三维惯性传感参数表征下的行人混合步态分类

doi:10.12066/j.issn.1007-2861.1659

上海大学学报(自然科学版) ›› 2017, Vol. 23 ›› Issue (4): 491-500.doi: 10.12066/j.issn.1007-2861.1659

• • 下一篇

三维惯性传感参数表征下的行人混合步态分类

蔡春艳¹, 张金艺^1,2,3, 李建宇¹, 王伟², 张洪晖²

1. 上海大学微电子研究与开发中心, 上海 200072;
2. 上海大学特种光纤与光接入网省部共建重点实验室, 上海 200072;
3. 上海大学新型显示与系统应用重点实验室, 上海 200072

收稿日期:2015-08-26 出版日期:2017-08-30 发布日期:2017-08-30
通讯作者: 张金艺(1965—), 男, 研究员, 博士生导师, 博士, 研究方向为通信类SoC设计与室内无线定位技术. E-mail: zhangjinyi@staff.shu.edu.cn
作者简介:张金艺(1965—), 男, 研究员, 博士生导师, 博士, 研究方向为通信类SoC设计与室内无线定位技术. E-mail: zhangjinyi@staff.shu.edu.cn
基金资助:
国家高技术研究发展计划(863计划)资助项目(2013AA03A1121, 2013AA03A1122); 上海市教委重点学科建设资助项目(J50104)

Mixed pedestrian gait classification under 3D inertial sensor parameters characterization

CAI Chunyan¹, ZHANG Jinyi^1,2,3, LI Jianyu¹, WANG Wei², ZHANG Honghui²

1. Microelectronic Research and Development Center, Shanghai University, Shanghai 200072, China;
2. Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University, Shanghai 200072, China;
3. Key Laboratory of Advanced Displays and System Application, Shanghai University, Shanghai 200072, China

Received:2015-08-26 Online:2017-08-30 Published:2017-08-30

摘要/Abstract

摘要：

在行人步态分类研究领域中, 传统的基于微机电系统(micro-electro-mechanical system, MEMS)惯性传感器技术的步态分类方法侧重于对行人单一步态模式进行区分, 忽略了两个单一步态模式之间的过渡步态模式, 从而降低了行人行走过程中走、跑、停等混合步态的分类精度, 还会在时间上造成缺失, 进而造成行人航迹推算产生不可估量的定位误差. 从人体运动学角度出发分析了行人步态特点, 同时利用9轴MEMS惯性传感器采集了行人步态原始数据并对其进行剖析, 设定了人体三维惯性传感参数, 以供后续分类算法使用. 为了进一步提高整体混合步态的分类精度, 针对朴素贝叶斯算法对相反过渡步态模式区分精度不高的问题, 在其基础上通过加窗判断前后两个步态的连续性, 完成了行人混合步态的最终分类. 验证结果表明, 和传统的样本熵与小波能量相结合方法相比, 提出的三维惯性传感参数表征下的行人混合步态分类方法, 不仅能区分出行人混合步态中的多种单一步态模式和多种过渡步态模式, 同时整体分类精度提高了14.46%, 从而有效证明了该方法在行人步态分类领域具有良好的理论价值和应用价值.

关键词: 惯性传感, 人体运动学, 微机电系统, 混合步态

Abstract:

In pedestrian gait classification research, the traditional method based on the micro-electro-mechanical system (MEMS) inertial sensor technique focuses on distinguishing a single pedestrian gait, and ignoring transition gait between two single gaits. It leads to poor classification accuracy of mixed gaits such as walking, running, halting, and even causes loss of time. As a result, positioning error of pedestrian dead reckoning becomes large. This paper analyzes gait characteristics based on kinesiology, and collects raw data of pedestrian using a 9-axis MEMS sensor. 3D inertial sensor parameters are then selected to be applied to the subsequent classification algorithm. Because the Naive Bayes algorithm has low accuracy to distinguish reverse transition gaits, the improved algorithm based on the Naive Bayes algorithm judges continuity of two adjacent windows to realize mixed gait classification. Experimental results show that the proposed mixed pedestrian gait classification method with 3D inertial sensor parameters characterization can distinguish a variety of single gaits and transition gaits from mixed gaits. It can also improve the overall classification accuracy by 14.46% as compared with the method of combining sample entropy and wavelet energy. Therefore, the proposed method has a good theoretical and practical value in gait classification.

