Human Identification Using Gait Skeletal Joint Distance Features

Int. J. Softw. Sci. Comput. Intell. Pub Date : 2017-10-01 DOI:10.4018/IJSSCI.2017100102

Md Wasiur Rahman, M. Gavrilova

{"title":"Human Identification Using Gait Skeletal Joint Distance Features","authors":"Md Wasiur Rahman, M. Gavrilova","doi":"10.4018/IJSSCI.2017100102","DOIUrl":null,"url":null,"abstract":"Gaitnotonlydefinesthewayapersonwalks,butalsoprovidesinsightsonanindividual’sdaily routine,mentalstateorevencognitivefunction.Theimportanceofincorporatingcognitivebehavior andanalysisinbiometricsystemshasbeennotedrecently.Inthisarticle,authorsdevelopabiometric securitysystemusinggait-basedskeletalinformationobtainedfromMicrosoftKinectv1sensor.The gaitcycleiscalculatedbydetectingthethreeconsecutivelocalminimabetweenthejointdistance ofleftandrightankles.Authorshaveutilizedthedistancefeaturevectorforeachofthejointswith respecttootherjointsinthegaitcycle.Aftermeanandvariancefeaturesareextractedfromthedistance featurevector,theKNNalgorithmisusedforclassificationpurpose.Theclassificationaccuracyofthe authors’approachis93.33%.Experimentalresultsshowthattheproposedapproachachievesbetter recognitionaccuracythenotherstate-of-the-artapproaches.Incorporatinggaitbiometricinasituation awarenesssystemforidentificationofamentalstateisoneofthefuturedirectionsofthisresearch. KeywoRDS Biometric System, Cognitive Function, Feature Distance Vector, Gait, Gait Cycle, K Nearest Neighbors (KNN), Kinect Sensor, Pattern Recognition","PeriodicalId":432255,"journal":{"name":"Int. J. Softw. Sci. Comput. Intell.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Softw. Sci. Comput. Intell.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/IJSSCI.2017100102","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

Gaitnotonlydefinesthewayapersonwalks,butalsoprovidesinsightsonanindividual’sdaily routine,mentalstateorevencognitivefunction.Theimportanceofincorporatingcognitivebehavior andanalysisinbiometricsystemshasbeennotedrecently.Inthisarticle,authorsdevelopabiometric securitysystemusinggait-basedskeletalinformationobtainedfromMicrosoftKinectv1sensor.The gaitcycleiscalculatedbydetectingthethreeconsecutivelocalminimabetweenthejointdistance ofleftandrightankles.Authorshaveutilizedthedistancefeaturevectorforeachofthejointswith respecttootherjointsinthegaitcycle.Aftermeanandvariancefeaturesareextractedfromthedistance featurevector,theKNNalgorithmisusedforclassificationpurpose.Theclassificationaccuracyofthe authors’approachis93.33%.Experimentalresultsshowthattheproposedapproachachievesbetter recognitionaccuracythenotherstate-of-the-artapproaches.Incorporatinggaitbiometricinasituation awarenesssystemforidentificationofamentalstateisoneofthefuturedirectionsofthisresearch. KeywoRDS Biometric System, Cognitive Function, Feature Distance Vector, Gait, Gait Cycle, K Nearest Neighbors (KNN), Kinect Sensor, Pattern Recognition

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于步态骨骼关节距离特征的人体识别

Gaitnotonlydefinesthewayapersonwalks，butalsoprovidesinsightsonanindividual 'sdaily routine，mentalstateorevencognitivefunction。Theimportanceofincorporatingcognitivebehavior andanalysisinbiometricsystemshasbeennotedrecently。Inthisarticle，authorsdevelopabiometric securitysystemusinggait-basedskeletalinformationobtainedfromMicrosoftKinectv1sensor。The gaitcycleiscalculatedbydetectingthethreeconsecutivelocalminimabetweenthejointdistance ofleftandrightankles。Authorshaveutilizedthedistancefeaturevectorforeachofthejointswith respecttootherjointsinthegaitcycle。Aftermeanandvariancefeaturesareextractedfromthedistance featurevector，theKNNalgorithmisusedforclassificationpurpose。Theclassificationaccuracyofthe作者approachis93.33%。Experimentalresultsshowthattheproposedapproachachievesbetter recognitionaccuracythenotherstate-of-the-artapproaches。Incorporatinggaitbiometricinasituation awarenesssystemforidentificationofamentalstateisoneofthefuturedirectionsofthisresearch。关键词:生物识别系统，认知功能，特征距离向量，步态，步态周期，K近邻，Kinect传感器，模式识别

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Int. J. Softw. Sci. Comput. Intell.

自引率

0.00%

发文量