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:
Online Access:http://dx.doi.org/10.1109/TSP.2021.3103125
http://hdl.handle.net/20.500.11937/91029
_version_ 1848765488376578048
author Nguyen, Hoa
Rezatofighi, H.
Vo, Ba-Ngu
Ranasinghe, D.C.
author_facet Nguyen, Hoa
Rezatofighi, H.
Vo, Ba-Ngu
Ranasinghe, D.C.
author_sort Nguyen, Hoa
building Curtin Institutional Repository
collection Online Access
description 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.
first_indexed 2025-11-14T11:36:03Z
format Journal Article
id curtin-20.500.11937-91029
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:36:03Z
publishDate 2021
publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-910292023-05-22T08:05:14Z Distributed Multi-Object Tracking under Limited Field of View Sensors Nguyen, Hoa Rezatofighi, H. Vo, Ba-Ngu Ranasinghe, D.C. 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.MA cs.RO 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. 2021 Journal Article http://hdl.handle.net/20.500.11937/91029 10.1109/TSP.2021.3103125 English http://dx.doi.org/10.1109/TSP.2021.3103125 http://purl.org/au-research/grants/arc/DP160104662 IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC fulltext
spellingShingle 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.MA
cs.RO
Nguyen, Hoa
Rezatofighi, H.
Vo, Ba-Ngu
Ranasinghe, D.C.
Distributed Multi-Object Tracking under Limited Field of View Sensors
title Distributed Multi-Object Tracking under Limited Field of View Sensors
title_full Distributed Multi-Object Tracking under Limited Field of View Sensors
title_fullStr Distributed Multi-Object Tracking under Limited Field of View Sensors
title_full_unstemmed Distributed Multi-Object Tracking under Limited Field of View Sensors
title_short Distributed Multi-Object Tracking under Limited Field of View Sensors
title_sort distributed multi-object tracking under limited field of view sensors
topic 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.MA
cs.RO
url http://dx.doi.org/10.1109/TSP.2021.3103125
http://dx.doi.org/10.1109/TSP.2021.3103125
http://hdl.handle.net/20.500.11937/91029