TY - JOUR
T1 - Multi-level cross-view consistent feature learning for person re-identification
AU - Liu, Yixiu
AU - Zhang, Yunzhou
AU - Bhanu, Bir
AU - Coleman, Sonya
AU - Kerr, Dermot
N1 - Funding Information:
Sonya Coleman (M11) received a BSc (Hons) in Mathematics, Statistics and Computing (first class) from the Ulster University, UK in 1999, and a PhD in Mathematics from the Ulster University, UK in 2003. She is a Professor and a leader in the Cognitive Robotics team of Intelligent Systems Research Centre. She is a Fellow of the Higher Education Academy. She has many publications in image processing, pattern recognition, computational intelligence and robotics. Her research has been supported by funding from various sources such as EPSRC, The Nuffield Foundation, The Leverhulme Trust and the European Commission. Additionally, she was co-investigator on the EU FP7 funded project RUBICON, the FP7 project VISUALISE and is currently co-investigator in the FP7 SLANDIAL project. She is also secretary of the Irish Pattern Recognition and Classification Society.
Funding Information:
Yunzhou Zhang received B.S. and M.S. degree in Mechanical and Electronic engineering from National University of Defense Technology, Changsha, China in 1997 and 2000, respectively. He received Ph.D. degree in pattern recognition and intelligent system from Northeastern University, Shenyang, China, in 2009. He is currently a professor with the Faculty of Robot Science and Engineering, Northeastern University, China. Now he leads the Cloud Robotics and Visual Perception Research Group. His research has been supported by funding from various sources such as National Natural Science Foundation of China, Ministry of science and technology of China, Ministry of Education of China and some famous high-tech companies. He has published many journal papers and conference papers in intelligent robots, computer vision and wireless sensor networks. His research interests include intelligent robot, computer vision, and sensor networks.
Funding Information:
This work is supported by National Natural Science Foundation of China (No. 61973066 ), Equipment Pre-research Fundation ( 61403120111 ), Distinguished Creative Talent Program of Liaoning Colleges and Universities ( LR2019027 ), and Fundamental Research Funds for the Central Universities ( N172608005 , N182608004 , N2004022 ).
Publisher Copyright:
© 2021 Elsevier B.V.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/1/12
Y1 - 2021/1/12
N2 - Person re-identification plays an important role in searching for a specific person in a camera network with non-overlapping cameras. The most critical problem for re-identification is feature representation. In this paper, a multi-level cross-view consistent feature learning framework is proposed for person re-identification. First, local deep, LOMO and SIFT features are extracted to form multi-level features. Specifically, local features from the lower and higher layers of a convolutional neural network (CNN) are extracted, these features complement each other as they extract apparent and semantic properties. Second, an ID-based cross-view multi-level dictionary learning (IDB-CMDL) is carried out to obtain sparse and discriminant feature representation. Third, a cross-view consistent word learning is performed to get the cross-view consistent BoVW histograms from sparse feature representation. Finally, a multi-level metric learning fuses multiple BoVW histograms, and learns the sample distance in the subspace for ranking. Experiments on the public CUHK03, Market1501, and DukeMTMC-ReID datasets show results that are superior to many state-of-the-art methods for person re-identification.
AB - Person re-identification plays an important role in searching for a specific person in a camera network with non-overlapping cameras. The most critical problem for re-identification is feature representation. In this paper, a multi-level cross-view consistent feature learning framework is proposed for person re-identification. First, local deep, LOMO and SIFT features are extracted to form multi-level features. Specifically, local features from the lower and higher layers of a convolutional neural network (CNN) are extracted, these features complement each other as they extract apparent and semantic properties. Second, an ID-based cross-view multi-level dictionary learning (IDB-CMDL) is carried out to obtain sparse and discriminant feature representation. Third, a cross-view consistent word learning is performed to get the cross-view consistent BoVW histograms from sparse feature representation. Finally, a multi-level metric learning fuses multiple BoVW histograms, and learns the sample distance in the subspace for ranking. Experiments on the public CUHK03, Market1501, and DukeMTMC-ReID datasets show results that are superior to many state-of-the-art methods for person re-identification.
KW - person re-identification
KW - ocal deep features
KW - ID-based crossview multi-level dictionary learning
KW - cross-view consistent word learning
KW - multi-level metric learning
KW - ID-based cross-view multi-level dictionary learning
KW - Multi-level metric learning
KW - Local deep features
KW - Person re-identification
KW - Cross-view consistent word learning
UR - http://www.scopus.com/inward/record.url?scp=85100437396&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2021.01.010
DO - 10.1016/j.neucom.2021.01.010
M3 - Article
VL - 435
SP - 1
EP - 14
JO - Neurocomputing
JF - Neurocomputing
SN - 0925-2312
ER -