[3] [3] Shelhamer E ,Long J ,Darrell T. Fully Convolutional Net- works for Semantic Segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017 ,39( 4) : 640-651.

[4] [4] Zunair H ,Ben Hamza A. Sharp U-Net : Depthwise convo- lutional network for biomedical image segmentation[J]. Computers in Biology and Medicine. 2021 ,136 : 104699 -104699.

[5] [5] Chen C ,Zhao H ,Cui W ,et al. Dual Crisscross Attention Module for Road Extraction from Remote Sensing Images[J]. Sensors. 2021 ,21(20) : 6873- 6873.

[7] [7] Zhou Z ,Siddiquee M ,Tajbakhsh N ,et al. UNet + + : A Nested U-Net Architecture for Medical Image Segmentation[J]. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support ,2018 ,11045 : 3- 11.

[15] [15] Zunair H ,Ben Hamza A. Sharp U-Net : Depthwise convo- lutional network for biomedical image segmentation[J]. Computers in Biology and Medicine. 2021 ,136 : 104699 - 104699.

[17] [17] Zhang Y ,Zuo Z ,Xu X ,et al. Road damage detection u- sing UAV images based on multi-level attention mechanism[J]. Automation in Construction. 2022 ,144 : 104613 - 104613.

[18] [18] Woo S ,Park J ,Lee J ,et al. CBAM : Convolutional Block Attention Module[ C]// Cham : Springer International Pub- lishing ,2018.

[19] [19] Su H ,Wang X ,Han T ,et al. Research on a U-Net Bridge Crack Identification and Feature-Calculation Methods Based on a CBAM Attention Mechanism[J]. Buildings. 2022 ,12(10) : 1561- 1561.