Multi-person vision tracking approach based on human body localization features

Ao-Lei Yang; Hai-Yan Ren; Min-Rui Fei; Wasif Naeem

doi:10.1007/s40436-021-00363-0

Advances in Manufacturing ›› 2021, Vol. 9 ›› Issue (4) : 496 -508. DOI: 10.1007/s40436-021-00363-0

Article

Multi-person vision tracking approach based on human body localization features

Author information +

¹ School of Mechatronic Engineering and Automation, Shanghai University, 200444, Shanghai, People’s Republic of China

² School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, BT7 1NN, Belfast, Northern Ireland, UK

^a ayang02@qub.ac.uk

Ao-Lei Yang received the B.Sc. degree from the Hubei University of Technology, Wuhan, China, in 2004, the M.Sc. degree from Shanghai University, Shanghai, China, in 2009, and Ph.D. degree from Queens University Belfast, Belfast, U.K., in 2012. He is currently an Associate Professor with the School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China. He is the author of over 50 peer-reviewed journal and conference papers. His current research interests include robotics, image processing and vision learning, and cooperative control of multi-agents.

[graphic not available: see fulltext]

Hai-Yan Ren received the B.Sc. degree from the Hanjng Institute of Technology, Nanjing, China, in 2017, and the M.Sc. degree from Shanghai University, Shanghai, China, in 2020. Her current research interests include image processing and machine learning image.

[graphic not available: see fulltext]

Min-Rui Fei received the B.Sc., M.Sc., and Ph.D. degrees from Shanghai University, Shanghai, China, in 1984, 1992, and 1997, respectively. He is a Professor with Shanghai University, where he is the Vice Chairman of Chinese Association for System Simulation, and the Standing Director of China Instrument and Control Society. His research interests include networked advanced control and system implementation, distributed and fieldbus control systems, key technology and applications in multi-fieldbus conversion and performance evaluation, as well as the application of virtual reality, and digital simulation in industry.

[graphic not available: see fulltext]

Wasif Naeem received the B.Eng. degree from NED University, Karachi, Pakistan, the M.Sc. degrees from King Fahd University, Dhahran, Saudi Arabia, in 1998 and 2001, respectively, both in electrical engineering, and the Ph.D. degree in mechanical and marine engineering from the University of Plymouth, Plymouth, U.K., in 2004. He is currently a Reader with the School of Electronics, Electrical Engineering, and Computer Science, Queens University Belfast, Belfast, U.K. He has authored over 80 peer-reviewed journal and conference papers and three IET book chapters. His current research interests include optimal and robust control, system identification, multivehicle formation control, and systems engineering.

[graphic not available: see fulltext]

Show less

History +

PDF

Abstract

This paper presents a multi-person vision tracking approach based on human body localization features to address the problem of interactive object localization and tracking in a home monitoring scenario. Firstly, the human body localization model is used to obtain the 3D position of the human body, which is then used to construct the human body motion model based on the Kalman filter method. At the same time, the human appearance model is constructed by fusing human color features and features of the histogram of oriented gradient to better characterize the human body. Secondly, the human body observation model is constructed based on the human body motion model and appearance model to measure the similarities between the human body state sequence in the historical frame and the human body observation result in the current frame, and the cost matrix is then obtained. Thirdly, the Hungarian maximum matching algorithm is employed to match each human body in the current and historical frames, and the exception detection mechanism is simultaneously constructed to further reduce the probability of human tracking and matching failure. Finally, a multi-person vision tracking verification platform was constructed, and the achieved average accuracy was 96.6% in the case of human body overlapping, occlusion, disappearance, and appearance; this verifies the feasibility and effectiveness of the proposed method.

Keywords

Multi-person vision tracking / Human body positioning / Motion model / Body observation model

Cite this article

Download citation ▾

Ao-Lei Yang,Hai-Yan Ren,Min-Rui Fei,Wasif Naeem. Multi-person vision tracking approach based on human body localization features. Advances in Manufacturing, 2021, 9(4): 496-508 DOI:10.1007/s40436-021-00363-0