Cargando…

Person Re-Identification Method Based on Dual Descriptor Feature Enhancement

Person re-identification is a technology used to identify individuals across different cameras. Existing methods involve extracting features from an input image and using a single feature for matching. However, these features often provide a biased description of the person. To address this limitati...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Ronghui, Wang, Rong, Zhang, Wenjing, Wu, Ao, Sun, Yang, Bi, Yihan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10453489/
https://www.ncbi.nlm.nih.gov/pubmed/37628184
http://dx.doi.org/10.3390/e25081154
_version_ 1785095948404260864
author Lin, Ronghui
Wang, Rong
Zhang, Wenjing
Wu, Ao
Sun, Yang
Bi, Yihan
author_facet Lin, Ronghui
Wang, Rong
Zhang, Wenjing
Wu, Ao
Sun, Yang
Bi, Yihan
author_sort Lin, Ronghui
collection PubMed
description Person re-identification is a technology used to identify individuals across different cameras. Existing methods involve extracting features from an input image and using a single feature for matching. However, these features often provide a biased description of the person. To address this limitation, this paper introduces a new method called the Dual Descriptor Feature Enhancement (DDFE) network, which aims to emulate the multi-perspective observation abilities of humans. The DDFE network uses two independent sub-networks to extract descriptors from the same person image. These descriptors are subsequently combined to create a comprehensive multi-view representation, resulting in a significant improvement in recognition performance. To further enhance the discriminative capability of the DDFE network, a carefully designed training strategy is employed. Firstly, the CurricularFace loss is introduced to enhance the recognition accuracy of each sub-network. Secondly, the DropPath operation is incorporated to introduce randomness during sub-network training, promoting difference between the descriptors. Additionally, an Integration Training Module (ITM) is devised to enhance the discriminability of the integrated features. Extensive experiments are conducted on the Market1501 and MSMT17 datasets. On the Market1501 dataset, the DDFE network achieves an mAP of 91.6% and a Rank1 of 96.1%; on the MSMT17 dataset, the network achieves an mAP of 69.9% and a Rank1 of 87.5%. These outcomes outperform most SOTA methods, highlighting the significant advancement and effectiveness of the DDFE network.
format Online
Article
Text
id pubmed-10453489
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104534892023-08-26 Person Re-Identification Method Based on Dual Descriptor Feature Enhancement Lin, Ronghui Wang, Rong Zhang, Wenjing Wu, Ao Sun, Yang Bi, Yihan Entropy (Basel) Article Person re-identification is a technology used to identify individuals across different cameras. Existing methods involve extracting features from an input image and using a single feature for matching. However, these features often provide a biased description of the person. To address this limitation, this paper introduces a new method called the Dual Descriptor Feature Enhancement (DDFE) network, which aims to emulate the multi-perspective observation abilities of humans. The DDFE network uses two independent sub-networks to extract descriptors from the same person image. These descriptors are subsequently combined to create a comprehensive multi-view representation, resulting in a significant improvement in recognition performance. To further enhance the discriminative capability of the DDFE network, a carefully designed training strategy is employed. Firstly, the CurricularFace loss is introduced to enhance the recognition accuracy of each sub-network. Secondly, the DropPath operation is incorporated to introduce randomness during sub-network training, promoting difference between the descriptors. Additionally, an Integration Training Module (ITM) is devised to enhance the discriminability of the integrated features. Extensive experiments are conducted on the Market1501 and MSMT17 datasets. On the Market1501 dataset, the DDFE network achieves an mAP of 91.6% and a Rank1 of 96.1%; on the MSMT17 dataset, the network achieves an mAP of 69.9% and a Rank1 of 87.5%. These outcomes outperform most SOTA methods, highlighting the significant advancement and effectiveness of the DDFE network. MDPI 2023-08-01 /pmc/articles/PMC10453489/ /pubmed/37628184 http://dx.doi.org/10.3390/e25081154 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Lin, Ronghui
Wang, Rong
Zhang, Wenjing
Wu, Ao
Sun, Yang
Bi, Yihan
Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title_full Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title_fullStr Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title_full_unstemmed Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title_short Person Re-Identification Method Based on Dual Descriptor Feature Enhancement
title_sort person re-identification method based on dual descriptor feature enhancement
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10453489/
https://www.ncbi.nlm.nih.gov/pubmed/37628184
http://dx.doi.org/10.3390/e25081154
work_keys_str_mv AT linronghui personreidentificationmethodbasedondualdescriptorfeatureenhancement
AT wangrong personreidentificationmethodbasedondualdescriptorfeatureenhancement
AT zhangwenjing personreidentificationmethodbasedondualdescriptorfeatureenhancement
AT wuao personreidentificationmethodbasedondualdescriptorfeatureenhancement
AT sunyang personreidentificationmethodbasedondualdescriptorfeatureenhancement
AT biyihan personreidentificationmethodbasedondualdescriptorfeatureenhancement