Cracks in Concrete

Finding cracks in images of concrete and properly classifying each pixel to belong either to a crack or to the complement of the crack system, i.e., segmenting the image into crack system and background, is a challenging task. Cracks are thin and rough, and being air filled they yield a very weak contrast in 3D images obtained by computed tomography. Enhancing and segmenting dark lower-dimensional structures is already demanding. The heterogeneous concrete matrix and typical computed tomography images having more than 8 million voxels further increase the complexity. Machine learning methods have proven to solve difficult segmentation problems when trained on enough and well-annotated data. However, so far, there is not much 3D image data of cracks available at all, let alone annotated. Interactive annotation is error-prone as humans can easily tell cats from dogs or roads without from roads with cars but have a hard time deciding whether a thin and dark structure seen in a 2D slice continues in the next one. Training networks by synthetic, simulated images is an elegant way out, yet bears its own challenges. In this contribution, we describe how to generate semisynthetic image data to train CNN like the well-known 3D U-Net or random forests for segmenting cracks in 3D images of concrete. The thickness of real cracks varies widely, even within the same sample and within one crack. The segmentation method should therefore be invariant with respect to scale changes. We introduce the so-called RieszNet designed for exactly this purpose. Finally, we discuss how to generalize the ML crack segmentation methods to other concrete types.