Artificial Neural Network-Based Automated Crack Detection and Analysis for the Inspection of Concrete Structures

The damage investigation and inspection methods for infrastructures performed in small-scale (type III) facilities usually involve a visual examination by an inspector using surveying tools (e.g., cracking, crack microscope, etc.) in the field. These methods can interfere with the subjectivity of the inspector, which may reduce the objectivity and reliability of the record. Therefore, a new image analysis technique is needed to automatically detect cracks and analyze the characteristics of the cracks objectively. In this study, an image analysis technique using deep learning is developed to detect cracks and analyze characteristics (e.g., length, and width) in images for small-scale facilities. Three stages of image processing pipeline are proposed to obtain crack detection and its characteristics. In the first and second stages, two-dimensional convolutional neural networks are used for crack image detection (e.g., classification and segmentation). Based on convolution neural network for the detection, hierarchical feature learning architecture is applied into our deep learning network. After deep learning-based detection, in the third stage, thinning and tracking algorithms are applied to analyze length and width of crack in the image. The performance of the proposed method was tested using various crack images with label and the results showed good performance of crack detection and its measurement.