Riemannian Geometric Approaches for Measuring Movement Quality

Anirudh Som, Rushil Anirudh, Qiao Wang, Pavan Turaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

A growing set of applications in home-based interactive physical therapy require the ability to monitor, inform and assess the quality of everyday movements. Interactive therapy requires both real-time feedback of movement quality, as well as summative feedback of quality over a period of time. Obtaining labeled data from trained experts is the main limitation, since it is both expensive and time consuming. Motivated by recent studies in motor-control, we propose an unsupervised approach that measures movement quality of simple actions by considering the deviation of a trajectory from an ideal movement path in the configuration space. We use two different configuration spaces to demonstrate this idea - the product space S1×S1 to model the interaction of two joint angles, and SE(3)×SE(3) to model the movement of two joints, for two different applications in movement quality estimation. We also describe potential applications of these ideas to assess quality in real-time.

Original languageEnglish (US)
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
PublisherIEEE Computer Society
Pages1005
Number of pages1
ISBN (Electronic)9781467388504
DOIs
StatePublished - Dec 16 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Other

Other29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Fingerprint

Physical therapy
Feedback
Trajectories

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Som, A., Anirudh, R., Wang, Q., & Turaga, P. (2016). Riemannian Geometric Approaches for Measuring Movement Quality. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016 (pp. 1005). [7789619] IEEE Computer Society. https://doi.org/10.1109/CVPRW.2016.129

Riemannian Geometric Approaches for Measuring Movement Quality. / Som, Anirudh; Anirudh, Rushil; Wang, Qiao; Turaga, Pavan.

Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. p. 1005 7789619.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Som, A, Anirudh, R, Wang, Q & Turaga, P 2016, Riemannian Geometric Approaches for Measuring Movement Quality. in Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016., 7789619, IEEE Computer Society, pp. 1005, 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016, Las Vegas, United States, 6/26/16. https://doi.org/10.1109/CVPRW.2016.129
Som A, Anirudh R, Wang Q, Turaga P. Riemannian Geometric Approaches for Measuring Movement Quality. In Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society. 2016. p. 1005. 7789619 https://doi.org/10.1109/CVPRW.2016.129
Som, Anirudh ; Anirudh, Rushil ; Wang, Qiao ; Turaga, Pavan. / Riemannian Geometric Approaches for Measuring Movement Quality. Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016. IEEE Computer Society, 2016. pp. 1005
@inproceedings{98126f98256f433d9432d2bb526c420d,
title = "Riemannian Geometric Approaches for Measuring Movement Quality",
abstract = "A growing set of applications in home-based interactive physical therapy require the ability to monitor, inform and assess the quality of everyday movements. Interactive therapy requires both real-time feedback of movement quality, as well as summative feedback of quality over a period of time. Obtaining labeled data from trained experts is the main limitation, since it is both expensive and time consuming. Motivated by recent studies in motor-control, we propose an unsupervised approach that measures movement quality of simple actions by considering the deviation of a trajectory from an ideal movement path in the configuration space. We use two different configuration spaces to demonstrate this idea - the product space S1×S1 to model the interaction of two joint angles, and SE(3)×SE(3) to model the movement of two joints, for two different applications in movement quality estimation. We also describe potential applications of these ideas to assess quality in real-time.",
author = "Anirudh Som and Rushil Anirudh and Qiao Wang and Pavan Turaga",
year = "2016",
month = "12",
day = "16",
doi = "10.1109/CVPRW.2016.129",
language = "English (US)",
pages = "1005",
booktitle = "Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Riemannian Geometric Approaches for Measuring Movement Quality

AU - Som, Anirudh

AU - Anirudh, Rushil

AU - Wang, Qiao

AU - Turaga, Pavan

PY - 2016/12/16

Y1 - 2016/12/16

N2 - A growing set of applications in home-based interactive physical therapy require the ability to monitor, inform and assess the quality of everyday movements. Interactive therapy requires both real-time feedback of movement quality, as well as summative feedback of quality over a period of time. Obtaining labeled data from trained experts is the main limitation, since it is both expensive and time consuming. Motivated by recent studies in motor-control, we propose an unsupervised approach that measures movement quality of simple actions by considering the deviation of a trajectory from an ideal movement path in the configuration space. We use two different configuration spaces to demonstrate this idea - the product space S1×S1 to model the interaction of two joint angles, and SE(3)×SE(3) to model the movement of two joints, for two different applications in movement quality estimation. We also describe potential applications of these ideas to assess quality in real-time.

AB - A growing set of applications in home-based interactive physical therapy require the ability to monitor, inform and assess the quality of everyday movements. Interactive therapy requires both real-time feedback of movement quality, as well as summative feedback of quality over a period of time. Obtaining labeled data from trained experts is the main limitation, since it is both expensive and time consuming. Motivated by recent studies in motor-control, we propose an unsupervised approach that measures movement quality of simple actions by considering the deviation of a trajectory from an ideal movement path in the configuration space. We use two different configuration spaces to demonstrate this idea - the product space S1×S1 to model the interaction of two joint angles, and SE(3)×SE(3) to model the movement of two joints, for two different applications in movement quality estimation. We also describe potential applications of these ideas to assess quality in real-time.

UR - http://www.scopus.com/inward/record.url?scp=85010192516&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010192516&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2016.129

DO - 10.1109/CVPRW.2016.129

M3 - Conference contribution

AN - SCOPUS:85010192516

SP - 1005

BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016

PB - IEEE Computer Society

ER -