A 3D Visual Tracking Method for Rehabilitation Path Planning

Rehabilitation devices are designed applying techniques that can determine the adaptability level of the patient using different type of exercises. It is important for the rehabilitation therapy applications to reproduce the exercise made by the therapist for a good recovery of the patient's motor functions. Thus, it is essential to track and use these tasks to design a path planning for controlling rehabilitation devices. In this paper, a 3D vision tracking method is presented. This method allows to track a medical ball also in poorly-lighted and not structured environments through images captured by a camera in combination with a depth sensor, obtaining the 3D Point Cloud of the centroid as result. The Point Cloud is then fitted to a curve to give a reference trajectory to reproduce the exercise.