Can I read Distributed Multi-object Tracking under Limited Field of View Sensors on EtoBox?

Distributed Multi-object Tracking under Limited Field of View Sensors by Van Nguyen, Hoa; Rezatofighi, Hamid; Vo, Ba-Ngu; Ranasinghe, Damith C. is a scholarly article available to read on EtoBox.

What is Distributed Multi-object Tracking under Limited Field of View Sensors about?

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 \textit{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 o

Author

Van Nguyen, Hoa; Rezatofighi, Hamid; Vo, Ba-Ngu; Ranasinghe, Damith C.

Published

2020

Language

EN