Real-time human pose detection and tracking for tele-rehabilitation in virtual reality

Štěpán Obdržálek; Gregorij Kurillo; Jay Han; Ted Abresch; Ruzena Bajcsy

doi:10.3233/978-1-61499-022-2-320

Real-time human pose detection and tracking for tele-rehabilitation in virtual reality

Štěpán Obdržálek, Gregorij Kurillo, Jay Han, Ted Abresch, Ruzena Bajcsy

Physical Medicine and Rehabilitation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

20 Scopus citations

Abstract

We present a real-time algorithm for human pose detection and tracking from vision-based 3D data and its application to tele-rehabilitation in virtual environments. We employ stereo camera(s) to capture 3D avatars of geographically dislocated patient and therapist in real-time, while sending the data remotely and displaying it in a virtual scene. A pose detection and tracking algorithm extracts kinematic parameters from each participant and determines pose similarity. The pose similarity score is used to quantify patient's performance and provide real-time feedback for remote rehabilitation.

Original language	English (US)
Title of host publication	Studies in Health Technology and Informatics
Pages	320-324
Number of pages	5
Volume	173
DOIs	https://doi.org/10.3233/978-1-61499-022-2-320
State	Published - 2012
Event	Medicine Meets Virtual Reality 19: NextMed, MMVR 2012 - Newport Beach, CA, United States Duration: Feb 9 2012 → Feb 11 2012

Other

Other	Medicine Meets Virtual Reality 19: NextMed, MMVR 2012
Country/Territory	United States
City	Newport Beach, CA
Period	2/9/12 → 2/11/12

Keywords

Human pose estimation and tracking
Stereo vision
Tele-rehabilitation

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/978-1-61499-022-2-320

Cite this

@inproceedings{385ba75e5acd4edcb616b5e7f35662cf,

title = "Real-time human pose detection and tracking for tele-rehabilitation in virtual reality",

abstract = "We present a real-time algorithm for human pose detection and tracking from vision-based 3D data and its application to tele-rehabilitation in virtual environments. We employ stereo camera(s) to capture 3D avatars of geographically dislocated patient and therapist in real-time, while sending the data remotely and displaying it in a virtual scene. A pose detection and tracking algorithm extracts kinematic parameters from each participant and determines pose similarity. The pose similarity score is used to quantify patient's performance and provide real-time feedback for remote rehabilitation.",

keywords = "Human pose estimation and tracking, Stereo vision, Tele-rehabilitation",

author = "{\v S}t{\v e}p{\'a}n Obdr{\v z}{\'a}lek and Gregorij Kurillo and Jay Han and Ted Abresch and Ruzena Bajcsy",

year = "2012",

doi = "10.3233/978-1-61499-022-2-320",

language = "English (US)",

isbn = "9781614990215",

volume = "173",

pages = "320--324",

booktitle = "Studies in Health Technology and Informatics",

note = "Medicine Meets Virtual Reality 19: NextMed, MMVR 2012 ; Conference date: 09-02-2012 Through 11-02-2012",

}

TY - GEN

T1 - Real-time human pose detection and tracking for tele-rehabilitation in virtual reality

AU - Obdržálek, Štěpán

AU - Kurillo, Gregorij

AU - Han, Jay

AU - Abresch, Ted

AU - Bajcsy, Ruzena

PY - 2012

Y1 - 2012

N2 - We present a real-time algorithm for human pose detection and tracking from vision-based 3D data and its application to tele-rehabilitation in virtual environments. We employ stereo camera(s) to capture 3D avatars of geographically dislocated patient and therapist in real-time, while sending the data remotely and displaying it in a virtual scene. A pose detection and tracking algorithm extracts kinematic parameters from each participant and determines pose similarity. The pose similarity score is used to quantify patient's performance and provide real-time feedback for remote rehabilitation.

AB - We present a real-time algorithm for human pose detection and tracking from vision-based 3D data and its application to tele-rehabilitation in virtual environments. We employ stereo camera(s) to capture 3D avatars of geographically dislocated patient and therapist in real-time, while sending the data remotely and displaying it in a virtual scene. A pose detection and tracking algorithm extracts kinematic parameters from each participant and determines pose similarity. The pose similarity score is used to quantify patient's performance and provide real-time feedback for remote rehabilitation.

KW - Human pose estimation and tracking

KW - Stereo vision

KW - Tele-rehabilitation

UR - http://www.scopus.com/inward/record.url?scp=84860645603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860645603&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-022-2-320

DO - 10.3233/978-1-61499-022-2-320

M3 - Conference contribution

C2 - 22357010

AN - SCOPUS:84860645603

SN - 9781614990215

VL - 173

SP - 320

EP - 324

BT - Studies in Health Technology and Informatics

T2 - Medicine Meets Virtual Reality 19: NextMed, MMVR 2012

Y2 - 9 February 2012 through 11 February 2012

ER -

Real-time human pose detection and tracking for tele-rehabilitation in virtual reality

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this