Geometrical gait based model for fall detection using thresholding

Win Kong, Mohamad Hanif Md Saad, Mohd Asyraf Zulkifley, M. A. Hannan, Aini Hussain

Research output: Contribution to journalArticle

Abstract

© 2015 by Binary Information Press. This paper describes a method for real-time detection of human fall for video surveillance application. The proposed algorithm utilizes gait information in judging the fall incident. Gait refers to the pattern of human walking. Therefore, a fall is defined whenever there is a variation from the normal gait parameters. The detection algorithm is divided into three stages: human gait modeling, feature extraction and fall classification. Point Distribution Model (PDM) is employed to fit a skeleton model from a training set of data on the extracted human body contour. Then, the gait features are derived from the skeleton. The detection performance relies on the threshold values, which differ according to gait pattern. The results demonstrate that the gait analysis was able to detect fall incident accurately.
Original languageEnglish
Pages (from-to)6693-6700
Number of pages6022
JournalJournal of Information and Computational Science
DOIs
Publication statusPublished - 10 Dec 2015
Externally publishedYes

Fingerprint

incident
Gait analysis
skeleton
surveillance
Feature extraction
video
walking
performance
modeling
detection
time
human body
analysis
threshold value
parameter
method
distribution

All Science Journal Classification (ASJC) codes

  • Building and Construction
  • Energy(all)
  • Mechanical Engineering
  • Management, Monitoring, Policy and Law

Cite this

Kong, Win ; Saad, Mohamad Hanif Md ; Zulkifley, Mohd Asyraf ; Hannan, M. A. ; Hussain, Aini. / Geometrical gait based model for fall detection using thresholding. In: Journal of Information and Computational Science. 2015 ; pp. 6693-6700.
@article{a34cdda6614e426d8435ae51c69ba2cb,
title = "Geometrical gait based model for fall detection using thresholding",
abstract = "{\circledC} 2015 by Binary Information Press. This paper describes a method for real-time detection of human fall for video surveillance application. The proposed algorithm utilizes gait information in judging the fall incident. Gait refers to the pattern of human walking. Therefore, a fall is defined whenever there is a variation from the normal gait parameters. The detection algorithm is divided into three stages: human gait modeling, feature extraction and fall classification. Point Distribution Model (PDM) is employed to fit a skeleton model from a training set of data on the extracted human body contour. Then, the gait features are derived from the skeleton. The detection performance relies on the threshold values, which differ according to gait pattern. The results demonstrate that the gait analysis was able to detect fall incident accurately.",
author = "Win Kong and Saad, {Mohamad Hanif Md} and Zulkifley, {Mohd Asyraf} and Hannan, {M. A.} and Aini Hussain",
year = "2015",
month = "12",
day = "10",
doi = "10.12733/jics20106973",
language = "English",
pages = "6693--6700",
journal = "Journal of Information and Computational Science",
issn = "1548-7741",
publisher = "Binary Information Press",

}

Geometrical gait based model for fall detection using thresholding. / Kong, Win; Saad, Mohamad Hanif Md; Zulkifley, Mohd Asyraf; Hannan, M. A.; Hussain, Aini.

In: Journal of Information and Computational Science, 10.12.2015, p. 6693-6700.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Geometrical gait based model for fall detection using thresholding

AU - Kong, Win

AU - Saad, Mohamad Hanif Md

AU - Zulkifley, Mohd Asyraf

AU - Hannan, M. A.

AU - Hussain, Aini

PY - 2015/12/10

Y1 - 2015/12/10

N2 - © 2015 by Binary Information Press. This paper describes a method for real-time detection of human fall for video surveillance application. The proposed algorithm utilizes gait information in judging the fall incident. Gait refers to the pattern of human walking. Therefore, a fall is defined whenever there is a variation from the normal gait parameters. The detection algorithm is divided into three stages: human gait modeling, feature extraction and fall classification. Point Distribution Model (PDM) is employed to fit a skeleton model from a training set of data on the extracted human body contour. Then, the gait features are derived from the skeleton. The detection performance relies on the threshold values, which differ according to gait pattern. The results demonstrate that the gait analysis was able to detect fall incident accurately.

AB - © 2015 by Binary Information Press. This paper describes a method for real-time detection of human fall for video surveillance application. The proposed algorithm utilizes gait information in judging the fall incident. Gait refers to the pattern of human walking. Therefore, a fall is defined whenever there is a variation from the normal gait parameters. The detection algorithm is divided into three stages: human gait modeling, feature extraction and fall classification. Point Distribution Model (PDM) is employed to fit a skeleton model from a training set of data on the extracted human body contour. Then, the gait features are derived from the skeleton. The detection performance relies on the threshold values, which differ according to gait pattern. The results demonstrate that the gait analysis was able to detect fall incident accurately.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84957837425&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84957837425&origin=inward

U2 - 10.12733/jics20106973

DO - 10.12733/jics20106973

M3 - Article

SP - 6693

EP - 6700

JO - Journal of Information and Computational Science

JF - Journal of Information and Computational Science

SN - 1548-7741

ER -