Commit Graph
705 Commits
Author SHA1 Message Date
60d748e57d fix: read COCO export image sizes from headers instead of decoding pixels (#2442)
save_coco_annotations iterated the dataset, cv2-decoding every image only
to read its shape — even for labels-only exports. Sizes now come from the
in-memory array when present, else a lazy PIL header read, the same
optimization from_yolo uses (#1636).

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2026-07-17 18:30:24 +02:00
f7b63f149a perf(cv2): simplify fallback operations (#2441)
- Remove unused compatibility operations and use focused Pillow and NumPy paths to reduce maintained fallback code.
- Preserve numerical decisions and hot-path performance with exact regression coverage and bounded algorithms.
- Preserve INTER_LINEAR uint8 reductions within one LSB while retaining the resize performance budget and numeric RGBA handling.
- Restore repeated-endpoint contour anchors and bound cross-platform chamfer coefficient drift in regression tests.

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-07-17 17:31:57 +02:00
9aaf7fdbd6 fix(metrics): avoid division by zero RuntimeWarning in F1Score using np.divide (#2437)
* fix(metrics): avoid division by zero RuntimeWarning in F1Score using np.divide
* test+changelog: add F1Score zero-denom regression test; add changelog entry
* follow-up cleanup: mirror F1Score np.divide fix in mean_average_recall

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-17 17:11:45 +02:00
jirkaandclaude[bot] a4b9c4e097 fix(cv2): pad getTextSize height/baseline from actual stroke_width
_get_text_size approximated thickness-to-stroke padding with
thickness // 2 formulas that diverge from the thickness - 1
stroke_width _put_text actually renders with. Past thickness 2 the
padding grows too slowly, so heavy-stroke descender pixels can fall
outside the reported box, breaking the documented enclosure
guarantee. Both functions now derive stroke_width from one shared
helper.

---
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-17 10:29:55 +02:00
Jirka Borovecandclaude[bot] 68e63f9e39 refactor(cv2): replace Hershey text with Pillow (#2440)
Text fallback now renders through Pillow with the DejaVu Sans face
resolved via matplotlib font_manager, replacing the Hershey stroke-font
reader; getTextSize metrics derive from the same font and differ from
OpenCV within the documented visual-divergence tier.

Remove the packaged Hershey glyph data (hershey_fonts.json, provenance,
license) and its _cv2/data package-data entry.

Delete unused fallbacks: _geometry _fill_poly and _point_in_polygon
(live fillPoly is the Pillow one in _drawing) and _common _unavailable.

Replace test_hershey with Pillow-oriented test_text, drop test_common,
and point test_contours/test_geometry at _drawing._fill_poly. Document
the fallback text-backend change in the changelog.

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-17 10:22:32 +02:00
jirkaandclaude[bot] bc7b9fc69e docs(changelog): document cv2 fallback fixes from resolve pass
[resolve] PR #2439 — changelog entries for items 2,3 and the
copyMakeBorder scalar-channel bugfix, per AGENTS.md changelog policy.

---
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-17 09:08:16 +02:00
1efa5b8eaa feat(cv2): complete fallback integration (#2439)
* feat(cv2): complete fallback integration
* fallback-fixes: reject invalid addWeighted dtype; O(N) approxPolyDP anchor seeding
* tests: copyMakeBorder sequence parity; drop non-empty facade-import assert; fix Windows path separator in boundary check
* fix(cv2): copyMakeBorder scalar value only fills channel 0 on multichannel images

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-17 07:50:45 +02:00
20b7c085b7 feat(video): require PyAV during cv2 transition (#2438)
- Add the PyAV-backed file-video and audio fallback to the compatibility layer.
- Declare PyAV alongside OpenCV until the final dependency-removal integration.
- _VideoWriter now rejects is_color=False (NotImplementedError) instead of
  silently dropping it, since the PyAV fallback only encodes 3-channel frames.
- _mux_audio cleanup (container closes, temp-file removal) is now best-effort
  so a failing close/remove in finally can no longer mask the primary result
  or the original exception.
- The subprocess used to validate the cv2-free fallback had no timeout;
  a hang (import deadlock, codec probe stall) could block the whole CI
  run. Added a 60s timeout so a hang fails fast with a clear traceback
  instead of an opaque suite-wide stall.
- process_video(preserve_audio=True) docstring still described the old
  ffmpeg-based muxing; audio remuxing was reimplemented with PyAV and no
  longer requires an external ffmpeg executable.
- get_video_frames_generator's documented webcam fallback
  (`_cv2.VideoCapture(0)`) silently fails under the PyAV backend: the
  BackendUnavailableError raised for integer sources was swallowed with no
  logging, so isOpened() just returns False with zero diagnostic signal.
  Doc note now states the limitation explicitly and the capture logs a
  warning instead of failing silently.

