行人重识别技术理论研究综述

雷 名云, 芦 丽旭, 杨 继翔
广东工贸职业技术学院

摘要


行人重识别技术主要是运用在多摄像头网络中，其核心作用是用于检索同一行人的图像信息，该技术在现
实生活中具有重要的应用价值，如智能安防、智能交通和商业分析等。然而，该技术的实践应用面临诸多挑战，如
摄取角度不同统一、成图分辨率高低参差、受光照摄有差别、甚至还会出现干扰物遮挡以及行人姿态变化等一系列
的问题。本文对行人重识别技术的研究现状进行了综述。详细介绍了受限制场景下基于表征学习和度量学习的方法，
通用场景下的多模态重识别、无监督学习与半监督学习等研究方向。最后，本文总结了行人重识别技术的现状，并
对未来的研究方向提出了展望。

关键词


行人重识别；受限制场景；通用场景；多模态

全文:

PDF


参考


[1]张永飞，杨航远，张雨佳，豆朝鹏，廖胜才，郑

伟诗，张史梁，叶茫，晏轶超，and李俊杰，“行人再识

别技术研究进展，”中国图象图形学报，vol. 28，no. 6，

pp. 1829-1862，2023.

[2]“震惊全国8年之久的周克华案是怎么侦破的？”，

https://www.163.com/dy/article/DA9LMJ3S0514DP91.

html,%202018-02-10,2.10,2018-2-10

[3]M. Ye, J. Shen, G. Lin, T. Xiang, L. Shao, and S.

C. H. Hoi,“Deep Learning for Person Re-Identification: A

Survey and Outlook,”IEEE Trans Pattern Anal Mach Intell,

vol. 44, no. 6, pp. 2872-2893, Jun, 2022.[4]R. Yu, D. Du, R. LaLonde, D. Davila, C. Funk, A.

Hoogs, and B. Clipp, "Cascade transformers for end-to-end

person search." pp. 7267-7276

[5]Y. Suh, J. Wang, S. Tang, T. Mei, and K. M. Lee,

"Part-Aligned Bilinear Representations for Person Reidentification," Lecture Notes in Computer Science. pp. 418-

437, 2018.

[6]W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, and

J. Jiao, "Image-Image Domain Adaptation with Preserved

Self-Similarity and Domain-Dissimilarity for Person Reidentification." pp. 994-1003.

[7]D. Chen, H. Li, X. Liu, Y. Shen, Z. Yuan, and X.

J. a. e.-p. Wang, "Improving Deep Visual Representation

for Person Re-identification by Global and Local Imagelanguage Association," arXiv180801571C, 2018.

[8]J. Zuo, H. Zhou, Y. Nie, F. Zhang, T. Guo, N.

Sang, Y. Wang, and C. Gao,“UFineBench: Towards Textbased Person Retrieval with Ultra-fine Granularity,”arXiv

preprint, arXiv:.03441, 2023.

[9]Y. Qin, Y. Chen, D. Peng, X. Peng, J. T. Zhou, and

P. Hu,“Noisy-Correspondence Learning for Text-to-Image

Person Re-identification,”arXiv preprint, arXiv:.09911, 2023.

[10]K. Ren, and L. Zhang,“Implicit Discriminative

Knowledge Learning for Visible-Infrared Person ReIdentification,”arXiv preprint, arXiv:.11708, 2024

[11]M. Ye, X. Lan, Z. Wang, and P. C. Yuen,“BiDirectional Center-Constrained Top-Ranking for Visible

Thermal Person Re-Identification,”Ieee Transactions on

Information Forensics and Security, vol. 15, pp. 407-419,

Jun, 2019.

[12]C. Zou, Z. Chen, Z. Cui, Y. Liu, and C. Zhang,

"Discrepant and multi-instance proxies for unsupervised

person re-identification." pp. 11058-11068.

[13]W. Zhuang, Y. Wen, and S. Zhang, "Joint

optimization in edge-cloud continuum for federated

unsupervised person re-identification." pp. 433-441.


Refbacks

  • 当前没有refback。