Example

The starting point of this project was to find very affordable solutions to adopt augmented reality techniques in film and online broadcasting (television) production. We aimed to boost the next generation video based "tweating" and help students to become familiar with augmented reality technology. In particular, we have developed very accurate and efficient (state-of-the-art quality) RGB-D (Kinect) base dense camera tracking and reconstruction. Our methods run on commodity laptop and perform camera tracking and reconstruction real-time online.

The project has been funded by the Teknologiateollisuuden 100-vuotissäätiö and European Union Regional Development Fund. We collaborate with the Audio-Video Production team in Kymenlaakso University of Applied Sciences (KyAMK)

Teknologiateollisuuden 100-vuotissaatio logo EU Regional Funding Kymenlaakso University of Applied Sciences

Demos

People

Tommi Tykkälä E-mail Post-doctoral Researcher
Jori Pölkki E-mail Senior Lecturer (KyAMK)
Joni Kamarainen E-mail Professor

Selected Publications

Photorealistic 3D Mapping of Indoors by RGB-D Scanning Process

By T. Tykkälä, A.I. Comport, J.-K. Kämäräinen In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2013.

The method produces high-quality real-time 3D reconstruction of indoor environmens (e.g., apartments).

Download: PDF, BibTexVideo, Code (available soon)

Live RGB-D Camera Tracking for Television Production Studios

By T. Tykkälä, A.I. Comport, J.-K. Kämäräinen and H. Hartikainen In Journal of Visual Communication and Image Representation 2013.

The method uses Kinect to real-time track studio camera and tolerates moving characters (actors) in the foreground. No special equipments such as blue screens needed.

Download: PDF, BibTexVideo, Code (available soon)

Links

Other approaches

Kinect Fusion in Kinect Windows SDK
The famous method first proposed by Newcombe
Kinfu - the open source Kinect Fusion
Open source version of the above