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-16 20:13:15 +02:00
c3496134bc feat(cv2): add Hershey text fallback (#2435)
* feat(cv2): add Hershey text fallback
* fix(cv2): sync Hershey provenance hash

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-16 17:10:49 +02:00
16814acff3 feat(utils): add TkImageWindow to unblock switch to opencv-python-headless (#2320)
- Added `sv.ImageWindow`, a Tkinter/Pillow-based desktop image viewer with BGR, grayscale, and BGRA support, keyboard polling, left-click callbacks, context-manager usage, window-state checks, and clean close handling
- Added responsive image resizing with optional aspect-ratio preservation and correctly mapped mouse coordinates after scaling or letterboxing
- Updated compatible runnable examples to use `sv.ImageWindow`, while retaining OpenCV display APIs for worker-thread streaming examples that are incompatible with Tkinter
- Improved `sv.cv2_to_pillow` to support grayscale and BGRA images
- Updated webcam guidance to clarify capture ownership and explicit `VideoCapture` cleanup
- Fixed image-window event handling to prevent stale keypresses, ghost windows, close-time races, and blocked waits after the window closes

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-15 15:06:55 +02:00
94cfb7f290 fix(metrics): ignore out-of-bucket detections in size-bucketed sco… (#2428)
* fix: ignore out-of-bucket   detections in size-bucketed scoring
* fix: honor area metadata in buckets

- Prefer stored COCO area metadata before geometry, mask, or OBB fallbacks.
- Add explicit-area, mask, and OBB regression coverage.
- Align COCO, mAP, and changelog area semantics.

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
2026-07-15 12:48:19 +02:00
d5cadf526a Add cookbook for blurring faces with hosted api (#923)
* Add cookbook for blurring faces with hosted api
* fix: correct Colab URL and spelling errors
* fix: strip outputs and remove GPU section
* fix: improve code quality and notebook structure
* fix: align HTML card and prose style

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-11 01:41:49 +02:00
Teïlo MandJirka Borovec 14c3c86e22 Fix hex parser accepting multiple leading prefixes (#2421)
`hex_to_rgba` previously stripped every leading `#`, so invalid inputs such as `##000000` were accepted despite `is_valid_hex` rejecting them.

Remove only one optional prefix and add regression coverage for the minimized failing input.

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
2026-07-11 00:55:51 +02:00
287868e171 feature: add KeyPoints.merge() method (#2412)
* feat: add KeyPoints.merge() method
* docs: address review comments on merge docstring and changelog date
* chore: retrigger CI after transient links-check failure
* ci(links-check): accept transient 5xx responses to stop flaky failures
* test(keypoints): add validation for consistent coordinate depth across skeletons
* docs(keypoints): document coordinate-depth ValueError in merge() Raises
* test(keypoints): add docstring, zero-keypoint, and merge+with_nms coverage

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-09 21:37:26 +02:00
5344cb99dd fix: close out remaining review findings (#2418)
Re-verify remaining supervision review backlog against develop HEAD; most items were already resolved by an intervening commit, only genuinely-open gaps got new fixes.
Fix float32 precision loss in box_iou_batch for large coordinates (GeoTIFF-scale) by accumulating in float64.
Raise ValueError instead of a strippable assert in EvaluationDataset.load_predictions for unknown image ids.
Add HeatMapAnnotator.reset() to clear accumulated heat for annotator reuse.
Add missing coverage: labelme export basename collisions, _greedy_match matcher, metrics.core ABC/enum contracts, metrics.utils.utils pandas guard; remove a global RNG-seed pollution site in a metrics test.
Document the last two undocumented public exports (calculate_masks_centroids, is_compressed_rle) and add usage examples to 17 previously-example-less public functions/classes (NMS/NMM helpers, draw utils, PolygonZoneAnnotator, mask/polygon converters).

