一种改进的基于地面反作用力的步态识别方法  

An Improved Gait Recognition Method Based on Ground Reaction Force

作　　者：林尔东[1,2] 姚志明[1,2] 郑重[1] 周旭[1] 孙向阳[1,2] 孙怡宁[1] 

机构地区：[1]中国科学院合肥智能机械研究所安徽省仿生感知与先进机器人技术重点实验室,合肥230031 [2]中国科学技术大学信息科学与技术学院,合肥230027

出　　处：《模式识别与人工智能》2011年第3期353-359,共7页Pattern Recognition and Artificial Intelligence

基　　金：中国科学院合肥物质科学研究院院长基金(基于步态触觉信息的生物特征识别方法研究;0722B11141)

摘　　要：提出一种改进的基于地面反作用力的步态识别方法.该方法通过由三维测力台构建的步态通道获取步行时足底受到的三方向地面反作用力,并采用小波包分解提取时频域特征,利用模糊C-均值聚类算法从中挑选出最具分类能力的特征子集,最后在训练样本上用支持向量机训练分类器,并在测试集上进行步态识别.为提高识别率,对样本进行拆分和波形对齐操作,并设计多分类器以降低步行速度变化对识别准确率的影响.在103人的步态数据库上的测试结果表明,该方法即使在训练样本较少的情况下也可以得到较高的识别率.An improved gait recognition approach based on ground reaction force （GRF） is proposed. 3-directional GRF are acquired by 3-dimensional force plate while a person is walking through the gait walkway. Wavelet packet （WP） decomposition is used to extract features in time-frequency domain, and optimal feature subset is selected using a fuzzy c-means （FCM） clustering algorithm. Support vector machine （SVM） classifier is trained on training-set, and then gait recognition is implemented by SVM on testingset. In order to improve the recognition accuracy, waveform alignment and re-sampling approach are utilized. Multiple classifiers are designed to reduce the negative influence of changes in walking speed. The approach is tested on a gait database collected from 103 subjects. Comparative results demonstrate that high recognition accuracy can be reached even in fewer training-samples.

关 键 词：步态识别 地面反作用力 小波包分解 模糊C-均值 多分类器 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]