Addressing Occlusions in Upper Limb Kinematic Reconstruction

In this paper, we propose a new approach for human motion reconstruction based on Gaussian Mixture Probability Hypothesis Density (GM-PHD) Filter applied to human joint positions extracted from RGB-D camera. The results demonstrate that our approach outperforms the standard Kinect solution in occlusion scenarios and can be applied in robotics field. To evaluate the applicability of the approach, we employ it as interface to remotely control a drone.