Keyword(s):Camera pose estimation, Shape from texture, Poisson point process, Posson-Voronoi tessellation.

Related
Ontology
Subjects/Areas/Topics:Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Statistical Approach

Abstract: Determining the pose of the camera is a need to many higher level computer vision tasks. We assume a set of features to be distributed on a planar surface (the world plane) as a Poisson point process, and to know their positions in the image plane. Then we propose an algorithm to recover the pose of the camera, in the case of two degrees of freedom (slant angle and distance from the ground). The algorithm is based on the observation that cell areas of the Voronoi tessellation generated by the points in the image plane represent a reliable sampling of the Jacobian determinant of the perspective transformation up to a scaling factor, the density of points in the world plane, which we demand as input. In the process, we develop a transformation of our input data (areas of Voronoi cells) so that they show almost constant variances among the locations, and analytically find a correcting factor to considerably reduce the bias of our estimates. We perform intensive synthetic simulations and show that with few hundreds of random points our errors on angle and distance are not more than few percents.(More)

Determining the pose of the camera is a need to many higher level computer vision tasks. We assume a set of features to be distributed on a planar surface (the world plane) as a Poisson point process, and to know their positions in the image plane. Then we propose an algorithm to recover the pose of the camera, in the case of two degrees of freedom (slant angle and distance from the ground). The algorithm is based on the observation that cell areas of the Voronoi tessellation generated by the points in the image plane represent a reliable sampling of the Jacobian determinant of the perspective transformation up to a scaling factor, the density of points in the world plane, which we demand as input. In the process, we develop a transformation of our input data (areas of Voronoi cells) so that they show almost constant variances among the locations, and analytically find a correcting factor to considerably reduce the bias of our estimates. We perform intensive synthetic simulations and show that with few hundreds of random points our errors on angle and distance are not more than few percents.

*Limit of Downloads ExceededJoin SciTePress now to download more papers for free and get access to over
full text papers.

Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.

Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.

Gherdovich G.; Descombes X. and (2010). TWO DOF CAMERA POSE ESTIMATION WITH A PLANAR STOCHASTIC REFERENCE GRID.In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 179-184. DOI: 10.5220/0002828501790184

@conference{visapp10, author={Giovanni Gherdovich and Xavier Descombes}, title={TWO DOF CAMERA POSE ESTIMATION WITH A PLANAR STOCHASTIC REFERENCE GRID}, booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)}, year={2010}, pages={179-184}, publisher={SciTePress}, organization={INSTICC}, doi={10.5220/0002828501790184}, isbn={978-989-674-029-0}, }

TY - CONF

JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) TI - TWO DOF CAMERA POSE ESTIMATION WITH A PLANAR STOCHASTIC REFERENCE GRID SN - 978-989-674-029-0 AU - Gherdovich, G. AU - Descombes, X. PY - 2010 SP - 179 EP - 184 DO - 10.5220/0002828501790184