Automatic crack detection and structural inspection of cultural heritage buildings using UAV photogrammetry and digital twin technology

Current methods for rapidly inspecting structures are difficult to document and subjective. Automating the process with innovative technologies is necessary to overcome these limitations. Precisely monitoring cracking in cultural heritage buildings is vital as they pose a significant risk to their integrity. Recent advancements in artificial intelligence, including imaging equipment and computer vision, offer significant advantages for automating the detection of structural cracks. This study conducted tests to investigate utilizing unmanned aerial vehicle photogrammetry, a modern surveying method, for monitoring such inspections. Initially, a level of detail 3 digital model of the structure was generated. Finally, the metric accuracy of the detected cracks was analyzed. The cracks measured by the traditional method were considered as reference data and compared with the automatically detected cracks. As a result, 83 % of the cracks were detected by the modern techniques and the RMSE value was 0.802 cm because of the metric comparison.