首页 | 本学科首页   官方微博 | 高级检索  
     

窗宽自适应Mean-Shift跟踪算法
引用本文:白向峰,李艾华,李喜来,蔡艳平.窗宽自适应Mean-Shift跟踪算法[J].计算机应用,2011,31(1):254-257.
作者姓名:白向峰  李艾华  李喜来  蔡艳平
作者单位:1. 第二炮兵工程学院2. 西安第二炮兵工程学院502教研室
摘    要:针对固定窗宽Mean-Shift算法在目标运动速度过快或尺度发生明显变化时可能导致跟踪失败的问题,提出一种窗宽自适应的Mean-Shift跟踪算法。该方法基于均值漂移矢量预测跟踪窗口中心位置,同时自动调整跟踪窗口大小,保证目标始终处于跟踪窗口内部,使算法得以准确定位目标;在确定空间位置后,利用基于Bhattacharyya系数的二分法自动选取窗口缩放比例,得到与目标尺度一致的跟踪窗口。实验结果证明,该方法能很好地定位目标的空间位置和尺度。

关 键 词:目标跟踪    均值漂移    窗宽自适应    Bhattacharyya系数
收稿时间:2010-07-13
修稿时间:2010-08-25

Mean-Shift tracking algorithm based on adaptive bandwidth
BAI Xiang-feng,LI Ai-hua,LI Xi-lai,CAI Yan-ping.Mean-Shift tracking algorithm based on adaptive bandwidth[J].journal of Computer Applications,2011,31(1):254-257.
Authors:BAI Xiang-feng  LI Ai-hua  LI Xi-lai  CAI Yan-ping
Affiliation:BAI Xiang-feng,LI Ai-hua,LI Xi-lai,CAI Yan-ping(502 Faculty,The Second Artillery Engineering College,Xi'an Shaanxi 710025,China)
Abstract:Mean-Shift algorithm with fixed bandwidth often fails in tracking an object that moves too fast or owns a dramatic change in scale.To solve the problem,a new Mean-Shift tracking algorithm based on adaptive bandwidth was proposed.Mean-Shift vector was used to predict the center position and automatically modulate the size of tracking window that fixed the object inside the window and gained accurate object position.After confirming the position,a Bhattacharyya coefficient based dichotomy was adopted to selec...
Keywords:object tracking  Mean-Shift  adaptive bandwidth  Bhattacharyya coefficient  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
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