A Hybrid Object Tracking Method in Complex Backgrounds

摘要：

Tracking moving objects in video sequencesrequires a robust technique.In this paper,a novelobject tracking method is discussed The colordistributions histograms is integrated into particlefilter,which is also considered the targets shape as anecessary factor in target model.To compare thetarget model with the current hypotheses of the particlefilter,the Bhattacharyya coefficient is applied.Experimental results demonstrate new method is ableto dealing with the complex backgrounds such asclutter and partial occlusion,target rotation,scalechange,and even when the target disappears for awhile or the camera is moving with high accuracy.

作者: Fenlan Li Chao Li Zhemin Zhuang

作者单位: Department of Electronic Engineering of Shantou University,Guangdong,China 515063

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 1086-1091

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）