import cv2
import numpy as np
import yt_dlp

# YOLO 
weights_path = 'yolov3.weights'
config_path = 'yolov3.cfg'
coco_names_path = 'coco.names'

# COCO 
with open(coco_names_path, 'r') as f:
    class_names = f.read().strip().split('n')

# YOLO 
net = cv2.dnn.readNetFromDarknet(config_path, weights_path)
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)

# YouTube API 
API_KEY = ''
VIDEO_ID = 'DnUFAShZKus'  

url = f"https://www.youtube.com/watch?v={VIDEO_ID}"

ydl_opts = {
    'format': 'best',
}

with yt_dlp.YoutubeDL(ydl_opts) as ydl:
    info_dict = ydl.extract_info(url, download=False)
    video_url = info_dict.get('url', None)

if not video_url:
    print("Canlı yayının video URL'si alınamadı.")
else:
    # OpenCV
    cap = cv2.VideoCapture(video_url)

    frame_count = 0
    while True:
        ret, frame = cap.read()
        frame_count += 1

        if not ret:
            break

        if frame_count % 40 == 0:
            # YOLO ile nesne tespiti
            blob = cv2.dnn.blobFromImage(frame, 1 / 255.0, (416, 416), swapRB=True, crop=False)
            net.setInput(blob)

            # YOLO modelindeki çıkış katmanlarının isimlerini al
            layer_names = net.getLayerNames()

            # YOLO modelindeki çıkış katmanlarının indislerini al
            output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers()]

            detections = net.forward(output_layers)
            boxes = []
            confidences = []
            class_ids = []
            for detection in detections:
                for obj in detection:
                    scores = obj[5:]
                    class_id = np.argmax(scores)
                    confidence = scores[class_id]
                    if confidence > 0.5 and class_names[class_id] == 'car':
                        box = obj[0:4] * np.array([frame.shape[1], frame.shape[0], frame.shape[1], frame.shape[0]])
                        (centerX, centerY, width, height) = box.astype('int')
                        x = int(centerX - (width / 2))
                        y = int(centerY - (height / 2))
                        boxes.append([x, y, int(width), int(height)])
                        confidences.append(float(confidence))
                        class_ids.append(class_id)
            indices = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
            for i in indices:
                i = i[0]
                box = boxes[i]
                (x, y, w, h) = box
                color = (0, 255, 0)
                cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
                text = f"{class_names[class_ids[i]]}: {confidences[i]:.2f}"
                cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)


            cv2.imshow('Live Stream', frame)

        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

 

In this code I tried to use YOLO for the first time. Also I used a lot of chatGPT in here so there are parts that I don’t understand. It should of make a square around the cars in the live video , but after that I press to start button for a 6 or 7 seconds there are only video with a VERY LOW performance and no squares . . After 7 seconds video close itself and the program gives the
Traceback (most recent call last): File “C:UserscasperOneDriveMasaüstüKunorDenemeCar_AICar_AI_Video.py”, line 78, in i = i[0] IndexError: invalid index to scalar variable.
error.