交通监控场景下的相机标定与车辆速度测量

针对交通监控场景中对车辆速度测量的需求，提出了一种相机标定方法和车辆速度测量方案。首先，通过深度学习YOLO检测算法和光流跟踪算法对图像中的车辆目标进行检测和跟踪，根据获得的轨迹集合使用级联霍夫变换计算出道路方向上的消失点，从而检测出道路上的标志线。之后根据消失点和标志线，使用试探焦距思想完成相机标定任务。最后通过计算多帧之间瞬时速度的平均值来实现车辆速度的测量。通过真实交通监控场景的实验结果表明，这种基于消失点的自动相机标定方法具有较好的稳定性和较高的标定精度，能够满足车辆速度测量和实际工程应用的需求。

Camera calibration and vehicle speed measurement in traffic monitoring scene

Aiming at the demand for vehicle speed measurement in traffic monitoring scenarios, this paper proposed a camera calibration method and vehicle speed measurement scheme. Firstly, this method detected and tracked the vehicle target in the video based on deep learning YOLO detection algorithm and optical flow tracking algorithm. According to the obtained trajectory set, this paper calculated the vanishing points in the road direction by cascade Hough transform, and detected marking lines. Then, according to the vanishing point and marking line, it completed the camera calibration task with the idea of exploratory focal length. Finally, this paper achieved vehicle speed by calculating the average of the instantaneous speeds between the multiple frames. The experimental results of real traffic monitoring scenarios show that the automatic camera calibration method based on vanishing point has good stability and high calibration accuracy, which can meet the needs of vehicle speed measurement and practical engineering applications.