Robust matching in an uncertain world - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

Robust matching in an uncertain world

Abstract

Finding point correspondences which are consistent with a geometric constraint is one of the cornerstones of many computer vision problems. This is a difficult task because of spurious measurements leading to ambiguously matched points and because of uncertainty in point location. In this article we address these problems and propose a new robust algorithm that explicitly takes account of location uncertainty. We propose applications to Sift matching and 3D data fusion.
Fichier principal
Vignette du fichier
PID1291587.pdf (675.87 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00474083 , version 1 (20-09-2010)

Identifiers

Cite

Frédéric Sur. Robust matching in an uncertain world. 20th International Conference on Pattern Recognition - ICPR 2010, IAPR, Aug 2010, Istanbul, Turkey. pp.2350 - 2353, ⟨10.1109/ICPR.2010.575⟩. ⟨inria-00474083⟩
110 View
130 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More