Multi-level cross-view consistent feature learning for person re-identification

Yixiu Liu; Yunzhou Zhang; Bir Bhanu; Sonya Coleman; Dermot Kerr

doi:10.1016/j.neucom.2021.01.010

Multi-level cross-view consistent feature learning for person re-identification

Yixiu Liu
, Yunzhou Zhang
, Bir Bhanu
, Sonya Coleman
, Dermot Kerr

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

368 Downloads (Pure)

Abstract

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.

Original language	English
Pages (from-to)	1-14
Number of pages	14
Journal	Neurocomputing
Volume	435
Early online date	12 Jan 2021
DOIs	https://doi.org/10.1016/j.neucom.2021.01.010
Publication status	Published (in print/issue) - 7 May 2021

Bibliographical note

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.

Funding

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.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 4 Quality Education

Keywords

person re-identification
ocal deep features
ID-based crossview multi-level dictionary learning
cross-view consistent word learning
multi-level metric learning
ID-based cross-view multi-level dictionary learning
Multi-level metric learning
Local deep features
Person re-identification
Cross-view consistent word learning

Access to Document

10.1016/j.neucom.2021.01.010

NEUCOM-D-20-01462_Acceptedversion (1)Author Accepted Manuscript, 2.78 MBLicence: CC BY-NC-ND

https://linkinghub.elsevier.com/retrieve/pii/S0925231221000187

Cite this

@article{e9dd316fc9ad44d7a21ab87e8fc911ec,

title = "Multi-level cross-view consistent feature learning for person re-identification",

abstract = "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.",

keywords = "person re-identification, ocal deep features, ID-based crossview multi-level dictionary learning, cross-view consistent word learning, multi-level metric learning, ID-based cross-view multi-level dictionary learning, Multi-level metric learning, Local deep features, Person re-identification, Cross-view consistent word learning",

author = "Yixiu Liu and Yunzhou Zhang and Bir Bhanu and Sonya Coleman and Dermot Kerr",

note = "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: {\textcopyright} 2021 Elsevier B.V. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",

year = "2021",

month = may,

day = "7",

doi = "10.1016/j.neucom.2021.01.010",

language = "English",

volume = "435",

pages = "1--14",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier BV",

}

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 - 2021/5/7

Y1 - 2021/5/7

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 - https://www.scopus.com/pages/publications/85100437396

U2 - 10.1016/j.neucom.2021.01.010

DO - 10.1016/j.neucom.2021.01.010

M3 - Article

SN - 0925-2312

VL - 435

SP - 1

EP - 14

JO - Neurocomputing

JF - Neurocomputing

ER -

Multi-level cross-view consistent feature learning for person re-identification

Abstract

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this