Automatic crack segmentation network based on large kernel pooling transformer
Advances in Structural Engineering · 2026-11 · 29 (15) · 3343-3362
DOI: 10.1177/13694332261420437 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advances in Structural Engineering, online erschienen am 23.03.2026. Verfasst von Jianxin Wang und 3 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China, The Key Project of Natural Science Foundation of Hunan Province, The Scientific Research Fund of Hunan Provincial Education Department.
Abstract (Originalsprache)
Automatic crack segmentation is crucial for ensuring the safe and stable operation of civil concrete buildings. However, due to the irregularity of cracks, low image quality, and complex background environment, automatic crack segmentation on concrete building surfaces still faces significant challenges. To address these issues, an automatic segmentation network (LKT-Net) based on a large kernel pooling Transformer is proposed, aiming to improve the comprehensiveness and accuracy of crack feature extraction while maintaining a lightweight design. First, the large kernel pooling Transformer (LKT) is proposed as the fundamental building block of LKT-Net, which combines large kernel convolution with pooling layers and attention mechanisms to effectively enhance global perception and capture local details at a lower computational cost. To extract edge information accurately, the Feedforward network is improved by integrating the Laplacian operator with multi-scale convolutions, thereby enhancing multiscale edge detection capabilities. Finally, to mitigate information loss during downsampling, we propose a feature enhancement module (FEM) to replace traditional skip-connections, thereby enhancing cross-level feature interactions. The experimental results showed that on three public datasets (DeepCrack537, CrackLS315, and CrackTree260), compared with eight advanced networks, LKT-Net achieved mean Intersection over Union (mIoU) scores of 86.23%, 70.82%, and 83.67%, respectively, demonstrating excellent segmentation performance. The codes are available at: https://github.com/wjxcsust2024/LKT-Net .
Förderung
- National Natural Science Foundation of China
- The Key Project of Natural Science Foundation of Hunan Province
- The Scientific Research Fund of Hunan Provincial Education Department
- Hunan Provincial Education Department Scientific Research Project of China
Zitieren
APA
Wang, J., Wang, J., Li, Y., & Li, L. (2026). Automatic crack segmentation network based on large kernel pooling transformer. Advances in Structural Engineering, 29(15), 3343-3362. https://doi.org/10.1177/13694332261420437
Vancouver
Wang J, Wang J, Li Y, Li L. Automatic crack segmentation network based on large kernel pooling transformer. Advances in Structural Engineering. 2026;29(15):3343-3362. doi:10.1177/13694332261420437
BibTeX
@article{Wang2026,
author = {Wang, Jianxin and Wang, Jin and Li, Yi and Li, Linyi},
title = {Automatic crack segmentation network based on large kernel pooling transformer},
journal = {Advances in Structural Engineering},
year = {2026},
volume = {29},
number = {15},
pages = {3343--3362},
doi = {10.1177/13694332261420437}
}
EUVIMED