Interframe Variation Vector-Based Gait Recognition

摘要：

The reliable extraction of characteristic gaitfeatures from image sequences is an important issuein gait recognition.In this paper we propose a simple,but efficient approach to extract gait feature.In viewof the spatio-temporal motion characteristic of gait,we adopt the shape variation information betweensuccessive frames to denote gait information,calledInterframe Variation Vector-IVV.Different with otherfeatures,IW doesnt condense a gait sequence intosingle image,which ignores the spatial attribute,butrecords the whole moving process in a IVV sequence.This signature not only preserves all the movements oflimbs of the body,above all it maintains the order ofmovement which is the nature of gait.Compared withother gait signatures,it can fully capture the essentialfeature of gait.Experimental result on CASIA gaitdatabase shows that our proposed method has anencouraging recognition performance.

作者: Song-Zhi Su Li Wang Shao-Zi Li

作者单位: Cognitive Science Department,Xiamen University,Xiamen,Fujian,361005,China School of Control Science and Engineering,Shandong University,Jinan,Shandong,250061,China

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: 707-712

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）