Learnable Camera Motion Models
This project started January 2015.
The project runs for four years, and is funded by The Swedish Research Council (VR).
In this project, we will develop continuous camera motion models that can be adapted to specific situations through learning. Such models are needed in video stabilisation and rectification on mobile platforms. They are also useful for control of motorised gimbals that mechanically stabilise the camera aim.
The project is a continuation of the VGS project.
More information will follow soon.
Senast uppdaterad: 2016-08-08