模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2022, Vol. 35 Issue (6): 516-525    DOI: 10.16451/j.cnki.issn1003-6059.202206004
Deep Learning Based Object Detection and Recognition Current Issue| Next Issue| Archive| Adv Search |
Cross-Domain Person Re-identification Method Based on Point-by-Point Feature Matching
YANG Ping1, WU Xiaohong1, HE Xiaohai1, CHEN Honggang1, LIU Qiang1, LI Bo1
1. College of Electronics and Information Engineering, Sichuan University, Chengdu 610065

Download: PDF (1393 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  To improve the poor generalization and cross-domain capability of the existing direct cross-dataset person re-identification methods, a cross-domain person re-identification method based on point-by-point feature matching is proposed. By the proposed method, the model only needs to be trained on the source domain and tested on the target domain to achieve better results. Firstly, to improve the poor robustness of the network for style and color of cross-domain pedestrian images, instance normalization layer(IN) is introduced into the ResNet50 basic network to extract image features. Secondly, the multi-head self-attention module of Transformer is combined with convolution to enhance the representation ability of features. Finally, by establishing a point-by-point feature mapping relationship in the deep features, image matching is regarded as a point-by-point process of finding the local optimum to improve the ability of the proposed model to resist perspective changes in unknown scenes and enhance its generalization. The experimental results show that the advantages of the proposed method in improving the generalization ability.
Key wordsPerson Re-identification      Cross-Domain Person Re-identification      Instance Normalization      Multi-head Self-Attention      Point-by-Point Matching     
Received: 25 February 2022     
ZTFLH: TP 391  
Fund:National Natural Science Foundation of China(No.61871278), Natural Science Foundation of Sichuan Province(No.2022NSFSC0922), Sichuan Science and Technology Plan Project(No.2021YFS0239)
Corresponding Authors: HE Xiaohai, Ph.D., professor. His research interests include image processing, pattern recognition, computer vision and image compression.   
About author:: YANG Ping, master student. Her research interests include deep learning and person re-identification.
WU Xiaohong, Ph.D., associate profe-ssor. Her research interests include image processing, pattern recognition and computer vision.
CHEN Honggang, Ph.D., associate professor. His research interests include image/video processing, computer vision and artificial intelligence.
LIU Qiang, Ph.D. candidate. His research interests include image processing, person re-identification and computer vision.
LI Bo, master student. His research inte-rests include computer vision and pattern re-cognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
YANG Ping
WU Xiaohong
HE Xiaohai
CHEN Honggang
LIU Qiang
LI Bo
Cite this article:   
YANG Ping,WU Xiaohong,HE Xiaohai等. Cross-Domain Person Re-identification Method Based on Point-by-Point Feature Matching[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(6): 516-525.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202206004      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2022/V35/I6/516
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn