Variational motion estimation in computer vision

Motion Estimation in Computer Vision: Optimization on Stiefel Manifolds

Motion recovery from image correspondences is typically a problem of optimizing an objective function associated with the epipolar (or LonguetHiggins) constraint. This objective function is defined on the so called essential manifold. In this paper, the intrinsic Riemannian structure of the essential manifold is thoroughly studied. Based on existing optimization techniques on Riemannian manifol...

Robust Parameter Estimation in Computer Vision

Estimation techniques in computer vision applications must estimate accurate model parameters despite small-scale noise in the data, occasional large-scale measurement errors (outliers), and measurements from multiple populations in the same data set. Increasingly, robust estimation techniques, some borrowed from the statistics literature and others described in the computer vision literature, ...

Hierarchical curvature estimation in computer vision

3d Shape Estimation in Computer Vision

3D shape estimation is an essential capability of human vision, which several computer vision processes try to emulate. The goal of this article is to present some of these processes, starting with very basic material, but also providing pointers to more recent and sophisticated approaches. We treat stereoscopy, structure from motion, shape from shading and photometric stereo – a choice of topi...

Variational fluid motion estimation with physical priors

In this thesis, techniques for Particle Image Velocimetry (PIV) and Particle Tracking Velocimetry (PTV) are developed that are based on variational methods. The basic idea is not to estimate displacement vectors locally and individually, but to estimate vector fields as a whole by minimizing a suitable functional defined over the entire image domain (which may be 2D or 3D and may also include t...