Data fusion of multiple kinect sensors for a rehabilitation system

Kinect-like depth sensors have been widely used in rehabilitation systems. However, single depth sensor processes limb-blocking, data loss or data error poorly, making it less reliable. This paper focus on using two Kinect sensors and data fusion method to solve these problems. First, two Kinect sensors capture the motion data of the healthy arm of the hemiplegic patient; Second, merge the data using the method of Set-Membership-Filter (SMF); Then, mirror this motion data by the Middle-Plane; In the end, control the wearable robotic arm driving the patient's paralytic arm so that the patient can interactively and initiatively complete a variety of recovery actions prompted by computer with 3D animation games.

I. Introduction

Physical disability is a big challenge in today's society. Because of the lack of therapist and the rising costs of health care, etc., more and more people cannot get timely rehabilitation and become permanently disabled. In addition, the traditional treatment is that the therapist assists the patient to do a variety of actions repeatedly to restore limb functionality. Patient cooperates with the therapist passively, lack of enthusiasm and initiative of participation. Studies have shown that, compared to the traditional treatment, interactive and initiative rehabilitation treatment restore limb functionality more effectively [1].