A random finite set conjugate prior and application to multi-target tracking

The objective of multi-object estimation is to simultaneously estimate the number of objects and their states from a set of observations in the presence of data association uncertainty, detection uncertainty, false observations and noise. This estimation problem can be formulated in a Bayesian frame...

Full description

Bibliographic Details
Main Authors: Vo, Ba Tuong, Vo, Ba-Ngu
Format: Conference Paper
Published: 2011
Online Access:http://hdl.handle.net/20.500.11937/55176
_version_ 1848759554594045952
author Vo, Ba Tuong
Vo, Ba-Ngu
author_facet Vo, Ba Tuong
Vo, Ba-Ngu
author_sort Vo, Ba Tuong
building Curtin Institutional Repository
collection Online Access
description The objective of multi-object estimation is to simultaneously estimate the number of objects and their states from a set of observations in the presence of data association uncertainty, detection uncertainty, false observations and noise. This estimation problem can be formulated in a Bayesian framework by modeling the (hidden) set of states and set of observations as random finite sets (RFSs) where the model for the observation covers thinning, Markov shifts and superposition of false observations. A prior for the hidden RFS together with the likelihood of the realisation of the observed RFS gives the posterior distribution via the application of Bayes rule. We propose a new class of prior distribution and show that it is a conjugate prior with respect to the multi-target observation likelihood. This result is then applied to develop an analytic implementation of the Bayes multi-target filter for the class of linear Gaussian multi-target models. © 2011 IEEE.
first_indexed 2025-11-14T10:01:44Z
format Conference Paper
id curtin-20.500.11937-55176
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:01:44Z
publishDate 2011
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-551762017-09-13T16:09:54Z A random finite set conjugate prior and application to multi-target tracking Vo, Ba Tuong Vo, Ba-Ngu The objective of multi-object estimation is to simultaneously estimate the number of objects and their states from a set of observations in the presence of data association uncertainty, detection uncertainty, false observations and noise. This estimation problem can be formulated in a Bayesian framework by modeling the (hidden) set of states and set of observations as random finite sets (RFSs) where the model for the observation covers thinning, Markov shifts and superposition of false observations. A prior for the hidden RFS together with the likelihood of the realisation of the observed RFS gives the posterior distribution via the application of Bayes rule. We propose a new class of prior distribution and show that it is a conjugate prior with respect to the multi-target observation likelihood. This result is then applied to develop an analytic implementation of the Bayes multi-target filter for the class of linear Gaussian multi-target models. © 2011 IEEE. 2011 Conference Paper http://hdl.handle.net/20.500.11937/55176 10.1109/ISSNIP.2011.6146549 restricted
spellingShingle Vo, Ba Tuong
Vo, Ba-Ngu
A random finite set conjugate prior and application to multi-target tracking
title A random finite set conjugate prior and application to multi-target tracking
title_full A random finite set conjugate prior and application to multi-target tracking
title_fullStr A random finite set conjugate prior and application to multi-target tracking
title_full_unstemmed A random finite set conjugate prior and application to multi-target tracking
title_short A random finite set conjugate prior and application to multi-target tracking
title_sort random finite set conjugate prior and application to multi-target tracking
url http://hdl.handle.net/20.500.11937/55176