Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach

The dissertation proposes an online solution for separating an unknown and time-varying number of moving sources using audio and visual data. The random finite set framework is used for the modeling and fusion of audio and visual data. This enables an online tracking algorithm to estimate the source...

Full description

Bibliographic Details
Main Author: Ong, Jonah Soon Xuan
Format: Thesis
Published: Curtin University 2021
Online Access:http://hdl.handle.net/20.500.11937/89300
_version_ 1848765199281029120
author Ong, Jonah Soon Xuan
author_facet Ong, Jonah Soon Xuan
author_sort Ong, Jonah Soon Xuan
building Curtin Institutional Repository
collection Online Access
description The dissertation proposes an online solution for separating an unknown and time-varying number of moving sources using audio and visual data. The random finite set framework is used for the modeling and fusion of audio and visual data. This enables an online tracking algorithm to estimate the source positions and identities for each time point. With this information, a set of beamformers can be designed to separate each desired source and suppress the interfering sources.
first_indexed 2025-11-14T11:31:27Z
format Thesis
id curtin-20.500.11937-89300
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:31:27Z
publishDate 2021
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-893002022-09-09T03:50:28Z Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach Ong, Jonah Soon Xuan The dissertation proposes an online solution for separating an unknown and time-varying number of moving sources using audio and visual data. The random finite set framework is used for the modeling and fusion of audio and visual data. This enables an online tracking algorithm to estimate the source positions and identities for each time point. With this information, a set of beamformers can be designed to separate each desired source and suppress the interfering sources. 2021 Thesis http://hdl.handle.net/20.500.11937/89300 Curtin University fulltext
spellingShingle Ong, Jonah Soon Xuan
Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title_full Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title_fullStr Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title_full_unstemmed Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title_short Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
title_sort online audio-visual multi-source tracking and separation: a labeled random finite set approach
url http://hdl.handle.net/20.500.11937/89300