Computer Vision 1

Benjamin Guthier, Holger Heidrich, Winter semester 2017/2018

Computer vision is a science that develops models and methods for understanding, analysing, acquiring and processing images, and more generally high-dimensional “visual” data. Computer vision is a discipline which makes use of many other fields such as discrete optimization, machine learning, human-computer interaction and computer graphics. We offer two courses in computer vision: Computer Vision 1 runs every winter semester, and Computer Vision 2 every summer semester. Computer Vision 1 considers predominantly the basic aspects of computer vision, such as image processing fundamentals and interest point detection. We use these methods in applications like the generation of panoramic images, the recognition of gestures in depth images and high dynamic range imaging. Computer Vision 2 will take a closer look at more advanced aspects of computer vision. Here we will discuss topics such as tracking, face recognition and 3D reconstruction. Both courses focus on algorithms, modelling and applications. In contrast to this, the courses in machine learning focus more on theoretical aspects of inference and learning from data.


Lectures: Tuesday, 1. DS, 07:30 – 09:00 Uhr, INF E023, Start: 10. October 2017.

Practice: Tuesday, 2. DS, 9:20 – 10:50 Uhr, room: E046
15.11.2017 – Not offered any more: Tuesday, 4. DS, 13:00 – 14:30 Uhr, room: E046

Prerequisites: good knowledge of math (linear algebra, optimization), programming (C++).

Credits: 2/2/0, oral exam

Enrollment: jExam

Attendees: max. 60

Note: Lectures are held in English or German (if understood by all) with slides in English. The course is based on the book: “Computer Vision: Algorithms and Applications” by Richard Szeliski which can also be found online:; This course is a prerequisite for the course “Computer Vision II” in SS’18.

Info about the oral exam: The oral exam is mainly focused on the lectures. You may also be asked questions about the exercises.


15.11.2017 – Not offered any more: Tuesday, 4. DS, 13:00 – 14:30 Uhr, room: E046

10.10.2017: Could not get a place in jExam? Don’t worry: the only reason is, that the number of computers is limited in the class room. So come to the exercise with your laptop. (And preinstall OpenCV in debug mode.) Please enroll in jExam as waiting or for the lecture in that case, so that we have your contact data.


Lectures: (slides available around time of lecture)
Chapter 1: Introduction
Chapter 2: Image Processing
Chapter 3: Feature Detection
Chapter 4: Feature Matching
Chapter 5: Stereo Vision

Code Examples from the lecture
(Harris corner detector and Canny)


Exercise 1: 10.10.: Set up your OpenCV environment and program a simple image manipulation, Slides, QtCreator Project File, Solution Example.

Exercise 2: 24.10.: Solarisation. (deadline: 01.11.2017)

Exercise 3: 24.10.: Orientation Histograms and main direction in images. Example images: lines1, lines2, keyb7 (deadline: 13.11.2017)

Exercise 4: 14.11.: sampling theorem and correct filtering. (deadline: 27.11.2017)

Exercise 5: 28.11.: features. (deadline: 11.12.2017)

Exercise 6: 12.12.: matching. (deadline: 08.01.2018)