Person Re-Identification Using Local Relation-Aware Graph Convolutional Network
Author:
Lian Yu1, Huang Wenmin1, Liu Shuang1ORCID, Guo Peng2, Zhang Zhong1ORCID, Durrani Tariq S.3
Affiliation:
1. Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin 300387, China 2. CATARC (Tianjin) Automotive Engineering Research Institute Co., Ltd., Tianjin 300300, China 3. Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1QE, UK
Abstract
Local feature extractions have been verified to be effective for person re-identification (re-ID) in recent literature. However, existing methods usually rely on extracting local features from single part of a pedestrian while neglecting the relationship of local features among different pedestrian images. As a result, local features contain limited information from one pedestrian image, and cannot benefit from other pedestrian images. In this paper, we propose a novel approach named Local Relation-Aware Graph Convolutional Network (LRGCN) to learn the relationship of local features among different pedestrian images. In order to completely describe the relationship of local features among different pedestrian images, we propose overlap graph and similarity graph. The overlap graph formulates the edge weight as the overlap node number in the node’s neighborhoods so as to learn robust local features, and the similarity graph defines the edge weight as the similarity between the nodes to learn discriminative local features. To propagate the information for different kinds of nodes effectively, we propose the Structural Graph Convolution (SGConv) operation. Different from traditional graph convolution operations where all nodes share the same parameter matrix, SGConv learns different parameter matrices for the node itself and its neighbor nodes to improve the expressive power. We conduct comprehensive experiments to verify our method on four large-scale person re-ID databases, and the overall results show LRGCN exceeds the state-of-the-art methods.
Funder
National Natural Science Foundation of China atural Science Foundation of Tianjin Scientific Research Project of Tianjin Educational Committee Tianjin Normal University Research Innovation Project for Postgraduate Students
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference73 articles.
1. Lin, R., Wang, R., Zhang, W., Wu, A., and Bi, Y. (2023). Joint Modal Alignment and Feature Enhancement for Visible-Infrared Person Re-Identification. Sensors, 23. 2. Zhou, Y., Liu, P., Cui, Y., Liu, C., and Duan, W. (2022). Integration of Multi-Head Self-Attention and Convolution for Person re-identification. Sensors, 22. 3. Zhou, J., Dong, Q., Zhang, Z., Liu, S., and Durrani, T.S. (2023). Cross-Modality Person Re-Identification via Local Paired Graph attention network. Sensors, 23. 4. Yu, H.X., and Zheng, W.S. (2020, January 14–19). Weakly Supervised Discriminative Feature Learning with State Information for Person Identification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA. 5. Context-Interactive CNN for Person Re-Identification;Song;IEEE Trans. Image Process.,2020
|
|