Upper body joint angle measurements for physical rehabilitation using visual feedback

Abstract

In clinical rehabilitation, biofeedback increases patient’s motivation making it one of the most effective motor rehabilitation mechanisms. In this field, it is very helpful for the patient and even for the therapist to know the level of success and performance of the training process. New rehabilitation technologies allow new forms of therapy for patients with Range of Motion (ROM) disorders. The aim of this work is to introduce a simple biofeedback system in a clinical environment for ROM measurements, since there is currently a lack of practical and cost-efficient methods available for this purpose. The Microsoft KinectTM introduces the possibility of low cost, non intrusive human motion analysis in the rehabilitation field. In this paper we conduct a comparison study of the accuracy in the computation of ROM measurements between the KinectTMSkeleton Tracking provided by Microsoft and the proposed algorithm based on depth analysis. Experimental results showed that our algorithm is able to overcome the limitations of the Microsoft algorithm when the pose estimation is used as a measuring system making it a valuable rehabilitation tool.