Citation

Wang A, Togo R, Ogawa T, Haseyama M. Sensors (Basel) 2022; 22(6): e2330.

Copyright

(Copyright © 2022, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s22062330

PMID

35336501

Abstract

In 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.

Language: en

Keywords

deep learning; U-Net; semantic segmentation; defect detection; subway tunnel