Group Reidentification with Multigrained Matching and Integration

Citation

Lin, Weiyao and Li, Yuxi and Hao, Xiao and See, John Su Yang and Zou, Junni and Xiong, Hongkai and Wang, Jingdong and Tao, Mei (2021) Group Reidentification with Multigrained Matching and Integration. IEEE Transactions on Cybernetics, 51 (3). pp. 1478-1492. ISSN 2168-2267, 2168-2275

Full text not available from this repository.

Abstract

The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group. To achieve robust group Re-ID, we first introduce multigrained representations which can be extracted via the development of two separate schemes, that is, one with handcrafted descriptors and another with deep neural networks. The proposed representation seeks to characterize both appearance and spatial relations of multigrained objects, and is further equipped with importance weights which capture variations in intragroup dynamics. Optimal group-wise matching is facilitated by a multiorder matching process which, in turn, dynamically updates the importance weights in iterative fashion. We evaluated three multicamera group datasets containing complex scenarios and large dynamics, with experimental results demonstrating the effectiveness of our approach.

Item Type: Article
Uncontrolled Keywords: Biometric identification
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 11 Apr 2021 20:22
Last Modified: 11 Apr 2021 20:22
URII: http://shdl.mmu.edu.my/id/eprint/8600

Downloads

Downloads per month over past year

View ItemEdit (login required)