Modeling of human motion through motion captured data using non-linear identification

The importance of estimating human motion analysis can be illustrated by numerous applications such as performance measurement for human factors engineering, posture and gait analysis for training athletes and physically challenged persons, animation of the human body, hands and face, automatic anno...

Full description

Saved in:

Bibliographic Details
Main Author:	Che Omar, Muhammad Budiman
Format:	Thesis
Language:	English
Published:	2007
Subjects:	TJ Mechanical engineering and machinery
Online Access:	http://eprints.utm.my/id/eprint/36571/1/MuhammadBudimanMFKM2007.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.36571
record_format	uketd_dc
spelling	my-utm-ep.365712018-07-28T06:26:19Z Modeling of human motion through motion captured data using non-linear identification 2007-12 Che Omar, Muhammad Budiman TJ Mechanical engineering and machinery The importance of estimating human motion analysis can be illustrated by numerous applications such as performance measurement for human factors engineering, posture and gait analysis for training athletes and physically challenged persons, animation of the human body, hands and face, automatic annotation of human activities in video databases, control in video games and virtual reality or teleoperation of anthropometric robots. Image processing technique from motion captured images is an accurate and cost effective method to give a set of data that defines the location of specified limb at every sequence of human motion. From this set of data, system identification was done to model the human motion. This project is a study on how performance of an identified model is influenced by different types of model representation whether it is a linear model or non-linear model and a single variable model or multi variable model. Two types of parameter estimator was used which were least square and recursive least square. The study also included the effects of different number of lags on the model. The objective is to formulate a predictive model to analyze human motion. Simulation studies were done on this model representation and compared with actual human motion. Several model validation techniques were done to validate the identified models. In this study, multivariable non-linear model is a good human motion representative. The model accuracy increases as the degree of non-linearity and number of lags are increased but it makes the model become more complex. 2007-12 Thesis http://eprints.utm.my/id/eprint/36571/ http://eprints.utm.my/id/eprint/36571/1/MuhammadBudimanMFKM2007.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:69242 masters Universiti Teknologi Malaysia, Faculty of Mechanical Engineering Faculty of Mechanical Engineering
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	TJ Mechanical engineering and machinery
spellingShingle	TJ Mechanical engineering and machinery Che Omar, Muhammad Budiman Modeling of human motion through motion captured data using non-linear identification
description	The importance of estimating human motion analysis can be illustrated by numerous applications such as performance measurement for human factors engineering, posture and gait analysis for training athletes and physically challenged persons, animation of the human body, hands and face, automatic annotation of human activities in video databases, control in video games and virtual reality or teleoperation of anthropometric robots. Image processing technique from motion captured images is an accurate and cost effective method to give a set of data that defines the location of specified limb at every sequence of human motion. From this set of data, system identification was done to model the human motion. This project is a study on how performance of an identified model is influenced by different types of model representation whether it is a linear model or non-linear model and a single variable model or multi variable model. Two types of parameter estimator was used which were least square and recursive least square. The study also included the effects of different number of lags on the model. The objective is to formulate a predictive model to analyze human motion. Simulation studies were done on this model representation and compared with actual human motion. Several model validation techniques were done to validate the identified models. In this study, multivariable non-linear model is a good human motion representative. The model accuracy increases as the degree of non-linearity and number of lags are increased but it makes the model become more complex.
format	Thesis
qualification_level	Master's degree
author	Che Omar, Muhammad Budiman
author_facet	Che Omar, Muhammad Budiman
author_sort	Che Omar, Muhammad Budiman
title	Modeling of human motion through motion captured data using non-linear identification
title_short	Modeling of human motion through motion captured data using non-linear identification
title_full	Modeling of human motion through motion captured data using non-linear identification
title_fullStr	Modeling of human motion through motion captured data using non-linear identification
title_full_unstemmed	Modeling of human motion through motion captured data using non-linear identification
title_sort	modeling of human motion through motion captured data using non-linear identification
granting_institution	Universiti Teknologi Malaysia, Faculty of Mechanical Engineering
granting_department	Faculty of Mechanical Engineering
publishDate	2007
url	http://eprints.utm.my/id/eprint/36571/1/MuhammadBudimanMFKM2007.pdf
_version_	1747816436283211776

Modeling of human motion through motion captured data using non-linear identification

Similar Items