path: str,
model_id: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
sink = CustomSink(zone_configuration_path=zone_configuration_path, classes=classes)
pipeline = InferencePipeline.init(
model_id=model_id,
video_reference=rtsp_url,
on_prediction=sink.on_prediction,
confidence=confidence,
iou_threshold=iou,
)
pipeline.start()
try:
pipeline.join()
except KeyboardInterrupt:
pipeline.terminate()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using RTSP stream."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--rtsp_url",
type=str,
required=True,
help="Complete RTSP URL for the video stream.",
)
parser.add_argument(
"--model_id", type=str, default="yolov8s-640", help="Roboflow model ID."
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
rtsp_url=args.rtsp_url,
zone_configuration_path=args.zone_configuration_path,
model_id=args.model_id,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)
+5
View File
@@ -0,0 +1,5 @@
opencv-python
supervision
ultralytics
inference
pytube
@@ -0,0 +1,46 @@
import argparse
import os
from typing import Optional
from pytube import YouTube
def main(url: str, output_path: Optional[str], file_name: Optional[str]) -> None:
yt = YouTube(url)
stream = yt.streams.get_highest_resolution()
if not os.path.exists(output_path):
os.makedirs(output_path)
stream.download(output_path=output_path, filename=file_name)
final_name = file_name if file_name else yt.title
final_path = output_path if output_path else "current directory"
print(f"Download completed! Video saved as '{final_name}' in '{final_path}'.")
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Download a specific YouTube video by providing its URL."
)
parser.add_argument(
"--url",
type=str,
required=True,
help="The full URL of the YouTube video you wish to download.",
)
parser.add_argument(
"--output_path",
type=str,
default="data/source",
required=False,
help="Optional. Specifies the directory where the video will be saved.",
)
parser.add_argument(
"--file_name",
type=str,
default="video.mp4",
required=False,
help="Optional. Sets the name of the saved video file.",
)
args = parser.parse_args()
main(url=args.url, output_path=args.output_path, file_name=args.file_name)
+176
View File
@@ -0,0 +1,176 @@
import argparse
import json
import os
from typing import Any, Optional, Tuple
import cv2
import numpy as np
import supervision as sv
KEY_ENTER = 13
KEY_NEWLINE = 10
KEY_ESCAPE = 27
KEY_QUIT = ord("q")
KEY_SAVE = ord("s")
THICKNESS = 2
COLORS = sv.ColorPalette.DEFAULT
WINDOW_NAME = "Draw Zones"
POLYGONS = [[]]
current_mouse_position: Optional[Tuple[int, int]] = None
def resolve_source(source_path: str) -> Optional[np.ndarray]:
if not os.path.exists(source_path):
return None
image = cv2.imread(source_path)
if image is not None:
return image
frame_generator = sv.get_video_frames_generator(source_path=source_path)
frame = next(frame_generator)
return frame
def mouse_event(event: int, x: int, y: int, flags: int, param: Any) -> None:
global current_mouse_position
if event == cv2.EVENT_MOUSEMOVE:
current_mouse_position = (x, y)
elif event == cv2.EVENT_LBUTTONDOWN:
POLYGONS[-1].append((x, y))
def redraw(image: np.ndarray, original_image: np.ndarray) -> None:
global POLYGONS, current_mouse_position
image[:] = original_image.copy()
for idx, polygon in enumerate(POLYGONS):
color = (
COLORS.by_idx(idx).as_bgr()
if idx < len(POLYGONS) - 1
else sv.Color.WHITE.as_bgr()
)
if len(polygon) > 1:
for i in range(1, len(polygon)):
cv2.line(
img=image,
pt1=polygon[i - 1],
pt2=polygon[i],
color=color,
thickness=THICKNESS,
)
if idx < len(POLYGONS) - 1:
cv2.line(
img=image,
pt1=polygon[-1],
pt2=polygon[0],
color=color,
thickness=THICKNESS,
)
if idx == len(POLYGONS) - 1 and current_mouse_position is not None and polygon:
cv2.line(
img=image,
pt1=polygon[-1],
pt2=current_mouse_position,
color=color,
thickness=THICKNESS,
)
cv2.imshow(WINDOW_NAME, image)
def close_and_finalize_polygon(image: np.ndarray, original_image: np.ndarray) -> None:
if len(POLYGONS[-1]) > 2:
cv2.line(
img=image,
pt1=POLYGONS[-1][-1],
pt2=POLYGONS[-1][0],
color=COLORS.by_idx(0).as_bgr(),
thickness=THICKNESS,
)
POLYGONS.append([])
image[:] = original_image.copy()
redraw_polygons(image)
cv2.imshow(WINDOW_NAME, image)
def redraw_polygons(image: np.ndarray) -> None:
for idx, polygon in enumerate(POLYGONS[:-1]):
if len(polygon) > 1:
color = COLORS.by_idx(idx).as_bgr()
for i in range(len(polygon) - 1):
cv2.line(
img=image,
pt1=polygon[i],
pt2=polygon[i + 1],
color=color,
thickness=THICKNESS,
)
cv2.line(
img=image,
pt1=polygon[-1],
pt2=polygon[0],
color=color,
thickness=THICKNESS,
)
def save_polygons_to_json(polygons, target_path):
data_to_save = polygons if polygons[-1] else polygons[:-1]
with open(target_path, "w") as f:
json.dump(data_to_save, f)
def main(source_path: str, zone_configuration_path: str) -> None:
global current_mouse_position
original_image = resolve_source(source_path=source_path)
if original_image is None:
print("Failed to load source image.")
