Dynamic gait recognition method based on human model constraints

doi:10.11772/j.issn.1001-9081.2022010131

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (3): 972-977.DOI: 10.11772/j.issn.1001-9081.2022010131

• Frontier and comprehensive applications • Previous Articles

Dynamic gait recognition method based on human model constraints

Jinyue LIU(), Huiyu LI, Xiaohui JIA, Jiarui LI

School of Mechanical Engineering，Hebei University of Technology，Tianjin 300401，China

Received:2022-02-08 Revised:2022-03-16 Accepted:2022-03-21 Online:2022-04-21 Published:2023-03-10
Contact: Jinyue LIU
About author:LI Huiyu， born in 1994， M. S. candidate. His research interests include force tactile perception， intelligent detection.
JIA Xiaohui， born in 1976， Ph. D.， associate professor. Her research interests include flexible precision system design， force tactile perception mechanism， intention recognition.
LI Jiarui， born in 1996， M. S. candidate. Her research interests include tactile perception mechanism， intention recognition.
Supported by:
National Natural Science Foundation of China(U1813222)

基于人体模型约束的步态动态识别方法

刘今越(), 李慧宇, 贾晓辉, 李佳蕊

河北工业大学机械工程学院，天津 300401

通讯作者: 刘今越
作者简介:刘今越（1977—），男，河北唐山人，教授，博士，主要研究方向：机器人环境感知、智能检测与控制
李慧宇（1994—），男，黑龙江佳木斯人，硕士研究生，主要研究方向：力触觉感知、智能检测
贾晓辉（1976—），女，河北唐山人，副教授，博士，主要研究方向：柔性精密系统设计、力触觉感知机理、意图识别
李佳蕊（1996—），女，辽宁铁岭人，硕士研究生，主要研究方向：力触觉感知机理、意图识别。
基金资助:
国家自然科学基金资助项目(U1813222)

Abstract

Abstract:

Aiming at the issue of accurate recognition of human motion gait in exoskeleton robot human computer interaction and medical rehabilitation， a dynamic gait recognition method based on human model constraints was proposed. Firstly， Anybody Modeling System （AMS） simulation software was used to establish different motion simulation models， the gait phases were devided according to the model constraints， and the corresponding relationship between the real data and the simulation data was established through regression mapping. Then， the plantar pressure data collected by the flexible pressure sensor and the foot displacement data collected by the inertial measurement unit were fused into the foot motion data， and the motion data was dynamically segmented according to its dynamic changes and the model constraints to determine the gait phase. Finally， Convolutional Neural Network （CNN） was built to identify the walking gait phase. Experimental results show that the proposed method has the average recognition accuracy of walking action gait of 94.58%， and the average gait recognition accuracy for going upstairs and downstairs actions is 93.21% and 94.64% respectively， which has the gait recognition accuracy of the three actions （walking， going upstairs and downstairs） increased by 11.34， 12.19 and 16.03 percentage points， respectively. It can be seen that CNN recognition based on dynamically segmented foot motion data has a high accuracy， and is suitable for gait recognition of different actions.

Key words: gait recognition, dynamic detection, human model, Convolutional Neural Network (CNN), plantar pressure

摘要：

针对外骨骼机器人在人机交互、医疗康复中的人体运动步态准确识别问题，提出一种基于人体模型约束的步态动态识别方法。首先，利用AMS仿真软件建立不同运动的仿真模型，根据模型约束划分步态相位，并通过回归映射建立真实数据与仿真数据间的对应关系；然后，将柔性压力传感器采集的足底压力数据以及惯性测量单元采集的足部位移数据融合为足部运动数据，并根据动态变化结合模型约束条件动态分割运动数据，以判断步态相位；最后，搭建卷积神经网络（CNN）识别行走步态相位。实验结果表明，所提方法的行走动作步态平均识别准确率为94.58%，上、下楼梯动作的平均步态识别准确率分别为93.21%和94.64%，与未经动态分割的足底压力数据的步态识别相比，分别提高了11.34、12.19和16.03个百分点。可见，通过经动态分割的足部运动数据进行CNN识别具有较高的准确率，且适用于不同动作的步态识别。

关键词: 步态识别, 动态检测, 人体模型, 卷积神经网络, 足底压力

CLC Number:

TP242.6

Jinyue LIU, Huiyu LI, Xiaohui JIA, Jiarui LI. Dynamic gait recognition method based on human model constraints[J]. Journal of Computer Applications, 2023, 43(3): 972-977.

