复杂交通环境中车辆的视觉检测

基于复杂的交通环境中检测行驶车辆是视觉交通监控系统的一个关键问题,提出了一种新的检测行驶车辆的方法.用序列图像中连续三帧图像的差分粗分出运动区域,并用一种基于图论的静止分割产生的区域信息来修正运动分割的结果.给出了一种模板来增强图像区域间的对比度,以改进分割效果.实验结果表明,该检测方法能有效地在复杂背景中定位运动车辆.

Vision-Based Vehicles Detection in Complex Traffic Scenes

Moving vehicle detection in complex traffic scenes is the key of vision based traffic monitoring systems. At present the main applied method is motion segmentation. In this paper a new moving vehicle detection method was presented. First the moving regions were coarsely detected using the difference of three consecutive frames in an image sequence. Then, the results of motion segmentation were regulated using the region information produced by a graph based static segmentation method. A template was presented so as to improve the segmentation results by enhancing the contrast of image regions. The experimental results show that the technique can effectively locate the moving vehicles in complex background.