PRACTICAL SINGLE VIEW METROLOGY FOR CUBOIDS

Nick Pears, Paul Wright, Chris Bailey

2007

Abstract

Generally it is impossible to determine the size of an object from a single image due to the depth-scale ambiguity problem. However, with knowledge of the geometry of the scene and the existence of known reference dimensions in the image, it is possible to infer the real world dimensions of objects with only a single image. In this paper, we investigate different methods of automatically determining the dimensions of cuboids (rectangular boxes) from a single image, using a novel reference target. In particular, two approaches will be considered: the first will use the cross-ratio projective invariant and the other will use the planar homography. The accuracy of the measurements will be evaluated in the presence of noise in the feature points. The effects of lens distortions on the accuracy of the measurements will be investigated. Automatic feature detection techniques will also be considered.

Paper Citation

in Harvard Style

Pears N., Wright P. and Bailey C. (2007). PRACTICAL SINGLE VIEW METROLOGY FOR CUBOIDS . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 85-90. DOI: 10.5220/0002042400850090

in Bibtex Style

@conference{visapp07,
author={Nick Pears and Paul Wright and Chris Bailey},
title={PRACTICAL SINGLE VIEW METROLOGY FOR CUBOIDS},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={85-90},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002042400850090},
isbn={978-972-8865-74-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - PRACTICAL SINGLE VIEW METROLOGY FOR CUBOIDS
SN - 978-972-8865-74-0
AU - Pears N.
AU - Wright P.
AU - Bailey C.
PY - 2007
SP - 85
EP - 90
DO - 10.5220/0002042400850090