Development of a human fall detection system based on depth maps

Assistive care related products are increasingly in demand with the recent developments in health sector associated technologies. There are several studies concerned in improving and eliminating barriers in providing quality health care services to all people, especially elderly who live alone an...

Full description

Saved in:

Bibliographic Details
Main Author:	Nizam, Yoosuf
Format:	Thesis
Language:	English English English
Published:	2018
Subjects:	TA1501-1820 Applied optics Photonics
Online Access:	http://eprints.uthm.edu.my/281/1/24p%20YOOSUF%20NIZAM.pdf http://eprints.uthm.edu.my/281/2/YOOSUF%20NIZAM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/281/3/YOOSUF%20NIZAM%20WATERMARK.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uthm-ep.281
record_format	uketd_dc
spelling	my-uthm-ep.2812021-07-21T02:22:52Z Development of a human fall detection system based on depth maps 2018-05 Nizam, Yoosuf TA1501-1820 Applied optics. Photonics Assistive care related products are increasingly in demand with the recent developments in health sector associated technologies. There are several studies concerned in improving and eliminating barriers in providing quality health care services to all people, especially elderly who live alone and those who cannot move from their home for various reasons such as disable, overweight. Among them, human fall detection systems play an important role in our daily life, because fall is the main obstacle for elderly people to live independently and it is also a major health concern due to aging population. The three basic approaches used to develop human fall detection systems include some sort of wearable devices, ambient based devices or non-invasive vision based devices using live cameras. Most of such systems are either based on wearable or ambient sensor which is very often rejected by users due to the high false alarm and difficulties in carrying them during their daily life activities. Thus, this study proposes a non-invasive human fall detection system based on the height, velocity, statistical analysis, fall risk factors and position of the subject using depth information from Microsoft Kinect sensor. Classification of human fall from other activities of daily life is accomplished using height and velocity of the subject extracted from the depth information after considering the fall risk level of the user. Acceleration and activity detection are also employed if velocity and height fail to classify the activity. Finally position of the subject is identified for fall confirmation or statistical analysis is conducted to verify the fall event. From the experimental results, the proposed system was able to achieve an average accuracy of 98.3% with sensitivity of 100% and specificity of 97.7%. The proposed system accurately distinguished all the fall events from other activities of daily life. 2018-05 Thesis http://eprints.uthm.edu.my/281/ http://eprints.uthm.edu.my/281/1/24p%20YOOSUF%20NIZAM.pdf text en public http://eprints.uthm.edu.my/281/2/YOOSUF%20NIZAM%20COPYRIGHT%20DECLARATION.pdf text en staffonly http://eprints.uthm.edu.my/281/3/YOOSUF%20NIZAM%20WATERMARK.pdf text en validuser phd doctoral Universiti Tun Hussein Onn Malaysia Fakulti Kejuruteraan Elektrik dan Elektronik
institution	Universiti Tun Hussein Onn Malaysia
collection	UTHM Institutional Repository
language	English English English
topic	TA1501-1820 Applied optics Photonics
spellingShingle	TA1501-1820 Applied optics Photonics Nizam, Yoosuf Development of a human fall detection system based on depth maps
description	Assistive care related products are increasingly in demand with the recent developments in health sector associated technologies. There are several studies concerned in improving and eliminating barriers in providing quality health care services to all people, especially elderly who live alone and those who cannot move from their home for various reasons such as disable, overweight. Among them, human fall detection systems play an important role in our daily life, because fall is the main obstacle for elderly people to live independently and it is also a major health concern due to aging population. The three basic approaches used to develop human fall detection systems include some sort of wearable devices, ambient based devices or non-invasive vision based devices using live cameras. Most of such systems are either based on wearable or ambient sensor which is very often rejected by users due to the high false alarm and difficulties in carrying them during their daily life activities. Thus, this study proposes a non-invasive human fall detection system based on the height, velocity, statistical analysis, fall risk factors and position of the subject using depth information from Microsoft Kinect sensor. Classification of human fall from other activities of daily life is accomplished using height and velocity of the subject extracted from the depth information after considering the fall risk level of the user. Acceleration and activity detection are also employed if velocity and height fail to classify the activity. Finally position of the subject is identified for fall confirmation or statistical analysis is conducted to verify the fall event. From the experimental results, the proposed system was able to achieve an average accuracy of 98.3% with sensitivity of 100% and specificity of 97.7%. The proposed system accurately distinguished all the fall events from other activities of daily life.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Nizam, Yoosuf
author_facet	Nizam, Yoosuf
author_sort	Nizam, Yoosuf
title	Development of a human fall detection system based on depth maps
title_short	Development of a human fall detection system based on depth maps
title_full	Development of a human fall detection system based on depth maps
title_fullStr	Development of a human fall detection system based on depth maps
title_full_unstemmed	Development of a human fall detection system based on depth maps
title_sort	development of a human fall detection system based on depth maps
granting_institution	Universiti Tun Hussein Onn Malaysia
granting_department	Fakulti Kejuruteraan Elektrik dan Elektronik
publishDate	2018
url	http://eprints.uthm.edu.my/281/1/24p%20YOOSUF%20NIZAM.pdf http://eprints.uthm.edu.my/281/2/YOOSUF%20NIZAM%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/281/3/YOOSUF%20NIZAM%20WATERMARK.pdf
_version_	1747830572231688192

Development of a human fall detection system based on depth maps

Similar Items