Multi-object particle filter revisited

Instead of the filtering density, we are interested in the entire posterior density that describes the random set of object trajectories. So far only Markov Chain Monte Carlo (MCMC) technique have been proposed to approximate the posterior distribution of the set of trajectories. Using labeled rando...

Full description

Bibliographic Details
Main Authors: Kim, Du Yong, Vo, Ba Tuong, Vo, Ba-Ngu
Format: Conference Paper
Published: 2017
Online Access:http://hdl.handle.net/20.500.11937/50663
_version_ 1848758515095568384
author Kim, Du Yong
Vo, Ba Tuong
Vo, Ba-Ngu
author_facet Kim, Du Yong
Vo, Ba Tuong
Vo, Ba-Ngu
author_sort Kim, Du Yong
building Curtin Institutional Repository
collection Online Access
description Instead of the filtering density, we are interested in the entire posterior density that describes the random set of object trajectories. So far only Markov Chain Monte Carlo (MCMC) technique have been proposed to approximate the posterior distribution of the set of trajectories. Using labeled random finite set we show how the classical multi-object particle filter (a direct generalisation of the standard particle filter to the multi-object case) can be used to recursively compute posterior distribution of the set of trajectories. The result is a generic Bayesian multi-object tracker that does not require re-computing the posterior at every time step nor running a long Markov chain, and is much more efficient than the MCMC approximations.
first_indexed 2025-11-14T09:45:13Z
format Conference Paper
id curtin-20.500.11937-50663
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:45:13Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-506632017-09-13T15:37:03Z Multi-object particle filter revisited Kim, Du Yong Vo, Ba Tuong Vo, Ba-Ngu Instead of the filtering density, we are interested in the entire posterior density that describes the random set of object trajectories. So far only Markov Chain Monte Carlo (MCMC) technique have been proposed to approximate the posterior distribution of the set of trajectories. Using labeled random finite set we show how the classical multi-object particle filter (a direct generalisation of the standard particle filter to the multi-object case) can be used to recursively compute posterior distribution of the set of trajectories. The result is a generic Bayesian multi-object tracker that does not require re-computing the posterior at every time step nor running a long Markov chain, and is much more efficient than the MCMC approximations. 2017 Conference Paper http://hdl.handle.net/20.500.11937/50663 10.1109/ICCAIS.2016.7822433 restricted
spellingShingle Kim, Du Yong
Vo, Ba Tuong
Vo, Ba-Ngu
Multi-object particle filter revisited
title Multi-object particle filter revisited
title_full Multi-object particle filter revisited
title_fullStr Multi-object particle filter revisited
title_full_unstemmed Multi-object particle filter revisited
title_short Multi-object particle filter revisited
title_sort multi-object particle filter revisited
url http://hdl.handle.net/20.500.11937/50663