Deep Learning in Image and Video Processing

Within this course, we want to explore Image and Video Processing tasks boosted by Deep Learning methods. These methods gain more and more attraction in the scientific environment driven by their continuing success in solving a plethora of diverse signal processing tasks. Especially in the field of image and video processing, deep learning methods are able to greatly improve over existing algorithms and to solve entirely new tasks that were deemed intractable using classical approaches.

Possible areas of application are numerous. From artistic applications like coloring black-and-white videos, generating deceptively real fake images or transferring the style of one image to another, to industrial applications like image super-resolution, frame rate up-conversion or object detection and object tracking for surveillance and autonomous driving, deep learning based image and video processing has widespread impact.

This course offers an overview of classical image and video processing algorithms, an introduction to deep learning and discusses various practical applications. It is organized in two parts. In part 1, each participant will give a 30-minute presentation on a selected topic. In part 2, the participants will work together on the development of a self-driving robotic car implementing both classical and deep-learning based image and video processing algorithms.

The course takes place within the scope of the Ferienakademie 2021 (19.09.2021 – 01.10.2021) in the Sarntal Alps (South Tirol). It aims at students at late Bachelor-level and Master-level. Due to the extensive programming part, an advanced level in programming is required.

Students will have to apply by May 2, 2021 via the website of the Ferienakademie.

Category: Chair