Detail výsledku

LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors

BREJCHA, J.; LUKÁČ, M.; HOLD-GEOFFROY, Y.; WANG, O.; ČADÍK, M. LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors. In Computer Vision - ECCV 2020. Lecture Notes in Computer Science. Cham: Springer Nature Switzerland AG, 2020. p. 295-312. ISBN: 978-3-030-58525-9.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Brejcha Jan, Ing., Ph.D., UPGM (FIT)
Lukáč Michal, FIT (FIT)
Hold-Geoffroy Yannick
Wang Oliver
Čadík Martin, doc. Ing., Ph.D., UPGM (FIT)
Abstrakt

We introduce a solution to large scale Augmented Reality for outdoor scenes by registering camera images to textured Digital Elevation Models (DEMs). To accommodate the inherent differences in appearance between real images and DEMs, we train a cross-domain feature descriptor using Structure From Motion (SFM) guided reconstructions to acquire training data. Our method runs efficiently on a mobile device and outperforms existing learned and hand-designed feature descriptors for this task.

Klíčová slova

augmented reality, descriptor matching, cross domain matching, camera calibration, visual localization, structure-from-motion, terrain model, digital elevation model, photograph, computational photography

URL
Rok
2020
Strany
295–312
Sborník
Computer Vision - ECCV 2020
Řada
Lecture Notes in Computer Science
Svazek
12374
Konference
European Conference on Computer Vision 2020
ISBN
978-3-030-58525-9
Vydavatel
Springer Nature Switzerland AG
Místo
Cham
DOI
10.1007/978-3-030-58526-6_18
EID Scopus
2-s2.0-85093082471
BibTeX 
@inproceedings{BUT168487,
  author="Jan {Brejcha} and Michal {Lukáč} and Yannick {Hold-Geoffroy} and Oliver {Wang} and Martin {Čadík}",
  title="LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors",
  booktitle="Computer Vision - ECCV 2020",
  year="2020",
  series="Lecture Notes in Computer Science",
  volume="12374",
  pages="295--312",
  publisher="Springer Nature Switzerland AG",
  address="Cham",
  doi="10.1007/978-3-030-58526-6\{_}18",
  isbn="978-3-030-58525-9",
  url="https://link.springer.com/chapter/10.1007/978-3-030-58526-6_18"
}
Projekty
Moderní metody zpracování, analýzy a zobrazování multimediálních a 3D dat, VUT, Vnitřní projekty VUT, FIT-S-20-6460, zahájení: 2020-03-01, ukončení: 2023-02-28, ukončen
Topografická analýza obrazu s využitím metod hlubokého učení, MŠMT, INTER-EXCELLENCE - Podprogram INTER-ACTION, LTAIZ19004, zahájení: 2019-07-01, ukončení: 2022-06-30, ukončen
Výzkumné skupiny
Výzkumná skupina výpočetní fotografie - CPhoto@FIT (VZ CPHOTO)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru