Progressive Domain Adaptation for Robot Vision Person Re-identification

被引：4
作者：
Sha, Zijun [1 ]
Zeng, Zelong [2 ]
Wang, Zheng [3 ]
Natori, Yoichi [1 ]
Taniguchi, Yasuhiro [1 ]
Satoh, Shin'ichi [3 ]
机构：
[1] Honda Res & Dev Co Ltd, Wako, Saitama, Japan
[2] Univ Tokyo, Tokyo, Japan
[3] Natl Inst Informat, Tokyo, Japan
来源：
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA | 2020年
关键词：
Robot Vision; Domain Adaptation; Person Re-identification;
D O I：
10.1145/3394171.3414358
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Person re-identification has received much attention in the last few years, as it enhances the retrieval effectiveness in the video surveillance networks and video archive management. In this paper, we demonstrate a guiding robot with person followers system, which recognizes the follower using a person re-identification technology. It first adopts existing face recognition and person tracking methods to generate person tracklets with different IDs. Then, a classic person re-identification model, pre-trained on the surveillance dataset, is adapted to the new robot vision condition incrementally. The demonstration showcases the quality of robot follower focusing.
引用
收藏
页码：4488 / 4490
页数：3
相关论文
共 50 条
[41]   Domain-Adaptation Person Re-Identification via Style Translation and Clustering [J].
Wei, Peiyi ;
Zhang, Canlong ;
Li, Zhixin ;
Tang, Yanping ;
Wang, Zhiwen .
NEURAL INFORMATION PROCESSING, ICONIP 2021, PT I, 2021, 13108 :464-475
[42]   Weakly supervised end-to-end domain adaptation for person re-identification [J].
Zhang, Lei ;
Li, Haisheng ;
Liu, Ruijun ;
Wang, Xiaochuan ;
Wu, Xiaoqun .
COMPUTERS & ELECTRICAL ENGINEERING, 2024, 113
[43]   Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identification [J].
Chen, Guangyi ;
Lu, Yuhao ;
Lu, Jiwen ;
Zhou, Jie .
COMPUTER VISION - ECCV 2020, PT VIII, 2020, 12353 :643-659
[44]   Heterogeneous dual network with feature consistency for domain adaptation person re-identification [J].
Zhou, Hua ;
Kong, Jun ;
Jiang, Min ;
Liu, Tianshan .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 14 (05) :1951-1965
[45]   MTNet: Mutual tri-training network for unsupervised domain adaptation on person re-identification [J].
Chen, Si ;
Qiu, Liuxiang ;
Tian, Zimin ;
Yan, Yan ;
Wang, Da-Han ;
Zhu, Shunzhi .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 90
[46]   Domain disentanglement and contrastive learning with source-guided sampling for unsupervised domain adaptation person re-identification [J].
Wu, Cheng-Hsuan ;
Liu, An-Sheng ;
Chen, Chiung-Tao ;
Fu, Li-Chen .
MACHINE VISION AND APPLICATIONS, 2024, 35 (06)
[47]   Progressive Learning for Person Re-Identification With One Example [J].
Wu, Yu ;
Lin, Yutian ;
Dong, Xuanyi ;
Yan, Yan ;
Bian, Wei ;
Yang, Yi .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (06) :2872-2881
[48]   Cross-domain person re-identification based on progressive attention and block occlusion [J].
Li Y. ;
Cheng D. ;
Li J. ;
Huang J. ;
Zhang J. ;
Ma H. .
Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2023, 49 (11) :3167-3176
[49]   Cross adversarial consistency self-prediction learning for unsupervised domain adaptation person re-identification [J].
Li, Huafeng ;
Pang, Jian ;
Tao, Dapeng ;
Yu, Zhengtao .
INFORMATION SCIENCES, 2021, 559 :46-60
[50]   Vision transformer with multiple granularities for person re-identification [J].
Bingcai Chen ;
Fansheng Zhang ;
Xin Yang ;
Qian Ning ;
Victor C. M. Leung .
Neural Computing and Applications, 2023, 35 :23213-23223
12345