Optical Flow Estimation with Prior Models Obtained from Phase Correlation

摘要

Motion estimation is one of the most important tasks in computer vision. One popular technique for computing dense motion fields consists in defining a large enough set of candidate motion vectors, and assigning one of such vectors to each pixel, so that a given cost function is minimized. In this work we propose a novel method for finding a small set of adequate candidates, making the minimization process computationally more efficient. Based on this method, we present algorithms for the estimation of dense optical flow using two minimization approaches: one based on a classic block-matching procedure, and another one based on entropy-controlled quadratic Markov measure fields which allow one to obtain smooth motion fields. Finally, we present the results obtained from the application of these algorithms to examples taken from the Middlebury database.