Zimmer, Henning Lars
[Author]
;
Weickert, Joachim
[Contributor]
Correspondence problems in computer vision : novel models, numerics, and applications ; Korrespondenzprobleme im Maschinellen Sehen : neue Modelle, Numerik und Anwendungen
You can manage bookmarks using lists, please log in to your user account for this.
Media type:
Electronic Thesis;
E-Book;
Doctoral Thesis
Title:
Correspondence problems in computer vision : novel models, numerics, and applications ; Korrespondenzprobleme im Maschinellen Sehen : neue Modelle, Numerik und Anwendungen
Contributor:
Zimmer, Henning Lars
[Author]
imprint:
Scientific publications of the Saarland University (UdS), 2011
Footnote:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Description:
Correspondence problems like optic flow belong to the fundamental problems in computer vision. Here, one aims at finding correspondences between the pixels in two (or more) images. The correspondences are described by a displacement vector field that is often found by minimising an energy (cost) function. In this thesis, we present several contributions to the energy-based solution of correspondence problems: (i) We start by developing a robust data term with a high degree of invariance under illumination changes. Then, we design an anisotropic smoothness term that works complementary to the data term, thereby avoiding undesirable interference. Additionally, we propose a simple method for determining the optimal balance between the two terms. (ii) When discretising image derivatives that occur in our continuous models, we show that adapting one-sided upwind discretisations from the field of hyperbolic differential equations can be beneficial. To ensure a fast solution of the nonlinear system of equations that arises when minimising the energy, we use the recent fast explicit diffusion (FED) solver in an explicit gradient descent scheme. (iii) Finally, we present a novel application of modern optic flow methods where we align exposure series used in high dynamic range (HDR) imaging. Furthermore, we show how the alignment information can be used in a joint super-resolution and HDR method. ; Korrespondenzprobleme wie der optische Fluß, gehören zu den fundamentalen Problemen im Bereich des maschinellen Sehens (Computer Vision). Hierbei ist das Ziel, Korrespondenzen zwischen den Pixeln in zwei (oder mehreren) Bildern zu finden. Die Korrespondenzen werden durch ein Verschiebungsvektorfeld beschrieben, welches oft durch Minimierung einer Energiefunktion (Kostenfunktion) gefunden wird. In dieser Arbeit stellen wir mehrere Beiträge zur energiebasierten Lösung von Korrespondenzproblemen vor: (i) Wir beginnen mit der Entwicklung eines robusten Datenterms, der ein hohes Maß an Invarianz unter Beleuchtungsänderungen ...