Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation

Moderate clothes-changing person re-identification is to find the same person from different camera scenes under the premise of considering the moderate change of clothes.The implementation of existing person re-identification methods is usually based on the assumption that the pedestrian’s clothing...

Full description

Bibliographic Details
Main Author: CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
Format: Article
Language:zho
Published: Editorial office of Computer Science 2022-08-01
Series:Jisuanji kexue
Subjects:
Online Access:https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-8-165.pdf
_version_ 1797845170570395648
author CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
author_facet CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
author_sort CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
collection DOAJ
description Moderate clothes-changing person re-identification is to find the same person from different camera scenes under the premise of considering the moderate change of clothes.The implementation of existing person re-identification methods is usually based on the assumption that the pedestrian’s clothing is invariant,so they rely on clothing-related features.Then,when the above assumptions are not valid,these methods are difficult to achieve the ideal recognition performance.Considering the important characteristic that pedestrian’s shape hardly change when the change of clothes is moderate,the moderate clothes-changing person re-identification is studied.Inspired by the binocular summation in biological vision system,a self-attention siamese network is proposed in this paper.Analogous to biological binocular information acquisition process,the network takes two types of images of the same pedestrian with different clothes as two branch inputs,and then achieves summation effect with siamese architecture.Subsequently,the contrastive learning and fusion learning of multiple features are carried out to obtain the pedestrian feature representation with identity discrimination.Finally,empirical studies show that the proposed method achieves best performance at present on clothes-changing person re-identification benchmark.
first_indexed 2024-04-09T17:35:33Z
format Article
id doaj.art-f85894137dcb4e329045c4c052a3cde4
institution Directory Open Access Journal
issn 1002-137X
language zho
last_indexed 2024-04-09T17:35:33Z
publishDate 2022-08-01
publisher Editorial office of Computer Science
record_format Article
series Jisuanji kexue
spelling doaj.art-f85894137dcb4e329045c4c052a3cde42023-04-18T02:32:21ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-08-0149816517110.11896/jsjkx.210600140Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular SummationCHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin0College of Command and Control Engineering,Army Engineering University of PLA,Nanjing 210007,ChinaModerate clothes-changing person re-identification is to find the same person from different camera scenes under the premise of considering the moderate change of clothes.The implementation of existing person re-identification methods is usually based on the assumption that the pedestrian’s clothing is invariant,so they rely on clothing-related features.Then,when the above assumptions are not valid,these methods are difficult to achieve the ideal recognition performance.Considering the important characteristic that pedestrian’s shape hardly change when the change of clothes is moderate,the moderate clothes-changing person re-identification is studied.Inspired by the binocular summation in biological vision system,a self-attention siamese network is proposed in this paper.Analogous to biological binocular information acquisition process,the network takes two types of images of the same pedestrian with different clothes as two branch inputs,and then achieves summation effect with siamese architecture.Subsequently,the contrastive learning and fusion learning of multiple features are carried out to obtain the pedestrian feature representation with identity discrimination.Finally,empirical studies show that the proposed method achieves best performance at present on clothes-changing person re-identification benchmark.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-8-165.pdfperson re-identification|moderate clothes-changing|binocular summation|self-attention|siamese network
spellingShingle CHEN Kun-feng, PAN Zhi-song, WANG Jia-bao, SHI Lei, ZHANG Jin
Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
Jisuanji kexue
person re-identification|moderate clothes-changing|binocular summation|self-attention|siamese network
title Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
title_full Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
title_fullStr Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
title_full_unstemmed Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
title_short Moderate Clothes-Changing Person Re-identification Based on Bionics of Binocular Summation
title_sort moderate clothes changing person re identification based on bionics of binocular summation
topic person re-identification|moderate clothes-changing|binocular summation|self-attention|siamese network
url https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-8-165.pdf
work_keys_str_mv AT chenkunfengpanzhisongwangjiabaoshileizhangjin moderateclotheschangingpersonreidentificationbasedonbionicsofbinocularsummation