Deep learning-based rapid inspection of concrete structures

This paper proposes a deep learning-based rapid inspection method for concrete structures. The proposed method is composed of three steps: (1) collection of a large volume of images containing damage information from internet, (2) development of a deep learning model (i.e., convolutional neural network (CNN)) using collected images, and (3) automatic selection of damage images using the trained deep learning model. In the first step, the internet-based search benefits in easy classification of collected images by varying searching word, and in collection of images taken under diverse environmental conditions. In the second step, a transfer learning approach has been introduced to save the time and cost for developing a deep learning model. In the third step, the probability map is introduced based on duplicated searching to make the searching process robust. The whole procedure of the proposed method has been applied to some figures taken in a real structure. This method is expected to facilitate the regular inspection and speed up the assessment of detailed damage distribution the without losing accuracy.