基于尺度不变特征变换的Mean-Shift目标跟踪  

Mean-Shift object tracking based on scale invariant feature transform

作　　者：杨心力[1] 杨恢先[1] 曾金芳[1] 于洪[2] 

机构地区：[1]湘潭大学材料与光电物理学院,湖南湘潭411105 [2]琼州学院物理系,海南五指山572200

出　　处：《计算机应用》2009年第10期2678-2680,共3页journal of Computer Applications

基　　金：海南省自然科学基金资助项目(60897);海南省教育厅项目(Hj2009-135)

摘　　要：均值漂移(Mean-Shift)目标跟踪算法由于具有快速模板匹配和无参数密度估计等特点,但也存在其固有的缺陷。为了提高该算法的鲁棒性,把目标分成多个区域,对每个区域利用Mean-Shift进行跟踪,迭代次数大于8的放弃迭代。然后利用尺度不变特征变换(SIFT)剔除那些匹配的关键点数目少的子区域。最后,利用匹配关键点数目多的区域得到目标的位置。实验结果表明该方法在目标受遮挡、尺度变化、旋转、环境场景等变化等具有很强的鲁棒性。Mean-Shift algorithm performs well in object tracking field because of its advantages of fast pattern matching and non-parametric estimation. However, this algorithm has its inherent deficiencies. In order to improve the robustness of Mean-Shift algorithm, the target was divided into a number of sub-regions in this paper, each sub-region individually used Mean-Shift tracking, and those whose iterations are more than eight times quit. And Scale Invariant Feature Transform （SIFT） was employed to exclude those sub-regions with smaller matching key points. Finally, the object location was obtained according to the sub-regions with more matching key points. Experiments show that the proposed method is of high robustness in situations of occlusion, scale change, rotation, scene change, etc.

关 键 词：目标区域划分 尺度不变特征变换 均值漂移 目标跟踪 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP751[自动化与计算机技术—计算机科学与技术]