基于视频图像处理的车辆排队长度检测  

Vehicle Queue Length Detection Based on Video Image Processing

作　　者：贺晓锋[1] 杨玉珍[1] 陈阳舟[1] 

机构地区：[1]北京工业大学,北京100022

出　　处：《交通与计算机》2006年第5期43-46,共4页Computer and Communications

摘　　要：综合灰度检测和边缘检测的优点,提出了一种将灰度与边缘检测相结合的方法来检测队列长度,采用帧平均法来处理视频流,可以减小由于摄像头抖动或背景微小变化而产生的误差。提出的队列检测算法包含运动检测和车辆存在检测,通过合理分配使用这两种操作,节省了运算时间。实验结果表明,此方法实现简单,能够获得较满意的检测结果。Queue length is an important parameter of intelligent traffic system. This paper proposes a measurement of queue length,which is based on the combination of gray value and edge detection. This system uses a frame averaging method to reduce the error brought by camera wobbling or background changing. The queue detection algorithm described here consists of a motion detection and vehicle detection operation. These operations are reasonably applied,and the computation time is reduced. Experimental results show that it is a simple and feasible method for queue detection.

关 键 词：视频图像处理 道路交通 队列检测 

分 类 号：TN941.1[电子电信—信号与信息处理] U491.112[电子电信—信息与通信工程]