2D/3D semantic annotation towards a set of spatially-oriented photographs

Abstract. In the domain of conservation and promotion of cultural heritage, the development of new information technologies offers new tools for sharing knowledge on heritage building. These tools are destined to help experts to enrich and access information about buildings. This article proposes an approach allowing the automatic transfer of annotations in a set of spatially-oriented photographs (whose positions and orientations in space are estimated) by using 3D information. First of all, an automated image-based 3D reconstruction method produces 3D information (specifically 3D coordinates) by processing photographs of the set. Then, the process of annotations' transfer between images uses this generated 3D information. Finally, this process allows the implementation of the annotations modification. As a consequence, this process provides a simple way to annotate blocs of images all at once instead of one by one.