Laying the Foundations for an Information System Dedicated to Heritage Building Degradation Monitoring Based on the 2D/3D Semantic Annotation of Photographs

In the last decade many 3D digitization techniques have emerged allowing the generation of dense and precise digital representations of historical building. However, regardless their level of geometric accuracy or visual realism, 3D models are not yet fully adapted to the conservation analysis purposes. In fact, even if a 3D model can be considered an efficient way to accurately record the state of a building, its potentiality in terms of semantic annotation and spatial distribution of heterogeneous data still remain almost unexplored today. Since several years, photographs appear to be a flexible and well diffused portable support for the heritage documentation. They are a natural medium to annotate and compare temporal states. Thanks to the recent advances in photogrammetry, computer vision and augmented reality, photographs can be also considered as an excellent support for accurate spatial localization. This article presents the first principles for the development of an information system to monitor the historic building degradation based on three main components: a high dynamic range (HDR) imagebased automatic pipeline, an hybrid (2D/3D) semantic annotation method and a domain ontology describing knowledge related to degradation phenomena. The innovative integration of these main components allows us to introduce the notion of ”informative continuum” as a key for interconnecting spatialized and semanticallyenriched photographs to populate a knowledge base on the building degradation. The first steps of this on-going project are illustrated by an experimentation carried out on the Caromb church in the south of France.

[1]  Hirokazu Kato,et al.  Marker tracking and HMD calibration for a video-based augmented reality conferencing system , 1999, Proceedings 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR'99).

[2]  Livio De Luca,et al.  Automated Image-Based Procedures for Accurate Artifacts 3D Modeling and Orthoimage Generation , 2011 .

[3]  A. Vedaldi An open implementation of the SIFT detector and descriptor , 2007 .

[4]  V. Vergès-Belmin Illustrated glossary on stone deterioration patterns , 2008 .

[5]  Thomas R. Gruber,et al.  Toward principles for the design of ontologies used for knowledge sharing? , 1995, Int. J. Hum. Comput. Stud..

[6]  Jean-Marie Pérouse de Montclos,et al.  Architecture : méthode et vocabulaire , 1972 .

[7]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Eero Hyvönen,et al.  Publishing and Using Cultural Heritage Linked Data on the SemanticWeb.In: A Publication in the Morgan & Claypool Publishers series, SYNTHESIS LECTURES ON SEMANTIC WEB: THEORY AND TECHNOLOGY , 2012 .

[9]  Livio De Luca,et al.  A database of spatialized and semantically-enriched iconographic sources for the documentation of cultural heritage buildings , 2012, 2012 18th International Conference on Virtual Systems and Multimedia.

[10]  Livio De Luca,et al.  2D/3D semantic annotation towards a set of spatially-oriented photographs , 2013 .