Deep Learning-Based Crack Detection and Classification for Concrete Structures Inspection

Automatic crack detection is a main task in a crack map generation of the existing concrete infrastructure inspection. This paper presents an automatic crack detection and classification method based on genetic algorithm (GA) to optimize the parameters of image processing techniques (IPTs). The crack detection results of concrete infrastructure surface images under various complex photometric conditions still remain noise pixels. Next, a deep convolution neural network (DCNN) method is applied to classify crack candidates and non-crack candidates automatically. Moreover, the proposed method compared with the different deep learning methods for crack detection. The experimental results validate the reasonable accuracy in practical application.