Fast pseudo-semantic segmentation for joint region-based hierarchical and multiresolution representation

Rafik Sekkal 1 Clément Strauss 1 François Pasteau 1 Marie Babel 2 Olivier Déforges 1
2 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : In this paper, we present a new scalable segmentation algorithm called JHMS (Joint Hierarchical and Multiresolution Segmentation) that is characterized by region-based hierarchy and resolution scalability. Most of the proposed algorithms either apply a multiresolution segmentation or a hierarchical segmentation. The proposed approach combines both multiresolution and hierarchical segmentation processes. Indeed, the image is considered as a set of images at different levels of resolution, where at each level a hierarchical segmentation is performed. Multiresolution implies that a segmentation of a given level is reused in further segmentation processes operated at next levels so that to insure contour consistency between different resolutions. Each level of resolution provides a Region Adjacency Graph (RAG) that describes the neighborhood relationships between regions within a given level of the multiresolution representation. Region label consistency is preserved thanks to a dedicated projection algorithm based on inter-level relationships. Moreover, a preprocess based on a quadtree partitioning reduces the amount of input data thus leading to a lower overall complexity of the segmentation framework. Experiments show that we obtain effective results when compared to the state of the art together with a lower complexity.
Type de document :
Communication dans un congrès
SPIE Electronic Imaging - Visual Communications and Image Processing, Jan 2012, San Francisco, United States. 8305, pp.83050J, 2012, 〈10.1117/12.908829〉
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00657805
Contributeur : Marie Babel <>
Soumis le : lundi 9 janvier 2012 - 11:53:11
Dernière modification le : jeudi 15 novembre 2018 - 11:58:16
Document(s) archivé(s) le : mardi 10 avril 2012 - 02:30:07

Fichier

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

Identifiants

Citation

Rafik Sekkal, Clément Strauss, François Pasteau, Marie Babel, Olivier Déforges. Fast pseudo-semantic segmentation for joint region-based hierarchical and multiresolution representation. SPIE Electronic Imaging - Visual Communications and Image Processing, Jan 2012, San Francisco, United States. 8305, pp.83050J, 2012, 〈10.1117/12.908829〉. 〈hal-00657805〉

Partager

Métriques

Consultations de la notice

1281

Téléchargements de fichiers

273