Intelligent mobile detection of cracks in concrete utilising an unmanned aerial vehicle

Abstract

Cracks in constructions may result in negative consequences in terms of expenditure and safety. This in turn highlights the importance of finding ways to detect these cracks easily and effectively. Hence, technological advances play significant role in enabling effective and innovative ideas, such as the use of autonomous drones and artificial intelligence solutions. In this research, we utilise a type of drone called an unmanned aerial vehicle, equipped with a high-speed camera that can capture images of cracks in buildings, and pass the information to the system. We utilised a dataset that has images collected from different Middle East Technical University (METU) campus buildings with various concrete surfaces (with and without cracks). The crack detection approach uses statistical measures and a support vector machine that prevents overfitting, attains a good rate of accuracy, tackles problems in real-time, and can train a model when a small dataset exists. The combination of an unmanned aerial vehicle, artificial intelligence, and digital image processing gives excellent results. Performance metrics reported for seven rounds of experiments showed rates of accuracy in detection ranging from 83.3–100% (with 100% achieved in two rounds). This demonstrates the effectiveness of our proposed detection system in detecting cracks in constructions.