2008 | OriginalPaper | Buchkapitel
An Unbiased Second-Order Prior for High-Accuracy Motion Estimation
verfasst von : Werner Trobin, Thomas Pock, Daniel Cremers, Horst Bischof
Erschienen in: Pattern Recognition
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly textured areas. We propose a novel regularization approach, based on decorrelated second-order derivatives, that does not suffer from this shortcoming. We then derive an efficient numerical scheme to solve the new model using projected gradient descent. A comparison to a TV regularized model shows that the proposed second-order prior exhibits superior performance, in particular in low-textured areas (where the prior becomes important). Finally, we show that the proposed model yields state-of-the-art results on the Middlebury optical flow database.