首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种适用于动态背景下的改进Camshift算法
引用本文:乐应英,张学杰,高赟.一种适用于动态背景下的改进Camshift算法[J].玉溪师范学院学报,2011(8):47-54.
作者姓名:乐应英  张学杰  高赟
作者单位:玉溪师范学院信息技术工程学院;
摘    要:针对摄像机运动下的目标跟踪问题,提出了一种适用于动态背景下的改进的Camshift算法.该算法用基于背景运动参数估计的二次差分法进行目标提取,跟踪过程则融合精简的主色调直方图和对遮挡与背景目标颜色相近情况具有鲁棒性的边缘方向直方图作为目标特征,以所得质心为初始搜索点,进行目标模板和候选目标相似性检测,搜索最佳匹配点得到目标对象在当前帧的准确位置.在动态背景下,该算法显著地提高了跟踪的准确性和鲁棒性.

关 键 词:Camshift背景运动参数估计  二次差分  边缘直方图  多特征融合

An Improved Camshift Algorithm Suitable for Dynamic Background
YUE Yingying ZHANG Xuejie GAO Yun.An Improved Camshift Algorithm Suitable for Dynamic Background[J].Journal of Yuxi Teachers' College,2011(8):47-54.
Authors:YUE Yingying ZHANG Xuejie GAO Yun
Institution:YUE Yingying ZHANG Xuejie GAO Yun(School of Information Technology and Engineering,Yuxi Normal University,Yuxi,Yunnan,China 653100)
Abstract:To solve the problem of object tracking in the condition of camera motion,an improved Camshift Algorithm was put forward.With this algorithm,objects are detected by a twice-frame-difference method which is based on the parameter estimation of background movement.And the tracking process uses the simple main hue histogram and spatial edge orientation histogram as the object feature,the centroid calculated with inter-frame difference as the original searching point,to detect the similarity between the target ...
Keywords:Camshift parameter estimation of background movement  twice-frame-difference  spatial edge orientation histogram  multi-feature fusion  
本文献已被 CNKI 维普 等数据库收录!
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