Behaviour recognition of ground vehicle using airborne monitoring of unmanned aerial vehicles

Abstract

This paper proposes a behaviour recognition methodology for ground vehicles moving within road traffic using unmanned aerial vehicles in order to identify suspicious or abnormal behaviour. With the target information acquired by unmanned aerial vehicles and estimated by filtering techniques, ground vehicle behaviour is first classified into representative driving modes, and then a string pattern matching theory is applied to detect suspicious behaviours in the driving mode history. Furthermore, a fuzzy decision-making process is developed to systematically exploit all available information obtained from a complex environment and confirm the characteristic of behaviour, while considering spatiotemporal environment factors as well as several aspects of behaviours. To verify the feasibility and benefits of the proposed approach, numerical simulations on moving ground vehicles are performed using realistic car trajectory data from an off-the-shelf traffic simulation software.

Keywords:

• behaviour recognition
• unmanned aerial vehicles
• trajectory classification
• tracking filter
• string matching
• decision-making

Additional information

Notes on contributors

Hyondong Oh

Hyondong Oh received the BSc and MSc degrees in Aerospace Engineering from KAIST, South Korea, in 2004 and 2010, respectively. He is currently pursuing his PhD degree in the Department of Engineering Physics, School of Engineering, Cranfield University, UK. His research interests include cooperative control and path planning of autonomous systems, target surveillance and tracking guidance and information/sensor fusion.

Seungkeun Kim

Seungkeun Kim received a BSc degree in Mechanical and Aerospace Engineering from Seoul National University, Seoul, Korea, in 2002 and then acquired a PhD on Three-dimensional Optimum Controller Design for UAV Formation Flight Using Behavioural Decentralized Approach from Seoul National University in 2008. He is currently an assistant professor at the Dept of Aerospace Engineering, Chungnam National University, Daejeon, Korea. Previously he was a lecturer in Cooperative Control and Estimation at Autonomous Systems Group in Cranfield University, UK between Dec 2010 and Feb 2012 and also worked as a Research Fellow at Cranfield University between Apr 2008 and Dec 2010. He has actively published book chapters, journal and conference papers related to unmanned systems. He was also awarded Postdoctorates and Research Fellows Program from Korea Research Foundation in 2008. His research interests cover nonlinear guidance and control, estimation, sensor and information fusion, fault diagnosis, fault tolerant control and decision-making for unmanned systems.

Hyo-Sang Shin

Hyo-Sang Shin received his BSc from Pusan National University and gained an MSc on flight dynamics, guidance and control in Aerospace Engineering from KAIST and a PhD on cooperative missile guidance from Cranfield University. He is currently Lecturer on Guidance, Control and Navigation Systems in Autonomous and Intelligent Systems Group at Cranfield University. He has actively published book chapters, journal and conference papers and has been invited for many lectures in Universities, industries and research institutes. His current research interests include cooperative guidance and control for multiple vehicles, coordinated health monitoring and management and information-driven sensing.

Antonios Tsourdos

Antonios Tsourdos obtained an MEng on Electronic, Control and Systems Engineering from the University of Sheffield (1995), an MSc on Systems Engineering from Cardiff University (1996) and a PhD on Nonlinear Robust Missile Autopilot Design and Analysis from Cranfield University (1999). He is a Professor of Control Engineering with Cranfield University. He was appointed Head of the Autonomous Systems Group in 2007. Professor Tsourdos was member of the Team Stellar, the winning team for the UK MoD Grand Challenge (2008) and the IET Innovation Award (Category Team, 2009).

Brian A. White

Brian A. White received the BScEng degree from the University of Leicester, Leicester, UK, in 1967 and the MSc degree in automatic control and the PhD degree in bond graph modelling from the University of Manchester Institute of Science and Technology, Manchester, UK, in 1971 and 1973, respectively. He is a Professor Emeritus with Cranfield University, Cranfield, UK. He is with the Autonomous Systems Group, Cranfield Defence and Security, Cranfield University, Defence Academy of the United Kingdom, Swindon, UK. His research interests include robust control, nonlinear control, estimation, observer applications, inertial navigation, guidance design, soft computing and sensor and data fusion.