Two‐way constraint network for RGB‐Infrared person re‐identification
Abstract RGB‐Infrared person re‐identification (RGB‐IR Re‐ID) is a task aiming to retrieve and match person images between RGB images and IR images. Since most surveillance cameras capture RGB images during the day and IR images at night, RGB‐IR Re‐ID is helpful when checking day and night surveilla...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-08-01
|
Series: | Electronics Letters |
Subjects: | |
Online Access: | https://doi.org/10.1049/ell2.12215 |
_version_ | 1811210231696326656 |
---|---|
author | Haitang Zeng Weipeng Hu Dihu Chen Haifeng Hu |
author_facet | Haitang Zeng Weipeng Hu Dihu Chen Haifeng Hu |
author_sort | Haitang Zeng |
collection | DOAJ |
description | Abstract RGB‐Infrared person re‐identification (RGB‐IR Re‐ID) is a task aiming to retrieve and match person images between RGB images and IR images. Since most surveillance cameras capture RGB images during the day and IR images at night, RGB‐IR Re‐ID is helpful when checking day and night surveillance for criminal investigations. Previous related work often only extracts sharable and identity‐related features in images for identification. Few researches specifically extract and make use of features that do not have the ability to distinguish identity, e.g. identity‐unrelated features derived from background and modality. In this Letter, we propose a novel and concise RGB‐IR Re‐ID network named two‐way constraint network (TWCN). Compared with traditional Re‐ID networks, TWCN not only extracts and utilises identity‐related features but also novelly makes full use of identity‐unrelated features to improve the accuracy of the experiment. TWCN uses a reverse‐triplet loss to extract identity‐unrelated features, and proposes an orthogonal constraint to remove identity‐unrelated information from identity‐related features, which improves the purity of identity‐related features. In addition, a correlation coefficient synergy and central clustering (CCSCC) loss is introduced into TWCN to extract identity‐related features effectively. Extensive experiments have been conducted to prove our method is effective. |
first_indexed | 2024-04-12T04:51:06Z |
format | Article |
id | doaj.art-450ecf060d5f4bb9851bd10f00fed744 |
institution | Directory Open Access Journal |
issn | 0013-5194 1350-911X |
language | English |
last_indexed | 2024-04-12T04:51:06Z |
publishDate | 2021-08-01 |
publisher | Wiley |
record_format | Article |
series | Electronics Letters |
spelling | doaj.art-450ecf060d5f4bb9851bd10f00fed7442022-12-22T03:47:17ZengWileyElectronics Letters0013-51941350-911X2021-08-01571765365510.1049/ell2.12215Two‐way constraint network for RGB‐Infrared person re‐identificationHaitang Zeng0Weipeng Hu1Dihu Chen2Haifeng Hu3School of Electronics and Information Technology Sun Yat‐Sen University Guangzhou Guangdong People's Republic of ChinaSchool of Electronics and Information Technology Sun Yat‐Sen University Guangzhou Guangdong People's Republic of ChinaSchool of Electronics and Information Technology Sun Yat‐Sen University Guangzhou Guangdong People's Republic of ChinaSchool of Electronics and Information Technology Sun Yat‐Sen University Guangzhou Guangdong People's Republic of ChinaAbstract RGB‐Infrared person re‐identification (RGB‐IR Re‐ID) is a task aiming to retrieve and match person images between RGB images and IR images. Since most surveillance cameras capture RGB images during the day and IR images at night, RGB‐IR Re‐ID is helpful when checking day and night surveillance for criminal investigations. Previous related work often only extracts sharable and identity‐related features in images for identification. Few researches specifically extract and make use of features that do not have the ability to distinguish identity, e.g. identity‐unrelated features derived from background and modality. In this Letter, we propose a novel and concise RGB‐IR Re‐ID network named two‐way constraint network (TWCN). Compared with traditional Re‐ID networks, TWCN not only extracts and utilises identity‐related features but also novelly makes full use of identity‐unrelated features to improve the accuracy of the experiment. TWCN uses a reverse‐triplet loss to extract identity‐unrelated features, and proposes an orthogonal constraint to remove identity‐unrelated information from identity‐related features, which improves the purity of identity‐related features. In addition, a correlation coefficient synergy and central clustering (CCSCC) loss is introduced into TWCN to extract identity‐related features effectively. Extensive experiments have been conducted to prove our method is effective.https://doi.org/10.1049/ell2.12215Optical, image and video signal processingImage sensorsComputer vision and image processing techniquesData handling techniquesNeural nets |
spellingShingle | Haitang Zeng Weipeng Hu Dihu Chen Haifeng Hu Two‐way constraint network for RGB‐Infrared person re‐identification Electronics Letters Optical, image and video signal processing Image sensors Computer vision and image processing techniques Data handling techniques Neural nets |
title | Two‐way constraint network for RGB‐Infrared person re‐identification |
title_full | Two‐way constraint network for RGB‐Infrared person re‐identification |
title_fullStr | Two‐way constraint network for RGB‐Infrared person re‐identification |
title_full_unstemmed | Two‐way constraint network for RGB‐Infrared person re‐identification |
title_short | Two‐way constraint network for RGB‐Infrared person re‐identification |
title_sort | two way constraint network for rgb infrared person re identification |
topic | Optical, image and video signal processing Image sensors Computer vision and image processing techniques Data handling techniques Neural nets |
url | https://doi.org/10.1049/ell2.12215 |
work_keys_str_mv | AT haitangzeng twowayconstraintnetworkforrgbinfraredpersonreidentification AT weipenghu twowayconstraintnetworkforrgbinfraredpersonreidentification AT dihuchen twowayconstraintnetworkforrgbinfraredpersonreidentification AT haifenghu twowayconstraintnetworkforrgbinfraredpersonreidentification |