Home // eTELEMED 2024, The Sixteenth International Conference on eHealth, Telemedicine, and Social Medicine // View article

Using Computer Vision based Markerless Pose Estimation for Measuring Shoulder Range of Motion

Authors:
Thomas Hellstén
Jonny Karlsson

Keywords: computer vision; range of motion; telerehabilitation; YOLO.

Abstract:
The use of health technology applications has increased during recent years among health care professionals. A novel and innovative approach for implementing health technologies in daily practice is through Computer Vision (CV) based markerless pose estimation. This approach is useful especially in rehabilitation applications for providing automatic guidance for clients performing rehabilitation exercises. The aim of this paper is to present the technical realization and early stage testing results of an open source prototype application for shoulder Range of Motion (ROM) analysis for rehabilitation purposes. The testing process included early stage accuracy tests of the prototype, in comparison to using a universal goniometer, for measuring all four active motion movements of the shoulder (flexion, extension, abduction, adduction). The results indicated that CV-based markerless pose estimation has the potential to accurately analyze shoulder joint ROM. In conclusion, the markerless CV application used in this study was found to have potential to be used in clinical practice by healthcare professionals. However, more comprehensive testing is still needed before it can be put into practice.

Pages: 25 to 28

Copyright: Copyright (c) IARIA, 2024

Publication date: May 26, 2024

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-68558-167-1

Location: Barcelona, Spain

Dates: from May 26, 2024 to May 30, 2024