* tests: load_predictions ValueError branch + empty-dataset coverage
* fix: box_iou_batch int-dtype overflow, narrow float32 precision claim
* feat: add reset() to TraceAnnotator/DetectionsSmoother, fix docstrings
* docs: fix temp file leak in coco.py docstring, rename misnamed test

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-09 17:53:52 +02:00
75023c5f2f fix: remaining review findings in dataset, docs, and tests (#2416)
- Added `sv.mask_to_roi` as an explicit migration path for exclusive mask bounds
- Fixed COCO, CreateML, and Pascal VOC export validation to reject ambiguous or colliding dataset paths before writing
- Fixed in-memory `DetectionDataset` split and merge behavior
- Fixed `supervision` imports to avoid loading ByteTrack until it is used
- Fixed detection conversion helpers to support coordinate-convention migration while preserving legacy inclusive defaults
- Fixed Azure tag mapping, anchor rounding, and line-zone smoothing to avoid incorrect or ghost detections
- Fixed video processing shutdown handling for timeout and full-queue cases
- Improved downloader, validator, documentation, and regression coverage for the shipped dataset, detection, annotator, image, and video behavior

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-08 23:00:32 +02:00
23a2227ae7 fix(docs): resolve review deprecation follow-ups (#2415)
- Extend active deprecation removals to 0.31.0 and align deprecated API docs, changelog, and warnings.
- Add missing reference docs for VLM, conversion helpers, geometry, metrics extras, and tracker deprecation notices.
- Raise when ImageSink cannot write an image and cover the failure path with a regression test.
- Correct conversion and deprecated docs to match exported names and restore KeyPoints.confidence.
- Add regression coverage for SUPERVISION_DEPRECATION_WARNING precedence and document ImageSink.save_image() failure behavior.

* test: add validation and behavior tests for Color, Position, and polygon approximation adjustments

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-08 14:30:32 +02:00
Jirka BorovecandCodex 072f78471c fix: resolve medium dataset findings (#2408)
- Reinstated NumPy-safe `Classifications` equality and ordered class-list comparisons in dataset equality.
- Restored greedy matching plus size-bucket scoring for Precision, Recall, F1, and MeanAverageRecall, with regression coverage for the medium-object boundary case.
- Filter size-bucket precision, recall, and F1 against target boxes so predictions no longer claim the bucket.
- Preserve confidence order for bucketed mAR@K scoring and return zero when a bucket has no support.
- Add regression coverage for bucket matching, empty-support mAR, top-K limits, and missing-mask errors.

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-08 08:56:34 +02:00
Jirka BorovecandCodex 74db9e29ff fix(utils): normalize timm confidences and verify assets (#2414)
- Convert timm classification logits with softmax so confidence values match the normalized scale used by other classification adapters.
- Verify asset MD5 hashes after fresh downloads and retry once when a payload is corrupted.
- Add focused regressions for timm confidence scaling and asset download integrity paths.
- Convert from_timm outputs to probabilities before applying thresholds and document that existing thresholds may need retuning.
- Add downloader regression coverage for repeated MD5 mismatches so exhausted retries now raise ValueError.

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-07 21:59:23 +02:00
Jirka BorovecandCodex dde422703c fix(tracker): harden ByteTrack edge cases (#2413)
- Keep ByteTrack confidence-threshold boundary detections eligible and avoid impossible activation thresholds above score 1.0.
- Stop mutating caller-owned detections and assignment cost matrices while preserving matched tracker output.
- Filter invalid tensor boxes before Kalman updates and respect minimum consecutive frames on first-frame tensor updates.
- Avoids per-call np.arange allocation by cloning detections with slice(None) while preserving non-mutation behavior.
- Adds regressions for delayed activation on the second consecutive tensor frame and broader invalid-tensor rejection cases.

