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

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.