Lectures
Imaging Science
This lecture teaches the basics of representation and processing of digital images. On the one hand, it should be learned how typical disturbances such as noise or blur can be removed from images without destroying the information important for further processing. On the other hand, it should be learned how exactly this important information in the form of edges, corners or segments can be extracted so that it can then be (more easily) interpreted by a human being or another computer. The algorithms discussed in this lecture are applied in a number of interesting areas. These include medical image processing and diagnostics, computer-aided quality analysis, navigation of autonomous vehicles (robots, cars), computer graphics, signal processing and artificial intelligence.
The first part of the lecture discusses image acquisition and the typical image disturbances associated with it. Then, suitable image representations are discussed, which allow an easier elimination of exactly these disturbances (Fourier/DCT/Wavelets). Compression and interpolation of images is also discussed so that images can be efficiently saved (JPG) and transformed as desired (e.g. scaling, rotation, distortion).
The second part of the lecture then deals with elementary algorithms for image analysis. These allow, among other things, to improve contrast, to find characteristic features such as corners or edges, to extract certain structures, to remove noise and blur, and to divide the image into semantically significant regions or segments.
Computer Vision
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.
Correspondence Problems in Computer Vision
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 master thesis in the CV group in the field of computer vision.
Teaching Activities
2023 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Colloquium: Computer Vision
Seminar (2 h)
2022 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision
Seminar (2 h)
2021 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Colloquium: Computer Vision
Seminar (2 h)
2021 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2020 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2020 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2019 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2019 - Summer Term
- Datenstrukturen und Algorithmen
Lectures (4 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2018 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2018 - Summer Term
- Datenstrukturen und Algorithmen
Lectures (4 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2017 - Winter Term
- Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2017 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2016 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Data Structures and Algorithms (INFOTECH)
Lectures (2 h) with theoretical and programming exercises (1 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2016 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2015 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Data Structures and Algorithms (INFOTECH)
Lectures (2 h) with theoretical and programming exercises (1 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2015 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2014 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Data Structures and Algorithms (INFOTECH)
Lectures (2 h) with theoretical and programming exercises (1 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2014 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2013 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Grundlagen der künstlichen Intelligenz
Lectures (3 h) with theoretical and programming exercises (1 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2013 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h) - Main Seminar: Recent Advances in Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2012 - Winter Term
- Computer Vision
Lectures (3 h) with theoretical and programming exercises (1 h) - Grundlagen der künstlichen Intelligenz
Lectures (3 h) with theoretical and programming exercises (1 h) - Seminar: Bildverarbeitung und Computer Vision
Seminar (2 h) - Colloquium: Computer Vision and Intelligent Systems
Seminar (2 h)
2012 - Summer Term
- Correspondence Problems in Computer Vision
Lectures (2 h) with theoretical and programming exercises (2 h) - Imaging Science
Lectures (3 h) with theoretical and programming exercises (1 h)