A JOINT 3D IMAGE SEMANTIC SEGMENTATION and SCALABLE CODING SCHEME with ROI APPROACH

Abstract : Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including monitoring visual degradation of compressed 3D image (especially upon edges), and increased complexity for scene representation. In this paper, we propose a semantic region representation and a scalable coding scheme. First, the semantic region representation scheme is based on a low resolution version of the 3D image. It provides the possibility to segment the image according to a desirable balance between 2D and depth. Second, the scalable coding scheme consists in selecting a number of regions as a Region of Interest (RoI), based on the region representation, in order to be refined at a higher bit-rate. Experiments show that the proposed scheme provides a high coherence between texture, depth and regions and ensures an efficient solution to the problems of compression and scene representation in the 3D image domain.
Type de document :
Communication dans un congrès
VCIP 2014, Dec 2014, La Valette, Malta. 2014
Liste complète des métadonnées

http://hal.univ-nantes.fr/hal-01113055
Contributeur : Khouloud Samrouth <>
Soumis le : mardi 3 mars 2015 - 09:23:37
Dernière modification le : mercredi 16 mai 2018 - 11:23:49
Document(s) archivé(s) le : samedi 12 septembre 2015 - 08:36:02

Fichier

VCIP_2014.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01113055, version 1

Citation

Khouloud Samrouth, Olivier Deforges, Yi Liu, Wassim Falou, Khalil Mohamad. A JOINT 3D IMAGE SEMANTIC SEGMENTATION and SCALABLE CODING SCHEME with ROI APPROACH. VCIP 2014, Dec 2014, La Valette, Malta. 2014. 〈hal-01113055〉

Partager

Métriques

Consultations de la notice

476

Téléchargements de fichiers

134