A software tool for the semi-automatic segmentation of architectural 3D models with semantic annotation and Web fruition

Abstract

Semantic segmentation of 3D models of ancient and historic buildings and artifacts is an important modern Cultural Heritage topic. This work describes a software tool currently under development, for interactive and semi-automatic segmentation 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 circular-section columns and straight stairs. 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 obtained in collaboration with Corvallis SPA (Padua – Italy, http://www.corvallis.it).

3D Reconstruction of a Complex Grid Structure Combining UAS Images and Deep Learning

“…CNN methods [53][54][55][56][57][58][59] have also demonstrated their potential for detecting a numerous number of elements in the images and then boost the processing pipeline in terms of constrained tie point extraction or semantic multi-view stereo [60][61][62]. The advantages of image masking for dense point cloud generation are well known in the literature [62][63][64]. While there are multiple readily available segmenation models for oblique aerial photos [63] or buildings [64,65], the generation of pixel-level semantic segmentation for sparse wire objects is challenging.…”

“…The advantages of image masking for dense point cloud generation are well known in the literature [62][63][64]. While there are multiple readily available segmenation models for oblique aerial photos [63] or buildings [64,65], the generation of pixel-level semantic segmentation for sparse wire objects is challenging. The analysis of repetitive patterns [66,67] allows to partly solve this problem for opaque objects (e.g., skyscrapers).…”