Lecture and Exercises: Computer Vision

Lecturer: Prof. Andres Bruhn
Coordinator of Tutorials: Michael Stoll, Azin Jahedi, Jenny Schmalfuss

Winter Term 2019 / 2020
Lecture with Exercises (3+1SWS)
Language: English

Lecture: Wednesday, 11:30 - 13:00, Computer Science Building, Lecture Hall V38.03.
Lecture: Friday, 9:45 - 11:15, Computer Science Building, Lecture Hall V38.03 (bi-weekly).
Exercises: Friday, 9:45 - 11:15, Computer Science Building, Lecture Hall V38.03 (bi-weekly).

NEWS: Change of lecture hall: The lecture on Wednesday, November 13 takes place in room V57.06 (Pfaffenwaldring 57). The time slot (11:30 - 13:00) remains the same.

This class gives an in-depth introduction into the field of computer vision. It consists of four parts. In the first part, characteristic image features and feature descriptors are discussed that are typically used for recognition or matching, The second part of the course is dedicated to motion and stereo. Fundamental goals in this context are the recovery of the 3-D structure and the 2-D motion of objects from a recorded scene. The third part of the class is dedicated to segmentation - the subdivision of an image into different semantically meaningful regions. Here, the focus lies on contour based methods that are among the leading techniques in the field. Finally, the fourth part deals with pattern recognition the classification of features into different groups. In this context, basic approaches for reducing the dimensionality of features and strategies for supervised learning are discussed.

This class requires undergraduate knowledge in mathematics (e.g. ''Mathematik für Informatiker und Softwaretechniker", "Numerische und stochastische Grundlagen der Informatik"). The previous attendance of the class "Imaging Science" is recommended. Lectures will be in English.

This class is particularly useful for those students who wish to pursue a bachelor or master thesis in our group.

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

Part 1: Features and Descriptors

Lecture 01 16.10.2019 Introduction
Lecture 02 18.10.2019 Features and Descriptors I: Linear Diffusion,  Scale Space
Lecture 03 23.10.2019 Features and Descriptors II: Image Pyramids,  Edges and Corners
Lecture 04 25.10.2019 Features and Descriptors III: Hough Transform, Invariants
Lecture 05 30.10.2019 Features and Descriptors IV: Texture Analysis
No Lecture 01.11.2019 Public Holiday: All Saints
Lecture 06 07.11.2019 Features and Descriptors V: Scale Invariant  Feature Transform
Exercise 01 02.11.2019  


Part 2: Motion and Stereo
Lecture 07 13.11.2019 Image Sequence Analysis I: Local Methods
Lecture 08 15.11.2019 Image Sequence Analysis II: Motion Models, Tracking
Lecture 09 20.11.2019 Image Sequence Analysis III: Variational Methods
Exercise 02 22.11.2019  
Lecture 10 27.11.2019 3-D Reconstruction I: Camera Geometry
Lecture 11 29.11.2019 3-D Reconstruction II: Epipolar Geometry, Stereo Matching
Lecture 12 04.12.2019 3-D Reconstruction III: Shape-from-Shading
Exercise 03 06.11.2019  

Part 3: Segmentation
Lecture 13 11.12.2019 Foundations I: Isotropic Nonlinear Diffusion
Lecture 14 13.12.2019 Foundations II: Anisotropic Nonlinear Diffusion
Lecture 15 18.12.2019 Segmentation I: The Mumford/Shah Mode
Exercise 04 20.12.2019  
No Lecture 25.12.2019 Christmas Holidays
No Lecture 27.12.2019 Christmas Holidays
No Lecture 01.01.2020 Christmas Holidays
No Lecture 03.01.2020 Christmas Holidays
Lecture 16 08.01.2020 Segmentation II: Continuous Scaled Morphology,  Shock Filters
Lecture 17 10.01.2020 Segmentation III: Mean Curvature Motion
Lecture 18 15.01.2020 Segmentation IV: Self-Snakes, Active Contours
Exercise 05 17.01.2020  


Part 4: Pattern recognition
Lecture 19 22.01.2020 Pattern Recognition I: Basics, Terminology
Lecture 20 24.01.2020 Pattern Recognition II: Bayes Decision Theory
Lecture 21 29.01.2020 Pattern Recognition III: Parametric Techniques, Density Estimation
Exercise 06 31.01.2020  
Lecture 22 04.02.2020 Pattern Recognition IV: Non-Parametric Techniques
Lecture 23 07.02.2020 Pattern Recognition V: Dimensionality Reduction, Outlook
Math Sheet issued 16.10.2019 no grading
Programming Sheet issued 16.10.2019 no grading
Exercise 01 issued 01.11.2019 submission 08.11.2019
Exercise 02 issued 15.11.2019 submission 22.11.2019
Exercise 03 issued 29.11.2019 submission 06.12.2019
Exercise 04 issued 13.12.2019 submission 20.12.2019
Exercise 05 issued 10.01.2020 submission 17.01.2020
Exercise 06 issued 24.01.2020 submission 31.01.2020


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

  • The programming exercises are designed for Linux. We only guarantee that the code works under Linux.
  • If possible, we will provide executables for Windows. You may use them at your own risk.
  • Sometimes we may have to provide object files for copyright reasons. Object files will only be provided for Linux.
  • If there are any problems reading in and writing out files under Windows, adding the binary flag may help, i.e. inimage = fopen(in,"rb");
Zum Seitenanfang