基于极限学习机及多姿态信息融合的步态识别
徐红先，张书玮
（西南交通大学 机械工程学院，四川 成都 610031）
摘要：为了解决步态识别系统复杂度较高且设备较为昂贵的问题，本文设计了一种步态识别系统。通过采集安装在大腿、小腿和脚板的三个姿态传感器数据，利用时域与频域结合的多域特征方法和近邻成分分析（NCA）算法对姿态数据进行特征提取和降维，得到姿态数据的低维特征向量，使用极限学习机对低维特征向量进行分类，实现了三种步态的准确识别。实验结果表明，三种步态的识别率均达95%以上。
关键词：下肢步态；多姿态角度；极限学习机；步态识别
中图分类号：TP212 文献标志码：A doi：10.3969/j.issn.1006-0316.2023.11.010
文章编号：1006-0316 (2023) 11-0072-09
Gait Recognition Based on Extreme Learning Machine and Multi-Pose Information Fusion
XU Hongxian，ZHANG Shuwei
( School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China )
Abstract：In this paper, a gait recognition system is designed to solve the problems of high complexity and expensive equipment of the gait recognition system. By collecting the data of the three posture sensors installed on the thighs, the calves and the feet, the multi-domain feature method combining the time domain and frequency domain and the neighborhood component analysis (NCA) algorithm are used to extract and reduce the dimension of the posture data, and the low-dimensional feature vector of the posture data is obtained. The low-dimensional feature vector is classified by the extreme learning machine, and the three gaits are recognized accurately. The experimental results show that the recognition rate of the three gaits is all above 95%.
Key words：lower limb gait；multi-attitude angle；extreme learning machine；gait recognition
———————————————
收稿日期：2023-03-10
基金项目：四川省科技计划—智能仿生膝－踝型动力假肢关键技术研究与应用（2021YFS0065）
作者简介：徐红先（1998－），男，江西上饶人，硕士研究生，主要研究方向为智能踝关节假肢研究，E-mail：1097318376@qq.com。
（西南交通大学 机械工程学院，四川 成都 610031）
摘要：为了解决步态识别系统复杂度较高且设备较为昂贵的问题，本文设计了一种步态识别系统。通过采集安装在大腿、小腿和脚板的三个姿态传感器数据，利用时域与频域结合的多域特征方法和近邻成分分析（NCA）算法对姿态数据进行特征提取和降维，得到姿态数据的低维特征向量，使用极限学习机对低维特征向量进行分类，实现了三种步态的准确识别。实验结果表明，三种步态的识别率均达95%以上。
关键词：下肢步态；多姿态角度；极限学习机；步态识别
中图分类号：TP212 文献标志码：A doi：10.3969/j.issn.1006-0316.2023.11.010
文章编号：1006-0316 (2023) 11-0072-09
Gait Recognition Based on Extreme Learning Machine and Multi-Pose Information Fusion
XU Hongxian，ZHANG Shuwei
( School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China )
Abstract：In this paper, a gait recognition system is designed to solve the problems of high complexity and expensive equipment of the gait recognition system. By collecting the data of the three posture sensors installed on the thighs, the calves and the feet, the multi-domain feature method combining the time domain and frequency domain and the neighborhood component analysis (NCA) algorithm are used to extract and reduce the dimension of the posture data, and the low-dimensional feature vector of the posture data is obtained. The low-dimensional feature vector is classified by the extreme learning machine, and the three gaits are recognized accurately. The experimental results show that the recognition rate of the three gaits is all above 95%.
Key words：lower limb gait；multi-attitude angle；extreme learning machine；gait recognition
———————————————
收稿日期：2023-03-10
基金项目：四川省科技计划—智能仿生膝－踝型动力假肢关键技术研究与应用（2021YFS0065）
作者简介：徐红先（1998－），男，江西上饶人，硕士研究生，主要研究方向为智能踝关节假肢研究，E-mail：1097318376@qq.com。
- 下一篇：隧道支护设备机械臂运动学分析
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS