MULTI-VIEW VEHICLE IMAGE GENERATION NETWORK FOR VEHICLE RE-IDENTIFICATION

被引：0

作者：

Xun, Yizhe ^{[1
,2
]}

Liu, Jia ^{[1
,2
]}

Islam, Sardar M. N. ^{[3
]}

Chen, Yuanfang ^{[1
,2
]}

机构：

[1] Hangzhou Dianzi Univ, Sch Cyberspace Secur, Hangzhou 310018, Peoples R China

[2] Key Lab Discrete Ind Internet Things Zhejiang Pro, Hangzhou 310018, Peoples R China

[3] Victoria Univ, Inst Sustainable Ind & Liveable Cities, Melbourne, Vic 3030, Australia

来源：

2024 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS, ICC WORKSHOPS 2024 | 2024年

关键词：

vehicle re-identification; generative adversarial nets; viewpoint variation; multi-view vehicle image generation network;

D O I：

10.1109/ICCWORKSHOPS59551.2024.10615790

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Vehicle re-identification is a technology that continuously tracks and identifies vehicles in different spatial domains, and playing a critical role in Space-Air-Ground-Sea Integrated Networks(SAGSIN). Viewpoint variation problem, that is vehicle appearance changes greatly under various viewpoints, makes vehicle re-identification challenging. To eliminate the negative effects of viewpoint variation, in this paper, we propose a Multi-View Vehicle Image Generation Network for Vehicle Re-Identification(MVIGN). MVIGN generate images with the same identity as the input vehicle image but with a different and controllable pose to solve viewpoint variation problem. Extensive experiments indicate using images generated by MVIGN to expand training set can improve the model accuracy and reduce the cost of manually collecting and labeling data.

引用

页码：517 / 522

页数：6

共 18 条

[1]

Goodfellow I, 2014, Advances in Neural Information Processing Systems

[2] Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification [J].

Guo, Haiyun ;

Zhu, Kuan ;

Tang, Ming ;

Wang, Jinqiao .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (09) :4328-4338

[3] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[4]

Heusel M, 2017, ADV NEUR IN, V30

[5] Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond [J].

Li, Ming ;

Huang, Xinming ;

Zhang, Ziming .

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :194-204

[6] VARID: Viewpoint-Aware Re-IDentification of Vehicle Based on Triplet Loss [J].

Li, Yidong ;

Liu, Kai ;

Jin, Yi ;

Wang, Tao ;

Lin, Weipeng .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (02) :1381-1390

[7] Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles [J].

Liu, Hongye ;

Tian, Yonghong ;

Wang, Yaowei ;

Pang, Lu ;

Huang, Tiejun .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2167-2175

[8] Beyond the Parts: Learning Multi-view Cross-part Correlation for Vehicle Re-identification [J].

Liu, Xinchen ;

Liu, Wu ;

Zheng, Jinkai ;

Yan, Chenggang ;

Mei, Tao .

MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, :907-915

[9] PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance [J].

Liu, Xinchen ;

Liu, Wu ;

Mei, Tao ;

Ma, Huadong .

IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (03) :645-658

[10] A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance [J].

Liu, Xinchen ;

Liu, Wu ;

Mei, Tao ;

Ma, Huadong .

COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :869-884

← 1 2 →