Gait Recognition Using 2D Poses

Over the last decades, the field of biometrics has become an important ally for human identification, mainly used for fraud prevention and access control in restricted areas, with the final purpose of increasing the security of the individuals in society. Nowadays,the most common biometric systems a...

Descripción completa

Detalles Bibliográficos
Autores: dos Santos Jangua, Daniel Ricardo, Nilceu Marana, Aparecido
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:Brasil
Institución:Sociedade Brasileira de Computação (SBC)
Repositorio:Revista Eletrônica de Iniciação Científica
Idioma:inglés
OAI Identifier:oai:journals-sol.sbc.org.br:article/2081
Acceso en línea:https://journals-sol.sbc.org.br/index.php/reic/article/view/2081
Access Level:acceso abierto
Palabra clave:Biometrics
Gait Recognition
Pose Estimation
id BR_5fb1d5b9eb00d8ec0cea26429272891c
oai_identifier_str oai:journals-sol.sbc.org.br:article/2081
network_acronym_str BR
network_name_str Brasil
repository_id_str
spelling Gait Recognition Using 2D PosesGait Recognition Using 2D PosesBiometricsGait RecognitionPose EstimationBiometricsGait RecognitionPose EstimationOver the last decades, the field of biometrics has become an important ally for human identification, mainly used for fraud prevention and access control in restricted areas, with the final purpose of increasing the security of the individuals in society. Nowadays,the most common biometric systems are those based in features like fingerprints, face and iris. Despite the great performance of state-of-art methods that use these traits, an important challenge remains, which is the automatic human identification in low-resolution videos, at a distance and without the need for subject cooperation. In this context, the usual biometric systems do not meet the expected performance, and using gait features to identify individuals may be the only viable option. The goal of this work is to propose a new method for gait recognition using gait information extracted from 2D poses estimated over video sequences with high accuracy and low computational cost when compared to other state-of-art methods. In order to estimate the 2D poses, we use OpenPose, an open-source and robust pose estimator. The proposed new method was assessed in two public gait datasets, CASIA Gait Dataset-A and CASIA Gait Dataset-B, and obtained recognition rates comparable with state-of-the-art results, but using smaller feature vectors.Over the last decades, the field of biometrics has become an important ally for human identification, mainly used for fraud prevention and access control in restricted areas, with the final purpose of increasing the security of the individuals in society. Nowadays,the most common biometric systems are those based in features like fingerprints, face and iris. Despite the great performance of state-of-art methods that use these traits, an important challenge remains, which is the automatic human identification in low-resolution videos, at a distance and without the need for subject cooperation. In this context, the usual biometric systems do not meet the expected performance, and using gait features to identify individuals may be the only viable option. The goal of this work is to propose a new method for gait recognition using gait information extracted from 2D poses estimated over video sequences with high accuracy and low computational cost when compared to other state-of-art methods. In order to estimate the 2D poses, we use OpenPose, an open-source and robust pose estimator. The proposed new method was assessed in two public gait datasets, CASIA Gait Dataset-A and CASIA Gait Dataset-B, and obtained recognition rates comparable with state-of-the-art results, but using smaller feature vectors.SBC2021-06-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://journals-sol.sbc.org.br/index.php/reic/article/view/2081Revista Eletrônica de Iniciação Científica em Computação; Vol. 19 No. 2 (2021)Electronic Journal of Undergraduate Research on Computing; Vol. 19 No. 2 (2021)1519-821910.5753/reic.2021.19.2reponame:Revista Eletrônica de Iniciação Científicainstname:Sociedade Brasileira de Computação (SBC)instacron:SBCenghttps://journals-sol.sbc.org.br/index.php/reic/article/view/2081/1757Copyright (c) 2021 Revista Eletrônica de Iniciação Científica em Computaçãoinfo:eu-repo/semantics/openAccessdos Santos Jangua, Daniel RicardoNilceu Marana, Aparecido2021-09-04T21:47:41Zoai:journals-sol.sbc.org.br:article/2081Revistahttps://journals-sol.sbc.org.br/index.php/reic/ONGhttps://journals-sol.sbc.org.br/index.php/reic/oaipublicacoes@sbc.org.br1519-82191519-8219opendoar:2021-09-04T21:47:41Revista Eletrônica de Iniciação Científica - Sociedade Brasileira de Computação (SBC)false
