复杂环境下车辆阴影分割算法研究.pdfVIP

9 2 Vol9 No2 2009 4 Journal of Transportation Systems Engineering and Information Technology April 2009 : 0096744 (2009) 020 2905 * 高 韬, 刘正光 , 张 军 ( , 300072) : 车辆阴影分割是智能交通领域中车辆识别的一项重要内容, 阴影分割的好坏直 接影响到车辆识别的准确 以及整个智能交通监控系统的 能. 针对当前基于RGB 和HSV 颜色空间的车辆阴影分割算法缺陷与不足, 本文提出了一种新的基于YCbCr 空 间的车辆阴影分割算法. 首先选取图像中的运动区域, 运动区域包括车辆以及阴影; 然 后根据阴影区域出现的特点, 选择初始阴影数据; 最后, 通过本文提出的阴影分割算法 最终确定阴影区域的形状与位置. 经过实际道路运行测试, 该算法能提取出的车辆阴 影完整 好, 具有较好的鲁棒 , 在智能交通领域具有一定的应用价值与前景. : 阴影分割; 目标提取; 交通监控 : TP39 : A Vehicle Shadow Segmentation Algorithm in Complex Environment GAO Tao, LIU Zhengguang, ZHANG Jun (The Electrical Engineering and Automation College, Tianjin University, Tianjin 300072, China) Abstract: Vehicle shadow segmentation is one of the most important parts of vehicle detection in the field of in telligent traffic monitoring. Shadow segmentation directly influences the veracity of vehicle recognition even the per formance of the whole monitoring system. To cover the shortages of RGB or HSV color space based vehicle shadow segmentation algorithms, this paper puts forward a new shadow segmentation algorithm based on YCbCr color space. First, the motion area which includes the vehicle and the shadow is selected, and then the original data of the shadow according to the characteristics of the occurrence of shadow is chosen, finally, the shape and location of the shadow region is determined by theYCbCr shadow segmentation algorithm. Actual road test showsthat the inte gral vehicle shadow can be obtaine