A novel person re-identification network to address low-resolution problem in smart city context
We argue that accurate person re-identification is a vital problem for urban public monitoring systems in the smart city context. Since images captured from different cameras have arbitrary resolutions resulting in resolution mismatch, this work proposes a model that takes arbitrary images and conve...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | ICT Express |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405959522001072 |
_version_ | 1797653963652202496 |
---|---|
author | Irfan Yaqoob Muhammad Umair Hassan Dongmei Niu Xiuyang Zhao Ibrahim A. Hameed Saeed-Ul Hassan |
author_facet | Irfan Yaqoob Muhammad Umair Hassan Dongmei Niu Xiuyang Zhao Ibrahim A. Hameed Saeed-Ul Hassan |
author_sort | Irfan Yaqoob |
collection | DOAJ |
description | We argue that accurate person re-identification is a vital problem for urban public monitoring systems in the smart city context. Since images captured from different cameras have arbitrary resolutions resulting in resolution mismatch, this work proposes a model that takes arbitrary images and converts them to a pre-defined fixed resolution. The model then passes the images to a super-resolution network, producing high-resolution images. We employ a feedback network to generate more realistic super-resolution images, which are fed to the re-identification network to acquire a unique descriptor to disclose the person’s identity. We outperformed in all measures against other state-of-the-art methods. |
first_indexed | 2024-03-11T16:51:31Z |
format | Article |
id | doaj.art-84b5e6ccd8834009bab54ee5b6461c94 |
institution | Directory Open Access Journal |
issn | 2405-9595 |
language | English |
last_indexed | 2024-03-11T16:51:31Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | ICT Express |
spelling | doaj.art-84b5e6ccd8834009bab54ee5b6461c942023-10-21T04:22:56ZengElsevierICT Express2405-95952023-10-0195809814A novel person re-identification network to address low-resolution problem in smart city contextIrfan Yaqoob0Muhammad Umair Hassan1Dongmei Niu2Xiuyang Zhao3Ibrahim A. Hameed4Saeed-Ul Hassan5School of Information Science and Engineering, University of Jinan, Jinan, ChinaDepartment of ICT and Natural Sciences, Norwegian University of Science and Technology, Å lesund, Norway; Corresponding author.School of Information Science and Engineering, University of Jinan, Jinan, ChinaSchool of Information Science and Engineering, University of Jinan, Jinan, ChinaDepartment of ICT and Natural Sciences, Norwegian University of Science and Technology, Å lesund, NorwayDepartment of Computing and Mathematics, Manchester Metropolitan University, Manchester, United KingdomWe argue that accurate person re-identification is a vital problem for urban public monitoring systems in the smart city context. Since images captured from different cameras have arbitrary resolutions resulting in resolution mismatch, this work proposes a model that takes arbitrary images and converts them to a pre-defined fixed resolution. The model then passes the images to a super-resolution network, producing high-resolution images. We employ a feedback network to generate more realistic super-resolution images, which are fed to the re-identification network to acquire a unique descriptor to disclose the person’s identity. We outperformed in all measures against other state-of-the-art methods.http://www.sciencedirect.com/science/article/pii/S2405959522001072Person re-identificationHigh resolutionSmart citiesDeep learning |
spellingShingle | Irfan Yaqoob Muhammad Umair Hassan Dongmei Niu Xiuyang Zhao Ibrahim A. Hameed Saeed-Ul Hassan A novel person re-identification network to address low-resolution problem in smart city context ICT Express Person re-identification High resolution Smart cities Deep learning |
title | A novel person re-identification network to address low-resolution problem in smart city context |
title_full | A novel person re-identification network to address low-resolution problem in smart city context |
title_fullStr | A novel person re-identification network to address low-resolution problem in smart city context |
title_full_unstemmed | A novel person re-identification network to address low-resolution problem in smart city context |
title_short | A novel person re-identification network to address low-resolution problem in smart city context |
title_sort | novel person re identification network to address low resolution problem in smart city context |
topic | Person re-identification High resolution Smart cities Deep learning |
url | http://www.sciencedirect.com/science/article/pii/S2405959522001072 |
work_keys_str_mv | AT irfanyaqoob anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT muhammadumairhassan anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT dongmeiniu anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT xiuyangzhao anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT ibrahimahameed anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT saeedulhassan anovelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT irfanyaqoob novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT muhammadumairhassan novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT dongmeiniu novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT xiuyangzhao novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT ibrahimahameed novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext AT saeedulhassan novelpersonreidentificationnetworktoaddresslowresolutionprobleminsmartcitycontext |