cv/track/track2.py

from ultralytics import YOLO
import cv2

# Load an official or custom model
model = YOLO('yolov8s.pt')  # Load an official Detect model
#model = YOLO('yolov8n-seg.pt')  # Load an official Segment model
#model = YOLO('yolov8n-pose.pt')  # Load an official Pose model
#model = YOLO('path/to/best.pt')  # Load a custom trained model

# Perform tracking with the model
#results = model.predict(source=0, show=True)  #
#results = model.track(source="https://www.youtube.com/watch?v=6n5d1C1Alh4", show=True)  # Tracking with default tracker
#results = model.track(source="https://youtu.be/LNwODJXcvt4", show=True, tracker="bytetrack.yaml")  # Tracking with ByteTrack tracker


# Open the input video
cap = cv2.VideoCapture('track2.mp4')

if not cap.isOpened():
    raise Exception("Error: Could not open video.")

# Get input video frame rate and dimensions
#fps = int(cap.get(cv2.CAP_PROP_FPS))
#frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
#frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))

totall_class_ids = {}

while cap.isOpened():
    # Read a frame from the input video
    success, frame = cap.read()

    if success:
        # Run YOLOv8 tracking on the frame, persisting tracks between frames

        # results = model.predict(frame, iou=0.65, conf=0.50, tracker="botsort.yaml", imgsz=640, verbose=True)
        results = model.track(frame, iou=0.85, conf=0.50, tracker="botsort.yaml", imgsz=640, verbose=False, persist=True)

        ## Visualize the results on the frame
        #annotated_frame = results[0].plot()
        ##annotated_frame = cv2.resize(annotated_frame, (annotated_frame.shape[1]//2, annotated_frame.shape[0]//2))
        ## Display the annotated frame
        #cv2.imshow("YOLOv8 Tracking", annotated_frame)

        # Process results list
        for result in results:
            if result.boxes.id != None: # this will ensure that id is not None -> exist tracks
                boxes = result.boxes.xyxy.cpu().numpy().astype(int)
                ids = result.boxes.id.cpu().numpy().astype(int)
                classes = result.boxes.cls.cpu().numpy()
                class_names = result.names

                for box, id, class_id in zip(boxes, ids, classes):
                    color = (0, 0, 255)
                    cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3],), color, 2)
                    class_name = class_names[class_id]
                    cv2.putText(
                        frame,
                        f"{class_name} id: {id}",
                        (box[0], box[1]-5),
                        cv2.FONT_HERSHEY_SIMPLEX,
                        1,
                        (0, 0, 255),
                        2,
                    )
                    
                    #Statistics
                    if not class_id in totall_class_ids:
                        totall_class_ids[class_id]=[]

                    if not id in totall_class_ids[class_id]:
                        for cid in totall_class_ids:
                            if id in totall_class_ids[cid]:
                                totall_class_ids[cid].remove(id)

                        totall_class_ids[class_id].append(id)

        totall = {}
        for cid in totall_class_ids:
            totall[class_names[cid]] = len(totall_class_ids[cid])
        
        x = 0
        y = 20
        for cname in totall:
            cv2.putText(frame, f"{cname}: {totall[cname]}", (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
            y += 20

        cv2.imshow("YOLOv8 Tracking", frame)
        
        # Check for the 'q' key to exit
        if cv2.waitKey(10) & 0xFF == ord('q'):
            break
    else:
        break

# Release the input video capture and output video writerй
cap.release()

# Close all OpenCV windows
cv2.destroyAllWindows()