Algorithm of Adaptive Kernel-Bandwidth for Mean-Shift Based on Boundary Force
Journal of Software2010Vol. 20(7), pp. 1726–1734
Citations Over Time
Abstract
针对Mean-Shift(中值漂移)算法中核函数带宽不能实时改变的缺陷,提出一种基于边界力的Mean-Shift核函数带宽自适应更新算法.在分析目标加权核直方图模型的基础上,引入区域似然度以提取目标的局部信息.然后,比较相邻帧间的区域似然度并构建边界力.通过对边界力的计算,得到边界点的位置,进而自适应地更新核函数带宽.实验结果表明,这些工作改善了Mean-Shift 算法在目标尺度和形态发生变化时的跟踪效果,并且可以满足实时性的需要.
Related Papers
- → Mean Shift Algorithm and its Application in Tracking of Objects(2006)29 cited
- Application of Mean shift method in target tracking(2007)
- → Algorithm of Adaptive Kernel-Bandwidth for Mean-Shift Based on Boundary Force(2010)2 cited
- → Object Robust Tracking Based an Improved Adaptive Mean-Shift Method(2012)1 cited
- Application of Non-Parametric Mean Shift Method to Computer Vision(2010)