刘今越, 李慧宇, 贾晓辉, 李佳蕊. 基于人体模型约束的步态动态识别方法[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 972-977.

Figures/Tables 16

Fig. 1 Flow of gait recognition

Fig. 2 Sensor layout

Fig. 3 Structure and operation principle of pressure sensor

Fig. 4 Distribution of measurement points in foot and plantar pressure simulation results

Fig. 5 Simulated displacement curve of walking action

Fig.6 Plantar pressure area division

Tab. 1 Gait phase judgment conditions

步态相位	判断条件
足跟触地	$f k t o e = 0$ & $f k h e e l = - i n f$
足弓触地	$f k t o e = 0$ & $f k a r c h = - i n f$
足平放	$f k - 1 t o e = - i n f$
足跟离地	$f k - 1 h e e l = 0$ & $f k h e e l > 0$
足前支撑	$f k a r c h = 1$
摆动相	$f k t o e = 1$ & $f k h e e l = 0$

Tab. 1 Gait phase judgment conditions

步态相位	判断条件
足跟触地	$f k t o e = 0$ & $f k h e e l = - i n f$
足弓触地	$f k t o e = 0$ & $f k a r c h = - i n f$
足平放	$f k - 1 t o e = - i n f$
足跟离地	$f k - 1 h e e l = 0$ & $f k h e e l > 0$
足前支撑	$f k a r c h = 1$
摆动相	$f k t o e = 1$ & $f k h e e l = 0$

Fig.7 Z-axis displacement and velocity of foot

Fig.8 Foot motion data images

Fig.9 Structure of CNN

Tab. 2 Parameters of CNN

名称	类型	核大小及个数	步长	特征图与神经元
Input	输入层	—	—	1个34×16
C1	卷积层	6个5×5核	1	6个30×12
S2	降采样层	1个2×2核	2	6个15×6
C3	卷积层	16个5×5核	1	16个11×2
S4	降采样层	1个2×2核	1	16个6×2
C5	卷积层	120个1×1核	1	120个6×2
F6	全连接层	1×1核	1	—
Output	输出层	1×1核	1	—

