AR oriented pose matching mechanism from motion capture data

Research output: Contribution to journalArticle

Abstract

Pose matching and skeletal mapping method are an integral part of Augmented Reality (AR) based learning technology. In this paper a mechanism for pose matching is presented based on extraction of skeletal data from the dance trainer's physical movements in the form of color defined images snapped by Kinect, where each pose is modelled by a sequence of key movements and continues data frames. In order to extract the exact matched pose, the frame sequence is divided into pose feature frame and skeletal data frame by the use of pose matching dance training movement recognition algorithm (PMDTMR). This proposed algorithm is compared with other published methods in terms of frame level accuracy and learning time of dance session. The experimental results show that the proposed algorithm outperforms the state of art techniques for successful identification and recognition of matched pose between the dance trainer and the expert of the pre-recorded video through the Kinect sensor.

Original languageEnglish
Pages (from-to)294-298
Number of pages5
JournalInternational Journal of Engineering and Technology(UAE)
Volume7
Issue number4
DOIs
Publication statusPublished - 01 Jan 2018

Fingerprint

Augmented reality
Data acquisition
Learning
Color
Technology
Sensors
Recognition (Psychology)

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science (miscellaneous)
  • Environmental Engineering
  • Chemical Engineering(all)
  • Engineering(all)
  • Hardware and Architecture

Cite this

@article{04bb64ccf1504949b94504a7d4e99baf,
title = "AR oriented pose matching mechanism from motion capture data",
abstract = "Pose matching and skeletal mapping method are an integral part of Augmented Reality (AR) based learning technology. In this paper a mechanism for pose matching is presented based on extraction of skeletal data from the dance trainer's physical movements in the form of color defined images snapped by Kinect, where each pose is modelled by a sequence of key movements and continues data frames. In order to extract the exact matched pose, the frame sequence is divided into pose feature frame and skeletal data frame by the use of pose matching dance training movement recognition algorithm (PMDTMR). This proposed algorithm is compared with other published methods in terms of frame level accuracy and learning time of dance session. The experimental results show that the proposed algorithm outperforms the state of art techniques for successful identification and recognition of matched pose between the dance trainer and the expert of the pre-recorded video through the Kinect sensor.",
author = "Javid Iqbal and {Basant Singh}, {Manjit Sigh} and {Mohamed Ariff}, Mutahir",
year = "2018",
month = "1",
day = "1",
doi = "10.14419/ijet.v7i4.35.22749",
language = "English",
volume = "7",
pages = "294--298",
journal = "International Journal of Engineering and Technology(UAE)",
issn = "2227-524X",
publisher = "Science Publishing Corporation Inc",
number = "4",

}

AR oriented pose matching mechanism from motion capture data. / Iqbal, Javid; Basant Singh, Manjit Sigh; Mohamed Ariff, Mutahir.

In: International Journal of Engineering and Technology(UAE), Vol. 7, No. 4, 01.01.2018, p. 294-298.

Research output: Contribution to journalArticle

TY - JOUR

T1 - AR oriented pose matching mechanism from motion capture data

AU - Iqbal, Javid

AU - Basant Singh, Manjit Sigh

AU - Mohamed Ariff, Mutahir

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Pose matching and skeletal mapping method are an integral part of Augmented Reality (AR) based learning technology. In this paper a mechanism for pose matching is presented based on extraction of skeletal data from the dance trainer's physical movements in the form of color defined images snapped by Kinect, where each pose is modelled by a sequence of key movements and continues data frames. In order to extract the exact matched pose, the frame sequence is divided into pose feature frame and skeletal data frame by the use of pose matching dance training movement recognition algorithm (PMDTMR). This proposed algorithm is compared with other published methods in terms of frame level accuracy and learning time of dance session. The experimental results show that the proposed algorithm outperforms the state of art techniques for successful identification and recognition of matched pose between the dance trainer and the expert of the pre-recorded video through the Kinect sensor.

AB - Pose matching and skeletal mapping method are an integral part of Augmented Reality (AR) based learning technology. In this paper a mechanism for pose matching is presented based on extraction of skeletal data from the dance trainer's physical movements in the form of color defined images snapped by Kinect, where each pose is modelled by a sequence of key movements and continues data frames. In order to extract the exact matched pose, the frame sequence is divided into pose feature frame and skeletal data frame by the use of pose matching dance training movement recognition algorithm (PMDTMR). This proposed algorithm is compared with other published methods in terms of frame level accuracy and learning time of dance session. The experimental results show that the proposed algorithm outperforms the state of art techniques for successful identification and recognition of matched pose between the dance trainer and the expert of the pre-recorded video through the Kinect sensor.

UR - http://www.scopus.com/inward/record.url?scp=85059233144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059233144&partnerID=8YFLogxK

U2 - 10.14419/ijet.v7i4.35.22749

DO - 10.14419/ijet.v7i4.35.22749

M3 - Article

VL - 7

SP - 294

EP - 298

JO - International Journal of Engineering and Technology(UAE)

JF - International Journal of Engineering and Technology(UAE)

SN - 2227-524X

IS - 4

ER -