Home Monitoring Musculo-skeletal Disorders with a Single 3D Sensor

Ruizhe Wang, Gerard Medioni, Carolee J. Winstein, Cesar Blanco; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2013, pp. 521-528

Abstract


We address the problem of automated quantitative evaluation of musculo-skeletal disorders using a 3D sensor. This enables a non-invasive home monitoring system which extracts and analyzes the subject's motion symptoms and provides clinical feedback. The subject is asked to perform several clinically validated standardized tests (e.g. sit-to-stand, repeated several times) in front of a 3D sensor to generate a sequence of skeletons (i.e. locations of 3D joints). While the complete sequence consists of multiple repeated Skeletal Action Units (SAU) (e.g. sit-to-stand, one repetition), we generate a single robust Representative Skeletal Action Unit (RSAU) which encodes the subject's most consistent spatio-temporal motion pattern. Based on the Representative Skeletal Action Unit (RSAU) we extract a series of clinical measurements (e.g. step size, swing level of hand) which are crucial for prescription and rehabilitation plan design. In this paper, we propose a Temporal Alignment Spatial Summarization (TASS) method to decouple the complex spatio-temporal information of multiple Skeletal Action Units (SAU). Experimental results from people with Parkinson's Disease (PD) and people without Parkinson's Disease (non-PD) demonstrate the effectiveness of our methodology which opens the way for many related applications.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2013_CVPR_Workshops,
author = {Wang, Ruizhe and Medioni, Gerard and Winstein, Carolee J. and Blanco, Cesar},
title = {Home Monitoring Musculo-skeletal Disorders with a Single 3D Sensor},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2013}
}