基于视频的交叉路口车辆排队长度检测方法研究  

Research on Vehicle Queuing Length Detection Method of Crossroad Based on Video Processing

作　　者：杨良义 谢飞[2] 陈涛[2] YANG Liangyi;XIE Fei;CHEN Tao(Chongqing Xibu Automobile Proving Ground Management Co.,Ltd,Chongqing 401122,China;China Automotive Engineering Research Institute Co.,Ltd,Chongqing 401122,China)

机构地区：[1]重庆西部汽车试验场管理有限公司,重庆401122 [2]中国汽车工程研究院股份有限公司,重庆401122

出　　处：《重庆理工大学学报（自然科学）》2018年第6期169-174,共6页Journal of Chongqing University of Technology：Natural Science

基　　金：国家专项基金资助项目"基于宽带移动互联网的智能汽车和智慧交通应用示范工程及产品工程化公共服务平台"(0714-EMTC02-5593/20)

摘　　要：为获取城市交叉路口车流量情况,实现路口红绿灯的优化控制以提高交叉路口通行效率,探讨了一种基于视频图像的交叉路口车辆排队长度检测方法。论述了基于图像处理的车辆识别技术,讨论了车辆排队检测方法,借助灭点原理的参数标定方法获取了摄像机内外参数,基于成像原理分析了图像坐标与世界坐标中的转换关系,从而获得从像素距离到物理距离的转换关系。以典型车辆排队视频为例进行实际测量,结果表明:排队长度与计算所得结果误差均在允许范围之内,说明提出的检测方法是合理与可行的。In order to obtain the traffic flow and realize the traffic light optimal control of cities＇ crossroad to improve the efficiency of traffic,this paper discussed a detection method for vehicle queue length based on image processing. In the paper,it firstly discussed a kind of the vehicle identification technology based on image processing and the method of vehicle queue detection,and put forward a method of obtaining the internal and external parameters of camera based on vanishing point principle,analyzed the transformation relationship between the image coordinate and the world coordinate based on the principle of imaging to get conversion relationship between the pixel distanceand the physical distance. Taking typical vehicle queuing video as an example,it demonstrated that the actual error between measurement results and the calculated results for queue length detection would be within the allowable range. The experimental results show that the method proposed in this paper is reasonable and feasible.

关 键 词：城市交叉路口 车辆排队长度 视频图像检测方法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]