TY - JOUR
T1 - Group Reidentification with Multigrained Matching and Integration
AU - Lin, Weiyao
AU - Li, Yuxi
AU - Xiao, Hao
AU - See, John
AU - Zou, Junni
AU - Xiong, Hongkai
AU - Wang, Jingdong
AU - Mei, Tao
N1 - Funding Information:
Manuscript received January 26, 2019; revised April 28, 2019 and May 7, 2019; accepted May 12, 2019. Date of publication June 11, 2019; date of current version February 17, 2021. This work was supported in part by the National Natural Science Foundation of China under Grant 61529101, Grant 61425011, and Grant 61720106001, in part by the Shanghai “The Belt and Road” Young Scholar Exchange under Grant 17510740100, and in part by CREST Malaysia under Grant T03C1-17. This paper was recommended by Associate Editor D. Tao. (Corresponding author: Weiyao Lin.) W. Lin, Y. Li, and H. Xiong are with the Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China (e-mail: [email protected]; [email protected]; [email protected]).
Publisher Copyright:
© 2013 IEEE.
PY - 2021/3
Y1 - 2021/3
N2 - 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.
AB - 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.
KW - Group reidentification (Re-ID)
KW - group-wise matching
KW - multigrained representation
KW - Re-ID
UR - http://www.scopus.com/inward/record.url?scp=85101112221&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2019.2917713
DO - 10.1109/TCYB.2019.2917713
M3 - Article
C2 - 31199281
AN - SCOPUS:85101112221
SN - 2168-2267
VL - 51
SP - 1478
EP - 1492
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 3
ER -