Extract in and out numbers to variable

[Xkim2000]

Search before asking

• I have searched the Supervision issues and found no similar feature requests.

Question

START = sv.Point(320,0)
END = sv.Point(320,480)

def main():
    model = YOLO("yolov8l.pt") 
    model.to('cuda')

    line_counter = sv.LineZone(start=START, end=END)
    line_annotator = sv.LineZoneAnnotator(
        thickness=2, 
        text_thickness=1, 
        text_scale=0.5
    )

    CLASS_NAMES_DICT = model.model.names

    box_annotator = sv.BoxAnnotator(
        thickness=2,
        text_thickness=1,
        text_scale=0.5
    )

    out_count = 0
    in_count = 0


    for result in model.track(source=0, show=True, stream=True):
        frame = result.orig_img
        detections = sv.Detections.from_yolov8(result)

        if result.boxes.id is not None:
            detections.tracker_id = result.boxes.id.cpu().numpy().astype(int)
           
        
        # Only keep detections with class_id 0, 1, 3, or 67
        detections = detections[np.isin(detections.class_id, [0, 1, 3, 67])]

        labels = [
            f"#{tracker_id} {CLASS_NAMES_DICT[class_id]} {confidence:0.2f}"
            for _, _, confidence, class_id, tracker_id
            in detections
        ]

        frame = box_annotator.annotate(scene=frame, detections=detections, labels=labels)

        line_counter.trigger(detections=detections)
        out_count += line_counter.out_count
        in_count += line_counter.in_count
        line_annotator.annotate(frame=frame, line_counter=line_counter)

        #print(f"Out Count: {out_count}, In Count: {in_count}") # Print the updated values

        cv2.imshow("yolov8", frame)

        if(cv2.waitKey(30) == 27):
            break
    
    print(str(out_count))
    print(str(in_count))

if __name__ == "__main__":
    main()

OUTPUT:
0: 480x640 1 person, 40.5ms
0: 480x640 1 person, 41.1ms
0: 480x640 1 person, 40.4ms
0: 480x640 1 person, 40.8ms
0: 480x640 1 person, 38.9ms
0: 480x640 1 person, 41.9ms
39
75

In this example in the live video it was only me and the in_count in the line was 1 and the out_count was 2, but in the variables in code was 75 and 39. Are any way to extract the correct values ?

Additional

No response

[github-actions[bot]]

Hello there, thank you for opening an Issue ! 🙏🏻 The team was notified and they will get back to you asap.

[SkalskiP]

Hi, @Xkim2000 👋🏻! Lot's convert that question into discussion and move it into the Q/A section.

[SkalskiP]

@Xkim2000, the problem is here:

out_count += line_counter.out_count
in_count += line_counter.in_count

You are looping over frames and adding the current value of line_counter.out_count and line_counter.in_count to your variables. What you should do is just assign:

out_count = line_counter.out_count
in_count = line_counter.in_count

Or skip the assignment altogether and use:

line_counter.out_count
line_counter.in_count

[Xkim2000]

Thank you for the help and rapid response. Have a good one :)

[SkalskiP]

My pleasure ;)