Informationen für
Logo VIS

« Zurück

Computer Vision (auf Englisch)
Typ: Hauptstudium / Vertiefungslinie
Semester: WS 2015/2016
Umfang: 3V+1Ü
Studiengang: Diplom Informatik, Diplom Softwaretechnik, Master Informatik, Master Softwaretechnik, International Master in Computer Science - Studienprofil AUT, International Master in Computer Science - Studienprofil STE, International Master in Computer Science - Studienprofil VC
Dozent: Prof. Dr.-Ing. Andrés Bruhn


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 the 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, master or diploma thesis in our group.



    The first lecture will be on Thursday,  October 15th.
    Bi-weekly tutorials are moved from Friday to Thursday.



Lecture Notes:

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

PART 1 : Features and Descriptors

X • Lecture 01 X (15.10.2015) X Introduction
  • Lecture 02   (16.10.2015)   Features and Descriptors I: Linear Diffusion, Scale Space
  • Assignment 00   (22.10.2015)    
  • Lecture 03   (23.10.2015)   Features and Descriptors II: Image Pyramids, Edges and Corners
  • Lecture 04   (29.10.2015)   Features and Descriptors III: Hough Transform, Invariants
  • Lecture 05   (30.10.2015)   Features and Descriptors IV: Texture Analysis
  • Assignment 01   (05.11.2015)    
  • Lecture 06   (06.11.2015)   Features and Descriptors V: Scale Invariant Feature Transform


PART 2 : Motion and Stereo

X • Lecture 07 X (12.11.2015) X Image Sequence Analysis I: Local Methods
  • Lecture 08   (13.11.2015)   Image Sequence Analysis II: Motion Models, Tracking, Feature Matching
  • Assignment 02   (19.11.2015)    
  • Lecture 09   (20.11.2015)   Image Sequence Analysis III: Variational Methods
  • Lecture 10
  (26.11.2015)   3-D Reconstruction I: Camera Geometry
  • Lecture 11
  (27.11.2015)   3-D Reconstruction II: Epipolar Geometry, Stereo Matching
  • Assignment 03   (03.12.2015)    
  • Lecture 12
  (04.12.2015)   3-D Reconstruction III: Shape-from-Shading


PART 3 : Segmentation

X • Lecture 13
X (10.12.2015) X Foundations I: Isotropic Nonlinear Diffusion
  • Lecture 14   (11.12.2015)   Foundations II: Anisotropic Nonlinear Diffusion
  • Lecture 15
  (17.12.2015)   Segmentation I: The Mumford/Shah Model
  • Assignment 04   (18.12.2015)    
  • No Lecture
  (24.12.2015)   Christmas Holidays
  • No Lecture
  (25.12.2015)   Christmas Holidays
  • No Lecture
  (31.12.2015)   Christmas Holidays
  • No Lecture
  (01.01.2016)   Christmas Holidays
  • Lecture 16
  (07.01.2016)   Segmentation II: Continuous Scaled Morphology, Shock Filters
  • Lecture 17
  (08.01.2016)   Segmentation III: Mean Curvature Motion
  • Assignment 05   (14.01.2016)    
  • Lecture 18
  (15.01.2016)   Segmentation IV: Self-Snakes, Active Contours


PART 4: Pattern Recognition

X • Lecture 19
X (21.01.2016) X Pattern Recognition I: Basics, Terminology
  • Lecture 20   (22.01.2016)   Pattern Recognition II: Bayes Decision Theory
  • Assignment 06   (28.01.2016)    
  • Lecture 21
  (29.01.2016)   Pattern Recognition III: Parametric Techniques, Density Estimation
  • Lecture 22
  (04.02.2016)   Pattern Recognition IV: Non-Parametric Techniques
  • Lecture 23
  (05.02.2016)   Pattern Recognition V: Dimensionality Reduction, Outlook



X • Math Sheet
X (issued 16.10.2015, no correction)
  • Assignment 01   (issued 30.10.2015, submission 05.11.2015)
  • Assignment 02
  (issued 13.11.2015, submission 19.11.2015)
  Assignment 03   (issued 27.11.2015, submission 03.12.2015)
  Assignment 04   (issued 11.12.2015, submission 18.12.2015)
  Assignment 05   (issued 08.01.2016, submission 14.01.2016)
  Assignment 06   (issued 22.01.2016, submission 28.01.2016)




  • 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.
  • At some points 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");


Link zum LSF Online Portal:

Computer Vision

Übungen Computer Vision


Face reconstruction from a stereo pair.
Bild 1: Face reconstruction from a stereo pair.
Segmentation of a zebra and a frog.
Bild 2: Segmentation of a zebra and a frog.
Termine: Freitag, 9:45 - 11:15 Uhr in V38.04
Donnerstag, 15:45 - 17:15 Uhr (14-tägig) in V38.02
Übungen: Donnerstag, 15:45 - 17:15 Uhr (14-tägig) in V38.02
Tutor: Dipl.-Math. Sebastian Volz
Daniel Maurer M. Sc.

« Zurück