A hybrid approach to human posture classification during TV watching

Jonathan H. Chan, Thammarsat Visutarrom, Sung-Bae Cho, Worrawat Engchuan, Pornchai Mongolnam, Simon Fong

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.

Original languageEnglish
Pages (from-to)1119-1126
Number of pages8
JournalJournal of Medical Imaging and Health Informatics
Volume6
Issue number4
DOIs
Publication statusPublished - 2016 Aug 1

Fingerprint

Posture
Benchmarking
Television
Skeleton
Research
Datasets

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Chan, Jonathan H. ; Visutarrom, Thammarsat ; Cho, Sung-Bae ; Engchuan, Worrawat ; Mongolnam, Pornchai ; Fong, Simon. / A hybrid approach to human posture classification during TV watching. In: Journal of Medical Imaging and Health Informatics. 2016 ; Vol. 6, No. 4. pp. 1119-1126.
@article{67bd99d989db4b478a1ce9bf966dabd6,
title = "A hybrid approach to human posture classification during TV watching",
abstract = "Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.",
author = "Chan, {Jonathan H.} and Thammarsat Visutarrom and Sung-Bae Cho and Worrawat Engchuan and Pornchai Mongolnam and Simon Fong",
year = "2016",
month = "8",
day = "1",
doi = "10.1166/jmihi.2016.1809",
language = "English",
volume = "6",
pages = "1119--1126",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "4",

}

A hybrid approach to human posture classification during TV watching. / Chan, Jonathan H.; Visutarrom, Thammarsat; Cho, Sung-Bae; Engchuan, Worrawat; Mongolnam, Pornchai; Fong, Simon.

In: Journal of Medical Imaging and Health Informatics, Vol. 6, No. 4, 01.08.2016, p. 1119-1126.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hybrid approach to human posture classification during TV watching

AU - Chan, Jonathan H.

AU - Visutarrom, Thammarsat

AU - Cho, Sung-Bae

AU - Engchuan, Worrawat

AU - Mongolnam, Pornchai

AU - Fong, Simon

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.

AB - Human posture classification in near real time is a significant challenge in various fields of research. Recently, the use of the Microsoft Kinect system for 3D skeleton detection has shown to be of promise. This work compares four common classifiers and the use of a hybrid approach for classification. The results show that the use of a hybrid genetic algorithm and random forest classifier is able to provide fast and robust human posture classification. Finally, to aid in further development of posture detection, a comprehensive human posture data set while watching television has been generated in this work for benchmarking purpose and made available publicly at http://dlab.sit.kmutt.ac.th/index.php/human-posture-datasets.

UR - http://www.scopus.com/inward/record.url?scp=84988376944&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988376944&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2016.1809

DO - 10.1166/jmihi.2016.1809

M3 - Article

VL - 6

SP - 1119

EP - 1126

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 4

ER -