Computer Vision is a very active research field, having both theoretical and practical importance. The goal of computer vision is to enable machines to process, analyze, and interpret visual data acquired with cameras and other sensors.
This year's seminar mainly focuses on machine learning in the vision domain – in particular (while not exclusively limited to) on deep learning and ensemble learning in the context of remote sensing. What are the special characteristics of image data? What does it mean to understand an image? Which priors are especially suited? To answer these questions we will have a look at papers in the area published in leading conferences and journals. Participants will gain an overview of the state-of-the-art methods in the field, learn to read and understand research papers in this area, as well as improve their presentation and analytical skills.
- Trainer/in: Marion Dennert
- Trainer/in: Olaf Hellwich