Instructors: Prof. Dr. Simone Frintrop
Event type:
Lecture
Displayed in timetable as:
CV2 - VL
Hours per week:
2
Credits:
3,0
Language of instruction:
English
Min. | Max. participants:
- | 40
Comments/contents:
This lecture extends the basics from Computer Vision I and introduces more complex task and the state of the art in the field of computer vision.
A focus of the lecture is on cognitive approaches to computer vision, which seek for inspiration from the human visual system to obtain improved algorithms. This area of research is very interdisciplinary and bases on findings from Psychology and Neuroscience. The basics which are necessary for the course will be introduced at the beginning of the lecture. However, the main part of the lecture will be on computer vision algorithms and the state of the art in this field.
The following topics will be covered in the course:
The Human Visual System
Receptive Fields versus Digital Filters
Convolutional Neural Networks II
Visual Attention and Saliency
Visual Search for Objects
Semantic Segmentation
Active Perception
Object Proposal Detection (Object Discovery)
Learning objectives:
Knowledge of the state of the art in biologically-inspired computer vision and comprehension of capabilities and limitations of the methods.
Didactic concept:
Lecture with discussions complemented with the associated seminar including practical programming exercises. Course language is English. See seminar description for more details.
Literature:
Literature will be announced in the course.
|