zbMATH — the first resource for mathematics

On optical flow models for variational motion estimation. (English) Zbl 1406.49037
Bergounioux, Maïtine (ed.) et al., Variational methods. In imaging and geometric control. Berlin: De Gruyter (ISBN 978-3-11-043923-6/hbk; 978-3-11-043039-4/ebook; 978-3-11-043040-0/set). Radon Series on Computational and Applied Mathematics 18, 225-251 (2017).
Summary: The aim of this paper is to discuss and evaluate total variation based regularization methods for motion estimation, with particular focus on optical flow models. In addition to standard \(L^2\) and \(L^1\) data fidelities we give an overview of different variants of total variation regularization obtained from combination with higher order models and a unified computational optimization approach based on primal-dual methods. Moreover, we extend the models by Bregman iterations and provide an inverse problems perspective to the analysis of variational optical flow models.
A particular focus of the paper is the quantitative evaluation of motion estimation, which is a difficult and often underestimated task. We discuss several approaches for quality measures of motion estimation and apply them to compare the previously discussed regularization approaches.
For the entire collection see [Zbl 1398.49001].

49N45 Inverse problems in optimal control
35Q93 PDEs in connection with control and optimization
93C20 Control/observation systems governed by partial differential equations
68U10 Computing methodologies for image processing
Full Text: arXiv