Faculty of Information Technology, BUT

Publication Details

Five Shades of Grey for Fast and Reliable Camera Pose Estimation

HEROUT Adam, SZENTANDRÁSI István, ZACHARIÁŠ Michal, DUBSKÁ Markéta and KAJAN Rudolf. Five Shades of Grey for Fast and Reliable Camera Pose Estimation. In: Proceedings of CVPR. Portland, OR: IEEE Computer Society, 2013, pp. 1384-1390. ISBN 978-0-7695-4989-7.
Czech title
Pět odstínů šedé pro rychlé a spolehlivé určení pozice kamery
Type
conference paper
Language
english
Authors
Keywords
Fiduciary Markers, Uniform Marker Field, Checkerboard Detection, Seamless Marker, Overlapping Markers, Camera Localization, Augmented Reality, De-Bruijn Tori, Perfect Maps, Real-Time AR Localization, Visually Appealing Markers, Tolerance to Global/Local Lighting Conditions
Abstract
We introduce here an improved design of the Uniform
Marker Fields and an algorithm for their fast and reliable
detection. Our concept of the marker field is designed so
that it can be detected and recognized for camera pose esti-
mation: in various lighting conditions, under a severe per-
spective, while heavily occluded, and under a strong motion
blur.
Our marker field detection harnesses the fact that the
edges within the marker field meet at two vanishing points
and that the projected planar grid of squares can be defined
by a detectable mathematical formalism. The modules of
the grid are greyscale and the locations within the marker
field are defined by the edges between the modules.
The assumption that the marker field is planar allows
for a very cheap and reliable camera pose estimation in
the captured scene. The detection rates and accuracy are
slightly better compared to state-of-the-art marker-based
solutions. At the same time, and more importantly, our de-
tector of the marker field is several times faster and the re-
liable real-time detection can be thus achieved on mobile
and low-power devices. We show three targeted applica-
tions where the planarity is assured and where the presented
marker field design and detection algorithm provide a reliable and extremely fast solution.
Published
2013
Pages
1384-1390
Proceedings
Proceedings of CVPR
Conference
Computer Vision and Pattern Recognition (CVPR) 2013, Portland, Oregon, US
ISBN
978-0-7695-4989-7
Publisher
IEEE Computer Society
Place
Portland, OR, US
BibTeX
@INPROCEEDINGS{FITPUB10293,
   author = "Adam Herout and Istv\'{a}n Szentandr\'{a}si and Michal Zachari\'{a}\v{s} and Mark\'{e}ta Dubsk\'{a} and Rudolf Kajan",
   title = "Five Shades of Grey for Fast and Reliable Camera Pose Estimation",
   pages = "1384--1390",
   booktitle = "Proceedings of CVPR",
   year = 2013,
   location = "Portland, OR, US",
   publisher = "IEEE Computer Society",
   ISBN = "978-0-7695-4989-7",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10293"
}
Back to top