阴影处理在交通监控系统中的应用

A Shadow Handler in Traffic Monitoring System

在视频交通监控系统中阴影去除结果与后续的整个监控系统有很大的关系,例如车型分类,车辆跟踪以及车流量统计和测速都会因为阴影产生很大的困难。本文结合车辆监控系统所观测的道路场景的特点,分析了具体情况下阴影的特殊性,提出一种有效的阴影去除算法。该方法将时间信息和道路纹理特征有效的应用于算法中。首先,在序列图片中进行运动物体分割;下来,在前景中应用边缘信息和纹理特征实现车辆和阴影的区分。经过实时系统的应用显示出很好的阴影去除性能。

A typical shadow-eliminating algorithm is presented in this paper.Algorithm for vehicle detection,edge detection and texture detection are also given.If the shadow is not separated from the vehicle,the next traffic control processes,like vehicle classification,tracking and speed calculation,will be rather difficult. The knowledge,such as edge,texture and time,can be efficient used in the algorithm. First,we detect moving vehicles in a sequence image.Then we separate shadows from vehicles using knowledge including results of edges detection and texture deteetion,etc.The result of the algorithm is also given in the final of paper,which shows that this algorithm is quite promising.