dc.title.none.fl_str_mv Gait Recognition Using 2D Poses
Gait Recognition Using 2D Poses
title Gait Recognition Using 2D Poses
spellingShingle Gait Recognition Using 2D Poses
dos Santos Jangua, Daniel Ricardo
Biometrics
Gait Recognition
Pose Estimation
Biometrics
Gait Recognition
Pose Estimation
title_short Gait Recognition Using 2D Poses
title_full Gait Recognition Using 2D Poses
title_fullStr Gait Recognition Using 2D Poses
title_full_unstemmed Gait Recognition Using 2D Poses
title_sort Gait Recognition Using 2D Poses
dc.creator.none.fl_str_mv dos Santos Jangua, Daniel Ricardo
Nilceu Marana, Aparecido
author dos Santos Jangua, Daniel Ricardo
author_facet dos Santos Jangua, Daniel Ricardo
Nilceu Marana, Aparecido
author_role author
author2 Nilceu Marana, Aparecido
author2_role author
dc.subject.por.fl_str_mv Biometrics
Gait Recognition
Pose Estimation
Biometrics
Gait Recognition
Pose Estimation
topic Biometrics
Gait Recognition
Pose Estimation
Biometrics
Gait Recognition
Pose Estimation
description Over the last decades, the field of biometrics has become an important ally for human identification, mainly used for fraud prevention and access control in restricted areas, with the final purpose of increasing the security of the individuals in society. Nowadays,the most common biometric systems are those based in features like fingerprints, face and iris. Despite the great performance of state-of-art methods that use these traits, an important challenge remains, which is the automatic human identification in low-resolution videos, at a distance and without the need for subject cooperation. In this context, the usual biometric systems do not meet the expected performance, and using gait features to identify individuals may be the only viable option. The goal of this work is to propose a new method for gait recognition using gait information extracted from 2D poses estimated over video sequences with high accuracy and low computational cost when compared to other state-of-art methods. In order to estimate the 2D poses, we use OpenPose, an open-source and robust pose estimator. The proposed new method was assessed in two public gait datasets, CASIA Gait Dataset-A and CASIA Gait Dataset-B, and obtained recognition rates comparable with state-of-the-art results, but using smaller feature vectors.
publishDate 2021
dc.date.none.fl_str_mv 2021-06-03
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://journals-sol.sbc.org.br/index.php/reic/article/view/2081
url https://journals-sol.sbc.org.br/index.php/reic/article/view/2081
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://journals-sol.sbc.org.br/index.php/reic/article/view/2081/1757
dc.rights.driver.fl_str_mv Copyright (c) 2021 Revista Eletrônica de Iniciação Científica em Computação
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2021 Revista Eletrônica de Iniciação Científica em Computação
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv SBC
publisher.none.fl_str_mv SBC
dc.source.none.fl_str_mv Revista Eletrônica de Iniciação Científica em Computação; Vol. 19 No. 2 (2021)
Electronic Journal of Undergraduate Research on Computing; Vol. 19 No. 2 (2021)
1519-8219
10.5753/reic.2021.19.2
reponame:Revista Eletrônica de Iniciação Científica
instname:Sociedade Brasileira de Computação (SBC)
instacron:SBC
instname_str Sociedade Brasileira de Computação (SBC)
instacron_str SBC
institution SBC
reponame_str Revista Eletrônica de Iniciação Científica
collection Revista Eletrônica de Iniciação Científica
repository.name.fl_str_mv Revista Eletrônica de Iniciação Científica - Sociedade Brasileira de Computação (SBC)
repository.mail.fl_str_mv publicacoes@sbc.org.br
_version_ 1853662460596191232
score 15.198674

Similares en LA Referencia