Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques

This study investigated the skeleton points in the three dimensional (3D) space using Kinect sensor to be utilised as recognition of human based on their walking gait in frontal view. Firstly, walking gait of 30 subjects is captured using Kinect sensor. Next, all the twenty skeleton joints in the 3D...

Full description

Bibliographic Details
Published in:International Journal of Simulation: Systems, Science and Technology
Main Author: Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
Format: Article
Language:English
Published: UK Simulation Society 2018
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85056424386&doi=10.5013%2fIJSSST.a.19.05.25&partnerID=40&md5=d1dd7df3f4fe198e64ddc371c1061c3d
id 2-s2.0-85056424386
spelling 2-s2.0-85056424386
Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
2018
International Journal of Simulation: Systems, Science and Technology
19
5
10.5013/IJSSST.a.19.05.25
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85056424386&doi=10.5013%2fIJSSST.a.19.05.25&partnerID=40&md5=d1dd7df3f4fe198e64ddc371c1061c3d
This study investigated the skeleton points in the three dimensional (3D) space using Kinect sensor to be utilised as recognition of human based on their walking gait in frontal view. Firstly, walking gait of 30 subjects is captured using Kinect sensor. Next, all the twenty skeleton joints in the 3D space within one full gait cycle of each subjects are extracted as features. Further, the significant features amongst the skeleton joints are extracted using Orthogonal Least Square (OLS) technique followed by Locally Linear Embedded (LLE) as feature selection. The effectiveness of OLS as feature extraction along with LLE as feature selection is evaluated using Support Vector Machine as the machine classifier. Classification results attained for human gait recognition are 98.67% and 97% based on RBF and polynomial kernel respectively This proven that the significant gait features identified using OLS and LLE techniques are indeed suitable for gait recognition purpose. © 2018, UK Simulation Society. All rights reserved.
UK Simulation Society
14738031
English
Article

author Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
spellingShingle Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
author_facet Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
author_sort Sahak R.; Tahir N.M.; Yassin A.I.M.; Kamaruzaman F.H.; Al Misreb A.
title Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
title_short Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
title_full Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
title_fullStr Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
title_full_unstemmed Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
title_sort Human gait recognition using skeleton joint coordinates with orthogonal least square and locally linear embedded techniques
publishDate 2018
container_title International Journal of Simulation: Systems, Science and Technology
container_volume 19
container_issue 5
doi_str_mv 10.5013/IJSSST.a.19.05.25
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85056424386&doi=10.5013%2fIJSSST.a.19.05.25&partnerID=40&md5=d1dd7df3f4fe198e64ddc371c1061c3d
description This study investigated the skeleton points in the three dimensional (3D) space using Kinect sensor to be utilised as recognition of human based on their walking gait in frontal view. Firstly, walking gait of 30 subjects is captured using Kinect sensor. Next, all the twenty skeleton joints in the 3D space within one full gait cycle of each subjects are extracted as features. Further, the significant features amongst the skeleton joints are extracted using Orthogonal Least Square (OLS) technique followed by Locally Linear Embedded (LLE) as feature selection. The effectiveness of OLS as feature extraction along with LLE as feature selection is evaluated using Support Vector Machine as the machine classifier. Classification results attained for human gait recognition are 98.67% and 97% based on RBF and polynomial kernel respectively This proven that the significant gait features identified using OLS and LLE techniques are indeed suitable for gait recognition purpose. © 2018, UK Simulation Society. All rights reserved.
publisher UK Simulation Society
issn 14738031
language English
format Article
accesstype
record_format scopus
collection Scopus
_version_ 1809677906579816448