Enhancing Structural Crack Detection through a Multiscale Multilevel Mask Deep Convolutional Neural Network and Line Similarity Index

This paper proposes a novel and practical crack-detection method for infrastructure. The proposed method exhibits three key components. First, a multiscale multilevel mask deep convolutional neural network (MSML Mask DCNN) is proposed to accurately estimate crack candidates comprising linear and curvilinear features. Second, the proposed neural network is trained using only public image-sets. The main principle of this approach is that cracks have unique and distinct features, and therefore, public image-sets provide sufficient information to estimate crack candidates for a neural network. Third, a line similarity index (LSI), which is calculated using the Hough transform and coordinate transformation with principal component analysis, is incorporated to eliminate non-crack candidates from crack candidates based on two key characteristics: the variation in crack features with respect to the representative line and the number of crack features that crossed the representative line. Addressing these two crack-related characteristics improves accuracy and robustness by effectively eliminating non-crack features. Field tests performed inside a building and in an underground power tunnel demonstrated the effectiveness of the proposed method. The MSML Mask DCNN outperformed other neural networks, accurately recognizing local crack candidates characterized by linear and curvilinear features even though only public image-sets were used for training. The proposed LSI also effectively eliminated non-crack candidates estimated by the MSML Mask DCNN. The proposed method is practical for real-world applications, where several non-crack objects and noises are typically present.