Serial Local Patterns and Irregular Dependencies Extract and Cascaded Fusion Network for Structural Crack Segmentation

Achieving pixel-level crack segmentation in complex scenarios is a major challenge, as current methods have difficulty effectively integrating both local features and irregular pixel dependencies. In this paper, we introduce a Cascaded Fusion Network (LICFN) specifically designed for crack segmentation, which extracts fine local details and pixel dependencies using a hybrid feature extractor and effectively enhances and fuses them through a cascaded fusion module. To comprehensively evaluate the network, we also created a benchmark dataset, TUT, which includes various scenarios. Experimental results show that our method surpasses others, achieving F1 and mIoU scores of 0.8439 and 0.8509, respectively. The dataset is available at https://github.com/Karl1109/TUT.