DeepCrackAT

DeepCrackAT: An effective crack segmentation framework based on learning multi-scale crack features

<p align="center"> <img src="Overview.png" width="550px"/> </p>

Dataset

You can update your own data as:

/data 
  /dataset's name 
    /train
      111.jpg
      ...
    /train_mask
      111.jpg
      ...
    train.txt

Train and Test

run train.py or test.py

Citation

If you use this code for your research, please cite our paper.

@article{lin2023deepcrackat,
  title={DeepCrackAT: An effective crack segmentation framework based on learning multi-scale crack features},
  author={Lin, Qinghua and Li, Wei and Zheng, Xiangpan and Fan, Haoyi and Li, Zuoyong},
  journal={Engineering Applications of Artificial Intelligence},
  volume={126},
  pages={106876},
  year={2023},
  publisher={Elsevier}
}