부산대학교 도서관

Vision-based concrete crack detection has recently attracted significant attention from many researchers. Although promising results have been obtained, especially for deep learning (DL) approaches, it is difficult to maintain the robustness of implemented models when tested on completely new data. A possible reason for this is that the extracted feature from the trained set might not fully characterize the crack in the test set. We propose an interdisciplinary approach to improve the effectiveness of vision-based crack detection by modeling crack propagation using fracture mechanics, simulation, and machine learning (ML). Mathematical models of concrete cracks are obtained using ML on the simulation results. Experiments are conducted on various reputable crack image datasets, emphasizing the correlation between simulated and real-world cracks. The importance of propagation models is verified in a classification task, reporting a significant accuracy enhancement on results of some state-of-the-art detection and segmentation models, i.e., 1.27% on average on participating models, and 5.47% on U-Net. This novel approach is expected to have valuable points for a research area where the data quantity and quality still need to be improved.