Home video monitoring system for neurodegenerative diseases based on commercial HD cameras

摘要

Neurodegenerative disease (ND) is an umbrella term for chronic disorders that are characterized by severe joint cognitive-motor impairments, which are difficult to evaluate on a frequent basis. HD cameras in the home environment could extend and enhance the diagnosis process and could lead to better treatment adjustment of ND. In this paper we propose a video monitoring system that measures the quantity and quality of two clinically relevant motor symptoms. Our system separates the patients silhouette from the background exploiting the HSV color-space properties. Further, the silhouette is split into anatomical regions, which enables detection of the upper and lower limb extremities. Finally, step length and arm-swing angles are measured to assess ND severity. The experiments show that the system is able to accurately measure ND parameters (found tolerance 2-5%).