Using geometric quasi-invariants to match and model images of line segments - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 1995

Using geometric quasi-invariants to match and model images of line segments

Abstract

Image matching consists in finding in two images the features which represent a same feature of the observed scene. It is a basic process of vision as soon as several images are used. use of local geometric quasi-invariants. Once a first match is made, a projective approximation of the apparent motion and the epipolar geometry may be used to complete it. In the case where we consider more than two images, these images may be matched two by two in a first step, and a global match is deduced in a second step: this is exposed in the last section. The main advantages of the method presented here are the following: it still works even if the images are noisy and the polyhedral approximation of the contours is not exact, if the apparent motion between the images is not very small, if the whole scene has not a single rigid motion, if the camera is not calibrated and the camera motion between the two shots is not known... It is thus usable in many cases where no other method is available

Domains

Other [cs.OH]
Fichier principal
Vignette du fichier
RR-2608.pdf (587.22 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00074077 , version 1 (24-05-2006)

Identifiers

  • HAL Id : inria-00074077 , version 1

Cite

Patrick Gros, Olivier Bournez, Edmond Boyer. Using geometric quasi-invariants to match and model images of line segments. [Research Report] RR-2608, INRIA. 1995. ⟨inria-00074077⟩
345 View
83 Download

Share

Gmail Facebook X LinkedIn More