Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter

A new method is presented for integration of audio and visual information in multiple target tracking applications. The proposed approach uses a Bayesian filtering formulation and exploits multi-Bernoulli random finite set approximations. The work presented in this paper is the first principled Baye...

Full description

Bibliographic Details
Main Authors: Hoseinnezhad, R., Vo, Ba-Ngu, Vo, Ba Tuong, Suter, D.
Format: Conference Paper
Published: 2011
Online Access:http://hdl.handle.net/20.500.11937/55473
_version_ 1848759630919892992
author Hoseinnezhad, R.
Vo, Ba-Ngu
Vo, Ba Tuong
Suter, D.
author_facet Hoseinnezhad, R.
Vo, Ba-Ngu
Vo, Ba Tuong
Suter, D.
author_sort Hoseinnezhad, R.
building Curtin Institutional Repository
collection Online Access
description A new method is presented for integration of audio and visual information in multiple target tracking applications. The proposed approach uses a Bayesian filtering formulation and exploits multi-Bernoulli random finite set approximations. The work presented in this paper is the first principled Bayesian estimation approach to solve the sensor fusion problems that involve intermittent sensory data (e.g. audio data for a person who occasionally speaks.) We have examined our method with case studies from the SPEVI database. The results show nearly perfect tracking of people not only when they are silent but also when they are not visible to the camera (but speaking). © 2011 IEEE.
first_indexed 2025-11-14T10:02:57Z
format Conference Paper
id curtin-20.500.11937-55473
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:02:57Z
publishDate 2011
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-554732018-03-29T09:09:26Z Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter Hoseinnezhad, R. Vo, Ba-Ngu Vo, Ba Tuong Suter, D. A new method is presented for integration of audio and visual information in multiple target tracking applications. The proposed approach uses a Bayesian filtering formulation and exploits multi-Bernoulli random finite set approximations. The work presented in this paper is the first principled Bayesian estimation approach to solve the sensor fusion problems that involve intermittent sensory data (e.g. audio data for a person who occasionally speaks.) We have examined our method with case studies from the SPEVI database. The results show nearly perfect tracking of people not only when they are silent but also when they are not visible to the camera (but speaking). © 2011 IEEE. 2011 Conference Paper http://hdl.handle.net/20.500.11937/55473 10.1109/ICASSP.2011.5946942 restricted
spellingShingle Hoseinnezhad, R.
Vo, Ba-Ngu
Vo, Ba Tuong
Suter, D.
Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title_full Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title_fullStr Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title_full_unstemmed Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title_short Bayesian integration of audio and visual information for multi-target tracking using a CB-member filter
title_sort bayesian integration of audio and visual information for multi-target tracking using a cb-member filter
url http://hdl.handle.net/20.500.11937/55473