Leveraging Deep Learning to Assess Upper Limb Kinematics after Stroke with Off-the-shelf Webcams

We develop and validate a camera-based compensation classifier (“3C”) for tele-neurorehabilitation to discriminate normal arm-movements from those with compensation. The algorithm can be used with a webcam alone or in combination with inertial measurement unit (IMU).  This method enhances tele-rehabilitation and boosts the recovery process of the clients. 


Prof. Dr. Verena Klamroth-Marganska, ZHAW Gesundheit, Institut für Ergotherapie

Prof. Dr. med. Andreas Luft, UniversitätsSpital Zürich, Klinik für Neurologie

Dr. Elena Gavagnin, ZHAW School of Management and Law, Institut für Wirtschaftsinformatik



cereneo Foundation