改进的CamShift人脸跟踪算法  

Improved CamShift Algorithm for Face Tracking

作　　者：黄亚勤[1] 董秀成[1] 李郝[1] 王海涛[1] 

机构地区：[1]西华大学电气信息学院,成都610039

出　　处：《计算机工程》2011年第2期180-182,共3页Computer Engineering

基　　金：四川省科技厅基金资助重点项目(06209084)

摘　　要：经典CamShift算法在用于人脸跟踪时,遇到场景中有大面积类肤色区域出现的情况容易产生跟踪失误。针对该问题,提出在CamShift中融入模板匹配的改进算法。以颜色概率分布图中模板匹配是否成功作为CamShift算法迭代终止的条件,解决跟踪过程中的类肤色干扰问题。实验结果证明了该方法的有效性。Considered classic CamShift algorithm used for face tracking when there being large color regions in the scene easily leading to inaccurate tracking, an improved CamShit~ algorithm integrating the template matching algorithm is proposed. Making the template matching successing or not in color probability distribution as iteration termination condition of CamShift algorithm can well figure out the trouble caused by color regions in face tracking. Experimental results prove the validity of the method.

关 键 词：人脸跟踪 自适应均值偏移 模板匹配 颜色概率分布图 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]