Methodology for detecting and assessing the dynamics of defects in engineering structures by processing images from an unmanned aerial vehicle

We propose a non-invasive technique for automated detection and assessment of the dynamics of defects in engineering structures based on processing images received from unmanned aerial vehicles during periodic surveillance flights over an engineering structure. The technique includes stages of detecting defects, collating the defect images acquired during the latest and previous surveillance flights, and identifying the dynamics of defect development. An example of the implementation and testing of the methodology for detecting and assessing the dynamics of cracks in metal structures of bridge crossings is given. The technique allows you to significantly reduce the cost of monitoring the condition of defects in engineering structures while increasing the probability of detecting defects.