Deep learning-based instance segmentation of cracks from shield tunnel lining images

Abstract

This paper presents a deep learning (DL)-based method for the instance segmentation of cracks from shield tunnel lining images using a mask region-based convolutional neural network (Mask R-CNN) incorporated with a morphological closing operation. The Mask R-CNN herein is divided into a backbone architecture, a region proposal network (RPN), and a head architecture for specification, and the implementation details are introduced. Compared with the current image processing methods, the proposed DL-based method efficiently detects cracks in an image while simultaneously generating a high-quality segmentation mask for each crack. A shield tunnel lining image dataset is established for crack instance segmentation task. The established dataset contains a total of 1171 labelled crack instances in 761 images. The morphological closing operation was incorporated into a Mask R-CNN to form an integrated model to connect disjoint cracks that belong to one crack. Image tests were carried out among four trained models to explore the effect of the morphological closing operation, network depth, and feature pyramid network on crack segmentation performance, and a relative optimal model is found. The relative optimal model achieves a balanced accuracy of 81.94%, a F₁ score of 68.68%, and an intersection over union (IoU) of 52.72% with respect to 76 test images.

KEYWORDS:

• Crack
• convolutional neural networks
• instance segmentation
• morphological closing operation
• shield tunnel linings
• deep learning

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The authors are grateful to Mr. Qingtong LI from Shanghai Shentong Metro Co., Ltd. for his help in acquiring images of this work. The financial support from the National Natural Science Foundation of China (grant No. 51778474, 51978516, 52022070) and Key innovation team program of innovation talents promotion plan by MOST of China (grant No. 2016RA4059) are gratefully acknowledged.