To read this content please select one of the options below:

UCAN: U-shaped context aggregation network for thin crack segmentation under topological constraints

Jie Chen (College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China)
Guanming Zhu (College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China)
Yindong Zhang (College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China)
Zhuangzhuang Chen (College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China)
Qiang Huang (College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China)
Jianqiang Li (National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China)

Robotic Intelligence and Automation

ISSN: 2754-6969

Article publication date: 16 August 2024

Issue publication date: 29 August 2024

53

Abstract

Purpose

Thin cracks on the surface, such as those found in nuclear power plant concrete structures, are difficult to identify because they tend to be thin. This paper aims to design a novel segmentation network, called U-shaped contextual aggregation network (UCAN), for better recognition of weak cracks.

Design/methodology/approach

UCAN uses dilated convolutional layers with exponentially changing dilation rates to extract additional contextual features of thin cracks while preserving resolution. Furthermore, this paper has developed a topology-based loss function, called ℓcl Dice, which enhances the crack segmentation’s connectivity.

Findings

This paper generated five data sets with varying crack widths to evaluate the performance of multiple algorithms. The results show that the UCAN network proposed in this study achieves the highest F1-Score on thinner cracks. Additionally, training the UCAN network with the ℓcl Dice improves the F1-Scores compared to using the cross-entropy function alone. These findings demonstrate the effectiveness of the UCAN network and the value of incorporating the ℓcl Dice in crack segmentation tasks.

Originality/value

In this paper, an exponentially dilated convolutional layer is constructed to replace the commonly used pooling layer to improve the model receptive field. To address the challenge of preserving fracture connectivity segmentation, this paper introduces ℓcl Dice. This design enables UCAN to extract more contextual features while maintaining resolution, thus improving the crack segmentation performance. The proposed method is evaluated using extensive experiments where the results demonstrate the effectiveness of the algorithm.

Keywords

Acknowledgements

This work is supported in part by the National Natural Science Funds for Distinguished Young Scholar under Grant 62325307, in part by the National Natural Science Foundation of China under Grants 62072315, 62073225, 62176164, 62203134 and 62002239, in part by the Shenzhen Science and Technology Innovation Commission under Grants 20220809141216003, 20220809154139001, JCYJ20210324093808021 and JCYJ20220531102817040 and in part by the Scientific Instrument Developing Project of Shenzhen University under Grant 2023YQ019.

Citation

Chen, J., Zhu, G., Zhang, Y., Chen, Z., Huang, Q. and Li, J. (2024), "UCAN: U-shaped context aggregation network for thin crack segmentation under topological constraints", Robotic Intelligence and Automation, Vol. 44 No. 5, pp. 637-647. https://doi.org/10.1108/RIA-08-2023-0097

Publisher

:

Emerald Publishing Limited

Copyright © 2024, Emerald Publishing Limited

Related articles