基于反射对称的步态序列识别  

Gait Sequences Recognition Based on Reflective Symmetry

作　　者：赵国英[1] 向世明[1] 李华[1] 

机构地区：[1]中国科学院计算技术研究所智能信息处理重点实验室

出　　处：《计算机辅助设计与图形学学报》2005年第10期2239-2244,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家"八六三"高技术研究发展计划(2001AA231031);国家重点基础研究发展规划项目(G1998030608);国;家科技攻关计划课题奥运科技专项(2001BA904B08)

摘　　要：利用关键帧的反射对称作为步态特征识别测试序列.反射对称隐含表示了人体行走时胳膊和身体的摆动习惯.在USF数据库上的实验表明,使用反射对称结合频域特征以及人体比例的算法识别率高于不使用反射对称的结果.反射对称不是步态惟一的特征,但易于和其他特征相结合以改进识别结果.文中算法易于实现,而且对于行走速度的变化、背景变化等鲁棒性强.A method using reflective symmetry of key frames is proposed in the paper as gait feature to recognize test sequence. Reflective symmetry implicitly represents the habit with which the leg and body of a person swings. Experiments on USF dataset show that the recognition rate by using symmetry feature with frequency feature and proportion of body is higher than only exploiting the frequency feature and the proportion. Reflective symmetry is not a unique but a useful feature and it can be easily combined with other features to improve the recognition rate. The proposed algorithm is simple to implement and insensitive to the changes of walking speed, background, and the clothing of the person.

关 键 词：步态识别 反射对称 关键帧 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]