Adaptive multi-cue kernel tracking

Wang Yongzhong, Liang Yan, Zhao Chunhui, Pan Quan

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

This paper is a new attempt to introduce multiple cues to the kernel tracking by adaptive manner to improve the reliability and robustness of target tracking in the time-variant scenario. Based on Fisher rule, we construct the measure of discriminability to represent the ability of each cue in distinguishing the target from the background. According to the discriminability the weight of each cue is adjusted in time to accommodate the scene change, and then the cues are adaptively fused with kernel tracking method by these weights. In addition, we present a selective submodel update strategy via the discriminability for alleviating the model drift. In experiments, our scheme based on color cue and LBP texture cue is shown better effectiveness, compared with the well known mean shift tracker.

源语言英语
主期刊名Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
1814-1817
页数4
出版状态已出版 - 2007
活动IEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, 中国
期限: 2 7月 20075 7月 2007

出版系列

姓名Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

会议

会议IEEE International Conference onMultimedia and Expo, ICME 2007
国家/地区中国
Beijing
时期2/07/075/07/07

指纹

探究 'Adaptive multi-cue kernel tracking' 的科研主题。它们共同构成独一无二的指纹。

引用此