具有遮挡鲁棒性的目标中心距离加权的跟踪算法  

A robust occluded object tracking based on object center distance-weighting

作　　者：江淑红[1] 张建秋[1] 胡波[1] 

机构地区：[1]复旦大学电子工程系,上海200433

出　　处：《电路与系统学报》2009年第6期29-34,共6页Journal of Circuits and Systems

基　　金：国家自然科学基金资助项目(60572023)

摘　　要：本文提出了一种实时跟踪算法,以目标中心距离加权的目标图像直方图作为模板,采用mean-shift迭代方法进行目标定位;当目标被部分遮挡时,用"分块匹配"的方法提高算法鲁棒性;对于超过一定像素的较大目标,本算法进行"降采样",大大减小运算量,从而实现了对大尺度目标的实时跟踪。实时视频流的实际跟踪系统验证了该方法的有效性。A real-time image tracking algorithm is proposed, which gives small weights to pixels farther from the object center and uses the quantized image color scales as a template. It identifies the target＇s location by mean-shift iteration method and uses ＂block match＂ method to improve the algorithm in occluded object tracking. A decimation method is proposed to track large-sized targets. Real-time experimental results verify the effectiveness of the proposed algorithm.

关 键 词：目标跟踪 图像处理 mean—shift方法 目标遮挡 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]