Fig.10 Foot motion data acquisition system

Fig.11 Eigenvalue error of standing state

Fig. 12 Walking gait recognition

Fig. 13 Gait recognition of going upstairs and downstairs

Tab. 3 Gait recognition accuracy of different data

步态识别数据	行走	上楼梯	下楼梯
足部运动数据图像	94.58	93.21	94.64
足底压力图像	83.24	81.02	78.61

References 18

1	DING S， OUYANG X P， LIU T， et al. Gait event detection of a lower extremity exoskeleton robot by an intelligent IMU［J］. IEEE Sensors Journal， 2018， 18（23）：9728-9735. 10.1109/jsen.2018.2871328
2	DEMROZI F， BACCHIN R， TAMBURIN S， et al. Toward a wearable system for predicting the freezing of gait in people affected by Parkinson's disease［J］. IEEE Journal of Biomedical and Health Informatics， 2020， 24（9）：2444-2451. 10.1109/jbhi.2019.2952618
3	ZHANG B Q， WANG S A， ZHU H Q. A user-adaptive online learning approach of real-time gait phase detection for walking assistance［C］// Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence. Piscataway： IEEE， 2019：1127-1132. 10.1109/ssci44817.2019.9003107
4	LI H Z， ZHANG X D， LU Z F， et al. RP-based voluntary movement intention detection of lower limb using CNN［C］// Proceedings of the 10th IEEE International Conference on Cyber Technology in Automation， Control， and Intelligent Systems. Piscataway： IEEE， 2020：349-353. 10.1109/cyber50695.2020.9279117
5	PARDOEL S， SHALIN G， NANTEL J， et al. Early detection of freezing of gait during walking using inertial measurement unit and plantar pressure distribution data［J］. Sensors， 2021， 21（6）： No.2246. 10.3390/s21062246
6	ZHOU M L， REN C H， LIU H. An improved sEMG signal processing method for lower limb motion recognition［C］// Proceedings of the IEEE 3rd Advanced Information Management， Communicates， Electronic and Automation Control Conference. Piscataway： IEEE， 2019：21-25. 10.1109/imcec46724.2019.8984187
7	RYU J， LEE BH， KIM DH. sEMG signal-based lower limb human motion detection using a top and slope feature extraction algorithm［J］. IEEE Signal Processing Letters， 2017， 24（7）：929-932. 10.1109/lsp.2016.2636320
8	CHAKRABORTY S， NANDY A. An unsupervised approach for gait phase detection［C］// Proceedings of the 4th International Conference on Computational Intelligence and Networks. Piscataway： IEEE， 2020：1-5. 10.1109/cine48825.2020.234396
9	WANG L， LI Y J， XIONG F， et al. Gait recognition using optical motion capture： a decision fusion based method［J］. Sensors， 2021， 21（10）： No.3496. 10.3390/s21103496
10	KOLAGHASSI R， AL-HARES M K， SIRLANTZIS K. Systematic review of intelligent algorithms in gait analysis and prediction for lower limb robotic systems［J］. IEEE Access， 2021， 9：113788-113812. 10.1109/access.2021.3104464
11	WEIGAND F， ZEISS J， GRIMMER M， et al. A novel approach for gait phase estimation for different locomotion modes using kinematic shank information［J］. IFAC-PapersOnLine， 2020， 53（2）：8697-8703. 10.1016/j.ifacol.2020.12.287
12	SU B B， SMITH C， FAREWIK E G. Gait phase recognition using deep convolutional neural network with inertial measurement units［J］. Biosensors， 2020， 10（9）： No.109. 10.3390/bios10090109
13	赵飞. 基于连续足底分布式压力测量的步态分析［D］.哈尔滨：哈尔滨工业大学， 2020：7-11.
	ZHAO F. Gait analysis based on continuous plantar distributed pressure measurements［D］. Harbin： Harbin Institute of Technology， 2020：7-11.
14	郭士杰，肖杰，刘今越，等. 电容阵列柔性压力传感器设计与分析［J］.仪器仪表学报， 2018， 39（7）：49-55.
	GUO S J， XIAO J， LIU J Y， et al. Capacitor array flexible pressure sensor design and analysis［J］. Chinese Journal of Scientific Instrument， 2018， 39（7）：49-55.
15	PAPAVASILEIOU I， ZHANG W L， HAN S. Real-time data-driven gait phase detection using ground contact force measurements： algorithms， platform design and performance［J］. Smart Health， 2017， 1/2 ：34-49.
16	钟慧敏，黄萍. 不同体质量指数正常人的足底压力特征［J］. 中国组织工程研究， 2017， 21（23）：3730-3735. 10.3969/j.issn.2095-4344.2017.23.021
	ZHONG H M， HUANG P. Plantar pressure of normal people with different body mass index［J］. Chinese Journal of Tissue Engineering Research， 2017， 21（23）：3730-3735. 10.3969/j.issn.2095-4344.2017.23.021
17	FOXLIN E. Pedestrian tracking with shoe-mounted inertial sensors［J］. IEEE Computer Graphics and Applications， 2005， 25（6）：38-46. 10.1109/mcg.2005.140
18	邓平，赵荣鑫，朱飞翔. 一种基于人体运动状态识别的行人航迹推算方法［J］. 中国惯性技术学报， 2021， 29（1）：16-22.
	DENG P， ZHAO R X， ZHU F X. A PDR algorithm based on human motion recognition［J］. Journal of Chinese Inertial Technology， 2021， 29（1）： 16-22.

