Publication detail

Uniform Marker Fields: Camera Localization By Orientable De Bruijn Tori

SZENTANDRÁSI, I. ZACHARIÁŠ, M. HAVEL, J. HEROUT, A. JURÁNKOVÁ, M. KAJAN, R.

Original Title

Uniform Marker Fields: Camera Localization By Orientable De Bruijn Tori

English Title

Uniform Marker Fields: Camera Localization By Orientable De Bruijn Tori

Type

conference paper

Language

en

Original Abstract

In various applications, a wider area needs to be covered by fiduciary markers but a large marker cannot be used because only a fraction of the area is to be viewed by the camera. Such an area can be covered by a  number of small markers with unique identifiers. However, with the camera freely moving in the scene and with occluders present, it is difficult to ensure that at least one of the individual markers is completely visible, unless the markers are small and numerous. In that case, the markers are not recognizable from larger distances. In this paper we introduce the concept of Marker Fields which overcome this limitation. The Marker Field covers a large-scale planar (or non-planar) area and it is composed of mutually overlapping partial markers. We propose a particular arrangement of the Marker Field: a Uniform Checker-Board Marker Field, which is a black-and-white checkerboard whose square modules are defined by aperiodic 4-orientable binary (n,n)-window arrays (De Bruijn tori). We propose a genetic algorithm for construction of 4-orientable (n,n)-window arrays. We used a  supercomputer to synthesize large 4-orientable (n,n)-window arrays and offer them publicly for downloading. We prototyped an algorithm for detection of the checkerboard marker fields and measured its performance. When processing input video from a cellphone camera, the algorithm visits only about 5% of image pixels for reliable detection and the processing time is about 1ms on a mid-range PC processor. The Uniform Marker Field increases freedom of camera movement, especially with occluders present in the scene. The detection algorithm is efficient and real-time marker field detection will be feasible on ultramobile devices.

English abstract

In various applications, a wider area needs to be covered by fiduciary markers but a large marker cannot be used because only a fraction of the area is to be viewed by the camera. Such an area can be covered by a  number of small markers with unique identifiers. However, with the camera freely moving in the scene and with occluders present, it is difficult to ensure that at least one of the individual markers is completely visible, unless the markers are small and numerous. In that case, the markers are not recognizable from larger distances. In this paper we introduce the concept of Marker Fields which overcome this limitation. The Marker Field covers a large-scale planar (or non-planar) area and it is composed of mutually overlapping partial markers. We propose a particular arrangement of the Marker Field: a Uniform Checker-Board Marker Field, which is a black-and-white checkerboard whose square modules are defined by aperiodic 4-orientable binary (n,n)-window arrays (De Bruijn tori). We propose a genetic algorithm for construction of 4-orientable (n,n)-window arrays. We used a  supercomputer to synthesize large 4-orientable (n,n)-window arrays and offer them publicly for downloading. We prototyped an algorithm for detection of the checkerboard marker fields and measured its performance. When processing input video from a cellphone camera, the algorithm visits only about 5% of image pixels for reliable detection and the processing time is about 1ms on a mid-range PC processor. The Uniform Marker Field increases freedom of camera movement, especially with occluders present in the scene. The detection algorithm is efficient and real-time marker field detection will be feasible on ultramobile devices.

Keywords

Fiduciary Markers, Nested Marker, Seamless Marker, Overlapping Markers, Camera Localization, Augmented Reality, De-Bruijn Tori, Genetic Algorithm, Perfect Maps, UMF

RIV year

2012

Released

05.11.2012

Publisher

Institute of Electrical and Electronics Engineers

Location

Atlatnta, Georgia

ISBN

978-1-4673-4661-0

Book

Proceedings of the 2012 11th IEEE International Symposium on Mixed and Augmented Reality

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

1

Pages to

2

Pages count

2

Documents

BibTex


@inproceedings{BUT97028,
  author="István {Szentandrási} and Michal {Zachariáš} and Jiří {Havel} and Adam {Herout} and Markéta {Juránková} and Rudolf {Kajan}",
  title="Uniform Marker Fields: Camera Localization By Orientable De Bruijn Tori",
  annote="In various applications, a wider area needs to be covered by fiduciary markers
but a large marker cannot be used because only a fraction of the area is to be
viewed by the camera. Such an area can be covered by a  number of small markers
with unique identifiers. However, with the camera freely moving in the scene and
with occluders present, it is difficult to ensure that at least one of the
individual markers is completely visible, unless the markers are small and
numerous. In that case, the markers are not recognizable from larger distances.

In this paper we introduce the concept of Marker Fields which overcome this
limitation. The Marker Field covers a large-scale planar (or non-planar) area and
it is composed of mutually overlapping partial markers. We propose a particular
arrangement of the Marker Field: a Uniform Checker-Board Marker Field, which is
a black-and-white checkerboard whose square modules are defined by aperiodic
4-orientable binary (n,n)-window arrays (De Bruijn tori). We propose a genetic
algorithm for construction of 4-orientable (n,n)-window arrays.

We used a  supercomputer to synthesize large 4-orientable (n,n)-window arrays and
offer them publicly for downloading. We prototyped an algorithm for detection of
the checkerboard marker fields and measured its performance. When processing
input video from a cellphone camera, the algorithm visits only about 5% of image
pixels for reliable detection and the processing time is about 1ms on a mid-range
PC processor.

The Uniform Marker Field increases freedom of camera movement, especially with
occluders present in the scene. The detection algorithm is efficient and
real-time marker field detection will be feasible on ultramobile devices.",
  address="Institute of Electrical and Electronics Engineers",
  booktitle="Proceedings of the 2012 11th IEEE International Symposium on Mixed and Augmented Reality",
  chapter="97028",
  edition="NEUVEDEN",
  howpublished="online",
  institution="Institute of Electrical and Electronics Engineers",
  year="2012",
  month="november",
  pages="1--2",
  publisher="Institute of Electrical and Electronics Engineers",
  type="conference paper"
}