Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation

Detecting cracks with pixel-level precision for key structures is a significant challenge, existing methods struggle to integrate local textures and pixel dependencies of cracks. Furthermore, these methods possess numerous parameters and substantial computational requirements, complicating deployment on edge devices. In this paper, we propose the Staircase Cascaded Fusion Crack Segmentation Network (CrackSCF), which generates high-quality crack segmentation maps while reducing computational overhead. We design a lightweight convolutional block that substitutes all convolution operations, reducing the model's computational demands while maintaining an effective capture of local details. Additionally, we introduce a lightweight long-range dependency extractor to better capture the long-range dependencies. Furthermore, we develop a staircase cascaded fusion module, which seamlessly integrates local patterns and long-range dependencies, resulting in high-quality segmentation maps. To comprehensively evaluate our method, we created the challenging TUT benchmark dataset and evaluated it alongside five other public datasets. The results show that our method outperforms existing methods, particularly in handling background noise and achieving detailed segmentation. The F1 and mIoU scores on the TUT dataset are 0.8382 and 0.8473, respectively, demonstrating state-of-the-art (SOTA) performance with low computational resources. The code and dataset is available atthis https URL.

@article{liu2025_2408.12815,
  title={ Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation },
  author={ Hui Liu and Chen Jia and Fan Shi and Xu Cheng and Mianzhao Wang and Shengyong Chen },
  journal={arXiv preprint arXiv:2408.12815},
  year={ 2025 }
}