python+yolov3视频车辆检测代码
IDE工具：pycharm 2023
后端语言：python 3.11

import cv2
import numpy as npdef contour_check_car():url_temp = "rtsp://xxxx:xxxxxx@192.168.2.176:554/h264/ch1/sub/av_stream"# 打开视频文件cap = cv2.VideoCapture(url_temp)# 定义感兴趣区域（ROI）的坐标和大小roi_x, roi_y, roi_width, roi_height = 150, 150, 50, 20# 初始化前一帧ret, prev_frame = cap.read()# 初始化计数器count = 0object_in_roi = Falsewhile True:ret, frame = cap.read()if not ret:break# 将当前帧和前一帧相减frame_diff = cv2.absdiff(prev_frame, frame)# 将差异图像转换为灰度图像gray_diff = cv2.cvtColor(frame_diff, cv2.COLOR_BGR2GRAY)# 应用阈值来检测运动物体_, thresh = cv2.threshold(gray_diff, 30, 255, cv2.THRESH_BINARY)# 查找差异图像中的轮廓contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)# 绘制矩形框以标记运动物体，并进行计数for contour in contours:if cv2.contourArea(contour) > 10:  # 根据需要调整面积阈值x, y, w, h = cv2.boundingRect(contour)cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)# 检查物体是否进入ROIif x >= roi_x and y >= roi_y and x + w <= roi_x + roi_width and y + h <= roi_y + roi_height:if not object_in_roi:count += 1object_in_roi = Trueelse:object_in_roi = False# 显示计数结果cv2.putText(frame, f"Count: {count}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)# 更新前一帧prev_frame = frame.copy()# 在帧上绘制ROI区域cv2.rectangle(frame, (roi_x, roi_y), (roi_x + roi_width, roi_y + roi_height), (0, 255, 0), 2)# 显示帧cv2.imshow("Motion Detection and Counting", frame)# 退出循环if cv2.waitKey(30) & 0xFF == 27:break# 释放资源cap.release()cv2.destroyAllWindows()if __name__ == '__main__':car_detector()