Person Re-Identification by Low-Dimensional Features and Metric Learning

Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xingyuan Chen, Huahu Xu, Yang Li, Minjie Bian
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	person re-identification hand-crafted features color feature BLSTM Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/ec78b8e37aa444bbae93d8ef15f17e15
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ec78b8e37aa444bbae93d8ef15f17e15
record_format	dspace
spelling	oai:doaj.org-article:ec78b8e37aa444bbae93d8ef15f17e152021-11-25T17:39:57ZPerson Re-Identification by Low-Dimensional Features and Metric Learning10.3390/fi131102891999-5903https://doaj.org/article/ec78b8e37aa444bbae93d8ef15f17e152021-11-01T00:00:00Zhttps://www.mdpi.com/1999-5903/13/11/289https://doaj.org/toc/1999-5903Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also few studies that combine the powerful learning capabilities of deep learning with color features. Therefore, we hope to use the advantages of both to design a model with low computational resource consumption and excellent performance to solve the task of person re-identification. In this paper, we designed a color feature containing relative spatial information, namely the color feature with spatial information. Then, bidirectional long short-term memory (BLSTM) networks with an attention mechanism are used to obtain the contextual relationship contained in the hand-crafted color features. Finally, experiments demonstrate that the proposed model can improve the recognition performance compared with traditional methods. At the same time, hand-crafted features based on human prior knowledge not only reduce computational consumption compared with deep learning methods but also make the model more interpretable.Xingyuan ChenHuahu XuYang LiMinjie BianMDPI AGarticleperson re-identificationhand-crafted featurescolor featureBLSTMInformation technologyT58.5-58.64ENFuture Internet, Vol 13, Iss 289, p 289 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	person re-identification hand-crafted features color feature BLSTM Information technology T58.5-58.64
spellingShingle	person re-identification hand-crafted features color feature BLSTM Information technology T58.5-58.64 Xingyuan Chen Huahu Xu Yang Li Minjie Bian Person Re-Identification by Low-Dimensional Features and Metric Learning
description	Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also few studies that combine the powerful learning capabilities of deep learning with color features. Therefore, we hope to use the advantages of both to design a model with low computational resource consumption and excellent performance to solve the task of person re-identification. In this paper, we designed a color feature containing relative spatial information, namely the color feature with spatial information. Then, bidirectional long short-term memory (BLSTM) networks with an attention mechanism are used to obtain the contextual relationship contained in the hand-crafted color features. Finally, experiments demonstrate that the proposed model can improve the recognition performance compared with traditional methods. At the same time, hand-crafted features based on human prior knowledge not only reduce computational consumption compared with deep learning methods but also make the model more interpretable.
format	article
author	Xingyuan Chen Huahu Xu Yang Li Minjie Bian
author_facet	Xingyuan Chen Huahu Xu Yang Li Minjie Bian
author_sort	Xingyuan Chen
title	Person Re-Identification by Low-Dimensional Features and Metric Learning
title_short	Person Re-Identification by Low-Dimensional Features and Metric Learning
title_full	Person Re-Identification by Low-Dimensional Features and Metric Learning
title_fullStr	Person Re-Identification by Low-Dimensional Features and Metric Learning
title_full_unstemmed	Person Re-Identification by Low-Dimensional Features and Metric Learning
title_sort	person re-identification by low-dimensional features and metric learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ec78b8e37aa444bbae93d8ef15f17e15
work_keys_str_mv	AT xingyuanchen personreidentificationbylowdimensionalfeaturesandmetriclearning AT huahuxu personreidentificationbylowdimensionalfeaturesandmetriclearning AT yangli personreidentificationbylowdimensionalfeaturesandmetriclearning AT minjiebian personreidentificationbylowdimensionalfeaturesandmetriclearning
_version_	1718412138449469440

Person Re-Identification by Low-Dimensional Features and Metric Learning

Ejemplares similares