supervision/examples/time_in_zone/inference_naive_stream_exam...

139 lines
4.3 KiB
Python

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()
polygons = load_zones_config(file_path=zone_configuration_path)
zones = [
sv.PolygonZone(
polygon=polygon,
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,
)