Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 29, 2026

Determining and Controlling External Power Output During Regular Handrim Wheelchair Propulsion
08:55

Determining and Controlling External Power Output During Regular Handrim Wheelchair Propulsion

Published on: February 5, 2020

Computer Vision-Based Classification of Manual Wheelchair Propulsion Patterns.

Salman Nourbakhsh, Philippe S Archambault, Juan Martinez Rocha

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |May 27, 2026
    PubMed
    Summary

    This study developed a vision-based system to automatically classify wheelchair propulsion patterns. The technology accurately identifies efficient semicircular (SC) movements, aiding in preventing upper limb injuries for manual wheelchair users.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Evaluation of visual augmented feedback on manual wheelchair (MWC) users' wheelchair propulsion pattern in a MWC simulator to enhance training outcomes: a pilot study.

    Disability and rehabilitation. Assistive technology·2026
    Same author

    Improvement of powered wheelchair driving performance during virtual simulator training.

    Disability and rehabilitation. Assistive technology·2026
    Same author

    Turning Strategies While Walking on an Omnidirectional Treadmill With Virtual Reality.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025
    Same author

    A mapping review of good practices of participatory research for an impactful collaboration in disabilities studies.

    Disability and rehabilitation·2025
    Same author

    Exploring the challenges in manual wheelchair operation for new users.

    Disability and rehabilitation. Assistive technology·2025
    Same author

    Editorial: Human-centered solutions and synergies across robotic and digital systems for rehabilitation.

    Frontiers in robotics and AI·2024

    Area of Science:

    • Rehabilitation Engineering
    • Computer Vision
    • Biomechanics

    Background:

    • Manual wheelchair users (MWC) face high risks of upper limb overuse injuries from inefficient propulsion.
    • Clinical guidelines advocate the semicircular (SC) propulsion pattern to minimize joint stress.
    • Accessible automated feedback tools for classifying propulsion techniques are currently limited in rehabilitation settings.

    Purpose of the Study:

    • To develop a vision-based classifier using 2D wrist trajectory images and a convolutional neural network (CNN).
    • To distinguish SC from non-SC propulsion patterns at the cycle level.
    • To validate the classifier's performance on simulator-based application data against expert consensus.

    Main Methods:

    • Ten participants performed four propulsion patterns at three speeds on a wheelchair simulator.

    More Related Videos

    Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
    11:16

    Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

    Published on: July 22, 2014

    Related Experiment Videos

    Last Updated: May 29, 2026

    Determining and Controlling External Power Output During Regular Handrim Wheelchair Propulsion
    08:55

    Determining and Controlling External Power Output During Regular Handrim Wheelchair Propulsion

    Published on: February 5, 2020

    Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
    11:16

    Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

    Published on: July 22, 2014

  • Wrist trajectories were captured via RGB video and processed using markerless tracking (MediaPipe).
  • A CNN was trained on 150x150-pixel wrist trajectory images; performance was validated against expert-labeled data.

    • Main Results:

    • The CNN achieved 94% accuracy in controlled conditions and 93.3% on simulator-based application data.
    • Precision, recall, and F1 scores for the classifier reached 95.3%.
    • The system demonstrated feasibility for automated, cycle-level propulsion pattern classification.

    Conclusions:

    • A low-cost, video-based system can effectively classify wheelchair propulsion patterns.
    • This technology holds potential for real-time feedback tools in virtual reality (VR) simulators.
    • Automated classification can support skill acquisition and injury prevention for manual wheelchair users.