A computer vision based system for a rehabilitation of a human hand

Paper presents a rehabilitation system for patients who suff er from arm or wrist injury or similar. The idea of the rehabilitation using computer and additional hardware is not new, but our solution differs significantly. We tried to make it easily accessible and thus started with a limitation that only a personal computer and one standard web camera is required. Patient holds a simple object, cuboid, and moves it around. Camera records his movement while the software in real-time calculates position of the object in 3D space on the basis of color information and cuboid model. Object is then placed in the virtual 3D space, where another similar object is already present. The patient’s task is to move the real object in the position, which matches the position of the virtual object. Doing so the patient trains specific movements that speed up the recovery. Evaluation of the system shows that presented solution is suitable in cases where accuracy is not very critical and smaller 3D reconstruction deviations do not thwart the process of rehabilitation.