Intelligence Approach for Structural Monitoring via UAV-Artificial Intelligence-Based

In this work a novel artificial intelligence is trained with the structures images pickup by unmanned aerial vehicles (UAVs) for crack monitoring for extraction of structures state maps. The integrated between UAV sand artificial intelligence algorithm are increased the level of structures monitoring. In the same time, the self-motion influence of UAVs during detection is solved to enhancements of detection accuracy in order to meet the application of intelligent monitoring system. First, a deep convolutional neural network (CNN) is introduced for UAV generated image processing. Then, the performance of the existing crack image datasets and model are summarized. The results show that the proposed CNN network has achieved better performance, reaching 88.1 %, 87.1%, 88.5%, and 125 sec in terms of accuracy, regression, F-score, and training time, respectively, which can realize the automatic extraction of high-dimensional, complex, and abstract features of civil structures, in addition, the detection results can reduce interference, reduce detection error, obtain more completion, and clear the civil structures detection effect.