yolov8模型训练、目标跟踪

一、准备条件

1.下载yolov8

https://github.com/ultralytics/ultralytics

2.安装python

https://www.python.org/ftp/python/3.8.0/python-3.8.0-amd64.exe

3.安装依赖
进入ultralytics-main，执行：

pip install -r requirements.txt
pip install -U ultralytics

二、标注

1.安装pyqt5

pip install pyqt5 -i https://pypi.tuna.tsinghua.edu.cn/simple

2.安装labelme

pip install labelme -i https://pypi.tuna.tsinghua.edu.cn/simple

3.启动
labelimg 图片文件路径标注的类别txt文件路径标注结果txt文件路径

labelimg D:/Desktop/BicycleImgs/JPEGImages D:/Desktop/BicycleImgs/predefined_classes.txt D:/Desktop/BicycleImgs/Annotations

在这里插入图片描述

predefined_classes.txt内容：

E-bike

在这里插入图片描述

三、训练

1.到ultralytics所在的目录：

D:\workspace_all\pyCharm\ultralytics-main\ultralytics

2.放置位置如下：
在这里插入图片描述
3.ebike.yaml内容如下：

# Helmet
train: datasets/ebike/train
val: datasets/ebike/valid
test: datasets/ebike/test

# Classes
names:
  0: E-bike

4.在命令行，执行如下命令，进行训练：

yolo task=detect mode=train model=./models/yolov8s.pt data=./ebike.yaml epochs=300 batch=16

5.训练结果
在这里插入图片描述

四、跟踪

1.代码结构
在这里插入图片描述
2.代码

from collections import defaultdict

import cv2
import numpy as np

from ultralytics import YOLO

# Load the YOLOv8 model
model = YOLO('best.pt')

# Open the video file
video_path = "D:/Desktop/999/video.mp4"
cap = cv2.VideoCapture(video_path)

# 获取视频的帧率和尺寸
fps = cap.get(cv2.CAP_PROP_FPS)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
# 保存画框视频
output = cv2.VideoWriter('D:/Desktop/999/output.mp4', cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))

# 用于展示
cv2.namedWindow("YOLOv8 Tracking", 0)
cv2.resizeWindow("YOLOv8 Tracking", 1200, 900)  # 设置窗口的长和宽


# 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 YOLOv8 tracking on the frame, persisting tracks between frames
        results = model.track(frame, persist=True)

        # Get the boxes and track IDs
        boxes = results[0].boxes.xywh.cpu()
        if results[0].boxes.id == None:
            continue

        track_ids = results[0].boxes.id.int().cpu().tolist()

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

        # 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=(230, 230, 230), thickness=10)
        '''

        # Display the annotated frame
        cv2.imshow("YOLOv8 Tracking", annotated_frame)
        # 保存视频
        output.write(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()
output.release()