Robust optical flow estimation

In this paper a new robust estimator of the optical flow field is shown. Arising from the techniques based on the OFC (optical flow constraint), we develop an estimation that takes several measures around a given pixel and discards the erroneous ones, using a voting schema. In this way, velocities that have more accumulated votes are taken as the correct ones. A preliminary comparison with other well known techniques is shown, and clearly our approach performs quite better even in the cases where two or more movements are present in the analyzed pixels