Search

One of the emerging and powerful tools of Artificial Intelligence (AI) in computer vision is Convolutional Neural Network (CNN) which can outperform traditional algorithms for crack detection by extracting unique image features. The segmentation of crack images is intensively affected by the imbalanced presence of crack and non-crack elements. Tackling the influence of class imbalanced datasets on the training network, we proposed an additive attention gate-based network architecture called Crack Segmentation Network-II (CSN-II). CSN-II has fewer encoder–decoder blocks with improved accuracy and reduced computational cost as compared to other crack segmentation network architectures. An additive attention gate is used as a connecting block between the encoder–decoder section of CSN-II that focuses on significant crack regions in the image. The network performance is evaluated on two different crack image datasets i.e., MSCI (500 images) and CFD (118 images). The experimental results showed that the CSN-II architecture using a local balanced cross-entropy (LBCE) loss function has achieved 98.48 % and 94.39 % mean accuracy for MSCI and CFD dataset, respectively. Furthermore, extensive research experiments are performed on MSCI and CFD datasets to delineate the best combination of five network architectures (U-Net, SegNet, DeepLabv3＋, CSN, and CSN-II) and twelve loss functions for crack segmentation to observe the efficiency for tackling imbalanced dataset. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) have immense potential to solve a broad range of computer vision problems. It has achieved encouraging results in numerous applications of engineering, medical, and other research fields due to the advancement in hardware, data collection procedures, and efficient algorithms. These innovations have changed the way how specific problems are solved as compared to conventional methods. This article presents a review of CNN implementation on civil structure crack detection. The review highlights the significant research that has been performed to detect structure cracks through classification and segmentation of crack images with CNN in the perspective of image pre-processing techniques, processing hardware, software tools, datasets, network architectures, learning procedures, loss functions, and network performance. The key contribution of this review article is the study and analysis of the most recent developments on crack detection using CNN. Additionally, this work also presents a discussion on crack detection through a manual process, image processing techniques, and machine learning methods along with their limitations. Finally, this article aims for assisting the readers to understand the motivation and methodology of the various CNN-based crack detection methods and to invoke them for exploring the solutions of challenges outlined in future research. • The recent crack detection methods have adopted Convolutional Neural Networks for crack classification and segmentation. • Manual crack inspection, IPT's and other traditional ML methods and techniques have several limitations and drawbacks. • The performance of encoder-decoder architectures has better crack detection than that of simple CNN. • The use of augmentation techniques increases the size of dataset which indirectly boosts the network performance. • New loss functions can resolve the imbalanced data issue. [ABSTRACT FROM AUTHOR]