Title | ||
---|---|---|
L-Unet: A Landslide Extraction Model Using Multi-Scale Feature Fusion and Attention Mechanism |
Abstract | ||
---|---|---|
At present, it is challenging to extract landslides from high-resolution remote-sensing images using deep learning. Because landslides are very complex, the accuracy of traditional extraction methods is low. To improve the efficiency and accuracy of landslide extraction, a new model is proposed based on the U-Net model to automatically extract landslides from remote-sensing images: L-Unet. The main innovations are as follows: (1) A multi-scale feature-fusion (MFF) module is added at the end of the U-Net encoding network to improve the model's ability to extract multi-scale landslide information. (2) A residual attention network is added to the U-Net model to deepen the network and improve the model's ability to represent landslide features. (3) The bilinear interpolation algorithm in the decoding network of the U-Net model is replaced by data-dependent upsampling (DUpsampling) to improve the quality of the feature maps. Experimental results showed that the precision, recall, MIoU and F1 values of the L-Unet model are 4.15%, 2.65%, 4.82% and 3.37% higher than that of the baseline U-Net model, respectively. It was proven that the new model can extract landslides accurately and effectively. |
Year | DOI | Venue |
---|---|---|
2022 | 10.3390/rs14112552 | REMOTE SENSING |
Keywords | DocType | Volume |
landslide, remote sensing, U-Net, attention mechanism, deep learning | Journal | 14 |
Issue | ISSN | Citations |
11 | 2072-4292 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |