Managing semantics knowledge for 3D architectural reconstruction

Abstract : this work aims at bound geometrical detection of 3D objects from a point cloud using semantic descriptors to improve reusability of architectural building reconstruction and aid automatic reasoning in building information modeling (BIM). Based on exploring cognitive origins of spatial semantics representations, semantics conceptualization and classification is proposed for formal management of 3D architectural objects. The knowledge classification composes definition, partial knowledge and ambiguous knowledge, and is formalized with transformations among closed world assumption (CWA) and open world assumption (OWA). Systemic case study is conducted on a simplified building prototype complying with the IFC standard. The organization of empirical knowledge rules is revealed, and semantics scopes are addressed both in the bottom up manner of geometry  topology semantics, and a vice versa top down manner. Partial experiments are conducted in the form of intermediate analysis models during the knowledge modeling process, and initial reasoning demonstrations on the platform of protégé with semantic web rule language (SWRL) rules. This work is promising towards meeting optimization requirement which demands the integration of what users want, what theorists believe possible and what practitioners think practical.
Type de document :
Communication dans un congrès
11th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, Jun 2010, London, United Kingdom. pp.8, 2011
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-00612509
Contributeur : Christophe Nicolle <>
Soumis le : vendredi 29 juillet 2011 - 11:01:33
Dernière modification le : mercredi 12 septembre 2018 - 01:27:42

Identifiants

  • HAL Id : hal-00612509, version 1

Collections

Citation

Christophe Nicolle, Christophe Cruz, Duan Yucong. Managing semantics knowledge for 3D architectural reconstruction. 11th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, Jun 2010, London, United Kingdom. pp.8, 2011. 〈hal-00612509〉

Partager

Métriques

Consultations de la notice

280