A robust covariate‐invariant gait recognition based on pose features

Abstract Gait recognition uses video of human gait processed by computer vision methods to identify people based on walking style. The complexity introduced by covariates makes the previous methods less efficient and inaccurate. This study proposes an approach based on pose features to attempt gait...

Full description

Saved in:
Bibliographic Details
Main Authors: Anubha Parashar, Apoorva Parashar, Rajveer Singh Shekhawat
Format: Article
Language:English
Published: Wiley 2022-11-01
Series:IET Biometrics
Subjects:
Online Access:https://doi.org/10.1049/bme2.12103
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850233362592038912
author Anubha Parashar
Apoorva Parashar
Rajveer Singh Shekhawat
author_facet Anubha Parashar
Apoorva Parashar
Rajveer Singh Shekhawat
author_sort Anubha Parashar
collection DOAJ
description Abstract Gait recognition uses video of human gait processed by computer vision methods to identify people based on walking style. The complexity introduced by covariates makes the previous methods less efficient and inaccurate. This study proposes an approach based on pose features to attempt gait recognition of people with an overcoat, carrying objects, or other covariates. It aims to estimate human locomotion using Convolutional Neural Networks. Gathering video data, extracting video frames in a particular order, posture estimation for each frame, using multilayer RNN for gait recognition from the pose, and obtaining one‐dimensional object vectors, are all critical steps. Furthermore, these one‐dimensional identification vectors are stored in a data set along with the name of the person walking in the video. The proposed data set is used to train a classification model to predict the person in a new video by first processing it to get its identification vector and then to use it as a test case in the classification model. A graphical user interface was also developed so that anyone with no programming or technical experience can easily use the tool. The developed application does everything for gait detection from mp4 videos by obtaining the identification vectors and saving them into the data set. Using this application, one can quickly identify the person walking in a video. The results obtained offered an accuracy from 60.88% to 95.23%.
format Article
id doaj-art-05b85a60b52042b3b6b32c913a73aa49
institution OA Journals
issn 2047-4938
2047-4946
language English
publishDate 2022-11-01
publisher Wiley
record_format Article
series IET Biometrics
spelling doaj-art-05b85a60b52042b3b6b32c913a73aa492025-08-20T02:02:57ZengWileyIET Biometrics2047-49382047-49462022-11-0111660161310.1049/bme2.12103A robust covariate‐invariant gait recognition based on pose featuresAnubha Parashar0Apoorva Parashar1Rajveer Singh Shekhawat2Computer Science and Engineering Manipal University Jaipur Jaipur IndiaComputer Science and Engineering Maharshi Dayanand University Jaipur IndiaComputer Science and Engineering Manipal University Jaipur Jaipur IndiaAbstract Gait recognition uses video of human gait processed by computer vision methods to identify people based on walking style. The complexity introduced by covariates makes the previous methods less efficient and inaccurate. This study proposes an approach based on pose features to attempt gait recognition of people with an overcoat, carrying objects, or other covariates. It aims to estimate human locomotion using Convolutional Neural Networks. Gathering video data, extracting video frames in a particular order, posture estimation for each frame, using multilayer RNN for gait recognition from the pose, and obtaining one‐dimensional object vectors, are all critical steps. Furthermore, these one‐dimensional identification vectors are stored in a data set along with the name of the person walking in the video. The proposed data set is used to train a classification model to predict the person in a new video by first processing it to get its identification vector and then to use it as a test case in the classification model. A graphical user interface was also developed so that anyone with no programming or technical experience can easily use the tool. The developed application does everything for gait detection from mp4 videos by obtaining the identification vectors and saving them into the data set. Using this application, one can quickly identify the person walking in a video. The results obtained offered an accuracy from 60.88% to 95.23%.https://doi.org/10.1049/bme2.12103biometricscovariatesdeep learninggait recognitionpose estimation
spellingShingle Anubha Parashar
Apoorva Parashar
Rajveer Singh Shekhawat
A robust covariate‐invariant gait recognition based on pose features
IET Biometrics
biometrics
covariates
deep learning
gait recognition
pose estimation
title A robust covariate‐invariant gait recognition based on pose features
title_full A robust covariate‐invariant gait recognition based on pose features
title_fullStr A robust covariate‐invariant gait recognition based on pose features
title_full_unstemmed A robust covariate‐invariant gait recognition based on pose features
title_short A robust covariate‐invariant gait recognition based on pose features
title_sort robust covariate invariant gait recognition based on pose features
topic biometrics
covariates
deep learning
gait recognition
pose estimation
url https://doi.org/10.1049/bme2.12103
work_keys_str_mv AT anubhaparashar arobustcovariateinvariantgaitrecognitionbasedonposefeatures
AT apoorvaparashar arobustcovariateinvariantgaitrecognitionbasedonposefeatures
AT rajveersinghshekhawat arobustcovariateinvariantgaitrecognitionbasedonposefeatures
AT anubhaparashar robustcovariateinvariantgaitrecognitionbasedonposefeatures
AT apoorvaparashar robustcovariateinvariantgaitrecognitionbasedonposefeatures
AT rajveersinghshekhawat robustcovariateinvariantgaitrecognitionbasedonposefeatures