首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种分层Mean Shift目标跟踪算法
引用本文:许海霞,王耀南,袁小芳,周维,朱江.一种分层Mean Shift目标跟踪算法[J].自动化学报,2009,35(4):401-409.
作者姓名:许海霞  王耀南  袁小芳  周维  朱江
作者单位:1. 湖南大学电气与信息工程学院 长沙 410082 2. 湘潭大学信息工程学院 湘潭 411105
基金项目:国家自然科学基金重点项目,国家高技术研究发展计划(863计划),湖南省教育厅资助项目 
摘    要:针对经典Mean shift (MS)目标跟踪算法的颜色特征鲁棒差、匹配迭代复杂的缺点, 提出一种分层Mean shift (Hierarchical mean shift, HMS)目标跟踪算法. 首先通过MS迭代将目标区域特征空间的数据点聚类于模式点, 使得以简洁的方式描述前景跟踪目标, 建立目标模型与目标候选模型的聚类模式点描述, 进行聚类块匹配. 然后, 导出聚类块模式点匹配下的相似度量函数, 进行像素点匹配, 结合邻域一致性, 计算像素平移量, 分层估计序列帧中跟踪目标质心模式点的位置, 并给出HMS匹配迭代跟踪算法. 实验结果表明, 与其他两种MS跟踪算法相比, HMS既能提高序列帧跟踪目标表达与匹配的鲁棒性, 又无需匹配所有数据点, 算法简洁且有效可行.

关 键 词:目标跟踪  分层Mean  shift  聚类模式点  匹配
收稿时间:2007-11-6
修稿时间:2008-6-26

A Hierarchical Mean Shift Algorithm for Object Tracking
XU Hai-Xia WANG Yao-Nan YUAN Xiao-Fang ZHOU Wei ZHU Jiang .School of Electrical , Information Engineering,Hunan University,Changsha .School of Information Engineering,Xiangtan University,Xiangtan.A Hierarchical Mean Shift Algorithm for Object Tracking[J].Acta Automatica Sinica,2009,35(4):401-409.
Authors:XU Hai-Xia WANG Yao-Nan YUAN Xiao-Fang ZHOU Wei ZHU Jiang School of Electrical  Information Engineering  Hunan University  Changsha School of Information Engineering  Xiangtan University  Xiangtan
Institution:1. School of Electrical and Information Engineering, Hunan University, Changsha 410082 2. School of Information ngineering, Xiangtan University, Xiangtan 411105
Abstract:We propose a hierarchical mean shift (HMS) algorithm for object tracking. Firstly, cluster modal points are obtained by mean-shift iteratively processing all the data points in the region so that they can represent foreground object in a succinct manner. The target model and the target candidate model are described by the cluster modal points, and match processes of clustered blocks are performed. Then, on the basis of cluster blocks match, similarity measure function is set up to match between target model and target candidate at pixel level. And the pixel shift vector of target is calculated with the introduction of the neighborhood consistency concept. So, the centroid of tracking object is got layer by layer in the consecutive frames, and the HMS match iteration for object tracking is presented. Experimental comparisons with other two MS algorithms demonstrate the validity and performance of the proposed algorithm.
Keywords:Object tracking  hierarchical mean shift (HMS)  cluster modal point  match
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号