An underwater dam crack image segmentation method based on multi-level adversarial transfer learning

Crack detection is necessary to ensure the health of dams. Traditional detection methods perform poorly because of weak adaptability and poor image quality. Deep learning shows excellent performance in crack image detection. However, it is difficult to realize supervised learning due to the lack of labelled underwater crack image datasets. Thus, a transfer learning method named MA-AttUNet is proposed. The proposed method realizes knowledge transfer of crack image features using a multi-level adversarial transfer network. With this method, prior knowledge learned from the source domain can be applied to underwater crack image segmentation. Additionally, the attention mechanism is integrated into the segmentation network to eliminate noise interference during detection by assigning different weights to target and background pixels. Experiments show that the proposed method achieves higher segmentation precision than existing works.