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.

The study proposes a rotational multipyramid network (RoMP Net) with bounding-box transformation for object detection. The RoMP Net is a single-stage object detection neural network featuring three characteristics. First, the network uses a rotational bounding box to minimize the effect of background images when extracting features of objects. Bounding-box transformation was proposed to compensate for the limitation of the rotational bounding boxes, which have relatively low prediction accuracy for objects with a high aspect ratio. Second, the RoMP Net introduces a multi-scale and multi-level feature pyramid network to extract distinct and semantic features efficiently. This network architecture ensures high prediction accuracy and robustness regardless of the size and complexity of objects. Third, hyperparameters in the bounding boxes are automatically determined through an unsupervised clustering method. This optimization method is also critical in improving accuracy. The performance of the proposed network and preprocessing methods are validated through image-sets comprising critical components in power transmission facilities, which have a variety of sizes and aspect ratios. This case study demonstrates the effectiveness and robustness of the three key characteristics in the RoMP Net. Furthermore, the RoMP Net outperforms other state-of-the-art deep neural networks in prediction accuracy and robustness for object detection. Specifically, the mean average precision of the RoMP Net in the validation image-sets shows that it has the highest prediction accuracy, whereas its values in the test image-sets confirm the network's robustness. The fast yet accurate RoMP Net will expand the range of object detection through deep neural networks.