Automated crack detection based on image processing is widely used when inspecting concrete structures. The existing methods for crack detection are not yet accurate enough due to the difficulty and complexity of the problem; thus, more accurate and practical methods should be developed. This paper proposes an automated crack detection method based on image processing using the light gradient boosting machine (LightGBM), one of the supervised machine learning methods. In supervised machine learning, appropriate features should be identified to obtain accurate results. In crack detection, the pixel values of the target pixels and geometric features of the cracks that occur when they are connected linearly should be considered. This paper proposes a methodology for generating features based on pixel values and geometric shapes in two stages. The accuracy of the proposed methodology is investigated using photos of concrete structures with adverse conditions, such as shadows and dirt. The proposed methodology achieves an accuracy of 99.7%, sensitivity of 75.71%, specificity of 99.9%, precision of 68.2%, and an F-measure of 0.6952. The experimental results demonstrate that the proposed method can detect cracks with higher performance than the pix2pix-based approach. Furthermore, the training time is 7.7 times shorter than that of the XGBoost and 2.3 times shorter than that of the pix2pix. The experimental results demonstrate that the proposed method can detect cracks with high accuracy. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Photographs of bridges can reveal considerable technical information such as the part of the structure that is damaged and the type of damage. Maintenance and inspection engineers can benefit greatly from a technology that can automatically extract and express such information in readable sentences. This is possibly the first study on developing a deep learning model that can generate sentences describing the damage condition of a bridge from images through an image captioning method. Our study shows that by introducing an attention mechanism into the deep learning model, highly accurate descriptive sentences can be generated. In addition, often multiple forms of damage can be observed in the images of bridges; hence, our algorithm is adapted to output multiple sentences to provide a comprehensive interpretation of complex images. In our dataset, the scores of Bilingual Evaluation Understudy (BLEU)-1 to BLEU-4 were 0.782, 0.749, 0.711, and 0.693, respectively, and the percentage of correctly output explanatory sentences is 69.3%. All of these results are better than the model without the attention mechanism. The developed method makes it possible to provide user-friendly, text-based explanations of bridge damage in images, making it easier for engineers with relatively little experience and even administrative staff without extensive technical expertise to understand images of bridge damage. Future research in this field is expected to lead to the unification of field expertise with artificial intelligence (AI), which will be the foundation of the evolutionary development of bridge inspection AI.

Due to their wide applicability in inspection of concrete structures, there is considerable interest in the development of automated crack detection method by image processing. However, the accuracy of existing methods tends to be influenced by the existence of traces of tie-rod holes and formworks. In order to reduce these influences, this paper proposes a crack detection method based on semantic segmentation by deep learning. The accuracy of developed method is investigated by the photos of concrete structures with lots of adverse conditions including shadow and dirt, and it is found that not only the crack region could be detected but also the trace of tie-rod holes and formworks could be removed from the detection result with high accuracy. This paper is the English translation from the authors' previous work [Yamane, T. and Chun, P., (2019). "Crack detection from an image of concrete surface based on semantic segmentation by deep learning."

Machine learning models have been developed to perform damage detection using images to improve bridge inspection efficiency. However, in damage detection using images alone, the 3D coordinates of the damage cannot be recorded. Furthermore, the accuracy of the detection depends on the quality of the images. This paper proposes a method to integrate and record the damage detected from multiple images into a 3D model using deep learning to detect the damage from bridge images and structure from motion to identify the shooting position. The proposed method reduces the variability of the detection results between images and can assess the scale of damage or, conversely, where there is no damage and the extent of inspection omissions. The proposed method has been applied to a real bridge, and it has been shown that the actual damage locations can be recorded as a 3D model.

To conduct safety checks of corroded steel structures and formulate appropriate maintenance strategies, the residual strength of steel structural members must be assessed with high accuracy. Finite element method (FEM) analyses that precisely recreate the morphology of corroded surfaces using solid elements are expected to accurately assess the strength; however, the cost of conducting these calculations is extremely high. Therefore, a model that uses mean thickness as the thickness of the shell element is widely used but this method has precision issues, particularly regarding overestimation of risk. Thus, this study proposes a method of structural analysis in which the effective thickness of a shell element is assessed using the convolutional neural network (CNN), a type of deep learning performed on tensile structural members. An FEM model is then built based on the shell element that uses this effective thickness. We cross-validated this method by adding a feature extraction layer that reflects the domain knowledge, together with convolutional and pooling layers that are commonly used for CNN and found that a high level of accuracy could be achieved. Furthermore, regarding corroded steel plates and H-section steel, our method demonstrated results that were extremely close to those of models that used solid elements.