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-07 21:05:03 +02:00
Jirka BorovecandCodex 814a226eba fix(metrics): harden scoring edge cases (#2411)
- Use COCO 101-point AP averaging in the legacy mAP path so perfect and imperfect curves score consistently.
- Validate confusion-matrix class ids before indexing and preserve target ignore flags in the COCO-style evaluator.
- Keep mAR per-class recall for each max-detection cutoff and cover the scoring fixes with focused regressions.
- Return empty mAR scores with the same max-detection axis as non-empty results.
- Add an empty-input regression covering recall score and per-class result shapes.
- Update the public mAR docstring to describe per-image detection limits.

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-07 18:46:05 +02:00
Jirka BorovecandCodex 6a69197177 fix(dataset): harden dataset IO edge cases (#2410)
- Avoid mutating caller-owned Detections during dataset construction and reject invalid class ids with clear ValueErrors.
- Make COCO loading/export tolerant of missing optional metadata, add from_coco(use_iscrowd), and export mask pixel area when needed.
- Let folder-structure and YOLO loading skip common clutter and accept PIL-readable image modes with regression coverage.
- Preserve from_coco positional show_progress compatibility while keeping use_iscrowd keyword-only.
- Filter class-folder loading to image files and export missing COCO mask area from decoded masks.
- Add regression coverage, changelog updates, and types-tqdm for mypy.

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-07 16:29:43 +02:00
5b4c8b6d0d fix(key_points): handle empty and numpy index input, keep degenerate skeletons (#2402)
* handle empty and numpy index input, keep degenerate skeletons

- Filter non-finite keypoint coordinates when converting to detections while preserving finite zero-area skeletons.
- Treat zero-length KeyPoints selections as empty and add regression coverage for metadata alignment and selected-index equivalence.

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
2026-07-07 00:02:38 +02:00
Jirka BorovecandCodex c3413a8f10 fix(annotators): resolve annotator medium findings (#2407)
- Added deterministic color lookup with flexible palette resolution and clear errors for empty palettes
- Improved annotator and utility handling for warning formatting, plotting imports, and icon caching
- Added validation for keypoint edges, MediaPipe inputs, and VideoSink state

---------

Co-authored-by: Codex <codex@openai.com>
2026-07-06 22:43:35 +02:00
e13090f84b Fix detection medium review findings (#2400)
- Fixed detection medium findings across adapters, mask non-max merge, sinks, segmentation parsing, LineZone history, and mask ROI handling
- Fixed mask non-max merge deprecation warnings to honor the standard warning opt-out and include version context
- Fixed mask non-max merge validation for invalid IoU thresholds
- Fixed CompactMask non-max merge grouping to update merged mask candidates correctly
- Fixed selected and compacted detections to copy arrays and metadata, preventing mutations from leaking back to source detections
- Fixed LineZone crossing history eviction to tolerate short tracking gaps and evict stale state per tracker/class key
- Fixed semantic segmentation handling to preserve class ID 0
- Improved mask ROI conversion performance by avoiding unnecessary full-frame copies and repeated scans
- Updated JSONSink changelog/docs to document native bool/int/float output while leaving CSVSink unchanged
- Updated detection docstrings for mask parsing, selection copy semantics, validation errors, and argument readability guidance

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-06 19:02:38 +02:00
Jirka Borovecandclaude[bot] bd0f44fcfd fix: resolve remaining High findings from deep codebase review (#2389)
- Fixed crop annotation so overlapping detections sample from the original scene
- Fixed dataset exports to reject basename collisions, including case-insensitive collisions
- Fixed LMM connector mapping to support mirror enum aliases without a hand-maintained dispatch table
- Updated benchmark documentation to install the released inference package with metrics support

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-03 22:58:07 +02:00
afcf13a6f5 fix(annotators): clip BackgroundOverlayAnnotator boxes to the scene… (#2396)
* fix(annotators): clip BackgroundOverlayAnnotator boxes to the scene before   restoring detection regions
* fix(annotators): use explicit np.int32 cast in BackgroundOverlayAnnotator
* test(annotators): strengthen BackgroundOverlayAnnotator test coverage
* docs(changelog): add Unreleased entry for BackgroundOverlayAnnotator fix