Key words: inertial sensor, kinesiology , micro-electro-mechanical system (MEMS) , mixed gaits

蔡春艳1, 张金艺1,2,3, 李建宇1, 王伟2, 张洪晖2. 三维惯性传感参数表征下的行人混合步态分类[J]. 上海大学学报(自然科学版), 2017, 23(4): 491-500.

CAI Chunyan1, ZHANG Jinyi1,2,3, LI Jianyu1, WANG Wei2, ZHANG Honghui2. Mixed pedestrian gait classification under 3D inertial sensor parameters characterization[J]. Journal of Shanghai University（Natural Science Edition）, 2017, 23(4): 491-500.

参考文献

[1] Hu Z, Ai G, Zhang L, et al. Novel research on improving global positioning system accuracy in the pedestrian integrated navigation monitoring system [J]. Australian Journal of Electrical & Electronics Engineering, 2014, 11(4): 411-420.

[2] 李若涵, 张金艺, 徐德政, 等. 运动分类步频调节的微机电惯性测量单元室内行人航迹推算[J]. 上海大学学报(自然科学版), 2014, 20(5): 612-623.

[3] Wahab Y, Mazalan M, Bakar N A, et al. Low power shoe integrated intelligent wireless gait measurement system [J]. Journal of Physics: Conference, 2014, 495(1): 43-46.

[4] Qi Y, Soh C B, Gunawan E, et al. Estimation of spatial-temporal gait parameters using a low-cost ultrasonic motion analysis system [J]. Sensors, 2014, 14(8): 15434-15457.

[5] Kivim¨aki T, Vuorela T, Peltola P, et al. A review on device-free passive indoor positioning methods [J]. International Journal of Smart Home, 2014, 8(1): 71-94.

[6] Zhang M, Sawchuk A A. Human daily activity recognition with sparse representation using wearable sensors [J]. IEEE Journal of Biomedical and Health Informatics, 2013, 17(3): 553-560.

[7] Panahandeh G, Mohammadiha N, Leijon A, et al. Continuous hidden Markov model for pedestrian activity classification and gait analysis [J]. IEEE Trans on Instrumentation and Measurement, 2013, 62(5): 1073-1083.

[8] 邢秀玉, 刘鸿宇, 黄武. 基于加速度的小波能量特征及样本熵组合的步态分类算法[J]. 传感技术学报, 2013, 26(4): 545-549.

[9] Tian Z, Fang X, Zhou M, et al. Smartphone-based indoor integrated WiFi/MEMS positioning algorithm in a multi-floor environment [J]. Micromachines, 2015, 6(3): 347-363.

[10] 刘华, 吴文华. 高跟鞋对行走中女性躯干、下肢的力学影响[J]. 北京生物医学工程, 2011, 30(1): 105-108.

[11] 蒋伟宇, 于亮, 马维虎, 等. 一种新型寰枢椎后路动态固定系统的稳定性研究[J]. 中国临床解剖学杂志, 2014, 32(1): 76-79.

三维惯性传感参数表征下的行人混合步态分类

Mixed pedestrian gait classification under 3D inertial sensor parameters characterization

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	鲍深, 张金艺, 姚维强, 梁滨. 基于峰度系数的行人水平行走步态细化分类算法[J]. 上海大学学报(自然科学版), 2018, 24(4): 564-571.
[2]	张金艺1,2,3, 徐德政2, 李若涵1, 陈兴秀1, 徐秦乐2. 9轴MEMS-IMU实时姿态估算算法[J]. 上海大学学报(自然科学版), 2015, 21(5): 547-559.
[3]	张永宇;陈晓阳. 纳米致动器研究现状与工程应用的进展[J]. 上海大学学报(自然科学版), 2006, 12(2): 150-157 .