提出一种基于区域生长与Mean shift算法相结合的动
态变形手势跟踪算法.该算法在跟踪初始阶段通过帧间差分法对手势中心完成自动初始化,利用区域生长算法采
集手势样本点,并通过Mean shift算法对目标中心进行精确定位.实验结果表明,该方法能够对动态变形手势实现
精确实时的跟踪,可较好地降低算法的时间复杂度,保证运动目标跟踪的稳定性和连续性.
Considering the traditionalMean shift algorithm has the problem of low tracking accuracy owing to
the background pixels changing in searchingwindow and thatofhigh time complexity led by the updating
ofhand gesturemode,l a dynamic deforming hand gesture tracking algorithm based on the integration of
region growth and Mean shift is proposed in this paper.
(2011-01-11, CHM, 313KB, 下载14次)