Publications / 2018 Proceedings of the 35th ISARC, Berlin, Germany

High Level-of-Detail BIM and Machine Learning for Automated Masonry Wall Defect Surveying

Enrique Valero, Alan Forster, Frédéric Bosché, Camille Renier, Ewan Hyslop and Lyn Wilson
Pages 740-747 (2018 Proceedings of the 35th ISARC, Berlin, Germany, ISBN 978-3-00-060855-1, ISSN 2413-5844)

Despite the rapid development of reality capture technologies and progress in data processing techniques, current visual strategies for defect surveying are time consuming manual procedures. These methods often deliver subjective and inaccurate outcomes, leading to inconsistent conclusions for defect classification and ultimately repair needs. In this paper, a strategy for monitoring the evolution of ashlar masonry walls of historic buildings through reality capture, data processing (including machine learning), and (H)BIM models is presented. The proposed method has been tested, at different levels of granularity, in the main façade of the Chapel Royal in Stirling Castle (Scotland), demonstrating its potential.

Keywords: Terrestrial Laser Scanning, Data Processing, Surveying, HBIM, Ashlar