Correspondence problems are one of the key problems in computer vision.
They appear for example in motion analysis, image matching, or stereo vision.
The goal is to assign structures in one image to structures in a second image,
in a way that corresponding structures are as similar as possible.
For this, some property of the pixels has to be assumed to stay
constant.
In general the solutions of correspondence problems are nonunique. As everybody can imagine
there are several possibilities to match structures. To deal with this problem
additional smoothness assumptions have to be applied, which can considerably
affect the outcome. For more information see our
research
page.
The goal of the seminar is to give an introduction to actual solutions of correspondence problems in the areas of motion analysis, image matching and stereo vision. To this end selected work from the literature will be presented and discussed.
Date |
Name |
Title of the
Talk |
June 1 |
Petra Gentes |
Determing Optical Flow |
June 1 |
Karsten Lehmann |
An iterative image registration
technique with an applicaton to stereo vision |
June 8 |
Martin Burger |
Lukas/Kanade meets Horn/Schunck: Combining local and global optical flow methods |
June 8 |
Achim Borgmeister |
Nonlinear matrix diffusion for
optic flow estimation |
June 16 |
Ravinder Idarapu |
An Investiagation of Smoothness
Constraints for Estimation of Displacement Vector Fields from Image Sequences |
June 22 |
Natalia Slesareva |
Numerical Methods for Image
Registration: Principle Axed-based Registration |
June 22 |
Jens Rieskamp |
Image Matching as a diffusion
process: an analogy with Maxwell's demons |
June 22 |
Christian Erbelding |
Multi-Modal Volume Registration by Maximization of Mutual Information |
June 29 |
Micheal Eismann |
A theoratical framework for
convex regularizers in PDE-based computation of image motion |
July 6 |
Antje Mundt |
Performance of optical flow
techniques |