MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification

RGB–IR cross modality person re-identification (RGB–IR Re-ID) is an important task for video surveillance in poorly illuminated or dark environments. In addition to the common challenge of Re-ID, the large cross-modality variations between RGB and IR images must be considered. The existing RGB–IR Re...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jing Mei, Huahu Xu, Yang Li, Minjie Bian, Yuzhe Huang
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/b28eea40d8a344c585c7657b81e6d421
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b28eea40d8a344c585c7657b81e6d421
record_format dspace
spelling oai:doaj.org-article:b28eea40d8a344c585c7657b81e6d4212021-11-25T17:39:58ZMFCNet: Mining Features Context Network for RGB–IR Person Re-Identification10.3390/fi131102901999-5903https://doaj.org/article/b28eea40d8a344c585c7657b81e6d4212021-11-01T00:00:00Zhttps://www.mdpi.com/1999-5903/13/11/290https://doaj.org/toc/1999-5903RGB–IR cross modality person re-identification (RGB–IR Re-ID) is an important task for video surveillance in poorly illuminated or dark environments. In addition to the common challenge of Re-ID, the large cross-modality variations between RGB and IR images must be considered. The existing RGB–IR Re-ID methods use different network structures to learn the global shared features associated with multi-modalities. However, most global shared feature learning methods are sensitive to background clutter, and contextual feature relationships are not considered among the mined features. To solve these problems, this paper proposes a dual-path attention network architecture MFCNet. SGA (Spatial-Global Attention) module embedded in MFCNet includes spatial attention and global attention branches to mine discriminative features. First, the SGA module proposed in this paper focuses on the key parts of the input image to obtain robust features. Next, the module mines the contextual relationships among features to obtain discriminative features and improve network performance. Finally, extensive experiments demonstrate that the performance of the network architecture proposed in this paper is better than that of state-of-the-art methods under various settings. In the all-search mode of the SYSU and RegDB data sets, the rank-1 accuracy reaches 51.64% and 69.76%, respectively.Jing MeiHuahu XuYang LiMinjie BianYuzhe HuangMDPI AGarticleperson re-identificationRGB–IRMFCNetSGA moduleInformation technologyT58.5-58.64ENFuture Internet, Vol 13, Iss 290, p 290 (2021)
institution DOAJ
collection DOAJ
language EN
topic person re-identification
RGB–IR
MFCNet
SGA module
Information technology
T58.5-58.64
spellingShingle person re-identification
RGB–IR
MFCNet
SGA module
Information technology
T58.5-58.64
Jing Mei
Huahu Xu
Yang Li
Minjie Bian
Yuzhe Huang
MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
description RGB–IR cross modality person re-identification (RGB–IR Re-ID) is an important task for video surveillance in poorly illuminated or dark environments. In addition to the common challenge of Re-ID, the large cross-modality variations between RGB and IR images must be considered. The existing RGB–IR Re-ID methods use different network structures to learn the global shared features associated with multi-modalities. However, most global shared feature learning methods are sensitive to background clutter, and contextual feature relationships are not considered among the mined features. To solve these problems, this paper proposes a dual-path attention network architecture MFCNet. SGA (Spatial-Global Attention) module embedded in MFCNet includes spatial attention and global attention branches to mine discriminative features. First, the SGA module proposed in this paper focuses on the key parts of the input image to obtain robust features. Next, the module mines the contextual relationships among features to obtain discriminative features and improve network performance. Finally, extensive experiments demonstrate that the performance of the network architecture proposed in this paper is better than that of state-of-the-art methods under various settings. In the all-search mode of the SYSU and RegDB data sets, the rank-1 accuracy reaches 51.64% and 69.76%, respectively.
format article
author Jing Mei
Huahu Xu
Yang Li
Minjie Bian
Yuzhe Huang
author_facet Jing Mei
Huahu Xu
Yang Li
Minjie Bian
Yuzhe Huang
author_sort Jing Mei
title MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
title_short MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
title_full MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
title_fullStr MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
title_full_unstemmed MFCNet: Mining Features Context Network for RGB–IR Person Re-Identification
title_sort mfcnet: mining features context network for rgb–ir person re-identification
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/b28eea40d8a344c585c7657b81e6d421
work_keys_str_mv AT jingmei mfcnetminingfeaturescontextnetworkforrgbirpersonreidentification
AT huahuxu mfcnetminingfeaturescontextnetworkforrgbirpersonreidentification
AT yangli mfcnetminingfeaturescontextnetworkforrgbirpersonreidentification
AT minjiebian mfcnetminingfeaturescontextnetworkforrgbirpersonreidentification
AT yuzhehuang mfcnetminingfeaturescontextnetworkforrgbirpersonreidentification
_version_ 1718412126247190528