摘要： 提出一种基于D-S证据理论的车辆视频检测方法，通过一部或多部CCD摄像机采集多源图像，由边缘检测算法获取图像中的车辆特征数据，然后采用D-S证据理论对车辆类型进行判决，从而为交通量的准确检测提供依据。实验表明该方法是可靠而有效的。

关键词: D-S证据理论, 信息融合, 车辆特征提取, 视频检测, 图像处理

Abstract: This paper proposes a vehicle video detection method based on D-S evidence theory. The multi-source images are obtained from one or more CCD camcorders, the vehicle characteristic data are captured by using edge detecting algorithm, and then the vehicles can be classified by means of D-S evidence theory. So this can provide the basis for detecting traffic volume accurately. Experimentation shows that the method is reliable and efficient.

中图分类号: 

• TP399