Scale Invariant Feature Transform on the Sphere: Theory and Applications

Détails

ID Serval
serval:BIB_02762629EE43
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Titre
Scale Invariant Feature Transform on the Sphere: Theory and Applications
Périodique
International Journal of Computer Vision
Auteur(s)
Cruz-Mota J., Bogdanova I., Paquier B., Bierlaire M., Thiran J.P.
ISSN
0920-5691
Statut éditorial
Publié
Date de publication
2012
Volume
98
Numéro
2
Pages
217-241
Langue
anglais
Résumé
A SIFT algorithm in spherical coordinates for omnidirectional images is proposed. This algorithm can generate two types of local descriptors, Local Spherical Descriptors and Local Planar Descriptors. With the first ones, point matching between two omnidirectional images can be performed, and with the second ones, the same matching process can be done but between omnidirectional and planar images. Furthermore, a planar to spherical mapping is introduced and an algorithm for its estimation is given. This mapping allows to extract objects from an omnidirectional image given their SIFT descriptors in a planar image. Several experiments, confirming the promising and accurate performance of the system, are conducted.
Web of science
Création de la notice
06/01/2014 19:07
Dernière modification de la notice
03/03/2018 13:18
Données d'usage