An innovative image processing-based framework for the numerical modelling of cracked masonry structures

A vital aspect when modelling the mechanical behaviour of existing masonry structures is accuracy in which geometry real structure transferred numerical model. Commonly, captured with traditional techniques (e.g. visual inspection and manual surveying methods), are labour intensive error-prone. Over last ten years, advances photogrammetry image processing have started to change building industry since it possible capture rapidly remotely digital records objects features. Although limited work exists detecting distinct features from structures, up now there no automated procedure leading image-based recording their modelling. To address this, an innovative framework, based on image-processing, has been developed that automatically extracts geometrical (i.e. units, mortar, cracks pathologies, etc.) generate for advanced The proposed watershed-based algorithm initially deconstructs segmentation, then reconstructs them form shared vertices edges, finally converts scalable polylines. polylines extracted simplified using a contour generalisation procedure. elements further modified facilitate transition environment. framework tested by comparing analysis results undamaged damaged models generated through algorithmic approaches. methodology demonstrated here use discrete element modelling, can be applied other computational approaches detailed micro-modelling approach evaluating structural structures.