The proposed project deals with localization in natural environments. It builds on the applicant's experience in registration of photos with a 3D geo-referenced terrain model and on the expertise of graphics group @FIT-BUT in image processing, computer graphics & vision, machine learning and experience with research and development of avionics. It proposes an investigation of image to model registration techniques allowing for building accurate visual localization systems that are more robust to qualities of input photos. Particular attention will be devoted to finding applications of visual localization systems in challenging scenarios, e.g. in aircraft systems.

Description in Czech
Projekt LOCATE se zabývá vizuální geo-lokalizací v přírodě. Hlavní náplní projektu je výzkum technik pro registraci obrazu do modelu terénu umožňující implementaci přesných vizuálních lokalizačních systémů.

Keywords
image processing, computer graphics, computer vision, visual localization, terrain alignment, geo-localization, scene to model registration, viewing direction estimation, cameras, terrain mapping, cartographic data, photographic data, semantic image labeling, image registration

4SGA8694

English

Čadík Martin, doc. Ing., Ph.D. - principal person responsible

Department of Computer Graphics and Multimedia
- responsible department (13.9.2013 - not assigned)
Computational Photography Group - CPhoto@FIT
- internal (13.9.2013 - 19.7.2016)
Image and Video Processing Research Group
- internal (13.9.2013 - 19.7.2016)
Department of Computer Graphics and Multimedia
- beneficiary (13.9.2013 - 19.7.2016)

ČADÍK, M.; AYDIN, T. HDR Video Metrics. In High Dynamic Range Video: Concepts, Technologies and Applications. London: Elsevier Science, 2016. p. 111-125. ISBN: 978-0-12-809477-8.
Detail

ČADÍK, M.; VAŠÍČEK, J.; HRADIŠ, M.; RADENOVIĆ, F.; CHUM, O. Camera Elevation Estimation from a Single Mountain Landscape Photograph. In British Machine Vision Conference 2015. Swansea: The British Machine Vision Association and Society for Pattern Recognition, 2015. p. 1-12. ISBN: 978-1-901725-53-7.
Detail

FIŠER, J.; LUKÁČ, M.; JAMRIŠKA, O.; ČADÍK, M.; GINGOLD, Y.; ASENTE, G.; SÝKORA, D. Color Me Noisy: Example-based Rendering of Hand-colored Animations with Temporal Noise Control. COMPUTER GRAPHICS FORUM, 2014, vol. 2014, no. 4, p. 1-10. ISSN: 0167-7055.
Detail

Responsibility: Čadík Martin, doc. Ing., Ph.D.