Distress Detection in Subway Tunnel Images via Data Augmentation Based on Selective Image Cropping and Patching

Maeda, Keisuke; Takada, Saya; Haruyama, Tomoki; Togo, Ren; Ogawa, Takahiro; Haseyama, Miki

Distress Detection in Subway Tunnel Images via Data Augmentation Based on Selective Image Cropping and Patching

Maeda, Keisuke; Takada, Saya; Haruyama, Tomoki et al.

Sensors, 2022, 22(22), 8932

Permalink : https://hdl.handle.net/2115/87629

このアイテムのアクセス数:378件（2026-01-18 22:08 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
https://doi.org/10.3390/s22228932

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	metadata only access
URI	https://hdl.handle.net/2115/87629
タイトル	Distress Detection in Subway Tunnel Images via Data Augmentation Based on Selective Image Cropping and Patching
著者	Maeda, Keisuke ; Takada, Saya ; Haruyama, Tomoki ; Togo, Ren ; Ogawa, Takahiro ; Haseyama, Miki
著者名 Maeda, Keisuke
著者名 Takada, Saya
著者名 Haruyama, Tomoki
著者名 Togo, Ren
e-Rad_Researcher 20524028 著者名 Ogawa, Takahiro
e-Rad_Researcher 00218463 著者名 Haseyama, Miki
言語	英語
キーワード	deep learning
	distress detection
	data augmentation
	subway tunnels
	maintenance
発行日	2022-11-18
出版者	MDPI
収録物名	Sensors
巻(号)	22(22)
ページ	8932
抄録	Distresses, such as cracks, directly reflect the structural integrity of subway tunnels. Therefore, the detection of subway tunnel distress is an essential task in tunnel structure maintenance. This paper presents the performance improvement of deep learning-based distress detection to support the maintenance of subway tunnels through a new data augmentation method, selective image cropping and patching (SICAP). Specifically, we generate effective data for training the distress detection model by focusing on the distressed regions via SICAP. After the data augmentation, we train a distress detection model using the expanded training data. The new image generated based on SICAP does not change the pixel values of the original image. Thus, there is little loss of information, and the generated images are effective in constructing a robust model for various subway tunnel lines. We conducted experiments with some comparative methods. The experimental results show that the detection performance can be improved by our data augmentation.
資源タイプ	学術雑誌論文
出版タイプ	Version of Record
EISSN	1424-8220
関連情報 (isIdenticalTo)	出版社版DOI https://doi.org/10.3390/s22228932