Deep Large Margin Nearest Neighbor for Gait Recognition

Gait recognition in video surveillance is still challenging because the employed gait features are usually affected by many variations. To overcome this difficulty, this paper presents a novel Deep Large Margin Nearest Neighbor (DLMNN) method for gait recognition. The proposed DLMNN trains a convolu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Xu Wanjiang
Formato: article
Lenguaje:EN
Publicado: De Gruyter 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/4f04334e1af34b11be30d1da451dfccc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4f04334e1af34b11be30d1da451dfccc
record_format dspace
spelling oai:doaj.org-article:4f04334e1af34b11be30d1da451dfccc2021-12-05T14:10:51ZDeep Large Margin Nearest Neighbor for Gait Recognition0334-18602191-026X10.1515/jisys-2020-0077https://doaj.org/article/4f04334e1af34b11be30d1da451dfccc2021-05-01T00:00:00Zhttps://doi.org/10.1515/jisys-2020-0077https://doaj.org/toc/0334-1860https://doaj.org/toc/2191-026XGait recognition in video surveillance is still challenging because the employed gait features are usually affected by many variations. To overcome this difficulty, this paper presents a novel Deep Large Margin Nearest Neighbor (DLMNN) method for gait recognition. The proposed DLMNN trains a convolutional neural network to project gait feature onto a metric subspace, under which intra-class gait samples are pulled together as small as possible while inter-class samples are pushed apart by a large margin. We provide an extensive evaluation in terms of various scenarios, namely, normal, carrying, clothing, and cross-view condition on two widely used gait datasets. Experimental results demonstrate that the proposed DLMNN achieves competitive gait recognition performances and promising computational efficiency.Xu WanjiangDe Gruyterarticlegait recognitionsubspace learningdistance metric learningScienceQElectronic computers. Computer scienceQA75.5-76.95ENJournal of Intelligent Systems, Vol 30, Iss 1, Pp 604-619 (2021)
institution DOAJ
collection DOAJ
language EN
topic gait recognition
subspace learning
distance metric learning
Science
Q
Electronic computers. Computer science
QA75.5-76.95
spellingShingle gait recognition
subspace learning
distance metric learning
Science
Q
Electronic computers. Computer science
QA75.5-76.95
Xu Wanjiang
Deep Large Margin Nearest Neighbor for Gait Recognition
description Gait recognition in video surveillance is still challenging because the employed gait features are usually affected by many variations. To overcome this difficulty, this paper presents a novel Deep Large Margin Nearest Neighbor (DLMNN) method for gait recognition. The proposed DLMNN trains a convolutional neural network to project gait feature onto a metric subspace, under which intra-class gait samples are pulled together as small as possible while inter-class samples are pushed apart by a large margin. We provide an extensive evaluation in terms of various scenarios, namely, normal, carrying, clothing, and cross-view condition on two widely used gait datasets. Experimental results demonstrate that the proposed DLMNN achieves competitive gait recognition performances and promising computational efficiency.
format article
author Xu Wanjiang
author_facet Xu Wanjiang
author_sort Xu Wanjiang
title Deep Large Margin Nearest Neighbor for Gait Recognition
title_short Deep Large Margin Nearest Neighbor for Gait Recognition
title_full Deep Large Margin Nearest Neighbor for Gait Recognition
title_fullStr Deep Large Margin Nearest Neighbor for Gait Recognition
title_full_unstemmed Deep Large Margin Nearest Neighbor for Gait Recognition
title_sort deep large margin nearest neighbor for gait recognition
publisher De Gruyter
publishDate 2021
url https://doaj.org/article/4f04334e1af34b11be30d1da451dfccc
work_keys_str_mv AT xuwanjiang deeplargemarginnearestneighborforgaitrecognition
_version_ 1718371665843322880