The thorough documentation of Cultural Heritage artifacts is a fundamental concern for management and preservation. In this context, the semantic segmentation and annotation of 3D models of historic buildings is an important modern topic. This work describes a software tool currently under development, for interactive and semi-automatic segmentation, characterization, and annotation of 3D models produced by photogrammetric surveys. The system includes some generic and well-known segmentation approaches, such as region growing and Locally Convex Connected Patches segmentation, but it also contains original code for specific semantic segmentation of parts of buildings, in particular straight stairs and circular-section columns. Furthermore, a method for automatic wall-surface characterization is devoted to rusticated-ashlar detection, in view of masonry-unit segmentation. The software is modular, so allowing easy expandability. It also has tools for data encoding into formats ready for model fruition by Web technologies. These results were partly obtained in collaboration with Corvallis SPA (Padua-Italy, http://www.corvallis.it).
A software tool for the semi-automatic segmentation of architectural 3D models with semantic annotation and Web fruition
De Nunzio G.
2018-01-01
Abstract
The thorough documentation of Cultural Heritage artifacts is a fundamental concern for management and preservation. In this context, the semantic segmentation and annotation of 3D models of historic buildings is an important modern topic. This work describes a software tool currently under development, for interactive and semi-automatic segmentation, characterization, and annotation of 3D models produced by photogrammetric surveys. The system includes some generic and well-known segmentation approaches, such as region growing and Locally Convex Connected Patches segmentation, but it also contains original code for specific semantic segmentation of parts of buildings, in particular straight stairs and circular-section columns. Furthermore, a method for automatic wall-surface characterization is devoted to rusticated-ashlar detection, in view of masonry-unit segmentation. The software is modular, so allowing easy expandability. It also has tools for data encoding into formats ready for model fruition by Web technologies. These results were partly obtained in collaboration with Corvallis SPA (Padua-Italy, http://www.corvallis.it).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
