Saarland University | Mathematical Image Analysis Group
Summer Term 2004

Seminar on Correspondence Problems in Computer Vision

Prof. Joachim Weickert, Dr. Bernhard Burgeth, Nils Papenberg

(Building 27.1, Room 412, Phone 0681-302-64378)


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


Nils Papenberg / June 30, 2004 / back to MIA home.
The author is not responsible for the content of external pages.
Imprint - Data protection