Pose estimation algorithm for hand assessment

Patient performance assessment should be as much as possible precise and independent from the examiner subjective judgment in order to evaluate therapy efficacy in restoring impaired sensori-motor functions. In this paper, a method for continuously monitoring patient activity in order to correct wrong movements and to follow patient improvements is proposed. In particular, a novel low-cost method for hand pose estimation by using a monocular motion sensing device and a robust marker-based pose estimation approach based on the Unscented Kalman Filter is presented. The hand kinematics is used to enclose geometrical constraints in the estimation process. The approach is applied for evaluating some significant kinematic parameters necessary to understand human hand motor improvements during rehabilitation. In particular, the estimated performance indicators are joint positions, angles, Range of Motion (RoM) and trajectory for the fingers and position, orientation and velocity for the wrist.