Regularized motion estimation using robust entropic functionals

In this paper, regularized estimation of the displacement vector field (DVF) of a dynamic image sequence is considered. A new class of non-quadratic convex regularization functionals is employed to estimate the motion field in the presence of motion discontinuities and occlusions. The derivation of the functionals is based on entropy considerations and does not require parameter tuning as in previously proposed methods. This new class of functionals is both robust and convex making it possible to preserve motion boundaries and obtain a globally optimum solution. The performance of entropic functionals is compared to previously suggested functionals for motion estimation using real and synthetic image sequences.