Heritage Information Modeling: The Case of Chellah’s Gate

Abstract

This paper aims to propose an integrated workflow for the digitization of the built cultural heritage. To this end, we leverage the power of computational tools and the relevancy of Building Information Modeling (BIM) process to overcome the limitations and challenges faced by Scan-to-BIM. We describe the automatic generation of an as-built BIM model of a heritage building in a three-step procedure. Firstly, we outline the data acquisition method of the point cloud. Secondly, we describe the automatic processing and segmentation of the point cloud according to architectural elements using Machine Learning. Then, we tested and compared various meshing algorithms and utilized a combination depending on the desired level of details. Lastly, the resulting geometry is converted into a BIM object that will be subsequently semantically labeled. We used a UNESCO world heritage in Morocco—Chellah, as a case study to test the robustness of our protocol.