[1]	Haifeng LI, Fan ZHANG, Minnan PIAO, Huaichao WANG, Nansha LI, Zhongcheng GUI. Automatic detection of targets under airport pavement based on channel and spatial attention [J]. Journal of Computer Applications, 2023, 43(3): 930-935.
[2]	Ping WANG, Nan CHEN, Lei LU. Fall detection algorithm based on scene prior and attention guidance [J]. Journal of Computer Applications, 2023, 43(2): 529-535.
[3]	Ranyan NI, Yi ZHANG. Action recognition method based on video spatio-temporal features [J]. Journal of Computer Applications, 2023, 43(2): 521-528.
[4]	Jianzhuang LIN, Wenzhong YANG, Sixiang TAN, Lexin ZHOU, Danni CHEN. Fusing filter enhancement and reverse attention network for polyp segmentation [J]. Journal of Computer Applications, 2023, 43(1): 265-272.
[5]	Zhijun SHEN, Lina MU, Jing GAO, Yuanhang SHI, Zhiqiang LIU. Review of fine-grained image categorization [J]. Journal of Computer Applications, 2023, 43(1): 51-60.
[6]	Yuhang WANG, Yongxia ZHOU, Liangwu WU. Pooling algorithm based on Gaussian function [J]. Journal of Computer Applications, 2022, 42(9): 2800-2806.
[7]	Yuefeng LIU, Xiaoyan ZHANG, Wei GUO, Haodong BIAN, Yingjie HE. Remaining useful life prediction method of aero-engine based on optimized hybrid model [J]. Journal of Computer Applications, 2022, 42(9): 2960-2968.
[8]	Hongjun HENG, Tianbao XU. Attention sentiment analysis model based on multi-scale convolution and gating mechanism [J]. Journal of Computer Applications, 2022, 42(9): 2674-2679.
[9]	Chengxia XU, Qing YAN, Teng LI, Kaichao MIAO. De-raining algorithm based on joint attention mechanism for single image [J]. Journal of Computer Applications, 2022, 42(8): 2578-2585.
[10]	Xianjie ZHANG, Zhiming ZHANG. Handwritten English text recognition based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2022, 42(8): 2394-2400.
[11]	Nanjiang CHENG, Zhenxia YU, Lin CHEN, Hezhe QIAO. Multi-source and multi-label pedestrian attribute recognition based on domain adaptation [J]. Journal of Computer Applications, 2022, 42(8): 2401-2406.
[12]	Jiehang DENG, Wenquan GUO, Hanjie CHEN, Guosheng GU, Jingjian LIU, Yukun DU, Chao LIU, Xiaodong KANG, Jian ZHAO. Few-shot diatom detection combining multi-scale multi-head self-attention and online hard example mining [J]. Journal of Computer Applications, 2022, 42(8): 2593-2600.
[13]	Zhenhu LYU, Xinzheng XU, Fangyan ZHANG. Lightweight attention mechanism module based on squeeze and excitation [J]. Journal of Computer Applications, 2022, 42(8): 2353-2360.
[14]	Haiqi WANG, Zhihai WANG, Liuke LI, Haoran KONG, Qiong WANG, Jianbo XU. Spatial-temporal prediction model of urban short-term traffic flow based on grid division [J]. Journal of Computer Applications, 2022, 42(7): 2274-2280.
[15]	Ning DONG, Xiaorong CHENG, Mingquan ZHANG. Intrusion detection system with dynamic weight loss function based on internet of things platform [J]. Journal of Computer Applications, 2022, 42(7): 2118-2124.

Dynamic gait recognition method based on human model constraints

基于人体模型约束的步态动态识别方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 18

Related Articles 15

Recommended Articles

Metrics