Digital Heritage Documentation. Mapping Features Through Automatic, Critical-Interpretative Procedures

The contribution is focused on digital data segmentation in Heritage domain to define materials, construction techniques, and state of conservation. The proposed methodology aims to investigate further possibilities for thematic classification of data related to surface features of Cultural Heritage starting from current results in processing color-based data and adding data achieved by laser scanning. Anyway, nowadays the intensity value is hardly used for this kind of analysis, since it depends not only on surface specifications but also on different parameters such as the laser angle of incidence. To this aim, first comparative diagrams associating specific intensity value ranges with specific materials and states of conservation are required. Then, an adaptation and implementation of existing algorithms is needed, able to query the intensity value to generate a point cloud segmentation based on semantic features on controlled datasets. The purpose is to explore Artificial Intelligence processes in order to combine the irreplaceable cultural and interpretative skills with suitable tools useful to prioritizing data in a hierarchical way according to different levels of knowledge through automatic procedures.

The research is in its very beginning, methodologies are currently being set up, and some comparative data sets are being explored, but the final goal is to use obtained thematic models for the informative implementation of H-BIM models, toward an increasingly structured organization of interpretative data, also within shared semantic web platforms.