Abstract
AbstractIn this chapter, we present an approach of enriching photogrammetric point clouds with semantic information extracted from images of digital cameras or smartphones to enable a later automation of BIM modelling with object-oriented models. Based on the DeepLabv3+ architecture, we extract building components and objects of interiors in full 3D. During the photogrammetric reconstruction, we project the segmented categories derived from the images into the point cloud. Based on the semantic information, we align the point cloud, correct the scale and extract further information. The combined extraction of geometric and semantic information yields a high potential for automated BIM model reconstruction.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
