Abstract
Regular crack inspection of tunnels is essential to guarantee their safe operation. At present, the manual detection method is time-consuming, subjective and even dangerous, while the automatic detection method is relatively inaccurate. Detecting tunnel cracks is a challenging task since cracks are tiny, and there are many noise patterns in the tunnel images. This study proposes a deep learning algorithm based on U-Net and a convolutional neural network with alternately updated clique (CliqueNet), called U-CliqueNet, to separate cracks from background in the tunnel images. A consumer-grade DSC-WX700 camera (SONY, Wuxi, China) was used to collect 200 original images, then cracks are manually marked and divided into sub-images with a resolution of pixels. A total of 60,000 sub-images were obtained in the dataset of tunnel cracks, among which 50,000 were used for training and 10,000 were used for testing. The proposed framework conducted training and testing on this dataset, the mean pixel accuracy (MPA), mean intersection over union (MIoU), precision and F1-score are 92.25%, 86.96%, 86.32% and 83.40%, respectively. We compared the U-CliqueNet with fully convolutional networks (FCN), U-net, Encoder–decoder network (SegNet) and the multi-scale fusion crack detection (MFCD) algorithm using hypothesis testing, and it’s proved that the MIoU predicted by U-CliqueNet was significantly higher than that of the other four algorithms. The area, length and mean width of cracks can be calculated, and the relative error between the detected mean crack width and the actual mean crack width ranges from −11.20% to 18.57%. The results show that this framework can be used for fast and accurate crack semantic segmentation of tunnel images.
Highlights
U-CliqueNet on the tunnel crack datasets that we set skeleton extraction was carried out for the predicted binary image, the area, length and width up and compared with these most recent algorithms: fully convolutional networks (FCN) [23] proposed by Yang et al, U-net [25]
We evaluate our method on the test dataset of tunnels that were never used in the training set and compare with the following recent methods: U-Net, FCN, SegNet and multi-scale fusion crack detection (MFCD)
Clique block and attention mechanism are introduced into U-net
Summary
Tunnel construction technology is becoming increasingly sophisticated, but how to maintain the tunnels is a problem troubling the society [1]. Traditional monitoring methods rely on manual crack detection [3], but the process is subjective and operators face very difficult or even dangerous conditions, such as dust conditions, insufficient light or toxic exposure [4]. Another reason is that it’s time-consuming and laborious to detect the cracks. Sensors 2020, 20, 717 insufficient light or toxic exposure [4] Another reason is that it’s time-consuming and laborious to detect the cracks from thousands of pictures manually in front of the computer, so researchers are from thousands pictures manually in front of the computer, so[5].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