return
image = original_image.copy()
cv2.imshow(WINDOW_NAME, image)
cv2.setMouseCallback(WINDOW_NAME, mouse_event, image)
while True:
key = cv2.waitKey(1) & 0xFF
if key == KEY_ENTER or key == KEY_NEWLINE:
close_and_finalize_polygon(image, original_image)
elif key == KEY_ESCAPE:
POLYGONS[-1] = []
current_mouse_position = None
elif key == KEY_SAVE:
save_polygons_to_json(POLYGONS, zone_configuration_path)
print(f"Polygons saved to {zone_configuration_path}")
break
redraw(image, original_image)
if key == KEY_QUIT:
break
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Interactively draw polygons on images or video frames and save "
"the annotations."
)
parser.add_argument(
"--source_path",
type=str,
required=True,
help="Path to the source image or video file for drawing polygons.",
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path where the polygon annotations will be saved as a JSON file.",
)
arguments = parser.parse_args()
main(
source_path=arguments.source_path,
zone_configuration_path=arguments.zone_configuration_path,
)
@@ -0,0 +1,104 @@
import argparse
import os
import subprocess
import tempfile
from glob import glob
from threading import Thread
import yaml
SERVER_CONFIG = {"protocols": ["tcp"], "paths": {"all": {"source": "publisher"}}}
BASE_STREAM_URL = "rtsp://localhost:8554/live"
def main(video_directory: str, number_of_streams: int) -> None:
video_files = find_video_files_in_directory(video_directory, number_of_streams)
try:
with tempfile.TemporaryDirectory() as temporary_directory:
config_file_path = create_server_config_file(temporary_directory)
run_rtsp_server(config_path=config_file_path)
stream_videos(video_files)
finally:
stop_rtsp_server()
def find_video_files_in_directory(directory: str, limit: int) -> list:
video_formats = ["*.mp4", "*.webm"]
video_paths = []
for video_format in video_formats:
video_paths.extend(glob(os.path.join(directory, video_format)))
return video_paths[:limit]
def create_server_config_file(directory: str) -> str:
config_path = os.path.join(directory, "rtsp-simple-server.yml")
with open(config_path, "w") as config_file:
yaml.dump(SERVER_CONFIG, config_file)
return config_path
def run_rtsp_server(config_path: str) -> None:
command = (
"docker run --rm --name rtsp_server -d -v "
f"{config_path}:/rtsp-simple-server.yml -p 8554:8554 "
"aler9/rtsp-simple-server:v1.3.0"
)
if run_command(command.split()) != 0:
raise RuntimeError("Could not start the RTSP server!")
def stop_rtsp_server() -> None:
run_command("docker kill rtsp_server".split())
def stream_videos(video_files: list) -> None:
threads = []
for index, video_file in enumerate(video_files):
stream_url = f"{BASE_STREAM_URL}{index}.stream"
print(f"Streaming {video_file} under {stream_url}")
thread = stream_video_to_url(video_file, stream_url)
threads.append(thread)
for thread in threads:
thread.join()
def stream_video_to_url(video_path: str, stream_url: str) -> Thread:
command = (
f"ffmpeg -re -stream_loop -1 -i {video_path} "
f"-f rtsp -rtsp_transport tcp {stream_url}"
)
return run_command_in_thread(command.split())
def run_command_in_thread(command: list) -> Thread:
thread = Thread(target=run_command, args=(command,))
thread.start()
return thread
def run_command(command: list) -> int:
process = subprocess.run(command)
return process.returncode
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Script to stream videos using RTSP protocol."
