摘要
对视频图像处理中车辆速度检测所涉及的摄像机标定和基于图像匹配的测速算法进行了研究。首先经几何推导得出二维标定算法,得到一个精度满足需要、计算量小的标定算法。然后在图像匹配的基础上,将虚拟线圈和图像匹配算法结合起来,得到匹配前后车辆绝对像素位置。经实地验证,能够比较准确地检测出车辆经过时的瞬时速度,满足实际应用的要求。
The paper studies camera calibration that is involved with vehicle speed detection using video image processing and speed detection algorithm based on image matching. Firstly, the two-dimensional calibration algorithm is deduced from geo- metric relationship to get calibration algorithm with satisfactory precision and small computation. And then on the basis of image matching, the absolute pixel positon of vehicles before and after matching is calculated out by using of the combination method of the image matching algorithm and the position of virtual loop. The field test results show that the algorithm can detect vehicle＇s instantaneous speed accurately and meet the requirements in practical applications.
出处
《现代电子技术》
2013年第3期158-161,共4页
Modern Electronics Technique
关键词
交通参数检测
车辆速度检测
摄像机标定
图像匹配
traffic parameter detection
vehicle speed detection
camera calibration
image matching
