def video(
input_file: Path = typer.Argument(
...,
file_okay=True,
dir_okay=False,
),
output_file: Path = typer.Option(
"./output/norfair-test.mp4",
file_okay=True,
dir_okay=False,
),
max_distance: int = typer.Option(60),
debug: bool = typer.Option(False),
):
"""
Runs vehicle detection on frames of a video.
Outputs a directory of images ready for processing with the ``images`` command.
XXX not actually ready yet, I'm currently testing `norfair` package which tracks
detections through time so I can be smart about outputing only the largest and
most clear frame of a vehicle rather than many similiar frames of the same vehicle.
"""
yolo_net, yolo_labels, yolo_colors, yolo_layers = load_yolo_net()
video = Video(input_path=str(input_file), output_path=str(output_file))
tracker = Tracker(
distance_function=euclidean_distance,
distance_threshold=max_distance,
)
for frame in video:
detections = detect_objects(yolo_net, yolo_labels, yolo_layers,
yolo_colors, frame)
detections = list(
filter(lambda d: d["label"] in VEHICLE_CLASSES, detections))
detections = [
Detection(get_centroid(box, frame.shape[0], frame.shape[1]),
data=box) for box in detections
]
tracked_objects = tracker.update(detections=detections)
import pdb
pdb.set_trace()
norfair.draw_points(frame, detections)
norfair.draw_tracked_objects(frame, tracked_objects)
video.write(frame)
def tracker_update(frame, result):
# AlphaPose result
detected_poses = result["result"]
converted_detections = convert_and_filter(detected_poses)
predictions = tracker.update(converted_detections, dt=1)
norfair.draw_points(frame, converted_detections)
norfair.draw_predictions(frame, predictions)
# Draw on a copy of the frame
# frame_processed = frame_img.copy()
# for pose in poses:
# pos_nose = pose["keypoints"][0, :2].int().numpy()
# cv2.rectangle(
# frame_processed, tuple(pos_nose - (2, 2)), tuple(pos_nose + (2, 2)), (0, 0, 255), 1
# )
return frame
y2 = yolo_box[3] * img_height
return np.array([(x1 + x2) / 2, (y1 + y2) / 2])
parser = argparse.ArgumentParser(description="Track human poses in a video.")
parser.add_argument("files",
type=str,
nargs="+",
help="Video files to process")
args = parser.parse_args()
model = YOLO("yolov4.pth") # set use_cuda=False if using CPU
for input_path in args.files:
video = Video(input_path=input_path)
tracker = Tracker(
distance_function=euclidean_distance,
distance_threshold=max_distance_between_points,
)
for frame in video:
detections = model(frame)
detections = [
Detection(get_centroid(box, frame.shape[0], frame.shape[1]),
data=box) for box in detections if box[-1] == 2
]
tracked_objects = tracker.update(detections=detections)
norfair.draw_points(frame, detections)
norfair.draw_tracked_objects(frame, tracked_objects)
video.write(frame)
for frame in video:
detections = model(
frame,
conf=args.conf,
iou=args.iou_thres,
classes_model=args.classes_model) #__call__ method
detections = [
Detection(get_centroid(box, frame.shape[0], frame.shape[1]),
data=box) for box in detections
if not args.classes_track or box[-1] in
args.classes_track #select the classes you want to track
]
tracked_objects = tracker.update(detections=detections)
norfair.draw_points(frame,
detections,
radius=10,
thickness=5,
color=norfair.Color.green)
norfair.draw_tracked_objects(frame,
tracked_objects,
id_size=5,
id_thickness=10,
color=norfair.Color.green)
if (args.debug):
norfair.draw_debug_metrics(frame,
tracked_objects) #debug (optional)
#detections_c1 = [Detection(get_centroid(box, frame.shape[0], frame.shape[1]), data=box) for box in detections if box[-1] == 1]
#tracked_objects_c1 = tracker_c1.update(detections=detections_c1)
#norfair.draw_points(frame, detections_c1, color="green")
#norfair.draw_tracked_objects(frame, tracked_objects_c1, color="green")