Distributed Multi-Object Tracking under Limited Field of View Sensors

Distributed Multi-Object Tracking under Limited Field of View Sensors

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 th...

Full description

Bibliographic Details
Main Authors: Nguyen, Hoa, Rezatofighi, H., Vo, Ba-Ngu, Ranasinghe, D.C.
Format: Journal Article
Language:English
Published: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 2021
Subjects:
Science & Technology
Technology
Engineering, Electrical & Electronic
Engineering
Sensors
Signal processing algorithms
Sensor fusion
Trajectory
Bandwidth
Australia
Wireless sensor networks
Multi-sensor multi-object tracking
distributed multi-object tracking
label consistency
track consensus
MULTI-BERNOULLI FILTER
RANDOM FINITE SETS
EFFICIENT IMPLEMENTATION
DATA FUSION
ASSIGNMENT
ALGORITHMS
ARCHITECTURES
ASSOCIATION
CONSENSUS
AVERAGE
cs.MA
cs.RO
Online Access:http://dx.doi.org/10.1109/TSP.2021.3103125
http://hdl.handle.net/20.500.11937/91029
Description
Summary: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.

Similar Items