Correspondence Problems in Computer Vision
Dr. Andrés Bruhn
Office hours: Friday, 14:15 - 15:15.
Summer Term 2008
Lectures (2h) with programming/theoretical exercises (2h)
(6 credit points)
Lectures: Wednesday 14-16 c.t., Building E1.3, Lecture Hall 1
First lecture: Wednesday, April 16, 2008.
Tutorials: 2 hours each week, Thursday 16-18 c.t.
Turorials: Building E1.3, Lecture Hall 3 (theory)
Turorials: Building E2.4 (math building), Cip-Pool U009 (programming)
First tutorial: Thursday, April 24, 2008.
Planned Contents –
Example - Stereo Reconstruction
Example - Motion Estimation
Requires undergraduate knowledge in mathematics (e.g. ''Mathematik
für Informatiker I-III'') . Knowledge in image processing or differential
equations is useful. The lectures will be given
Correspondence problems are a central topic in computer vision. Thereby,
one is interested in identifying and matching corresponding
features in different images/views of the same scene. Typical corresondence
problems are the estimation of motion information from consecutive frames
of an image sequence (optic flow), the reconstruction of a 3-D scene from
a stereo image pair and the registration of medical image data from
different image acquisition devices (e.g. CT and MRT). Central
part of this lecture is the discussion of the most important correspondence
problems as well as the presentation of suitable algorithms for solving them.
This class is particularly useful for those students who wish to
to pursue a diploma or master thesis in our group in the field of
Block Matching, Correlation Techniques, Interest Points, Feature-Based Methods|
Optic Flow I: Local Differential Methods, Parameterisation Models|
Optic Flow II: Global Differential Methods, Horn and Schunck|
Optic Flow III: Advanced Constancy Assumptions, Large Motion|
Optic Flow IV: Advanced Data and Smoothness Terms|
Optic Flow V: High Accuracy Methods, Advanced Numerics|
Stereo Matching I: Projective and Epipolar Geometry|
Stereo Matching II: Estimation of the Fundamental Matrix|
Stereo Matching III: Correlation and Variational Methods, Graph Cuts|
Medical Image Registration: Mutual Information, Elastic and Curvature Based Registration, Landmarks|
Particle Image Velocimetry: Div-Curl-Regularisation, Incompressible Navier Stokes Prior|
Programming excercises and theoretical assignments are offered as part of the tutorials.
The regular attendence of these excercises is requirement for admission to
Depending on the numer of participants written or oral exams will take place.
The second chance exams is only available for those students who failed the first exam, or who did not take part in the first exam.
There is no specific book that covers the complete content of this class.
Many lectures will be based on articls from journals
and conferences. However, the following three books cover most
- Optic Flow
A. Bruhn: Variational Optic Flow Computation: Accurate Modeling and Efficient Numerics.
Ph.D. Thesis, 2006. Available from http://www.mia.uni-saarland.de/bruhn/PhDThesis.pdf
- Stereo Reconstruction
O. Faugeras and Q.-T. Luong:
The Geometry of Multiple Images.
MIT Press, 2001.
- Medical Image Registration
Numerical Methods for Image Registration.
Oxford Press, 2003.