Automatic detection method of cracks from concrete surface imagery using two‐step light gradient boosting machine

Abstract

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.

Development of a Machine Learning-Based Damage Identification Method Using Multi-Point Simultaneous Acceleration Measurement Results

“…The authors have already published crack detection [ 28 ] and nondestructive inspection methods [ 29 ] using decision tree-based algorithms such as Random Forest. In this section, however, the authors will also summarize the theory of Random Forest for the convenience of the reader.…”

Automatic Detection of Cracks in Asphalt Pavement Using Deep Learning to Overcome Weaknesses in Images and GIS Visualization

“…The present method is positioned as one that can obtain the crack ratio correctly unlike object detection methods such as SSD, and the effort of annotation is much smaller compared to semantic segmentation techniques such as Mask R-CNN. Based on our experience in [21][22][23][24][25][26] with research on damage detection using machine learning and deep learning, we believe that to improve the accuracy of deep learning, it is necessary not only to increase the amount of data but also to improve the quality of the training data. Therefore, in this study, we develop a framework to focus on training of types of images that are difficult to detect, from the viewpoint of improving the training performance.…”

Crack Detection from a Concrete Surface Image Based on Semantic Segmentation Using Deep Learning

“…There are much more projects such as the one by Amarasiri et al (2009), in which they proposed a crack detection technique using the bidirectional reflection distribution function derived from the model based on the Gaussian reflectance model introduced by Ward (1992); a research work by Lee et al (2013) that combined the binarization with a noise processing and a thinning processing; and a method proposed by Sohn et al (2005), in which they used a three dimension analysis based on the photogrammetric methods combined with the Hough transform and a filter processing. The author's group also proposed a method to detect the crack by focusing on the geometrical features (Chun and Igo 2015;Chun et al 2020b). There are various other methodologies.…”