老年人异常行走步态特征提取  

Elderly Abnormal Walking Gait Feature Extraction

作　　者：孔令富[1] 侯亚辉[1] 李海涛[1] 

机构地区：[1]燕山大学信息科学与工程学院,河北秦皇岛066004

出　　处：《计算机仿真》2010年第9期242-244,332,共4页Computer Simulation

基　　金：国家高技术研究发展(863)计划基金资助项目(2006AA04Z212)

摘　　要：计算机视觉的步态分析主要用于实现人体的身份识别,而通过异常步态分析来识别老年人异常状况方面的研究却很少。为对老人异常步态进行识别,提出了一种新的步态特征提取的方法,主要用于老年人异常行走步态特征的提取。使用运动历史图像进行图像序列的表示,并且从中提取出Zernike矩特征用来反应步态的特征向量。同时为了保证获取的特征量的充分性与有效性,更完备地描述人体行为序列,利用信息论中的互信息来确定分类时采用的Zernike矩的最高阶次,并进行仿真。实验结果表明,利用提出的方法进行特征提取,在老年人异常行走步态特征提取中取得了很好的效果。Computer vision-based gait analysis is mainly used to achieve the body＇s identity,and through the abnormal gait analysis to identify abnormal conditions of the elderly research is lacking in research. This paper presents a new method of gait feature extraction,mainly for the elderly characterized by abnormal walking gait extraction. Using the normal moving images as image sequence,and from which extracting the characteristics of Zernike moments as the feature vector of the gait. At the same time,in order to ensure the adequacy and effectiveness of the features,and a more comprehensive description of human behavior sequence,the mutual information theory is used to determine the classification used in the most high-order Zernike moments times. Finally,experimental results show that the method proposed in this paper for feature extraction,abnormal walking gait in the elderly feature extraction has been achieved very good results.

关 键 词：轮廓提取 运动历史图像 特征提取 互信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]