YOLO11 目标跟踪

1. 前沿

在《YOLO11 目标检测》 完成了 目标检测

在《YOLO11 图像分割》 完成了 图像分割

在实际应用中，常见的还有根据这两个模型，进行目标跟踪实现功能进阶的应用

2. 目标检测+跟踪

按官方的例程，新建 track_det.py，使用之前训练的模型，并采用摄像头作为数据源

import cv2
from collections import defaultdict
import numpy as np

from ultralytics import YOLO

# Load the YOLO11 model
model = YOLO("detect/train/weights/best.pt")

# Open the video file
cap = cv2.VideoCapture(0)

# Store the track history
track_history = defaultdict(lambda: [])

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

    if success:
        # Run YOLO11 tracking on the frame, persisting tracks between frames
        results = model.track(frame, persist=True)

        # Visualize the results on the frame
        annotated_frame = results[0].plot()

        # Get the boxes and track IDs
        if results[0].boxes.is_track:
            boxes = results[0].boxes.xywh.cpu()
            track_ids = results[0].boxes.id.int().cpu().tolist()

            # Plot the tracks
            for box, track_id in zip(boxes, track_ids):
                x, y, w, h = box
                track = track_history[track_id]
                track.append((float(x), float(y)))  # x, y center point
                if len(track) > 30:  # retain 90 tracks for 90 frames
                    track.pop(0)

                # Draw the tracking lines
                points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
                cv2.polylines(annotated_frame, [points], isClosed=False, color=(255, 168, 0), thickness=5)
        
        # Display the annotated frame
        cv2.imshow("YOLO11 Tracking", annotated_frame)

        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break

# Release the video capture object and close the display window
cap.release()
cv2.destroyAllWindows()

可以看到出来目标检测，还有 运动轨迹 和 ID编号

3. 图像分割+跟踪

按官方的例程，新建 track_seg.py，使用之前训练的模型，并采用摄像头作为数据源

import cv2
from collections import defaultdict
import numpy as np

from ultralytics import YOLO

# Load the YOLO11 model
model = YOLO("segment/train/weights/best.pt")

# Open the video file
cap = cv2.VideoCapture(0)

# Store the track history
track_history = defaultdict(lambda: [])

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

    if success:
        # Run YOLO11 tracking on the frame, persisting tracks between frames
        results = model.track(frame, persist=True)

        # Visualize the results on the frame
        annotated_frame = results[0].plot()

        # Get the boxes and track IDs
        if results[0].boxes.is_track:
            boxes = results[0].boxes.xywh.cpu()
            track_ids = results[0].boxes.id.int().cpu().tolist()

            # Plot the tracks
            for box, track_id in zip(boxes, track_ids):
                x, y, w, h = box
                track = track_history[track_id]
                track.append((float(x), float(y)))  # x, y center point
                if len(track) > 30:  # retain 90 tracks for 90 frames
                    track.pop(0)

                # Draw the tracking lines
                points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
                cv2.polylines(annotated_frame, [points], isClosed=False, color=(255, 168, 0), thickness=5)
        
        # Display the annotated frame
        cv2.imshow("YOLO11 Tracking", annotated_frame)

        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break

# Release the video capture object and close the display window
cap.release()
cv2.destroyAllWindows()

可以看到出来图像分割，还有 运动轨迹 和 ID编号

谢谢