作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (2): 180-182. doi: 10.3969/j.issn.1000-3428.2011.02.062

• 人工智能及识别技术 • 上一篇    下一篇

改进的CamShift人脸跟踪算法

黄亚勤,董秀成,李 郝,王海涛   

  1. (西华大学电气信息学院,成都 610039)
  • 出版日期:2011-01-20 发布日期:2011-01-25
  • 作者简介:黄亚勤(1986-),女,硕士研究生,主研方向:图像处理,计算机视觉;董秀成,教授;李 郝、王海涛,硕士研究生
  • 基金资助:
    四川省科技厅基金资助重点项目(06209084)

Improved CamShift Algorithm for Face Tracking

HUANG Ya-qin, DONG Xiu-cheng, LI Hao, WANG Hai-tao   

  1. (College of Electrical and Information Engineering, Xihua University, Chengdu 610039, China)
  • Online:2011-01-20 Published:2011-01-25

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。

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

Abstract: Considered classic CamShift algorithm used for face tracking when there being large color regions in the scene easily leading to inaccurate tracking, an improved CamShift 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.

Key words: face tracking, CamShift, template matching, color probability distribution image

中图分类号: