Machine vision-enhanced postearthquake inspection

Abstract

Current postearthquake inspection of structures relies on certified inspectors to make an assessment of the existing safety of the structure based primarily on qualitative measures. Completing the required inspection takes weeks to complete, which has adverse economic and societal impacts on the affected population. This paper proposes an automated framework for rapid postearthquake building evaluation. Under the framework, the visible damage (cracks and spalling) inflicted on RC members (columns) is detected using machine vision. The damage properties are then measured in relationship to the column's dimensions and orientation, so that the existing state of the column can be approximated as a damage index. The column damage index is then used to query fragility curves of similar buildings, constructed from the analyses of existing and ongoing experimental data. The framework is expected to automate the collection of building damage data, to provide a quantitative assessment of the building damage state, and to estimate the vulnerability of the building in the event of an aftershock.