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-03 18:36:25 +02:00
Jirka Borovecandclaude[bot] 15dbbb5cb1 fix(annotators): clip crops, fix heatmap wrap, release capture (#2393)
- Fixed annotators to avoid internal deprecation warnings from image overlay usage while preserving the public deprecated wrapper
- Fixed CropAnnotator crashes for partially out-of-frame detections by clipping crops to scene bounds and skipping degenerate boxes
- Fixed HeatMapAnnotator heat disappearing after 256 accumulated frames
- Fixed video frame generation to release the capture when iteration ends early
- Updated documentation for overlay deprecation, crop clipping behavior, and video capture release guarantees

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-03 11:03:45 +02:00
Jirka Borovecandclaude[bot] 99049d84e1 Fix: resolve major complex review (#2388)
- Fixed in-memory dict-form `DetectionDataset` image access, iteration, equality, and merge behavior, with deprecation messaging retained
- Fixed mAP to honor `metric_target` for mask and oriented-bounding-box evaluation, including correct IoU routing, area handling, crowd semantics, and missing-content errors
- Fixed `ConfusionMatrix.plot()` when plotting raw counts with default normalization disabled
- Improved mask mAP crowd handling performance and memory usage
- Updated the count-in-zone guide to use current APIs

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-02 18:14:04 +02:00
8692148c67 fix(detection): make get_anchors_coordinates OBB-aware (#2382)
- Fixed `get_anchors_coordinates` to compute anchor positions from oriented bounding boxes when OBB geometry is available, ensuring anchor-based operations (such as zone counting and annotators) align with the rotated object instead of its axis-aligned bounding box.
- Preserved existing behavior for axis-aligned boxes, while continuing to use mask centroids for `CENTER_OF_MASS` anchors when masks are available.
- Improved the `get_anchors_coordinates` documentation with the updated anchor selection order, OBB usage examples, and notes describing OBB winding-order requirements and anchor tie-breaking behavior.

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-02 00:04:26 +02:00
d590eb6658 perf(detection): keep mixed-mask Detections.merge compact (#2383)
- Improved `Detections.merge()` to preserve `CompactMask` output when merging dense and compact masks by converting dense masks to compact form, avoiding unnecessary full-mask materialization while keeping all-dense and all-compact behavior unchanged.
- Added validation to mixed-mask merging that raises `ValueError` when compact masks have inconsistent image shapes or dense mask dimensions do not match the compact mask image size.
- Added the public `CompactMask.image_shape` property for safe access to compact mask dimensions.
- Updated `Detections.merge()` documentation to describe mixed-mask merge behavior, output types, validation errors, the lossy dense-to-compact conversion outside detection bounding boxes, and that NMS/NMM pairwise operations do not preserve `CompactMask`.
- Added a comprehensive "Use Compact Masks" how-to guide covering compact mask ingestion, inference, annotator mask requirements, and mixed-mask merging, and integrated it into the documentation navigation.

---------

Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-07-01 21:01:29 +02:00
04858a2727 feat: declare annotator mask requirements (#2370)
- Added a `requires_mask` flag to annotators so integrations can determine whether masks must be materialized before annotation.
- Updated mask-only annotators to declare `requires_mask=True`, while mask-optional annotators explicitly declare `requires_mask=False`, including compatibility support for `ComparisonAnnotator`.

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-07-01 19:34:21 +02:00
beb047095f feat: add compact RLE mask ingestion (#2367)
- Added compact COCO RLE mask ingestion with a `CompactMask` representation and optional compact mask parsing during inference for substantially lower memory usage on sparse segmentation results.
- Added `Detections.to_compact_masks()` to convert existing dense masks into compact masks while preserving detection and collection metadata.
- Improved compact mask decoding performance with cropped RLE processing, batched decoding on the fast path, vectorized decoding for small images, optimized RLE traversal, and faster delta decoding.
- Improved mask metrics to operate directly on `CompactMask` instances, preserving the compact representation while producing results equivalent to dense masks.
- Fixed mixed-modality inference handling by keeping detections and masks aligned, isolating malformed RLE failures to individual predictions where possible, and falling back safely when decoding cannot be completed.
- Fixed compact mask conversion and parsing to preserve dense-mask pixel content across public parsing and slicing paths, while correctly documenting and applying the intended bbox-cropping behavior for compact COCO RLE masks.
- Improved COCO RLE validation with checks for malformed payloads, invalid dimensions, count overflows, image size limits, count-sum mismatches, bounding-box mismatches, and safe fallback behavior for incompatible mask sizes.
- Added inference benchmarks and documentation demonstrating the memory and inference-time characteristics of compact masks, including guidance on their performance tradeoffs and behavior.

