点击下方卡片，关注“机器视觉与AI深度学习”
视觉/图像重磅干货，第一时间送达!
背景介绍
在人工神经网络和计算机视觉领域，物体识别和跟踪是极其重要的技术，可以应用于无数的项目，其中许多可能不是很明显，例如使用这些算法来测量距离或物体的速度。因此，我向你介绍一个旨在使用 YOLOv8 测量高速公路上汽车速度的 Python 项目，目的是让你了解这些算法如何在日常解决方案中使用。
实现步骤
pip install ultralyticspip install opencv-pythonpip install --no-cache "lapx>=0.5.2"
https://docs.ultralytics.com/tasks/detect/#modelshttps://www.youtube.com/watch?v=-59Mr4UTgNg%27 完整代码：
from ultralytics import YOLOfrom ultralytics.solutions import speed_estimationimport cv2model = YOLO("yolov8s.pt")names = model.model.namescap = cv2.VideoCapture("src.mp4")assert cap.isOpened(), "Error reading video file"w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))video_writer = cv2.VideoWriter("out.avi",cv2.VideoWriter_fourcc(*'mp4v'),fps,(w, h))line_pts = [(0, 400), (1280, 400)]speed_obj = speed_estimation.SpeedEstimator()speed_obj.set_args(reg_pts=line_pts,names=names,view_img=True)while cap.isOpened():success, im0 = cap.read()if not success:print("Video frame is empty or video processing has been successfully completed.")breaktracks = model.track(im0, persist=True, show=False)im0 = speed_obj.estimate_speed(im0, tracks)video_writer.write(im0)cap.release()video_writer.release()cv2.destroyAllWindows()
代码解释
model = YOLO("yolov8s.pt")这里yolov8s 模型已足够。
tracks = model.track(im0, persist=True, show=False)line_pts = [(0, 400), (1280, 400)] #绘制从屏幕一侧到另一侧的线speed_obj.set_args(reg_pts=line_pts, names=names, view_img=True)line_pts = [(0, 400), (1280, 400)]speed_obj = speed_estimation.SpeedEstimator()speed_obj.set_args(reg_pts=line_pts,names=names,view_img=True)
—THE END—
觉得有用，麻烦给个赞和在看
