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

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.