Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks
Person re-identification in camera sensor networks is a challenging issue due to significant appearance variations of pedestrian images captured by different camera sensors. The contextual information of pedestrian images is a vital cue to overcome appearance variations. However, many existing appro...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8861333/ |
_version_ | 1811212194518401024 |
---|---|
author | Zhong Zhang Tongzhen Si Meiyan Huang Shuang Liu |
author_facet | Zhong Zhang Tongzhen Si Meiyan Huang Shuang Liu |
author_sort | Zhong Zhang |
collection | DOAJ |
description | Person re-identification in camera sensor networks is a challenging issue due to significant appearance variations of pedestrian images captured by different camera sensors. The contextual information of pedestrian images is a vital cue to overcome appearance variations. However, many existing approaches learn the distance metric in a global way or restrict to corresponding sub-regions, which discards the contextual information of pedestrians or learns the contextual information inadequately. In this paper, we propose an effective method to tackle the problem for person re-identification in camera sensor networks. Firstly, we propose the Contextual Region-based Metric Learning (CRML) to fully learn the contextual information in a local manner, which simultaneously utilizes three kinds of sub-region pairs to learn a discriminative transformation matrix. Secondly, we employ the greedy axis rotation algorithm to optimize the transformation matrix in the framework of mutual information. Thirdly, in the process of local similarity integration, we further propose the Context-Constrained Match (CCM) to overcome the misalignment problem by seeking the optimal match in the neighboring sub-regions. Fourthly, we further present the nCRML to avoid the dimensionality curse and fuse similarity scores in different low-dimensional subspaces. The experimental results on three challenging datasets (VIPeR, QMUL GRID and CUHK03) demonstrate the effectiveness of our method. |
first_indexed | 2024-04-12T05:25:04Z |
format | Article |
id | doaj.art-c88d5a1d932949be9c8cd0a0f22a667a |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T05:25:04Z |
publishDate | 2019-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-c88d5a1d932949be9c8cd0a0f22a667a2022-12-22T03:46:19ZengIEEEIEEE Access2169-35362019-01-01714684814685610.1109/ACCESS.2019.29460218861333Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor NetworksZhong Zhang0https://orcid.org/0000-0002-2993-8612Tongzhen Si1Meiyan Huang2Shuang Liu3https://orcid.org/0000-0002-9027-0690Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaTianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin, ChinaPerson re-identification in camera sensor networks is a challenging issue due to significant appearance variations of pedestrian images captured by different camera sensors. The contextual information of pedestrian images is a vital cue to overcome appearance variations. However, many existing approaches learn the distance metric in a global way or restrict to corresponding sub-regions, which discards the contextual information of pedestrians or learns the contextual information inadequately. In this paper, we propose an effective method to tackle the problem for person re-identification in camera sensor networks. Firstly, we propose the Contextual Region-based Metric Learning (CRML) to fully learn the contextual information in a local manner, which simultaneously utilizes three kinds of sub-region pairs to learn a discriminative transformation matrix. Secondly, we employ the greedy axis rotation algorithm to optimize the transformation matrix in the framework of mutual information. Thirdly, in the process of local similarity integration, we further propose the Context-Constrained Match (CCM) to overcome the misalignment problem by seeking the optimal match in the neighboring sub-regions. Fourthly, we further present the nCRML to avoid the dimensionality curse and fuse similarity scores in different low-dimensional subspaces. The experimental results on three challenging datasets (VIPeR, QMUL GRID and CUHK03) demonstrate the effectiveness of our method.https://ieeexplore.ieee.org/document/8861333/Person re-identificationcontextual region-based metric learningcontext-constrained matchcamera sensor networks |
spellingShingle | Zhong Zhang Tongzhen Si Meiyan Huang Shuang Liu Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks IEEE Access Person re-identification contextual region-based metric learning context-constrained match camera sensor networks |
title | Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks |
title_full | Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks |
title_fullStr | Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks |
title_full_unstemmed | Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks |
title_short | Person Re-Identification via Contextual Region-Based Metric Learning in Camera Sensor Networks |
title_sort | person re identification via contextual region based metric learning in camera sensor networks |
topic | Person re-identification contextual region-based metric learning context-constrained match camera sensor networks |
url | https://ieeexplore.ieee.org/document/8861333/ |
work_keys_str_mv | AT zhongzhang personreidentificationviacontextualregionbasedmetriclearningincamerasensornetworks AT tongzhensi personreidentificationviacontextualregionbasedmetriclearningincamerasensornetworks AT meiyanhuang personreidentificationviacontextualregionbasedmetriclearningincamerasensornetworks AT shuangliu personreidentificationviacontextualregionbasedmetriclearningincamerasensornetworks |