---------

Co-authored-by: Codex <codex@openai.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-07-01 12:50:40 +02:00
0a95bae8a8 chore: bump minimum Python to 3.10 (#2260)
- Drop Python 3.9 from CI test matrix
- requires-python = ">=3.10" in pyproject.toml
- ruff target-version py39 → py310
- mypy python_version 3.9 → 3.10
- Remove Python 3.9 classifier

---------

Co-authored-by: Claude Code <noreply@anthropic.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-29 14:45:30 +02:00
57bb5e7e8b Add adaptive TP/FP/FN validation mosaic export (#2271)
- remove top-level cv2/annotator imports; lazy-load inside rendering functions
- remove save_result_images bool; save_directory_path is now keyword-only after metric_target
- drop hardcoded result/ subdirectory from benchmark output path
- propagate metric_target into _split_detections_by_outcome for correct OBB IoU dispatch
- add filename collision UserWarning in benchmark loop
- remove dead/unreachable combined None-check in _split_detections_by_outcome
- add Google-style docstrings to all 5 new private visualization functions
- add TestSplitDetectionsByOutcome covering 7 edge cases (empty inputs, cross-class, confidence-None)
- fix FP/FN pixel assertions to check interior box pixels rather than border/title regions
- fix benchmark_a_model.md: full panel names, add Visual Benchmarking section, update API examples

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-26 21:33:49 +02:00
27ba0aa92f fix(detection): do not crash from_inference on partial tracker_id (#2353)
process_roboflow_result appended tracker_id only for predictions that carried
one, while xyxy/confidence/class_id were appended for every prediction. A
result where some predictions are tracked and others are not produced a
tracker_id array shorter than the boxes, so Detections.from_inference raised
"tracker_id must be a 1D np.ndarray with shape (N,)".

Collect tracker_id for every prediction (None when absent) and build the array
only when all detections carry one, otherwise leave it None. Fully-tracked and
untracked results are unchanged.

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-26 16:58:52 +02:00
2169192492 feat(dataset): add LabelMe format support to DetectionDataset (#2299)
- Added LabelMe import and export support for DetectionDataset, including per-image JSON loading/saving alongside existing dataset formats
- Added LabelMe rectangle-to-box and polygon-to-mask conversion, with rectangle masks available when mask output is requested or polygon annotations are present
- Added LabelMe path-safety protections by resolving image paths by basename and rejecting unsafe or ambiguous image references
- Added validation for duplicate image basenames, malformed shape points, missing imagePath values, and invalid class IDs during LabelMe load/export
- Improved LabelMe handling by warning and skipping unsupported shape types
- Updated documentation and changelog with LabelMe workflow examples and supported-format references

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
2026-06-25 17:07:39 +02:00
9ff41b9706 feat(dataset): add CreateML format support to DetectionDataset (#2284)
- Added CreateML import/export support for detection datasets, including pixel-space center/width/height box conversion, class-name inference, global class-id consistency, and image path safety validation.
- Added optional progress bars for CreateML loading, exporting, and image saving.
- Improved CreateML validation with clear errors for malformed JSON, missing fields, duplicate images, null annotations, and unsafe image paths.
- Updated dataset documentation and references to include CreateML workflows and `from_createml` / `as_createml` usage.

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
2026-06-25 15:26:34 +02:00
a179d9120f feat(detection): support windowed GeoTIFF reads in InferenceSlicer (#2281)
InferenceSlicer can now accept an open rasterio-style dataset and read each tile via a windowed read instead of loading the whole image into memory, enabling tiled inference on multi-GB aerial/drone GeoTIFFs. Detection is duck-typed so rasterio stays an optional dependency (supervision[geotiff]) and the library imports no rasterio symbols. Adds CRS projected validation and tests. Closes #2027.

