文献类型：期刊文献

英文题名：Research on Automatic Segmentation Algorithm of Tunnel Cracks Based on Generative Adversarial Network

作者：Li, Ziyi[1]; Rao, Zhiqiang[1]; Chang, Hui[2]; Li, Yichen[1]; Ding, Lu[1]; Fang, Jianjun[1]

第一作者：Li, Ziyi

机构：[1] College of Urban Rail Transit and Logistics, Beijing Union University, Beijing, 100101, China; [2] Institute of Automation, Chinese Aeademy of Seienees, Beijing, 100190, China

第一机构：北京联合大学城市轨道交通与物流学院

年份：2023

卷号：45

期号：5

起止页码：136-142

外文期刊名：Tiedao Xuebao/Journal of the China Railway Society

收录：EI(收录号：20233314550849)

语种：英文

外文关键词：Crack detection - Discriminators - Image segmentation - Railroad tunnels - Statistical tests

摘要：Traditional crack recognition technology requires a large number of crack images with annotations as experimental data sets. In order to reduce the workload of crack image annotation, a crack-GAN network was constructed for automatic segmentation of tunnel cracks by using the characteristics and advantages of generative adversarial network. The Crack-GAN network structure integrated two modules; the generator network of U-NET network integrating residual modules and the discriminator network generating confidence graphs using full convolution network. Firstly, the U-NET module used dense residual modules to generate deep representations that retain fine-grained information. Secondly, the discriminator was used to determine the true or false input. Finally, through end-to-end training and continuous iteration between generative adversarial models, the generated model reached the optimal state of crack segmentation. The test results show that compared with existing networks under the same conditions, the Crack-GAN network exhibits 98.35% pixel accuracy, 71.23% accuracy, 80.78% recall rate and 75.98% F1 score in self-made railway tunnel crack data set, with single detection time of 80ms and better overall performance than U-NET and CrackSegNet. ? 2023 Science Press. All rights reserved.