Semantic Segmentation of Cracks on Masonry Surfaces Using Deep-Learning Techniques

Detecting cracks can be challenging, especially on rough surfaces such as masonry. This research paper focuses on the detection of surface cracks on masonry surfaces using deep-learning techniques. This study compared the performance of various networks trained using deep-learning techniques for semantic segmentation of cracks on masonry surfaces. For the semantic segmentation of cracks, the segmentation models U-Net, feature pyramid network (FPN), DeepLabV3+, and PSPNet were integrated with several convolutional neural networks (CNNs) acting as the network's backbone. Two loss functions, binary cross entropy and binary focal loss, were used in the study. Comparisons among networks using different metrics were performed to find the most promising approaches. Over the training and validation masonry data sets, a total of 23 networks were examined. The results of this study show that three networks can also accurately detect finer surface cracks on masonry surfaces. Based on performance metrics [dice coefficient, intersection over union (IoU), and F1 score], the three best networks were FPN(#2a) (86.9%, 74.9%, 59.3%), FPN(#2c) (85.6%, 75.4%, 56.3%), DeepLabV3+(#1a) (83.1%, 72.0%, 54.4%), respectively. Trained networks have demonstrated proficient performance on existing masonry culverts. This study can significantly aid the detection of cracks in the masonry substructure of old railway bridges.