Informationen für
Logo VIS

« Zurück

Correspondence Problems in Computer Vision
Typ: Hauptstudium / Vertiefungslinie
Semester: SS 2013
Umfang: 2V+2Ü
Studiengang: Diplom Informatik, Diplom Softwaretechnik, Master Informatik, Master Softwaretechnik
Dozent: Prof. Dr.-Ing. Andrés Bruhn
Beschreibung:

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 diploma or master thesis in the CVIS group in the field of computer vision.

 

NEWS:

  • The lecture on Thursday 16.05 and the tutorial on Friday 17.05. are swapped,
    i.e. the tutorial takes place on Thursday, while the lecture will be given on Friday.

 

Lecture Notes:

  1. Introduction, Overview (11.04.2013)
  2. Block Matching, Correlation Methods, Occlusion Detection, Interest Points, Feature-based Methods (18.04.2013)
  3. Optic Flow I: Local Differential Methods, Parametrisation Models (25.04.2013)
  4. Optic Flow II: Global Differential Methods, Horn and Schunck (02.05.2013)
  5. Optic Flow III: Advanced Constancy Assumptions, Large Motion (10.05.2013)
  6. Optic Flow IV: Advanced Data and Smoothness Terms (17.05.2013)
  7. Optic Flow V: High Accuracy Methods (06.06.2013)
  8. Optic Flow VI: Advanced Numerics (13.06.2013)
  9. Stereo Matching I: Projective and Epipolar Geometry (20.06.2013)
  10. Stereo Matching II: Estimation of the Fundamental Matrix (21.06.2013)
  11. Optic Flow + Stereo: Scene Flow Estimation (27.06.2013)
  12. Medical Image Registration: Mutual Information, Elastic and Curvature-Based Regularisation, Landmarks (04.07.2013)
  13. Particle Image Velocimetry: Div-Curl-Regularisation, Incompressible Navier Stokes Prior  (11.07.2013)
  14. Summary and Outlook (18.07.2013)

 

 

Tutorials:

Assignment Sheets

  1. Assignment 2   (19.04.2013)
  2. Assignment 3   (26.04.2013)
  3. Assignment 4   (03.05.2013)
  4. Assignment 5   (16.05.2013)
  5. Assignment 6   (31.05.2013)
  6. Assignment 7   (07.06.2013)
  7. Assignment 8   (14.06.2013)
  8. Assignment 9   (28.06.2013)
  9. Assignment 10 (05.07.2013)
  10. Assignment 11 (12.07.2013)
  11. Assignment 12 (19.07.2013)

 

Material for Programming Assignments

  1. Assignment 2   (19.04.2013)
  2. Assignment 4   (03.05.2013)
  3. Assignment 6   (31.05.2013)
  4. Assignment 8   (14.06.2013)
  5. Assignment 10 (05.07.2013)
  6. Assignment 12 (19.07.2013)

 

Example Solutions

  1. Assignment 2   (19.04.2013)
  2. Assignment 3   (26.04.2013)
  3. Assignment 4   (03.05.2013)
  4. Assignment 5   (17.05.2013)
  5. Assignment 6   (31.05.2013)
  6. Assignment 7   (07.06.2013)
  7. Assignment 8   (14.06.2013)
  8. Assignment 9   (28.06.2013)
  9. Assignment 10 (05.07.2013)
  10. Assignment 11 (12.07.2013)
  11. Assignment 12 (19.07.2013)


Bilder:
Internet-Seite:
Termine: Donnerstag, 9:45 - 11:15 Uhr in 0.363
Übungen: Freitag, 11:30 - 13:00 Uhr in 0.363
Tutor: Dipl.-Math. Sebastian Volz

« Zurück