Deep adaptive feature embedding with local sample distributions for person re-identification

Wu, Lin, Wang, Yang, Gao, Junbin and Li, Xue (2017) Deep adaptive feature embedding with local sample distributions for person re-identification. Pattern Recognition, 73 275-288. doi:10.1016/j.patcog.2017.08.029


Author Wu, Lin
Wang, Yang
Gao, Junbin
Li, Xue
Title Deep adaptive feature embedding with local sample distributions for person re-identification
Journal name Pattern Recognition   Check publisher's open access policy
ISSN 0031-3203
1873-5142
Publication date 2017-08-31
Year available 2018
Sub-type Article (original research)
DOI 10.1016/j.patcog.2017.08.029
Open Access Status Not yet assessed
Volume 73
Start page 275
End page 288
Total pages 14
Place of publication Amsterdam, Netherlands
Publisher Elsevier BV
Language eng
Subject 1712 Software
1711 Signal Processing
1707 Computer Vision and Pattern Recognition
1702 Artificial Intelligence
Abstract Person re-identification (re-id) aims to match pedestrians observed by disjoint camera views. It attracts increasing attention in computer vision due to its importance to surveillance systems. To combat the major challenge of cross-view visual variations, deep embedding approaches are proposed by learning a compact feature space from images such that the Euclidean distances correspond to their cross-view similarity metric. However, the global Euclidean distance cannot faithfully characterize the ideal similarity in a complex visual feature space because features of pedestrian images exhibit unknown distributions due to large variations in poses, illumination and occlusion. Moreover, intra-personal training samples within a local range which are robust to guide deep embedding against uncontrolled variations cannot be captured by a global Euclidean distance. In this paper, we study the problem of person re-id by proposing a novel sampling to mine suitable positives (i.e., intra-class) within a local range to improve the deep embedding in the context of large intra-class variations. Our method is capable of learning a deep similarity metric adaptive to local sample structure by minimizing each sample's local distances while propagating through the relationship between samples to attain the whole intra-class minimization. To this end, a novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep feature embedding. This attains local discriminations by selecting local-ranged positive samples, and the learned features are robust to dramatic intra-class variations. Experiments on benchmarks show state-of-the-art results achieved by our method. (C) 2017 Elsevier Ltd. All rights reserved.
Keyword Signal Processing
Software
Artificial Intelligence
Computer Vision and Pattern Recognition
Q-Index Code C1
Q-Index Status Provisional Code
Grant ID DP 160104075
DP140102270
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: HERDC Pre-Audit
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 12 Sep 2017, 16:52:01 EST by Lin Wu on behalf of School of Information Technol and Elec Engineering