A Dual-Correlation Feature Enhancement Network Model Based on Transformer for Occluded Pedestrian Re-identification

Author:

Zhao Zoufei1,Li Lihong1,Liu Qingqing1,Zeng Ziwei2,Teng Peixian2

Affiliation:

1. Hebei University of Engineering

2. Beijing Jiaotong University

Abstract

Abstract

In pedestrian re-identification, retrieving occluded pedestrians remains a challenging problem. The current methods primarily utilize additional networks to provide body cues for distinguishing the visible parts of the body. However, the inevitable domain gap between the auxiliary models and the Re-ID datasets significantly increases the difficulty in obtaining effective and efficient models. To eliminate the need for additional pre-trained networks, a Transformer-based dual correlation feature enhancement network model is proposed. Specifically, this method designs a relation-based feature enhancement module that effectively compensates for the absence or inaccuracy of local features by modeling the relational information within pedestrian images. Additionally, a dual correlation fusion module is designed to adaptively generate feature weights, fusing global and local features with weighted summation. Finally, extensive experiments were conducted on both occluded and holistic datasets to demonstrate that the proposed model outperforms state-of-the-art methods. The proposed model achieved a Rank-1 accuracy of 72.2% on the Occluded-Duke dataset and 88.0% on the Partial-REID dataset. This proves the effectiveness of the proposed approach.

Publisher

Springer Science and Business Media LLC

Reference42 articles.

1. Deep learning for person re-identification: A survey and outlook;Ye M;IEEE Trans. Pattern Anal. Mach. Intell.,2021

2. A survey of open-world person re-identification;Leng Q;IEEE Trans. Circuits Syst. Video Technol.,2019

3. Deep learning algorithms for person re-identification: State-of-the-art and research challenges;Yadav A;Multimedia Tools Appl.,2024

4. TransPose Re-ID: Transformers for pose invariant person re-identification;Perwaiz N;J. Exp. Theor. Artif. Intell.,2023

5. Video person re-identification by temporal residual learning;Dai J;IEEE Trans. Image Process.,2018

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3