Computer Vision and Deep Learning 2021/2022

Lecture /w Excercise

Mo. 11:00-13:00, Di. 13:00-15:00, G29-K059

Prof. Dr.-Ing. Klaus Tönnies

This course is limited to 24 students only. Since we expect many more applicants than places are available, students have to successfully pass an admission exam in order to be allowed to enrol in this course (multiple choice questions testing required background knowledge – you are not expected to know everything, no worries).

The admission exam will take place online on 12.10. within this Moodle course (access will be open all day: GMT+2). You will be automatically enrolled on 11.10. to participate in the admission exam, provided you have registered in LSF by the deadline (until 8.10.). Please make sure to participate during this time. There will be NO exceptions if you cannot manage to take part in the online exam.

An introduction to image processing:

W. Burger & M.J. Burge. Digital Image Processing – An Algorithmic Introduction Using JAVA. 2nd edition, Springer, 2016

Computer Vision deals with the extraction of information from images or image sequences comprising, e.g., object detection and classification, pose estimation, activity recognition, semantic segmentation and many others. It has found numerous applications in industry and research. Solutions for most of these computer vision tasks have been established many years ago but are nowadays carried out using deep neural networks. Within this course, we will briefly review important aspects of classical, mostly high level computer vision tasks and then explore the different network topologies that have been developed for end-to-end learning solutions. A background in basic image processing or computer vision is expected.

Lecture topics:

  1. Introduction
  2. Features from Images
  3. Working with Features
  4. Classification with Generative Models
  5. Classification with Discriminative Models
  6. Using Neural Networks
  7. Deep Convolutional Neural Networks
  8. Learning in Deep CNNs
  9. Object Detection and Deep Learning
  10. Semantic Segmentation and Deep Learning
  11. Other Computer Vision Tasks (Pose Estimation, Activity Recognition, Object Tracking)
  12. Generative Models and Deep Learning

Courses of study:

See LSF.


This course is limited to 24 students only.

To be allowed to participate in the course, students have to successfully pass the admission exam. (see above).

Credits: 6

Language: Englisch