Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture

Yves Rybarczyk, Jan Kleine Deters, Arián Aladro Gonzalo, Danilo Esparza, Mario Gonzalez, Santiago Villarreal, Isabel L. Nunes

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

8 Citations (Scopus)

Abstract

Telemedicine is a current trend in healthcare. The present study is part of the ePHoRt project, which is a web-based platform for the rehabilitation of patients after hip replacement surgery. To be economically suitable the system is intended to be based on low-cost technologies, especially in terms of motion capture. This is the reason why the Kinect-based motion tracking is chosen. The paper focuses on the automatic assessment of the correctness of the exercises performed by the user. A Dynamic Time Warping (DTW) approach is used to discriminate between correct and incorrect movements. The classification of the movements through a Naïve Bayes classifier shows a very high percentage of accuracy (98.2%). Models are built for each individual and reeducation exercise with only few attributes and the same accuracy. Due to these promising results, the next step will consist of testing the algorithms on patients performing the exercises in real time.

Original languageEnglish
Title of host publicationAdvances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017
EditorsI. Nunes
Place of PublicationCham
PublisherSpringer
Pages348-360
Number of pages13
ISBN (Electronic)978-3-319-60366-7
ISBN (Print)978-3-319-60365-0
DOIs
Publication statusPublished - 1 Jan 2018
EventAHFE 2017 International Conference on Human Factors and Systems Interaction, 2017 - [state] CA, United States
Duration: 17 Jul 201721 Jul 2017

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer
Volume592
ISSN (Print)2194-5357

Conference

ConferenceAHFE 2017 International Conference on Human Factors and Systems Interaction, 2017
CountryUnited States
City[state] CA
Period17/07/1721/07/17

Fingerprint

Telemedicine
Patient rehabilitation
Surgery
Classifiers
Testing
Costs

Keywords

  • Dynamic Time Warping
  • Kinect-based motion tracking
  • Machine learning
  • Movement assessment
  • Telerehabilitation

Cite this

Rybarczyk, Y., Deters, J. K., Gonzalo, A. A., Esparza, D., Gonzalez, M., Villarreal, S., & Nunes, I. L. (2018). Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture. In I. Nunes (Ed.), Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017 (pp. 348-360). (Advances in Intelligent Systems and Computing; Vol. 592). Cham: Springer. https://doi.org/10.1007/978-3-319-60366-7_33
Rybarczyk, Yves ; Deters, Jan Kleine ; Gonzalo, Arián Aladro ; Esparza, Danilo ; Gonzalez, Mario ; Villarreal, Santiago ; Nunes, Isabel L. / Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture. Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017. editor / I. Nunes. Cham : Springer, 2018. pp. 348-360 (Advances in Intelligent Systems and Computing).
@inproceedings{98e307b08da64e27bfe07d26e1a24e34,
title = "Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture",
abstract = "Telemedicine is a current trend in healthcare. The present study is part of the ePHoRt project, which is a web-based platform for the rehabilitation of patients after hip replacement surgery. To be economically suitable the system is intended to be based on low-cost technologies, especially in terms of motion capture. This is the reason why the Kinect-based motion tracking is chosen. The paper focuses on the automatic assessment of the correctness of the exercises performed by the user. A Dynamic Time Warping (DTW) approach is used to discriminate between correct and incorrect movements. The classification of the movements through a Na{\"i}ve Bayes classifier shows a very high percentage of accuracy (98.2{\%}). Models are built for each individual and reeducation exercise with only few attributes and the same accuracy. Due to these promising results, the next step will consist of testing the algorithms on patients performing the exercises in real time.",
keywords = "Dynamic Time Warping, Kinect-based motion tracking, Machine learning, Movement assessment, Telerehabilitation",
author = "Yves Rybarczyk and Deters, {Jan Kleine} and Gonzalo, {Ari{\'a}n Aladro} and Danilo Esparza and Mario Gonzalez and Santiago Villarreal and Nunes, {Isabel L.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-60366-7_33",
language = "English",
isbn = "978-3-319-60365-0",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "348--360",
editor = "I. Nunes",
booktitle = "Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017",

}

Rybarczyk, Y, Deters, JK, Gonzalo, AA, Esparza, D, Gonzalez, M, Villarreal, S & Nunes, IL 2018, Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture. in I Nunes (ed.), Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017. Advances in Intelligent Systems and Computing, vol. 592, Springer, Cham, pp. 348-360, AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017, [state] CA, United States, 17/07/17. https://doi.org/10.1007/978-3-319-60366-7_33

Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture. / Rybarczyk, Yves; Deters, Jan Kleine; Gonzalo, Arián Aladro; Esparza, Danilo; Gonzalez, Mario; Villarreal, Santiago; Nunes, Isabel L.

Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017. ed. / I. Nunes. Cham : Springer, 2018. p. 348-360 (Advances in Intelligent Systems and Computing; Vol. 592).

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

TY - GEN

T1 - Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture

AU - Rybarczyk, Yves

AU - Deters, Jan Kleine

AU - Gonzalo, Arián Aladro

AU - Esparza, Danilo

AU - Gonzalez, Mario

AU - Villarreal, Santiago

AU - Nunes, Isabel L.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Telemedicine is a current trend in healthcare. The present study is part of the ePHoRt project, which is a web-based platform for the rehabilitation of patients after hip replacement surgery. To be economically suitable the system is intended to be based on low-cost technologies, especially in terms of motion capture. This is the reason why the Kinect-based motion tracking is chosen. The paper focuses on the automatic assessment of the correctness of the exercises performed by the user. A Dynamic Time Warping (DTW) approach is used to discriminate between correct and incorrect movements. The classification of the movements through a Naïve Bayes classifier shows a very high percentage of accuracy (98.2%). Models are built for each individual and reeducation exercise with only few attributes and the same accuracy. Due to these promising results, the next step will consist of testing the algorithms on patients performing the exercises in real time.

AB - Telemedicine is a current trend in healthcare. The present study is part of the ePHoRt project, which is a web-based platform for the rehabilitation of patients after hip replacement surgery. To be economically suitable the system is intended to be based on low-cost technologies, especially in terms of motion capture. This is the reason why the Kinect-based motion tracking is chosen. The paper focuses on the automatic assessment of the correctness of the exercises performed by the user. A Dynamic Time Warping (DTW) approach is used to discriminate between correct and incorrect movements. The classification of the movements through a Naïve Bayes classifier shows a very high percentage of accuracy (98.2%). Models are built for each individual and reeducation exercise with only few attributes and the same accuracy. Due to these promising results, the next step will consist of testing the algorithms on patients performing the exercises in real time.

KW - Dynamic Time Warping

KW - Kinect-based motion tracking

KW - Machine learning

KW - Movement assessment

KW - Telerehabilitation

UR - http://www.scopus.com/inward/record.url?scp=85041131278&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-60366-7_33

DO - 10.1007/978-3-319-60366-7_33

M3 - Conference contribution

SN - 978-3-319-60365-0

T3 - Advances in Intelligent Systems and Computing

SP - 348

EP - 360

BT - Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017

A2 - Nunes, I.

PB - Springer

CY - Cham

ER -

Rybarczyk Y, Deters JK, Gonzalo AA, Esparza D, Gonzalez M, Villarreal S et al. Recognition of Physiotherapeutic Exercises Through DTW and Low-Cost Vision-Based Motion Capture. In Nunes I, editor, Advances in Human Factors and Systems Interaction - Proceedings of the AHFE 2017 International Conference on Human Factors and Systems Interaction, 2017. Cham: Springer. 2018. p. 348-360. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-60366-7_33