Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation
Aiming at the problems caused by a lack of feature matching due to occlusion and fixed model parameters in cross-domain person re-identification, a method based on multi-branch pose-guided occlusion generation is proposed. This method can effectively improve the accuracy of person matching and enabl...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-01-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/25/2/473 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1832587529724887040 |
---|---|
author | Pengnan Liu Yanchen Wang Yunlong Li Deqiang Cheng Feixiang Xu |
author_facet | Pengnan Liu Yanchen Wang Yunlong Li Deqiang Cheng Feixiang Xu |
author_sort | Pengnan Liu |
collection | DOAJ |
description | Aiming at the problems caused by a lack of feature matching due to occlusion and fixed model parameters in cross-domain person re-identification, a method based on multi-branch pose-guided occlusion generation is proposed. This method can effectively improve the accuracy of person matching and enable identity matching even when pedestrian features are misaligned. Firstly, a novel pose-guided occlusion generation module is designed to enhance the model’s ability to extract discriminative features from non-occluded areas. Occlusion data are generated to simulate occluded person images. This improves the model’s learning ability and addresses the issue of misidentifying occlusion samples. Secondly, a multi-branch feature fusion structure is constructed. By fusing different feature information from the global and occlusion branches, the diversity of features is enriched. This enrichment improves the model’s generalization. Finally, a dynamic convolution kernel is constructed to calculate the similarity between images. This approach achieves effective point-to-point matching and resolves the problem of fixed model parameters. Experimental results indicate that, compared to current mainstream algorithms, this method shows significant advantages in the first hit rate (Rank-1), mean average precision (mAP), and generalization performance. In the MSMT17→DukeMTMC-reID dataset, after re-ranking (Rerank) and time-tift (Tlift) for the two indicators on Market1501, the mAP and Rank-1 reached 80.5%, 84.3%, 81.9%, and 93.1%. Additionally, the algorithm achieved 51.6% and 41.3% on DukeMTMC-reID→Occluded-Duke, demonstrating good recognition performance on the occlusion dataset. |
format | Article |
id | doaj-art-d45dc74aa55148a8a5e6fb02e677b8d6 |
institution | Kabale University |
issn | 1424-8220 |
language | English |
publishDate | 2025-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj-art-d45dc74aa55148a8a5e6fb02e677b8d62025-01-24T13:49:04ZengMDPI AGSensors1424-82202025-01-0125247310.3390/s25020473Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion GenerationPengnan Liu0Yanchen Wang1Yunlong Li2Deqiang Cheng3Feixiang Xu4School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, ChinaAiming at the problems caused by a lack of feature matching due to occlusion and fixed model parameters in cross-domain person re-identification, a method based on multi-branch pose-guided occlusion generation is proposed. This method can effectively improve the accuracy of person matching and enable identity matching even when pedestrian features are misaligned. Firstly, a novel pose-guided occlusion generation module is designed to enhance the model’s ability to extract discriminative features from non-occluded areas. Occlusion data are generated to simulate occluded person images. This improves the model’s learning ability and addresses the issue of misidentifying occlusion samples. Secondly, a multi-branch feature fusion structure is constructed. By fusing different feature information from the global and occlusion branches, the diversity of features is enriched. This enrichment improves the model’s generalization. Finally, a dynamic convolution kernel is constructed to calculate the similarity between images. This approach achieves effective point-to-point matching and resolves the problem of fixed model parameters. Experimental results indicate that, compared to current mainstream algorithms, this method shows significant advantages in the first hit rate (Rank-1), mean average precision (mAP), and generalization performance. In the MSMT17→DukeMTMC-reID dataset, after re-ranking (Rerank) and time-tift (Tlift) for the two indicators on Market1501, the mAP and Rank-1 reached 80.5%, 84.3%, 81.9%, and 93.1%. Additionally, the algorithm achieved 51.6% and 41.3% on DukeMTMC-reID→Occluded-Duke, demonstrating good recognition performance on the occlusion dataset.https://www.mdpi.com/1424-8220/25/2/473cross-domainperson re-identificationpose-guided occlusionmulti-branch |
spellingShingle | Pengnan Liu Yanchen Wang Yunlong Li Deqiang Cheng Feixiang Xu Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation Sensors cross-domain person re-identification pose-guided occlusion multi-branch |
title | Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation |
title_full | Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation |
title_fullStr | Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation |
title_full_unstemmed | Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation |
title_short | Cross-Domain Person Re-Identification Based on Multi-Branch Pose-Guided Occlusion Generation |
title_sort | cross domain person re identification based on multi branch pose guided occlusion generation |
topic | cross-domain person re-identification pose-guided occlusion multi-branch |
url | https://www.mdpi.com/1424-8220/25/2/473 |
work_keys_str_mv | AT pengnanliu crossdomainpersonreidentificationbasedonmultibranchposeguidedocclusiongeneration AT yanchenwang crossdomainpersonreidentificationbasedonmultibranchposeguidedocclusiongeneration AT yunlongli crossdomainpersonreidentificationbasedonmultibranchposeguidedocclusiongeneration AT deqiangcheng crossdomainpersonreidentificationbasedonmultibranchposeguidedocclusiongeneration AT feixiangxu crossdomainpersonreidentificationbasedonmultibranchposeguidedocclusiongeneration |