- Add threading.Lock around raster.read() in _run_callback to prevent
  data race when thread_workers > 1 shares a DatasetReader (GDAL releases
  GIL inside GDALRasterIO — reads are genuinely concurrent C code)
- Return TypeGuard[WindowedRasterDataset] from _is_windowed_raster;
  TYPE_CHECKING guard imports typing_extensions for Python 3.9 compat
- Add @runtime_checkable to WindowedRasterDataset Protocol; crs typed
  as object|None; guard .is_projected via getattr(..., True)
- Extract _get_resolution_wh and _apply_overlap_filter helpers from
  __call__ to bring cyclomatic complexity under PLR0912 limit (16 → ~4)
- Widen callback type to Callable[[NDArray[Any]], Detections] to accept
  any dtype (uint16 raster tiles are not NDArray[uint8])
- Add Raises section to __call__ docstring for geographic CRS ValueError
- Add one-line summary to move_detections docstring
- Export WindowedRasterDataset from sv.__init__
- Move changelog entry from 0.29.1 (released) to UnReleased
- Add comment explaining rasterio>=1.3 lower bound in pyproject.toml
- Restructure tests: class grouping, parametrize CRS cases, add
  docstrings; add compact_masks, thread_workers>1, single-band,
  single-tile test cases


---------

Co-authored-by: madhavcodez <madhavcodez@users.noreply.github.com>
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-06-25 14:07:42 +02:00
14f6f245c8 Docs/convert detections doctests (#2351)
* docs: convert Detections.empty and Detections.merge examples to doctests

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: Dylan Parsons <dylanparsons@users.noreply.github.com>
2026-06-24 08:19:04 +02:00
jirka 3e610a0558 Bump version to 0.30.0.dev 2026-06-23 22:14:07 +02:00
Jirka Borovec 49ecac0376 Releasing supervision 0.29.1 (#2350) 2026-06-23 21:53:06 +02:00
44546a13f2 fix(vlm): handle malformed Gemini/Qwen model output without crashing (#2342)
Two ways the VLM parsers crashed on adversarial model output instead of
degrading gracefully (the contract they already honor for invalid JSON):

1. Gemini 2.5: a mask value that is not a 'data:image/png;base64,' string
   appended an empty mask and then 'continue'd, skipping the confidence
   handler at the bottom of the loop. The item's box was recorded but its
   confidence was not, so the confidence array ended up shorter than xyxy
   and Detections.from_vlm raised a shape ValueError. Replaced the
   'continue' with an if/else so the confidence handler always runs.

2. Gemini 2.0 / Gemini 2.5 / Qwen 2.5: valid JSON whose top level is not a
   list, or whose elements are not dicts (e.g. '[1, 2, 3]'), raised
   TypeError from the 'key not in item' membership test. Added a top-level
   list guard (Gemini 2.0/2.5; Qwen already had one) and a per-element
   dict guard so wrong-shaped JSON degrades to empty Detections.

Add regression tests for the mask/confidence alignment and for graceful
degradation across all three parsers.

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-18 15:31:31 +02:00
4b60bbc9cc fix(dataset): stop Pascal VOC export from mutating source detections (#2341)
object_to_pascal_voc applied the 1-index offset in place (xyxy += 1).
Because Detections.__iter__ yields each row of xyxy as a view sharing
memory with detections.xyxy, detections_to_pascal_voc wrote the +1 shift
straight back into the caller's array. A single export shifted every box
by +1px; a second export compounded it, producing wrong XML. A single
export-then-reload happened to round-trip because from_pascal_voc
subtracts 1, which is why no test caught it.

Rebind to a new array (xyxy = xyxy + 1) instead of mutating in place.
On-disk output is unchanged; the source detections are left intact.

Add regression tests asserting object_to_pascal_voc does not mutate its
inputs and that two consecutive exports are identical and leave xyxy
unchanged.

