test1.py

import cv2
import argparse
import pyaudio
import wave

from ultralytics import YOLO
import supervision as sv

import numpy as np

ZONE_POLYGON = np.array([    [0, 0],
    [1, 0],
    [1, 1],
    [0, 1]
])

def parse_arguments() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description="YOLOv8 live")
    parser.add_argument(
        "--webcam-resolution",
        default=[1280, 720],
        nargs=2,
        type=int
    )
    args = parser.parse_args()
    return args

def play_audio(file):
    chunk = 1024
    wf = wave.open(file, 'rb')
    p = pyaudio.PyAudio()
    stream = p.open(format=p.get_format_from_width(wf.getsampwidth()),
                    channels=wf.getnchannels(),
                    rate=wf.getframerate(),
                    output=True)
    data = wf.readframes(chunk)
    while data != b'':
        stream.write(data)
        data = wf.readframes(chunk)
    stream.stop_stream()
    stream.close()
    p.terminate()

def main():
    args = parse_arguments()
    frame_width, frame_height = args.webcam_resolution

    cap = cv2.VideoCapture(0)
    cap.set(cv2.CAP_PROP_FRAME_WIDTH, frame_width)
    cap.set(cv2.CAP_PROP_FRAME_HEIGHT, frame_height)
    model = YOLO("yolov8m.pt")
    box_annotator = sv.BoxAnnotator(
        thickness=2,
        text_thickness=2,
        text_scale=1
    )
    zone_polygon = (ZONE_POLYGON * np.array(args.webcam_resolution)).astype(int)
    zone = sv.PolygonZone(polygon=zone_polygon, frame_resolution_wh=tuple(args.webcam_resolution))
    zone_annotator = sv.PolygonZoneAnnotator(
        zone=zone,
        color=sv.Color.red(),
        thickness=2,
        text_thickness=4,
        text_scale=2
    )

    while True:
        ret, frame = cap.read()

        result = model(frame, agnostic_nms=True)[0]
        detections = sv.Detections.from_yolov8(result)
        detections = detections[detections.class_id == 3] #class_id==? ?=number for only motorcycle
        labels = [
            f"{model.model.names[int(class_id)]} {confidence:0.2f}" 
            for _, confidence, class_id, _
            in detections.xyxy
        ]
        frame = box_annotator.annotate(
            scene=frame,
            detections=detections,
            labels=labels
        )

        zone.trigger(detections=detections)
        frame = zone_annotator.annotate(scene=frame)

        if len(detections) > 0:
            play_audio("motorcycle_sound.wav")

        cv2.imshow("yolov8", frame)

        if cv2.waitKey(30) == 27:
            break 

    cap.release()
    cv2.destroyAllWindows()

if __name__ == '__main__':
    main()