Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association

Recognising behaviours of multiple people, especially high-level behaviours, is an important task in surveillance systems. When the reliable assignment of people to the set of observations is unavailable, this task becomes complicated. To solve this task, we present an approach, in which the hierarc...

Full description

Bibliographic Details
Main Authors: Nguyen, Nam, Venkatesh, Svetha, Bui, H.H.
Other Authors: M. Chantler
Format: Conference Paper
Published: The British Machine Vision Association and Society for Pattern Recognition 2006
Online Access:http://www.macs.hw.ac.uk/bmvc2006/papers/190.pdf
http://hdl.handle.net/20.500.11937/15276
_version_ 1848748849781276672
author Nguyen, Nam
Venkatesh, Svetha
Bui, H.H.
author2 M. Chantler
author_facet M. Chantler
Nguyen, Nam
Venkatesh, Svetha
Bui, H.H.
author_sort Nguyen, Nam
building Curtin Institutional Repository
collection Online Access
description Recognising behaviours of multiple people, especially high-level behaviours, is an important task in surveillance systems. When the reliable assignment of people to the set of observations is unavailable, this task becomes complicated. To solve this task, we present an approach, in which the hierarchical hidden Markov model (HHMM) is used for modeling the behaviour of each person and the joint probabilistic data association filters (JPD AF) is applied for data association. The main contributions of this paper lie in the integration of multiple HHMMs for recognising high-le v el behaviours of multiple people and the construction of the Rao-Blackwellised particle filters (RBPF) for approximate inference. Preliminary experimental results in a real environment show the robustness of our integrated method in behaviour recognition and its advantage over the use of Kalman filter in tracking people.
first_indexed 2025-11-14T07:11:35Z
format Conference Paper
id curtin-20.500.11937-15276
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:11:35Z
publishDate 2006
publisher The British Machine Vision Association and Society for Pattern Recognition
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-152762022-10-20T07:26:56Z Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association Nguyen, Nam Venkatesh, Svetha Bui, H.H. M. Chantler R. Fisher E. Trucco Recognising behaviours of multiple people, especially high-level behaviours, is an important task in surveillance systems. When the reliable assignment of people to the set of observations is unavailable, this task becomes complicated. To solve this task, we present an approach, in which the hierarchical hidden Markov model (HHMM) is used for modeling the behaviour of each person and the joint probabilistic data association filters (JPD AF) is applied for data association. The main contributions of this paper lie in the integration of multiple HHMMs for recognising high-le v el behaviours of multiple people and the construction of the Rao-Blackwellised particle filters (RBPF) for approximate inference. Preliminary experimental results in a real environment show the robustness of our integrated method in behaviour recognition and its advantage over the use of Kalman filter in tracking people. 2006 Conference Paper http://hdl.handle.net/20.500.11937/15276 http://www.macs.hw.ac.uk/bmvc2006/papers/190.pdf The British Machine Vision Association and Society for Pattern Recognition restricted
spellingShingle Nguyen, Nam
Venkatesh, Svetha
Bui, H.H.
Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title_full Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title_fullStr Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title_full_unstemmed Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title_short Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
title_sort recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association
url http://www.macs.hw.ac.uk/bmvc2006/papers/190.pdf
http://hdl.handle.net/20.500.11937/15276