Deep learning-based fast detection of apparent concrete crack in slab tracks with dilated convolution. (25th April 2022)

• Record Type: Journal Article
• Authors: Ye, Wenlong; Deng, Shijie; Ren, Juanjuan; Xu, Xueshan; Zhang, Kaiyao; Du, Wei
• Is Part Of: Construction & building materials. Volume 329(2022)
• Publication Date: 2022-04-25
• Subjects: Deep learning -- STCNet Ⅰ -- Concrete crack image -- Fast detection -- Crack segmentation; Building materials -- Periodicals; 624.18
• DOI: 10.1016/j.conbuildmat.2022.127157
• Languages: English
• ISSNs: 0950-0618

Abstract

Highlights: A large number of images of apparent concrete cracks were acquired based on advanced equipment. A fast detection network architecture for detecting apparent cracks in slab tracks was proposed. Comparing the performance of the classical network structure and the STCNet Ⅰ model. Watershed algorithm was used to accurately segment the area of the concrete crack. Abstract: Slab tracks exposed to complicated environmental factors over a long period can cause cracks in the concrete, and if these cracks gradually expand, the concrete's durability and service life will be greatly impacted. How to quickly and effectively detect concrete cracks has become an urgent challenge during the maintenance and repair of high-speed railway slab tracks. In this study, a large number of images of concrete cracks were collected in a database, and STCNet Ⅰ, a fast detection network architecture using dilated convolution based on deep learning, was proposed to detect apparent concrete cracks in slab tracks. After that, the watershed algorithm was used to segment the detected cracks. The results show that: I) compared with traditional network models, the STCNet Ⅰ provides a faster calculation at lower space complexity. The number of parameters used in this network is reduced by 96.03% and 93.28%, respectively compared with that in the VGG 16 and ResNet 50, and the time complexity is lower, with the calculation time reduced by 49.94% and 73.28%, respectively; II) the average recognition accuracy on the training set and the validation set reached as high as 99.71% and 99.33%, respectively, proving the robustness of the model; III) the accuracy and F1 score in the test samples of concrete crack reached 99.54% and 99.54%, indicating the strong generalization ability of the model; and IV) the concrete crack area was accurately detected, and the crack contour was fully closed and continuous. The research results from this paper provide an improved detection method of slab tracks and promote the fine detection and maintenance of the apparent concrete of slab tracks.