Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/117926
Title: | Simultaneous pose, focal length and 2D-to-3D correspondences from noisy observations | Authors: | Peñate Sánchez, Adrián Serradell, Eduard Andrade-Cetto, Juan Moreno-Noguer, Francesc |
UNESCO Clasification: | 1203 Ciencia de los ordenadores | Keywords: | Focal lenght | Issue Date: | 2013 | Publisher: | B M V A PRESS | Journal: | 24th British Machine Vision Conference | Conference: | British Machine Vision Conference 2013 | Abstract: | Simultaneously recovering the camera pose and correspondences between a set of 2D-image and 3D-model points is a difficult problem, especially when the 2D-3D matches cannot be established based on appearance only. The problem becomes even more challenging when input images are acquired with an uncalibrated camera with varying zoom, which yields strong ambiguities between translation and focal length. We present a solution to this problem using only geometrical information. Our approach owes its robustness to an initial stage in which the joint pose and focal length solution space is split into several Gaussian regions. At runtime, each of these regions is explored using an hypothesize-and-test approach, in which the potential number of 2D-3D matches is progressively reduced using informed search through Kalman updates, iteratively refining the pose and focal length parameters. The technique is exhaustive but efficient, significantly improving previous methods in terms of robustness to outliers and noise. | URI: | http://hdl.handle.net/10553/117926 | ISBN: | 1-901725-49-9 | DOI: | 10.5244/c.27.82 | Source: | 24th British Machine Vision Conference, Bristol |
Appears in Collections: | Artículos |
SCOPUSTM
Citations
2
checked on Nov 10, 2024
WEB OF SCIENCETM
Citations
1
checked on Nov 10, 2024
Page view(s)
36
checked on Feb 3, 2024
Download(s)
5
checked on Feb 3, 2024
Google ScholarTM
Check
Altmetric
Share
Export metadata
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.