Publication Details

Real Projective Plane Mapping for Detection of Orthogonal Vanishing Points

DUBSKÁ Markéta and HEROUT Adam. Real Projective Plane Mapping for Detection of Orthogonal Vanishing Points. In: Proceedings of BMVC 2013. Bristol: The British Machine Vision Association and Society for Pattern Recognition, 2013, pp. 1-10. ISBN 1-901725-49-9.
Czech title
Mapování projektivní roviny pro detekci kolmých úbežníků
Type
conference paper
Language
english
Authors
Dubská Markéta, Ing., Ph.D. (DCGM FIT BUT)
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT)
Keywords

parallel coordinates, vanishing points, manhattan world, cascaded hough transform

Abstract
This paper deals with the detection of orthogonal vanishing points. The aim is to efficiently cope with the clutter edges in real-life images and to determine the camera orientation in the Manhattan world reliably. We are using a modified scheme of the Cascaded Hough Transform where only one Hough space is accumulated - the space of the vanishing points. The parameterization of the vanishing points - the "diamond space" - is based on the PClines line parameterization and it is defined as a mapping of the whole real projective plane to a finite space. 
Our parameterization of vanishing points is in all aspects linear; it involves no goniometric or other non-linear operations and thus it is suitable for implementation in embedded chips and circuitry. 
Published
2013
Pages
1-10
Proceedings
Proceedings of BMVC 2013
Conference
British Machine Vision Conference (BMVC) 2013, Bristol, GB
ISBN
1-901725-49-9
Publisher
The British Machine Vision Association and Society for Pattern Recognition
Place
Bristol, GB
DOI
10.5244/C.27.90
BibTeX 
@INPROCEEDINGS{FITPUB10400,
   author = "Mark\'{e}ta Dubsk\'{a} and Adam Herout",
   title = "Real Projective Plane Mapping for Detection of Orthogonal Vanishing Points",
   pages = "1--10",
   booktitle = "Proceedings of BMVC 2013",
   year = 2013,
   location = "Bristol, GB",
   publisher = "The British Machine Vision Association and Society for Pattern Recognition",
   ISBN = "1-901725-49-9",
   doi = "10.5244/C.27.90",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10400"
}
Back to top