Accurate Junction Detection and Characterization in Natural Images

Abstract : Accurate junction detection and characterization are of primary importance for several aspects of scene analysis, including depth recovery and motion analysis. In this work, we introduce a generic junction analysis scheme. The first asset of the proposed procedure is an automatic criterion for the detection of junctions, permitting to deal with textured parts in which no detection is expected. Second, the method yields a characterization of L-, Y- and X- junctions, including a precise computation of their type, localization and scale. Contrary to classical approaches, scale characterization does not rely on the linear scale-space, therefore enabling geometric accuracy. First, an {\it a contrario} approach is used to compute the meaningfulness of a junction. This approach relies on a statistical modeling of suitably normalized gray level gradients. Then, exclusion principles between junctions permit their precise characterization. We give implementation details for this procedure and evaluate its efficiency through various experiments.
Type de document :
Article dans une revue
International Journal of Computer Vision (IJCV), 2014, 106 (1), pp.31-56. <10.1007/s11263-013-0640-1>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00631609
Contributeur : Gui-Song Xia <>
Soumis le : mercredi 12 octobre 2011 - 18:17:18
Dernière modification le : jeudi 9 février 2017 - 15:02:46
Document(s) archivé(s) le : mardi 13 novembre 2012 - 16:36:30

Fichier

ACJ_preprint.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Gui-Song Xia, Julie Delon, Yann Gousseau. Accurate Junction Detection and Characterization in Natural Images. International Journal of Computer Vision (IJCV), 2014, 106 (1), pp.31-56. <10.1007/s11263-013-0640-1>. <hal-00631609>

Partager

Métriques

Consultations de
la notice

834

Téléchargements du document

1113