Model-free viewpoint invariant human activity recognition

The viewpoint assumption is becoming an obstacle in human activity recognition systems. There is increasing interest in the problem of human activity recognition, motivated by promising applications in many domains. Since camera position is arbitrary in many domains, human activity recognition syste...

Full description

Bibliographic Details
Main Authors:	Htike@Muhammad Yusof, Zaw Zaw, Egerton, Simon, Kuang, Ye Chow
Format:	Conference or Workshop Item
Language:	English
Published:	2011
Subjects:	AI Indexes (General)
Online Access:	http://irep.iium.edu.my/43204/ http://irep.iium.edu.my/43204/ http://irep.iium.edu.my/43204/1/IMECS_2011.pdf

id	iium-43204
recordtype	eprints
spelling	iium-432042015-06-05T03:14:12Z http://irep.iium.edu.my/43204/ Model-free viewpoint invariant human activity recognition Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow AI Indexes (General) The viewpoint assumption is becoming an obstacle in human activity recognition systems. There is increasing interest in the problem of human activity recognition, motivated by promising applications in many domains. Since camera position is arbitrary in many domains, human activity recognition systems have to be viewpoint invariant. The viewpoint invariance aspect has been ignored by a vast majority of computer vision researchers owing to inherent difficulty to train systems to recognize activities across all possible viewpoints. Fixed viewpoint systems are impractical in real scenarios. Therefore, we attempt to relax the infamous fixed viewpoint assumption by presenting a framework to recognize human activities from monocular video source from arbitrary viewpoint. The proposed system makes use of invariant human pose recognition. An ensemble of pose models performs inference on each video frame. Each pose model employs an expectation-maximization algorithm to estimate the probability that the given frame contains the corresponding pose. Over a sequence of frames, all the pose models collectively produce a multivariate time series. In the activity recognition stage, we use nearest neighbor, with dynamic time warping as a distance measure, to classify pose time series. We have performed some experiments on a publicly available dataset and the results are found to be promising 2011 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/43204/1/IMECS_2011.pdf Htike@Muhammad Yusof, Zaw Zaw and Egerton, Simon and Kuang, Ye Chow (2011) Model-free viewpoint invariant human activity recognition. In: International MultiConference of Engineers and Computer Scientists 2011 (IMECS 2011), , 16-18 March 2011, Hong Kong. http://www.iaeng.org/publication/IMECS2011/IMECS2011_pp154-158.pdf
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English
topic	AI Indexes (General)
spellingShingle	AI Indexes (General) Htike@Muhammad Yusof, Zaw Zaw Egerton, Simon Kuang, Ye Chow Model-free viewpoint invariant human activity recognition
description	The viewpoint assumption is becoming an obstacle in human activity recognition systems. There is increasing interest in the problem of human activity recognition, motivated by promising applications in many domains. Since camera position is arbitrary in many domains, human activity recognition systems have to be viewpoint invariant. The viewpoint invariance aspect has been ignored by a vast majority of computer vision researchers owing to inherent difficulty to train systems to recognize activities across all possible viewpoints. Fixed viewpoint systems are impractical in real scenarios. Therefore, we attempt to relax the infamous fixed viewpoint assumption by presenting a framework to recognize human activities from monocular video source from arbitrary viewpoint. The proposed system makes use of invariant human pose recognition. An ensemble of pose models performs inference on each video frame. Each pose model employs an expectation-maximization algorithm to estimate the probability that the given frame contains the corresponding pose. Over a sequence of frames, all the pose models collectively produce a multivariate time series. In the activity recognition stage, we use nearest neighbor, with dynamic time warping as a distance measure, to classify pose time series. We have performed some experiments on a publicly available dataset and the results are found to be promising
format	Conference or Workshop Item
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	Model-free viewpoint invariant human activity recognition
title_short	Model-free viewpoint invariant human activity recognition
title_full	Model-free viewpoint invariant human activity recognition
title_fullStr	Model-free viewpoint invariant human activity recognition
title_full_unstemmed	Model-free viewpoint invariant human activity recognition
title_sort	model-free viewpoint invariant human activity recognition
publishDate	2011
url	http://irep.iium.edu.my/43204/ http://irep.iium.edu.my/43204/ http://irep.iium.edu.my/43204/1/IMECS_2011.pdf
first_indexed	2023-09-18T21:01:34Z
last_indexed	2023-09-18T21:01:34Z
_version_	1777410658489335808

Model-free viewpoint invariant human activity recognition

Similar Items