PhD Offer: Automatic classification of photographic images for spatio-temporal monitoring of restoration sites

Over the last decade, a large number of digital documentation projects have demonstrated the potential of image-based modeling (photo modeling, photogrammetry, …) of heritage objects in the context of documentation, conservation and restoration. The inclusion of these emerging methods in the daily monitoring of the activities of a heritage restoration site (context in which hundreds of photographs per day can be acquired by multiple actors and according to several observation and analysis needs) raises new questions at the intersection of big data management and of the semantic enrichment and the automatic classification of this data, for the purpose of searching by content similarity. This PhD project has the ambition to introduce a disruptive approach for the massive processing of large collections of photographs, distributed in space and time. This project is part of the CNRS and French Ministry of Culture scientific workcamp for the restoration of Notre-Dame de Paris and, in particular, within the framework of a working group in charge of building a “digital ecosystem” capable of evolving as the studies progress, by progressively centralizing the resources collected, produced, analyzed and interpreted by the scientists and professionals involved in the restoration workcamp. Through interactions with the working groups involved in this scientific work site (wood/charpente, stone, stained glass, metals, structure, acoustics, heritage emotions, etc.), the problem of automatic indexing of masses of photographs will be addressed by combining several complementary 2D/3D semantic enrichment methods.