A finite state machine fall detection using quadrilateral shape features

M. F. Abu Hassan, Mohamad Hanif Md Saad, M. F.Ibrahimand A. Hussain

Research output: Contribution to journalArticle

Abstract

A video-based fall detection system was presented; which consists of data acquisition, image processing, feature extraction, feature selection, classification and finite state machine. A two-dimensional human posture image was represented by 12 features extracted from the generalisation of a silhouette shape to a quadrilateral. The corresponding feature vectors for three groups of human pose were statistically analysed by using a non-parametric Kruskal Wallis test to assess the different significance level between them. From the statistical test, non-significant features were discarded. Four selected kernel-based Support Vector Machine: linear, quadratics, cubic and Radial Basis Function classifiers were trained to classify three human posture groups. Among four classifiers, the last one performed the best in terms of performance matric on testing set. The classifier outperformed others with high achievement ofaverage sensitivity, precision and F-score of 99.19%, 99.25% and 99.22%, respectively. Such pose classification model output was further used in a simple finite state machine to trigger the falling event alarms. The fall detection system was tested on different fall video sets and able to detect the presence offalling events in a frame sequence of videos with accuracy of 97.32% and low computional time.

Original languageEnglish
Pages (from-to)359-366
Number of pages8
JournalBulletin of Electrical Engineering and Informatics
Volume7
Issue number3
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Turing machines
Shape Feature
Finite automata
State Machine
classifiers
posture
Classifiers
Classifier
Feature extraction
statistical tests
Silhouette
Significance level
Statistical tests
warning systems
Statistical test
Feature Vector
Data Acquisition
Radial Functions
falling
Trigger

Keywords

  • Fall detection
  • Finite state machine
  • Pose recognition
  • Quadrilateral shape features
  • Shape generalization

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Control and Systems Engineering
  • Information Systems
  • Instrumentation
  • Hardware and Architecture
  • Computer Networks and Communications
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

A finite state machine fall detection using quadrilateral shape features. / Abu Hassan, M. F.; Md Saad, Mohamad Hanif; Hussain, M. F.Ibrahimand A.

In: Bulletin of Electrical Engineering and Informatics, Vol. 7, No. 3, 01.09.2018, p. 359-366.

Research output: Contribution to journalArticle

@article{9903327592894d76862b1504b2610852,
title = "A finite state machine fall detection using quadrilateral shape features",
abstract = "A video-based fall detection system was presented; which consists of data acquisition, image processing, feature extraction, feature selection, classification and finite state machine. A two-dimensional human posture image was represented by 12 features extracted from the generalisation of a silhouette shape to a quadrilateral. The corresponding feature vectors for three groups of human pose were statistically analysed by using a non-parametric Kruskal Wallis test to assess the different significance level between them. From the statistical test, non-significant features were discarded. Four selected kernel-based Support Vector Machine: linear, quadratics, cubic and Radial Basis Function classifiers were trained to classify three human posture groups. Among four classifiers, the last one performed the best in terms of performance matric on testing set. The classifier outperformed others with high achievement ofaverage sensitivity, precision and F-score of 99.19{\%}, 99.25{\%} and 99.22{\%}, respectively. Such pose classification model output was further used in a simple finite state machine to trigger the falling event alarms. The fall detection system was tested on different fall video sets and able to detect the presence offalling events in a frame sequence of videos with accuracy of 97.32{\%} and low computional time.",
keywords = "Fall detection, Finite state machine, Pose recognition, Quadrilateral shape features, Shape generalization",
author = "{Abu Hassan}, {M. F.} and {Md Saad}, {Mohamad Hanif} and Hussain, {M. F.Ibrahimand A.}",
year = "2018",
month = "9",
day = "1",
doi = "10.11591/eei.v7i3.1184",
language = "English",
volume = "7",
pages = "359--366",
journal = "Bulletin of Electrical Engineering and Informatics",
issn = "2089-3191",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

TY - JOUR

T1 - A finite state machine fall detection using quadrilateral shape features

AU - Abu Hassan, M. F.

AU - Md Saad, Mohamad Hanif

AU - Hussain, M. F.Ibrahimand A.

PY - 2018/9/1

Y1 - 2018/9/1

N2 - A video-based fall detection system was presented; which consists of data acquisition, image processing, feature extraction, feature selection, classification and finite state machine. A two-dimensional human posture image was represented by 12 features extracted from the generalisation of a silhouette shape to a quadrilateral. The corresponding feature vectors for three groups of human pose were statistically analysed by using a non-parametric Kruskal Wallis test to assess the different significance level between them. From the statistical test, non-significant features were discarded. Four selected kernel-based Support Vector Machine: linear, quadratics, cubic and Radial Basis Function classifiers were trained to classify three human posture groups. Among four classifiers, the last one performed the best in terms of performance matric on testing set. The classifier outperformed others with high achievement ofaverage sensitivity, precision and F-score of 99.19%, 99.25% and 99.22%, respectively. Such pose classification model output was further used in a simple finite state machine to trigger the falling event alarms. The fall detection system was tested on different fall video sets and able to detect the presence offalling events in a frame sequence of videos with accuracy of 97.32% and low computional time.

AB - A video-based fall detection system was presented; which consists of data acquisition, image processing, feature extraction, feature selection, classification and finite state machine. A two-dimensional human posture image was represented by 12 features extracted from the generalisation of a silhouette shape to a quadrilateral. The corresponding feature vectors for three groups of human pose were statistically analysed by using a non-parametric Kruskal Wallis test to assess the different significance level between them. From the statistical test, non-significant features were discarded. Four selected kernel-based Support Vector Machine: linear, quadratics, cubic and Radial Basis Function classifiers were trained to classify three human posture groups. Among four classifiers, the last one performed the best in terms of performance matric on testing set. The classifier outperformed others with high achievement ofaverage sensitivity, precision and F-score of 99.19%, 99.25% and 99.22%, respectively. Such pose classification model output was further used in a simple finite state machine to trigger the falling event alarms. The fall detection system was tested on different fall video sets and able to detect the presence offalling events in a frame sequence of videos with accuracy of 97.32% and low computional time.

KW - Fall detection

KW - Finite state machine

KW - Pose recognition

KW - Quadrilateral shape features

KW - Shape generalization

UR - http://www.scopus.com/inward/record.url?scp=85052690847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052690847&partnerID=8YFLogxK

U2 - 10.11591/eei.v7i3.1184

DO - 10.11591/eei.v7i3.1184

M3 - Article

VL - 7

SP - 359

EP - 366

JO - Bulletin of Electrical Engineering and Informatics

JF - Bulletin of Electrical Engineering and Informatics

SN - 2089-3191

IS - 3

ER -