Automated Mapping of the roof damage in historic buildings in seismic areas with UAV photogrammetry

The paper presents a fast methodology to quantify the damage to the roof in historic buildings, suggested soon after a light seismic event occurs, in order to evaluate the necessity of provisional interventions to prevent further damages. The survey is based on UAV photogrammetry, a well-known technique that allows inspection and digital documentation even in hardly accessible or dangerous areas. The research aims to analyze the feasibility of the automated mapping of roof damage using an image classification procedure based on supervised machine learning. The procedure is summed up in an efficient workflow, where UAV photogrammetry is combined with other 3D survey techniques, such as terrestrial photogrammetry and laser scanning, to provide comprehensive documentation and quantitative data on a historical building. The methodology was validated on a large historical building, now suffering from a serious state of neglect, which roof was never surveyed before and with different damage types. The output orthoimage of the tiled roof allowed us to understand the past interventions and the current serious damage state with promising outcomes regarding the speed of the survey method.