Assessment of Post-Stroke Functioning using Machine Vision

May 2007

Assessment of Post-Stroke Functioning using Machine Vision

Authors:

Sonya Allin and Deva Ramanan

Abstract:

We present a system to automatically assess the functional performance of stroke survivors along axes defined by the Arm Motor Ability Test (AMAT). The upper body motion of seven stroke survivors was measured in a laboratory environment using a commercial motion capture device and a novel kinematic tracker of our design. Statistics generated by each individual were related to expert-determined assessments of functional health. Results indicate several kinematic targets that correlate with and predict opinions of health. These include recorded motion of the torso during the performance of tasks and flexion about the elbow on the hemiparetic (impaired) side. We show that both kinematic statistics can be cheaply and robustly measured with video cameras while still preserving their diagnostic value. Such cheap and robust measurements will ultimately facilitate assessment outside of clinics and in places where functioning is valuable to individuals, such as homes and workplaces.
@conference{Allin-2007-121227,
author = {Sonya Allin And Deva Ramanan},
title = {Assessment of Post-Stroke Functioning using Machine Vision},
booktitle = {Proceedings of 10th IAPR Conference on Machine Vision Applications (MVA '07)},
year = {2007},
month = {May},
pages = {299 - 302},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.