Lecture and Exercises: Correspondence Problems in Computer Vision

Lecturer: Prof. Andres Bruhn
Coordinator of Tutorials: Andres Bruhn

Winter Term 2019 / 2020
Lecture with Exercises (2+2SWS)
Language: English

Lecture: Thursday, 15:45 - 17:15, Computer Science Building, Seminar Room 0.108.
Theoretical Exercises: Friday, 11:30 - 13:00, Computer Science Building, Lecture Hall V38.02 (bi-weekly).
Programming Exercises: Friday, 11:30 - 13:00, Computer Science Building, VISGS Pool 0.452 (bi-weekly).

Correspondence problems are a central topic in computer vision. The basic task amounts to identifying and matching corresponding features in different images or views of the same scene. Typical examples for correspondence problems are (i) the estimation of motion information from consecutive frames of an image sequence (optic flow), (ii) the reconstruction of a 3-D scene from a stereo image pair, (iii) the registration of medical image data from different image acquisition devices (e.g. CT and MRT), and (iv) the analysis of the motion of fluid flows. The central part of this lecture is concerned with discussing the most important types of correspondence problems together with suitable models and algorithms for solving them.

This class requires undergraduate knowledge in mathematics ("e.g. Mathematik für Informatiker und Softwaretechniker"). Knowledge in image processing or computer vision is useful as well. Also basic knowledge in artificial intelligence can be helpful. The lectures will be given in English.

This class is particularly suited for those students who wish to pursue a master thesis in the CVIS group in the field of computer vision.

All course material (lecture notes, assignments, code, example solutions) are available in the ILIAS system.

Lecture 01 17.10.2019 Introduction, Overview
No Assignment 18.10.2018 cancelled
Lecture 02 24.10.2019 Block Matching, Correlation Methods, Interest Points
Assignment 01 25.10.2019 Programming
No Lecture 31.10.2019 cancelled
No Assignment 01.11.2019 Public Holiday: All Saints
Lecture 03 07.11.2019 Optic Flow I: Local Differential Methods, Parametrisation Models
Assignment 02 08.11.2019 Theory
Lecture 04 14.11.2019 Optic Flow II: Global Differential Methods, Horn and Schunck
Assignment 03 15.11.2019 Programming
Lecture 05 21.11.2019 Optic Flow III: Advanced Constancy Assumptions, Large Motion
Assignment 04 22.11.2019 Theory
Lecture 06 28.11.2019 Optic Flow IV: Advanced Data and Smoothness Terms
Assignment 05 29.11.2019 Programming
Lecture 07 05.12.2019 Optic Flow V: High Accuracy Methods
No Assignment 06.12.2019 cancelled
Lecture 08 12.12.2019 Optic Flow VI: Advanced Numerics
Assignment 06 13.12.2019 Theory
No Lecture 19.12.2019 cancelled
No Assignment 20.12.2019 cancelled
No Lecture 26.12.2019 Christmas Holidays
No Assignment 27.12.2019 Christmas Holidays
No Lecture 02.01.2020 Christmas Holidays
No Assignment 03.01.2020 Christmas Holidays
Lecture 09 09.01.2020 Stereo Matching I: Projective and Epipolar Geometry
Assignment 07 10.01.2020 Programming
Lecture 10 16.01.2020 Stereo Matching II: Estimation of the Fundamental Matrix
Assignment 08 17.01.2020 Theory
Lecture 11 23.01.2020 Optic Flow + Stereo: Scene Flow Estimation
Assignment 09 24.01.2020 Programming
Lecture 12 30.01.2020 Medical Image Registration
Assignment 10 31.01.2020 Theory
Lecture 13 06.02.2020 Particle Image Velocimetry
Assignment 11 07.02.2020 Programming

 

Assignment 01 issued 18.10.2019 tutorial 25.10.2019
Assignment 02 issued 01.11.2019 tutorial 08.11.2019
Assignment 03 issued 08.11.2019 tutorial 15.11.2019
Assignment 04 issued 15.11.2019 tutorial 22.11.2019
Assignment 05 issued 22.11.2019 tutorial 29.11.2019
Assignment 06 issued 06.12.2019 tutorial 13.12.2019
Assignment 07 issued 03.01.2020 tutorial 10.01.2020
Assignment 08 issued 10.01.2020 tutorial 17.01.2020
Assignment 09 issued 17.01.2020 tutorial 24.01.2020
Assignment 10 issued 24.01.2020 tutorial 31.01.2020
Assignment 11 issued 31.01.2020 tutorial 07.02.2020

Link to "Correspondence Problems in Computer Vision" in the Campus system (Lecture)
Link to "Correspondence Problems in Computer Vision" in the Campus system (Exercise)
Link to "Correspondence Problems in Computer Vision" in ILIAS

Zum Seitenanfang