“…The current research on crack edge detection based on deep learning is mainly to improve the methods based on a fully convolutional network (FCN; Dung & Anh, 2019; Li et al., 2019; Ye et al., 2019), a self‐attention mechanism (Y. Pan et al., 2020; Song et al., 2019), CNN (Fei et al., 2019; S.‐Y. Kong et al., 2021; Ni et al., 2019; A. Zhang et al., 2017), UNet (J. Chen & He, 2022), recurrent neural network (RNN; A. Zhang et al., 2018), and DeepLab (Meng et al., 2020). Besides, some researchers utilize multi‐stage crack detection and achieve high‐precision crack edge detection by combining the classification algorithm with the segmentation algorithm (J. Liu et al., 2020; Meng et al., 2022).…”