首页 | 本学科首页   官方微博 | 高级检索  
     

基于mean-shift算法的人脸实时跟踪方法*
引用本文:蒋建国,孙洪艳,齐美彬.基于mean-shift算法的人脸实时跟踪方法*[J].计算机应用研究,2008,25(7):2225-2227.
作者姓名:蒋建国  孙洪艳  齐美彬
作者单位:(合肥工业大学 计算机与信息学院, 合肥 230009)
基金项目:国家科技部创新基金资助项目(04c26213401216)
摘    要:复杂环境下实时人脸跟踪方法在视觉监控系统中具有很重要的意义,但目前的跟踪算法普遍存在目标遮挡、尺寸变化等过于敏感的不足,限制了其应用范围。提出了一种人脸检测、mean-shift算法与卡尔曼滤波器相结合的实时全自动人脸跟踪算法。实验结果表明该算法实时性很强,可以实现对运动人脸的快速跟踪,同时对目标遮挡也有很好的鲁棒性。

关 键 词:人脸跟踪  mean-shift算法  卡尔曼滤波器  目标遮挡

Real-time algorithm for face tracking based on mean-shift
JIANG Jian-guo,SUN Hong-yan,QI Mei-bin.Real-time algorithm for face tracking based on mean-shift[J].Application Research of Computers,2008,25(7):2225-2227.
Authors:JIANG Jian-guo  SUN Hong-yan  QI Mei-bin
Affiliation:(School of Computer & Information, Hefei University of Technology, Hefei 230009, China)
Abstract:A real-time face tracking under complex environment has significance in visual surveillance system, but one common problem to face tracking algorithms at present is their sensitivity to temporal occlusion and scale variations, which restrict them wide application. This paper proposed a real-time automatic face tracking algorithm which combined face detection and mean-shift algorithm with Kalman filter. In the experiments, the results show the proposed algorithm can track fast moving face successfully and have better robustness of occlusion.
Keywords:face tracking  mean-shift algorithm  Kalman filter  temporal occlusion
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》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