)
parser.add_argument(
"--video_directory",
type=str,
required=True,
help="Directory containing video files to stream.",
)
parser.add_argument(
"--number_of_streams",
type=int,
default=6,
help="Number of video files to stream.",
)
arguments = parser.parse_args()
main(
video_directory=arguments.video_directory,
number_of_streams=arguments.number_of_streams,
)
@@ -0,0 +1,144 @@
import argparse
from typing import List
import cv2
import numpy as np
from ultralytics import YOLO
from utils.general import find_in_list, load_zones_config
from utils.timers import FPSBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
def main(
source_video_path: str,
zone_configuration_path: str,
weights: str,
device: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
model = YOLO(weights)
tracker = sv.ByteTrack(minimum_matching_threshold=0.5)
video_info = sv.VideoInfo.from_video_path(video_path=source_video_path)
frames_generator = sv.get_video_frames_generator(source_video_path)
frame = next(frames_generator)
resolution_wh = frame.shape[1], frame.shape[0]
polygons = load_zones_config(file_path=zone_configuration_path)
zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in polygons
]
timers = [FPSBasedTimer(video_info.fps) for _ in zones]
for frame in frames_generator:
results = model(frame, verbose=False, device=device, conf=confidence)[0]
detections = sv.Detections.from_ultralytics(results)
detections = detections[find_in_list(detections.class_id, classes)]
detections = detections.with_nms(threshold=iou)
detections = tracker.update_with_detections(detections)
annotated_frame = frame.copy()
for idx, zone in enumerate(zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using video file."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--source_video_path",
type=str,
required=True,
help="Path to the source video file.",
)
parser.add_argument(
"--weights",
type=str,
default="yolov8s.pt",
help="Path to the model weights file. Default is 'yolov8s.pt'.",
)
parser.add_argument(
"--device",
type=str,
default="cpu",
help="Computation device ('cpu', 'mps' or 'cuda'). Default is 'cpu'.",
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
source_video_path=args.source_video_path,
zone_configuration_path=args.zone_configuration_path,
weights=args.weights,
device=args.device,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)
@@ -0,0 +1,154 @@
import argparse
from typing import List
import cv2
import numpy as np
from ultralytics import YOLO
from utils.general import find_in_list, get_stream_frames_generator, load_zones_config
from utils.timers import ClockBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
def main(
rtsp_url: str,
zone_configuration_path: str,
weights: str,
device: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
model = YOLO(weights)
tracker = sv.ByteTrack(minimum_matching_threshold=0.5)
frames_generator = get_stream_frames_generator(rtsp_url=rtsp_url)
fps_monitor = sv.FPSMonitor()
frame = next(frames_generator)
resolution_wh = frame.shape[1], frame.shape[0]
polygons = load_zones_config(file_path=zone_configuration_path)
zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in polygons
]
timers = [ClockBasedTimer() for _ in zones]
for frame in frames_generator:
fps_monitor.tick()
fps = fps_monitor.fps
results = model(frame, verbose=False, device=device, conf=confidence)[0]
detections = sv.Detections.from_ultralytics(results)
detections = detections[find_in_list(detections.class_id, classes)]
detections = detections.with_nms(threshold=iou)
detections = tracker.update_with_detections(detections)
annotated_frame = frame.copy()
annotated_frame = sv.draw_text(
scene=annotated_frame,
text=f"{fps:.1f}",
text_anchor=sv.Point(40, 30),
background_color=sv.Color.from_hex("#A351FB"),
text_color=sv.Color.from_hex("#000000"),
)
for idx, zone in enumerate(zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
if cv2.waitKey(1) & 0xFF == ord("q"):
break
cv2.destroyAllWindows()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using RTSP stream."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--rtsp_url",
type=str,
required=True,
help="Complete RTSP URL for the video stream.",
)
parser.add_argument(
"--weights",
type=str,
default="yolov8s.pt",
help="Path to the model weights file. Default is 'yolov8s.pt'.",
)
parser.add_argument(
"--device",
type=str,
default="cpu",
help="Computation device ('cpu', 'mps' or 'cuda'). Default is 'cpu'.",
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
rtsp_url=args.rtsp_url,
zone_configuration_path=args.zone_configuration_path,
weights=args.weights,
device=args.device,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)
@@ -0,0 +1,173 @@
import argparse
from typing import List
import cv2
import numpy as np
from inference import InferencePipeline
from inference.core.interfaces.camera.entities import VideoFrame
from ultralytics import YOLO
from utils.general import find_in_list, load_zones_config
from utils.timers import ClockBasedTimer
import supervision as sv
COLORS = sv.ColorPalette.from_hex(["#E6194B", "#3CB44B", "#FFE119", "#3C76D1"])
COLOR_ANNOTATOR = sv.ColorAnnotator(color=COLORS)
LABEL_ANNOTATOR = sv.LabelAnnotator(
color=COLORS, text_color=sv.Color.from_hex("#000000")
)
class CustomSink:
def __init__(self, zone_configuration_path: str, classes: List[int]):
self.classes = classes
self.tracker = sv.ByteTrack(minimum_matching_threshold=0.8)
self.fps_monitor = sv.FPSMonitor()
self.polygons = load_zones_config(file_path=zone_configuration_path)
self.timers = [ClockBasedTimer() for _ in self.polygons]
self.zones = None
def on_prediction(self, detections: sv.Detections, frame: VideoFrame) -> None:
if self.zones is None:
resolution_wh = frame.image.shape[1], frame.image.shape[0]
self.zones = [
sv.PolygonZone(
polygon=polygon,
frame_resolution_wh=resolution_wh,
triggering_anchors=(sv.Position.CENTER,),
)
for polygon in self.polygons
]
self.fps_monitor.tick()
fps = self.fps_monitor.fps
detections = detections[find_in_list(detections.class_id, self.classes)]
detections = self.tracker.update_with_detections(detections)
annotated_frame = frame.image.copy()
annotated_frame = sv.draw_text(
scene=annotated_frame,
text=f"{fps:.1f}",
text_anchor=sv.Point(40, 30),
background_color=sv.Color.from_hex("#A351FB"),
text_color=sv.Color.from_hex("#000000"),
)
for idx, zone in enumerate(self.zones):
annotated_frame = sv.draw_polygon(
scene=annotated_frame, polygon=zone.polygon, color=COLORS.by_idx(idx)
)
detections_in_zone = detections[zone.trigger(detections)]
time_in_zone = self.timers[idx].tick(detections_in_zone)
custom_color_lookup = np.full(detections_in_zone.class_id.shape, idx)
annotated_frame = COLOR_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
custom_color_lookup=custom_color_lookup,
)
labels = [
f"#{tracker_id} {int(time // 60):02d}:{int(time % 60):02d}"
for tracker_id, time in zip(detections_in_zone.tracker_id, time_in_zone)
]
annotated_frame = LABEL_ANNOTATOR.annotate(
scene=annotated_frame,
detections=detections_in_zone,
labels=labels,
custom_color_lookup=custom_color_lookup,
)
cv2.imshow("Processed Video", annotated_frame)
cv2.waitKey(1)
def main(
rtsp_url: str,
zone_configuration_path: str,
weights: str,
device: str,
confidence: float,
iou: float,
classes: List[int],
) -> None:
model = YOLO(weights)
def inference_callback(frame: VideoFrame) -> sv.Detections:
results = model(frame.image, verbose=False, conf=confidence, device=device)[0]
return sv.Detections.from_ultralytics(results).with_nms(threshold=iou)
sink = CustomSink(zone_configuration_path=zone_configuration_path, classes=classes)
pipeline = InferencePipeline.init_with_custom_logic(
video_reference=rtsp_url,
on_video_frame=inference_callback,
on_prediction=sink.on_prediction,
)
pipeline.start()
try:
pipeline.join()
except KeyboardInterrupt:
pipeline.terminate()
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Calculating detections dwell time in zones, using RTSP stream."
)
parser.add_argument(
"--zone_configuration_path",
type=str,
required=True,
help="Path to the zone configuration JSON file.",
)
parser.add_argument(
"--rtsp_url",
type=str,
required=True,
help="Complete RTSP URL for the video stream.",
)
parser.add_argument(
"--weights",
type=str,
default="yolov8s.pt",
help="Path to the model weights file. Default is 'yolov8s.pt'.",
)
parser.add_argument(
"--device",
type=str,
default="cpu",
help="Computation device ('cpu', 'mps' or 'cuda'). Default is 'cpu'.",
)
parser.add_argument(
"--confidence_threshold",
type=float,
default=0.3,
help="Confidence level for detections (0 to 1). Default is 0.3.",
)
parser.add_argument(
"--iou_threshold",
default=0.7,
type=float,
help="IOU threshold for non-max suppression. Default is 0.7.",
)
parser.add_argument(
"--classes",
nargs="*",
type=int,
default=[],
help="List of class IDs to track. If empty, all classes are tracked.",
)
args = parser.parse_args()
main(
rtsp_url=args.rtsp_url,
zone_configuration_path=args.zone_configuration_path,
weights=args.weights,
device=args.device,
confidence=args.confidence_threshold,
iou=args.iou_threshold,
classes=args.classes,
)

Some files were not shown because too many files have changed in this diff Show More