IEEE SA C&SP Tech Talk Series on Sensor Fusion and Tracking - Talk 1: Distributed Multi-Object Tracking Under Limited Field of View Sensors

#IEEE #tech #talk #series #sensor #fusion #and #tracking

Dear IEEE members and guests,

The IEEE South Australia Communications & Signal Processing (C&SP) chapter is pleased to announce a new tech talk series on sensor fusion and tracking.

The first talk in the series is scheduled on Oct 13, 2021 07:30 PM. The speaker is Dr. Hoa Van Nguyen from the University of Adelaide and he will be presenting a seminar on multi-object tracking. Please find below the seminar details.

Location: Virtual via the following meeting link

https://unisa.zoom.us/j/83751211051?pwd=bkNHcFRWM1VXT1NpV3lhN3pDbWMrQT09

Password (if get asked): Adelaide

Time/Date: Wednesday, 13 October 2021 - 07:30 PM (Adelaide time)

Talk Title:  Distributed Multi-Object Tracking Under Limited Field of View Sensors

Abstract: We consider the challenging problem of tracking multiple objects using a distributed network of sensors. In the practical setting of nodes with limited field of views (FoVs), computing power and communication resources, we develop a novel distributed multi-object tracking algorithm. To accomplish this, we first formalise the concept of label consistency, determine a sufficient condition to achieve it and develop a novel label consensus approach that reduces label inconsistency caused by objects' movements from one node's limited FoV to another. Second, we develop a distributed multi-object fusion algorithm that fuses local multi-object state estimates instead of local multi-object densities. This algorithm: i) requires significantly less processing time than multi-object density fusion methods; ii) achieves better tracking accuracy by considering Optimal Sub-Pattern Assignment (OSPA) tracking errors over several scans rather than a single scan; iii) is agnostic to local multi-object tracking techniques, and only requires each node to provide a set of estimated tracks. Thus, it is not necessary to assume that the nodes maintain multi-object densities, and hence the fusion outcomes do not modify local multi-object densities. Numerical experiments demonstrate our proposed solution's real-time computational efficiency and accuracy compared to state-of-the-art solutions in challenging scenarios. We also release source code at https://github.com/AdelaideAuto-IDLab/Distributed-limitedFoV-MOT for our fusion method to foster developments in DMOT algorithms.

Speaker Bio: Hoa Van Nguyen received his Bachelor degree in Electrical Engineering from Portland State University, Oregon, the USA in June 2012, and a PhD degree in computer science from The University of Adelaide, in July 2020. He is currently a Post-Doctoral Research Fellow with the School of Computer Science, The University of Adelaide. His research interests include signal processing, robotics, multi-object tracking and multi-sensor control.

If you have any problems with accessing the seminar, please contact ngoc.nguyen@mymail.unisa.edu.au.

Kind Regards,

Ngoc Hung Nguyen, PhD

IEEE SA C&SP Chapter Chair