Geometrical gait based model for fall detection using thresholding

Research output: Contribution to journalArticle

Abstract

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 pages8
JournalJournal of Information and Computational Science
Volume12
Issue number18
DOIs
Publication statusPublished - 10 Dec 2015

Fingerprint

incident
Gait analysis
surveillance
Feature extraction
video
performance
time

Keywords

  • Fall detection
  • Geometrical model
  • Thresholding

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Computational Theory and Mathematics
  • Library and Information Sciences

Cite this

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

In: Journal of Information and Computational Science, Vol. 12, No. 18, 10.12.2015, p. 6693-6700.

Research output: Contribution to journalArticle

@article{9b946722b58e4a029d542d9b372a304a,
title = "Geometrical gait based model for fall detection using thresholding",
abstract = "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.",
keywords = "Fall detection, Geometrical model, Thresholding",
author = "Win Kong and {Md Saad}, {Mohamad Hanif} and Zulkifley, {Mohd Asyraf} and {M A}, Hannan and Aini Hussain",
year = "2015",
month = "12",
day = "10",
doi = "10.12733/jics20106973",
language = "English",
volume = "12",
pages = "6693--6700",
journal = "Journal of Information and Computational Science",
issn = "1548-7741",
publisher = "Binary Information Press",
number = "18",

}

TY - JOUR

T1 - Geometrical gait based model for fall detection using thresholding

AU - Kong, Win

AU - Md Saad, Mohamad Hanif

AU - Zulkifley, Mohd Asyraf

AU - M A, Hannan

AU - Hussain, Aini

PY - 2015/12/10

Y1 - 2015/12/10

N2 - 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 - 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.

KW - Fall detection

KW - Geometrical model

KW - Thresholding

UR - http://www.scopus.com/inward/record.url?scp=84957837425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957837425&partnerID=8YFLogxK

U2 - 10.12733/jics20106973

DO - 10.12733/jics20106973

M3 - Article

AN - SCOPUS:84957837425

VL - 12

SP - 6693

EP - 6700

JO - Journal of Information and Computational Science

JF - Journal of Information and Computational Science

SN - 1548-7741

IS - 18

ER -