A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition

There is growing interest in the problem of human activity recognition, motivated by its countless promising applications in many domains. Despite much progress, most researchers have narrowed the problem towards fixed camera viewpoint owing to inherent difficulty to train their systems across all p...

Full description

Bibliographic Details
Main Authors:	Htike@Muhammad Yusof, Zaw Zaw, Egerton, Simon, Kuang, Ye Chow
Format:	Article
Language:	English English
Published:	Australian National University 2010
Subjects:	AI Indexes (General)
Online Access:	http://irep.iium.edu.my/43205/ http://irep.iium.edu.my/43205/ http://irep.iium.edu.my/43205/1/ICONIP.pdf http://irep.iium.edu.my/43205/2/ICONIP_evidence.pdf

id	iium-43205
recordtype	eprints
spelling	iium-432052015-06-05T03:58:52Z http://irep.iium.edu.my/43205/ A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow AI Indexes (General) There is growing interest in the problem of human activity recognition, motivated by its countless promising applications in many domains. Despite much progress, most researchers have narrowed the problem towards fixed camera viewpoint owing to inherent difficulty to train their systems across all possible viewpoints. Fixed viewpoint systems are impractical in real scenarios. Therefore, we attempt to relax the infamous fixed viewpoint assumption and present a novel, efficient and biologically-inspired framework to recognize and classify human activities from monocular video source from arbitrary viewpoint. The proposed framework comprises two stages: human pose recognition and human activity recognition. We cascade an ensemble of invariant pose models and activity models hierarchically. All the models operate simultaneously in parallel and perform inference on impinging patterns that come from lower level. Pose models operate in a hybrid 3-layered bottom-up neural architecture. Activity models employ fuzzy-state hidden Markov model to classify activities. We have built a small-scale architecture for a proof-of-concept and performed some experiments on two publicly available datasets. The satisfactory experimental results demonstrate the efficacy of our framework and encourage us to further develop a full-scale architecture. Australian National University 2010 Article PeerReviewed application/pdf en http://irep.iium.edu.my/43205/1/ICONIP.pdf application/pdf en http://irep.iium.edu.my/43205/2/ICONIP_evidence.pdf Htike@Muhammad Yusof, Zaw Zaw and Egerton, Simon and Kuang, Ye Chow (2010) A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition. Australian Journal of Intelligent Information Processing Systems, 12 (3). pp. 31-37. ISSN 1321-2133 http://dblp.l3s.de/?q=Austr.+J.+Intelligent+Information+Processing+Systems&search_opt=venuesOnlyExact&newQuery=yes&resTableName=query_resultZOF8Ko&resultsPerPage=100
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	AI Indexes (General)
spellingShingle	AI Indexes (General) Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
description	There is growing interest in the problem of human activity recognition, motivated by its countless promising applications in many domains. Despite much progress, most researchers have narrowed the problem towards fixed camera viewpoint owing to inherent difficulty to train their systems across all possible viewpoints. Fixed viewpoint systems are impractical in real scenarios. Therefore, we attempt to relax the infamous fixed viewpoint assumption and present a novel, efficient and biologically-inspired framework to recognize and classify human activities from monocular video source from arbitrary viewpoint. The proposed framework comprises two stages: human pose recognition and human activity recognition. We cascade an ensemble of invariant pose models and activity models hierarchically. All the models operate simultaneously in parallel and perform inference on impinging patterns that come from lower level. Pose models operate in a hybrid 3-layered bottom-up neural architecture. Activity models employ fuzzy-state hidden Markov model to classify activities. We have built a small-scale architecture for a proof-of-concept and performed some experiments on two publicly available datasets. The satisfactory experimental results demonstrate the efficacy of our framework and encourage us to further develop a full-scale architecture.
format	Article
author	Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow
author_facet	Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow
author_sort	Htike@Muhammad Yusof, Zaw Zaw
title	A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
title_short	A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
title_full	A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
title_fullStr	A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
title_full_unstemmed	A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition
title_sort	hybrid art-rbf network architecture for viewpoint invariant human activity recognition
publisher	Australian National University
publishDate	2010
url	http://irep.iium.edu.my/43205/ http://irep.iium.edu.my/43205/ http://irep.iium.edu.my/43205/1/ICONIP.pdf http://irep.iium.edu.my/43205/2/ICONIP_evidence.pdf
first_indexed	2023-09-18T21:01:34Z
last_indexed	2023-09-18T21:01:34Z
_version_	1777410658650816512

A hybrid ART-RBF Network Architecture for Viewpoint Invariant Human Activity Recognition

Similar Items