Semantic-based Technique for the Automation the 3D Reconstruction Process - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Semantic-based Technique for the Automation the 3D Reconstruction Process


The reconstruction of 3D objects based on point clouds data presents a major task in many application field since it consumes time and require human interactions to yield a promising result. Robust and quick methods for complete object extraction or identification are still an ongoing research topic and suffer from the complex structure of the data, which cannot be sufficiently modeled by purely numerical strategies. Our work aims at defining a new way of automatically and intelligently processing of 3D point clouds from a 3D laser scanner. This processing is based on the combination of 3D processing technologies and Semantic Web technologies. Therefore, the intention of our approach is to take the human cognitive strategy as an example, and to simulate this process based on available knowledge for the objects of interest. First, this process introduces a semantic structure for the object description. Second, the semantics guides the algorithms to detect and recognize objects, which will yield a higher effectiveness. Hence, our research proposes an approach which uses knowledge to select and guide the 3D processing algorithms on the 3D point clouds.
Fichier principal
Vignette du fichier
050_SEMAPRO_helmi_10.pdf (609.92 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00623889 , version 1 (16-09-2011)


  • HAL Id : hal-00623889 , version 1


Helmi Ben Hmida, Frank Boochs, Christophe Cruz, Christophe Nicolle. Semantic-based Technique for the Automation the 3D Reconstruction Process. SEMAPRO 2010 : The Fourth International Conference on Advances in Semantic Processing, Oct 2010, Florence, Italy. pp.Pages: 191 to 198, ISBN: 978-1-61208-104-5. ⟨hal-00623889⟩
359 Consultations
528 Téléchargements


Gmail Facebook Twitter LinkedIn More