Skeleton tracking solutions for a low-cost stroke rehabilitation support system
Publication Type
Conference Proceeding Article
Publication Date
9-2023
Abstract
Computer systems based on motion assessment are promising solutions to support stroke survivors' autonomous rehabilitation exercises. In this regard, researchers keep trying to achieve engaging and low-cost solutions suitable mainly for home use. Aiming to achieve a system with a minimal technical setup, we compare Microsoft Kinect, OpenPose, and MediaPipe skeleton tracking approaches for upper extremity quality of movement assessment after stroke. We determine if classification models assess accurately exercise performance with OpenPose and MediaPipe data against Kinect, using a dataset of 15 stroke survivors. We compute Root Mean Squared Error to determine the alignment of trajectories and kinematic variables. MediaPipe World Landmarks revealed high alignment with Kinect, revealing to be a potential alternative method.
Keywords
tracking, computational modeling, stroke (medical condition), assistive robots, skeleton, motion capture, libraries
Discipline
Artificial Intelligence and Robotics
Research Areas
Intelligent Systems and Optimization
Publication
2023 International Conference on Rehabilitation Robotics (ICORR): Singapore, September 24-28: Proceedings
ISBN
9798350342765
Identifier
10.1109/ICORR58425.2023.10304749
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
COIAS, Ana R.; LEE, Min Hun; BERNARDINO, Alexandre; and SMAILAGIC, Asim.
Skeleton tracking solutions for a low-cost stroke rehabilitation support system. (2023). 2023 International Conference on Rehabilitation Robotics (ICORR): Singapore, September 24-28: Proceedings.
Available at: https://ink.library.smu.edu.sg/sis_research/8506
Copyright Owner and License
Authors
Additional URL
https://doi.org/10.1109/ICORR58425.2023.10304749