A Solution for Large-Scale Multi-Object Tracking

A large-scale multi-object tracker based on the generalised labeled multi-Bernoulli (GLMB) filter is proposed. The algorithm is capable of tracking a very large, unknown and time-varying number of objects simultaneously, in the presence of a high number of false alarms, as well as missed detections...

Full description

Bibliographic Details
Main Authors: Beard, Michael, Vo, Ba Tuong, Vo, Ba-Ngu
Format: Journal Article
Language:English
Published: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC 2020
Subjects:
Online Access:http://purl.org/au-research/grants/arc/DP160104662
http://hdl.handle.net/20.500.11937/90795
_version_ 1848765430452191232
author Beard, Michael
Vo, Ba Tuong
Vo, Ba-Ngu
author_facet Beard, Michael
Vo, Ba Tuong
Vo, Ba-Ngu
author_sort Beard, Michael
building Curtin Institutional Repository
collection Online Access
description A large-scale multi-object tracker based on the generalised labeled multi-Bernoulli (GLMB) filter is proposed. The algorithm is capable of tracking a very large, unknown and time-varying number of objects simultaneously, in the presence of a high number of false alarms, as well as missed detections and measurement origin uncertainty due to closely spaced objects. The algorithm is demonstrated on a simulated tracking scenario, where the peak number objects appearing simultaneously exceeds one million. Additionally, we introduce a new method of applying the optimal sub-pattern assignment (OSPA) metric to determine a meaningful distance between two sets of tracks. We also develop an efficient strategy for its exact computation in large-scale scenarios to evaluate the performance of the proposed tracker.
first_indexed 2025-11-14T11:35:08Z
format Journal Article
id curtin-20.500.11937-90795
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:35:08Z
publishDate 2020
publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-907952023-04-20T06:52:55Z A Solution for Large-Scale Multi-Object Tracking Beard, Michael Vo, Ba Tuong Vo, Ba-Ngu Science & Technology Technology Engineering, Electrical & Electronic Engineering Radio frequency Target tracking Signal processing algorithms Approximation algorithms Trajectory Random finite sets generalised labeled multi-Bernoulli multi-object tracking large-scale tracking OSPA RANDOM FINITE SETS MULTITARGET TRACKING PERFORMANCE EVALUATION DISTRIBUTED FUSION BERNOULLI FILTER ALGORITHMS A large-scale multi-object tracker based on the generalised labeled multi-Bernoulli (GLMB) filter is proposed. The algorithm is capable of tracking a very large, unknown and time-varying number of objects simultaneously, in the presence of a high number of false alarms, as well as missed detections and measurement origin uncertainty due to closely spaced objects. The algorithm is demonstrated on a simulated tracking scenario, where the peak number objects appearing simultaneously exceeds one million. Additionally, we introduce a new method of applying the optimal sub-pattern assignment (OSPA) metric to determine a meaningful distance between two sets of tracks. We also develop an efficient strategy for its exact computation in large-scale scenarios to evaluate the performance of the proposed tracker. 2020 Journal Article http://hdl.handle.net/20.500.11937/90795 10.1109/TSP.2020.2986136 English http://purl.org/au-research/grants/arc/DP160104662 http://creativecommons.org/licenses/by/4.0/ IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC fulltext
spellingShingle Science & Technology
Technology
Engineering, Electrical & Electronic
Engineering
Radio frequency
Target tracking
Signal processing algorithms
Approximation algorithms
Trajectory
Random finite sets
generalised labeled multi-Bernoulli
multi-object tracking
large-scale tracking
OSPA
RANDOM FINITE SETS
MULTITARGET TRACKING
PERFORMANCE EVALUATION
DISTRIBUTED FUSION
BERNOULLI FILTER
ALGORITHMS
Beard, Michael
Vo, Ba Tuong
Vo, Ba-Ngu
A Solution for Large-Scale Multi-Object Tracking
title A Solution for Large-Scale Multi-Object Tracking
title_full A Solution for Large-Scale Multi-Object Tracking
title_fullStr A Solution for Large-Scale Multi-Object Tracking
title_full_unstemmed A Solution for Large-Scale Multi-Object Tracking
title_short A Solution for Large-Scale Multi-Object Tracking
title_sort solution for large-scale multi-object tracking
topic Science & Technology
Technology
Engineering, Electrical & Electronic
Engineering
Radio frequency
Target tracking
Signal processing algorithms
Approximation algorithms
Trajectory
Random finite sets
generalised labeled multi-Bernoulli
multi-object tracking
large-scale tracking
OSPA
RANDOM FINITE SETS
MULTITARGET TRACKING
PERFORMANCE EVALUATION
DISTRIBUTED FUSION
BERNOULLI FILTER
ALGORITHMS
url http://purl.org/au-research/grants/arc/DP160104662
http://hdl.handle.net/20.500.11937/90795