Image-based segmentation and quantification of weak interlayers in rock tunnel face via deep learning

被引：44

作者：

Chen, Jiayao ^{[1
]}

Zhang, Dongming ^{[1
]}

Huang, Hongwei ^{[1
]}

Shadabfar, Mahdi ^{[1
,2
]}

Zhou, Mingliang ^{[1
]}

Yang, Tongjun ^{[3
]}

机构：

[1] Tongji Univ, Dept Geotech Engn, Key Lab Geotech & Underground Engn, Minist Educ, Shanghai, Peoples R China

[2] Sharif Univ Technol, Dept Civil Engn, Tehran, Iran

[3] Yunnan Transportat Construct Grp Co Ltd, 188 Linxi Rd, Kunming, Yunnan, Peoples R China

来源：

AUTOMATION IN CONSTRUCTION | 2020年 / 120卷 / 120期

关键词：

Rock tunnel; Convolutional neural network; Weak interlayer; Image segmentation; CONVOLUTIONAL NEURAL-NETWORK; CRACK DETECTION; AUTOMATED DETECTION; DEFECTS;

D O I：

10.1016/j.autcon.2020.103371

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

In this paper, an advanced integrated pixel-level method based on the deep convolutional neural network (DCNN) approach named DeepLabv3+ is proposed for weak interlayers detection and quantification. Furthermore, a database containing 32,040 images of limestone, dolomite, loess clay, and red clay is established to verify this method. The proposed model is then trained, validated, and tested via feeding multiple weak interlayers. Moreover, robustness and adaptability of the proposed model are evaluated, and the weak interlayers are extracted. Compared with the fully convolutional network (FCN)-based method and traditional image techniques, the proposed model provides higher accuracy in terms of boundary recognition. Besides, it can further detect multiple weak interlayers at the pixel level in practice. The results reveal that the proposed model can efficiently segment damage for rock tunnel faces, eliminate more noises, and consequently provide a much faster running speed.

引用

页数：13

共 55 条

[1] Deep learning for biological image classification [J].