Non-Additive Approach for Omnidirectional Image Gradient Estimation

Abstract : The way catadioptric images are acquired implies that they present radial distortions. Therefore, classical processing may not be suitable. This statement will be illustrated by considering edge detection matter. Classical edge detectors usually consist in three steps : gradient computation, maximization and thresholding. The two lasts steps use pixels neighborhood concept. On the opposite of perspective images where pixel neighborhood is intuitive, catadioptric images present radial resolution changes. Then, the size and shape of pixel neighborhood have to be depending on pixel location. This article presents a new gradient estimation approach based on non-additive kernels. This technique is adapted to catadioptric images and also provides a natural threshold discarding the arbitrary thresholding step.
Type de document :
Communication dans un congrès
ICCV'07: International Conference on Computer Vision OMNIVIS'07: Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras, Oct 2007, Rio de Janeiro, Brésil, pp.1-4, 2007, 〈http://iccv2007.rutgers.edu/〉
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00194216
Contributeur : Florence Jacquey <>
Soumis le : jeudi 6 décembre 2007 - 08:58:32
Dernière modification le : jeudi 11 janvier 2018 - 06:26:18
Document(s) archivé(s) le : lundi 12 avril 2010 - 06:19:59

Fichier

Identifiants

  • HAL Id : lirmm-00194216, version 1

Collections

Citation

Florence Jacquey, Frédéric Comby, Olivier Strauss. Non-Additive Approach for Omnidirectional Image Gradient Estimation. ICCV'07: International Conference on Computer Vision OMNIVIS'07: Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras, Oct 2007, Rio de Janeiro, Brésil, pp.1-4, 2007, 〈http://iccv2007.rutgers.edu/〉. 〈lirmm-00194216〉

Partager

Métriques

Consultations de la notice

261

Téléchargements de fichiers

258