3D Motion Tracking Based on Probabilistic Volumetric Reconstruction and Optical Flow

This paper proposes a method for motion tracking of objects without a pre-defined shape, the main aspect of this method is the use of a probabilistic volumetric reconstruction that incorporates motion information. First, a volumetric reconstruction of the objects of interest is obtained by the 3D Probabilistic Occupancy Grid method, which was recently proposed for to be applied in environments sensed by multiple cameras. Then, we originally propose to add Optical Flow information to this reconstruction. Next, a method similar to the Expectation-Maximization (EM) algorithm is used to identify and track the body parts of objects of interest. It was noted that the proposed information of velocity vector fields are a good option to improve the perception of motion in 3D reconstruction, providing the best results in the tracking.