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-18 15:29:37 +02:00
6918d44190 docs(cookbooks): add Oriented Bounding Boxes cookbook (#2314)
- Added an end-to-end cookbook focused on oriented bounding boxes (OBB), demonstrating how OBB detections differ from axis-aligned boxes, why oriented overlap and NMS matter, how to use footprint-based filtering with `Detections.area`, and how to export annotations in YOLO OBB format.
- Added visual examples that clearly compare axis-aligned and oriented boxes, including a close-up showing how axis-aligned envelopes can significantly overestimate object footprints for angled objects.
- Improved the cookbook narrative to center on the practical consequences of using oriented versus axis-aligned boxes, including tighter localization and more appropriate NMS behavior for densely packed, rotated objects.
- Updated cookbook references, naming, dependency versions, image attribution, and changelog links to align with the released 0.29.0 documentation.
- Fixed the 0.29.0 changelog by removing a duplicate `Detections.area` entry and keeping the more accurate correctness-fix classification.

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-18 13:33:30 +02:00
31e84f7909 feat: add KeyPoints.with_nms() method (#2338)
* feat: add with_nms() method to KeyPoints class Derive axis-aligned bounding boxes from valid keypoints and delegate to box_non_max_suppression for filtering. Requires detection_confidence; supports class-aware and class-agnostic modes.

- Add overlap_metric: OverlapMetric = OverlapMetric.IOU param to KeyPoints.with_nms() for API parity with Detections.with_nms()
- Integrate self.visible into keypoint validity: valid = valid & self.visible when visible is not None
- Pass overlap_metric through to box_non_max_suppression
- Fix docstring: add Defaults to for threshold/class_agnostic, threshold range constraint, overlap_metric arg
- Add UnReleased changelog entry
- Add 5 new test cases: all-zero-skeleton-passes-through, visible-mask-excludes-keypoints-from-bbox, single-valid-keypoint-zero-area-bbox, threshold boundary 0.0/1.0
- Add missing raises test: no-detection-confidence-class-agnostic
- Update `with_nms` method to raise `ValueError` instead of `AssertionError` for missing required fields (`detection_confidence`, `class_id` when `class_agnostic=False`).
- Adjust corresponding test to check for `ValueError` with match argument.

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-18 10:42:43 +02:00
jirka 7e765eb054 docs: reformat entries in changelog for improved readability 2026-06-17 22:41:17 +02:00
393ff52954 fix(json_sink): serialize NumPy scalars in custom_data (#2334)
- Fixed `JSONSink` to correctly serialize NumPy scalar values stored in `custom_data`
- Added JSON serialization support for NumPy arrays by converting them to standard JSON-compatible lists
- Prevented buffered export failures caused by non-serializable NumPy values during `json.dump`
- Added regression coverage for multiple NumPy scalar types, NumPy arrays, and unsupported-object error handling
- Updated documentation and changelog to describe NumPy serialization behavior in `JSONSink`

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-17 22:27:03 +02:00
c9962c9262 fix(smoother): handle detections without confidence (#2333)
- Fixed `DetectionsSmoother` to work with detections that have no confidence scores
- Changed confidence aggregation to average only the confidence values that are present, leaving confidence as `None` when no values exist
- Fixed smoothing of mixed-confidence tracks (some frames with confidence, some without) while preserving available confidence information
- Fixed crashes when merging smoothed tracks that disagree on confidence availability by normalizing confidence fields before merge
- Added regression coverage for no-confidence, mixed-confidence, multi-track, full-window, and tracker-id-missing scenarios
- Updated documentation and changelog to reflect the new confidence-handling behavior

---------

Co-authored-by: jirka <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-17 21:16:43 +02:00
2854932965 fix(metrics): count false positives on background images and absent classes (#2331)
- Fixed Precision and F1Score metrics to correctly count false positives on images with no ground-truth objects
- Fixed Precision and F1Score metrics to include prediction-only classes when computing class statistics and confusion-matrix aggregates
- Corrected MICRO and MACRO averaging so false positives from absent classes affect the score as expected
- Preserved WEIGHTED averaging behavior by weighting only classes with ground-truth support
- Added safeguards for all-background evaluation batches, returning stable zero-valued weighted scores when no support exists
- Fixed handling of predictions with `class_id=None` in background-only evaluation paths
- Added regression coverage for background-image false positives, absent-class predictions, averaging modes, and zero-support edge cases
- Updated metric documentation and result metadata to reflect that tracked classes now include prediction-only classes

---------

Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com>
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
2026-06-17 19:46:10 +02:00