Navigation

Inhalt Hotkeys

Bildverstehen

Computer Vision - Image Understanding - Bildverstehen

Wintersemester 2018

Vorlesung: Donnerstag, 11:30 - 13:00, B006, (Dr. J. Vitay)
Übung: Montag, 19:00 - 20:30, 1/B202, (A. Al Ali)
Übung: Dienstag, 11:30 - 13:00, 1/B202, (A. Al Ali)

General Information

Prerequisites: Modules in Mathematics I to IV, basic knowledge in Python.

Exam: written examination (90 minutes), 5 credit points.

Contact: julien dot vitay at informatik dot tu-chemnitz dot de.

Language: English. The written exam can of course be done in German.

Content

The course is an introduction to computer vision, from basic image processing (filters, Fourier transformation) to more advanced algorithms (object recognition, movement, facial features extraction).

  1. Introduction
  2. Image formation
  3. Image processing
  4. Geometric transformations
  5. Feature detection and matching
  6. Segmentation
  7. Motion, optical flow
  8. Stereovision

The exercises are made on computers using the OpenCV computer vision library with the Python bindings.

References

The course is based primarily on the textbook by Richard Szeliski:

Richard Szeliski (2010). Computer Vision: Algorithms and Applications. Springer.

A free online draft is available at szeliski.org/Book/

The online book by Simon Prince, Computer vision: models, learning and inference (available at computervisionmodels.com) might also be helpful.

For German-speaking students, the book "Bildanalyse" by my predecessor Dr. Johannes Steinmueller will be very helpful.



FAQ

  • How do I register for the course?
    You don't. There is no OPAL or anything, just show up to the lectures/exercises and register for the exam in December.
  • How do I register for the exam?
    Registration on SBService happens in December. Only registered students can participate to the exam.
  • I cannot assist to the exercises. Can I take the exam anyway?
    Yes. The exercises are there to help you understand the concepts seen in the lectures and get practical experience with computer vision tools. But they are not obligatory for the exam.
  • Do I have to memorize all these equations?
    No, but to understand them, which is basically the same.

Slides for the lectures

Chapter 01 - Introduction (pdf)
Chapter 02 - Image Formation (pdf)
Chapter 03 - Image processing (pdf)
Chapter 04 - Geometric transformations (pdf)

Exercises

To use Jupyter notebooks in the B202, follow these guidelines (pdf).

Exercise 01 - Introduction to Python and NumPy. (1-1-pdf , 1-1-nb , 1-1-solution , 1-2-pdf , 1-2-nb , 1-2-solution )
Exercise 02 - Basic image processing. (exercise-2 , solution )
Exercise 03 - Linear Filtering. (exercise-3 , solution )
Exercise 04 - Edge detection. (exercise-4 , solution )
Exercise 05 - Fourier transforms. (exercise-5 )
Exercise 06 - Face Swapping. (exercise-6)

Presseartikel

  • Neurologisch vernetzt

    Das Smart Start-Programm ermöglicht Masterstudenten ab September einen Einblick in Labore in ganz Deutschland – Auch TU-Student Alex Schwarz profitiert davon …

  • Roboter als soziale Wesen – wie passt das zusammen?

    Andreas Bischof von der Professur Medienkommunikation verbrachte im Rahmen seines Dissertationsprojektes beim Graduiertenkolleg CrossWorlds einen dreimonatigen Forschungsaufenthalt in den USA …

  • Wissbegierige Schüler weiter auf Erfolgskurs

    Zwei von der TU betreute Gymnasiasten errangen am 29. März 2014 Fachgebietssiege beim sächsischen Landeswettbewerb "Jugend forscht" und lösten damit ihre Fahrkarten zum Bundesfinale …

  • 25 Jahre Wissen in allen Ausprägungen

    Philosophische Fakultät feiert am 24. Januar 2019 ihr 25-jähriges Bestehen – Festvortrag hält Literaturwissenschaftler Prof. Dr. Gerhard Lauer (Universität Basel) – Festwoche startet am 15. Januar …