Advanced video processing

Remove unwanted objects in 1-2-3. Algorithms and software for advanced video processing suitable for non-experienced user.
Master

It is too easy to record videos, but it is even easier to get something you don’t really want to see in picture. We cannot avoid this, but maybe we can fix this afterwards? Yes, we can! But what if I don’t know how to program and cannot use Photoshop? Here AI will step-in. Select your object and let us do all the job. Object recognition, tracking, background detection, image inpainting and much more under the hood to restore beauty.

Goal

The goal of the thesis is to produce an algorithm and web-based software that will be able to remove selected objects from video footage with dynamic content and moving objects.

Learning outcome

During the course of this master thesis, the candidate will gain in-depth knowledge in video processing using traditional computer vision and deep-learning-based approaches.

Qualifications

Python or Matlab or C/C++ programming, Knowledge about machine learning is an advantage

Supervisors

Konstantin Pogorelov