2024-03-29T05:48:56Zhttps://eprints.lib.hokudai.ac.jp/dspace-oai/requestoai:eprints.lib.hokudai.ac.jp:2115/850812022-11-17T02:08:08Zhdl_2115_20053hdl_2115_145Defect Detection of Subway Tunnels Using Advanced U-Net NetworkWang, AnTogo, RenOgawa, TakahiroHaseyama, Mikideep learningsemantic segmentationU-Netdefect detectionsubway tunnel007In this paper, we present a novel defect detection model based on an improved U-Net architecture. As a semantic segmentation task, the defect detection task has the problems of background-foreground imbalance, multi-scale targets, and feature similarity between the background and defects in the real-world data. Conventionally, general convolutional neural network (CNN)-based networks mainly focus on natural image tasks, which are insensitive to the problems in our task. The proposed method has a network design for multi-scale segmentation based on the U-Net architecture including an atrous spatial pyramid pooling (ASPP) module and an inception module, and can detect various types of defects compared to conventional simple CNN-based methods. Through the experiments using a real-world subway tunnel image dataset, the proposed method showed a better performance than that of general semantic segmentation including state-of-the-art methods. Additionally, we showed that our method can achieve excellent detection balance among multi-scale defects.MDPIJournal Articlehttp://hdl.handle.net/2115/850811424-8220Sensors22623302022-03-17enginfo:doi/10.3390/s22062330none