Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking

Multi-target tracking has been studied for many years, yet it remains a challenging problem, particularly in terms of implementing data association when tracking targets over several time steps. To achieve robustness, probabilistic approaches have been proposed, including Bayesian multi-target track...

Full description

Bibliographic Details
Main Authors: Shun Taguchi, Kiyosumi Kidono
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9234514/
id doaj-9913e86b33514c1a8a9c2a9fa7d0fd1a
record_format Article
spelling doaj-9913e86b33514c1a8a9c2a9fa7d0fd1a2021-03-30T04:08:12ZengIEEEIEEE Access2169-35362020-01-01819311619312710.1109/ACCESS.2020.30326929234514Exclusive Association Sampling to Improve Bayesian Multi-Target TrackingShun Taguchi0https://orcid.org/0000-0002-1612-6121Kiyosumi Kidono1Toyota Central R&D Labs., Inc., Nagakute, JapanToyota Central R&D Labs., Inc., Nagakute, JapanMulti-target tracking has been studied for many years, yet it remains a challenging problem, particularly in terms of implementing data association when tracking targets over several time steps. To achieve robustness, probabilistic approaches have been proposed, including Bayesian multi-target tracking methods. However, these approaches involve high calculation costs, which are incompatible with real-time applications. We propose exclusive association sampling (EAS) to improve the efficiency of Bayesian multi-target tracking methods. Although EAS is a simple procedure composed of random sorting and sampling based on the observation probability, it can be employed to increase the efficiency of association candidate generation and the calculation of statistical values. In this study, we proposed two Bayesian multi-target tracking methods based on EAS: stochastic joint probabilistic data association (SJPDA) and Rao-Blackwellized particle filter with EAS (RBPF with EAS). Evaluation of these methods with simulated data shows that integrating EAS into these methods can enhance their speed and accuracy. Moreover, evaluation on open datasets used for pedestrian tracking on camera sequences shows that the proposed methods achieve significantly better performance on some important metrics compared with representative methods.https://ieeexplore.ieee.org/document/9234514/Multi-target trackingjoint probabilistic data associationRao-Blackwellized particle filter
collection DOAJ
language English
format Article
sources DOAJ
author Shun Taguchi
Kiyosumi Kidono
spellingShingle Shun Taguchi
Kiyosumi Kidono
Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
IEEE Access
Multi-target tracking
joint probabilistic data association
Rao-Blackwellized particle filter
author_facet Shun Taguchi
Kiyosumi Kidono
author_sort Shun Taguchi
title Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
title_short Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
title_full Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
title_fullStr Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
title_full_unstemmed Exclusive Association Sampling to Improve Bayesian Multi-Target Tracking
title_sort exclusive association sampling to improve bayesian multi-target tracking
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description Multi-target tracking has been studied for many years, yet it remains a challenging problem, particularly in terms of implementing data association when tracking targets over several time steps. To achieve robustness, probabilistic approaches have been proposed, including Bayesian multi-target tracking methods. However, these approaches involve high calculation costs, which are incompatible with real-time applications. We propose exclusive association sampling (EAS) to improve the efficiency of Bayesian multi-target tracking methods. Although EAS is a simple procedure composed of random sorting and sampling based on the observation probability, it can be employed to increase the efficiency of association candidate generation and the calculation of statistical values. In this study, we proposed two Bayesian multi-target tracking methods based on EAS: stochastic joint probabilistic data association (SJPDA) and Rao-Blackwellized particle filter with EAS (RBPF with EAS). Evaluation of these methods with simulated data shows that integrating EAS into these methods can enhance their speed and accuracy. Moreover, evaluation on open datasets used for pedestrian tracking on camera sequences shows that the proposed methods achieve significantly better performance on some important metrics compared with representative methods.
topic Multi-target tracking
joint probabilistic data association
Rao-Blackwellized particle filter
url https://ieeexplore.ieee.org/document/9234514/
work_keys_str_mv AT shuntaguchi exclusiveassociationsamplingtoimprovebayesianmultitargettracking
AT kiyosumikidono exclusiveassociationsamplingtoimprovebayesianmultitargettracking
_version_ 1724182325117321216