Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population.

Stepán Obdrzálek, Gregorij Kurillo, Ferda Ofli, Ruzena Bajcsy, Edmund Seto, Holly Jimison, Michael Pavel

Research output: Contribution to journalArticle

94 Citations (Scopus)

Abstract

The Microsoft Kinect camera is becoming increasingly popular in many areas aside from entertainment, including human activity monitoring and rehabilitation. Many people, however, fail to consider the reliability and accuracy of the Kinect human pose estimation when they depend on it as a measuring system. In this paper we compare the Kinect pose estimation (skeletonization) with more established techniques for pose estimation from motion capture data, examining the accuracy of joint localization and robustness of pose estimation with respect to the orientation and occlusions. We have evaluated six physical exercises aimed at coaching of elderly population. Experimental results present pose estimation accuracy rates and corresponding error bounds for the Kinect system.

Original languageEnglish (US)
Pages (from-to)1188-1193
Number of pages6
JournalConference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
Volume2012
StatePublished - 2012
Externally publishedYes

Fingerprint

Human Activities
Rehabilitation
Joints
Exercise
Population
Patient rehabilitation
Data acquisition
Cameras
Mentoring
Monitoring

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population. / Obdrzálek, Stepán; Kurillo, Gregorij; Ofli, Ferda; Bajcsy, Ruzena; Seto, Edmund; Jimison, Holly; Pavel, Michael.

In: Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, Vol. 2012, 2012, p. 1188-1193.

Research output: Contribution to journalArticle

@article{b159bebdef0d452095f2ca9bc8c41ce9,
title = "Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population.",
abstract = "The Microsoft Kinect camera is becoming increasingly popular in many areas aside from entertainment, including human activity monitoring and rehabilitation. Many people, however, fail to consider the reliability and accuracy of the Kinect human pose estimation when they depend on it as a measuring system. In this paper we compare the Kinect pose estimation (skeletonization) with more established techniques for pose estimation from motion capture data, examining the accuracy of joint localization and robustness of pose estimation with respect to the orientation and occlusions. We have evaluated six physical exercises aimed at coaching of elderly population. Experimental results present pose estimation accuracy rates and corresponding error bounds for the Kinect system.",
author = "Step{\'a}n Obdrz{\'a}lek and Gregorij Kurillo and Ferda Ofli and Ruzena Bajcsy and Edmund Seto and Holly Jimison and Michael Pavel",
year = "2012",
language = "English (US)",
volume = "2012",
pages = "1188--1193",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Accuracy and robustness of Kinect pose estimation in the context of coaching of elderly population.

AU - Obdrzálek, Stepán

AU - Kurillo, Gregorij

AU - Ofli, Ferda

AU - Bajcsy, Ruzena

AU - Seto, Edmund

AU - Jimison, Holly

AU - Pavel, Michael

PY - 2012

Y1 - 2012

N2 - The Microsoft Kinect camera is becoming increasingly popular in many areas aside from entertainment, including human activity monitoring and rehabilitation. Many people, however, fail to consider the reliability and accuracy of the Kinect human pose estimation when they depend on it as a measuring system. In this paper we compare the Kinect pose estimation (skeletonization) with more established techniques for pose estimation from motion capture data, examining the accuracy of joint localization and robustness of pose estimation with respect to the orientation and occlusions. We have evaluated six physical exercises aimed at coaching of elderly population. Experimental results present pose estimation accuracy rates and corresponding error bounds for the Kinect system.

AB - The Microsoft Kinect camera is becoming increasingly popular in many areas aside from entertainment, including human activity monitoring and rehabilitation. Many people, however, fail to consider the reliability and accuracy of the Kinect human pose estimation when they depend on it as a measuring system. In this paper we compare the Kinect pose estimation (skeletonization) with more established techniques for pose estimation from motion capture data, examining the accuracy of joint localization and robustness of pose estimation with respect to the orientation and occlusions. We have evaluated six physical exercises aimed at coaching of elderly population. Experimental results present pose estimation accuracy rates and corresponding error bounds for the Kinect system.

UR - http://www.scopus.com/inward/record.url?scp=84881049238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881049238&partnerID=8YFLogxK

M3 - Article

C2 - 23366110

AN - SCOPUS:84881049238

VL - 2012

SP - 1188

EP - 1193

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -