Image-based concrete crack detection in tunnels using deep fully convolutional networks. (20th February 2020)

• Record Type: Journal Article
• Authors: Ren, Yupeng; Huang, Jisheng; Hong, Zhiyou; Lu, Wei; Yin, Jun; Zou, Lejun; Shen, Xiaohua
• Is Part Of: Construction & building materials. Volume 234(2020)
• Publication Date: 2020-02-20
• Subjects: SHM structural health monitoring -- CNN convolutional neural network -- FCN fully convolutional network -- PSPNet Pyramid Scene Parsing Network -- SPP spatial pyramid pooling -- ReLU Rectified Linear Unit -- PA pixel accuracy -- IoU Intersection over union; Concrete -- Crack detection -- Deep learning -- Convolutional neural network -- Pixel-wise segmentation -- Structural health monitoring; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2019.117367
• Languages: English
• ISSNs: 0950-0618

Abstract

Highlights: Deep learning-based automatic segmentation of concrete cracks in tunnels. A new end-to-end crack segmentation method based on fully convolutional networks. More efficiency and higher accuracy than the conventional and other deep learning-based crack segmentation methods. Use of dilated convolution, spatial pyramid pooling, skip connections, and an optimized loss function. Abstract: Automatic detection and segmentation of concrete cracks in tunnels remains a high-priority task for civil engineers. Image-based crack segmentation is an effective method for crack detection in tunnels. With the development of deep learning techniques, especially the development of image segmentation based on convolutional neural networks, new opportunities have been brought to crack detection. In this study, an improved deep fully convolutional neural network, named as CrackSegNet, is proposed to conduct dense pixel-wise crack segmentation. The proposed network consists of a backbone network, dilated convolution, spatial pyramid pooling, and skip connection modules. These modules can be used for efficient multiscale feature extraction, aggregation, and resolution reconstruction which greatly enhance the overall crack segmentation ability of the network. Compared to the conventional image processing and other deep learning-based crack segmentation methods, the proposed network shows significantly higher accuracy and generalization, making tunnel inspection and monitoring highly efficient, low cost, and eventually automatable.