Journal
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
Volume 19, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2021.3058049
Keywords
Sea ice; Radar polarimetry; Feature extraction; Decoding; Oceans; Kernel; Image segmentation; Dual-attention; sea ice and open water classification; synthetic aperture radar (SAR) image; U-Net
Categories
Funding
- Strategic Priority Research Program of the Chinese Academy of Sciences (CAS) [XDA19060101, XDB42040401]
- China Postdoctoral Science Foundation [2019M662452]
- Key Research and Development Project of Shandong Province [2019JZZY010102]
- Key Deployment Project of Center for Ocean Mega-Science, CAS [COMS2019R02]
- CAS Program [Y9KY04101L]
- National Natural Science Foundation of China [41776183]
Ask authors/readers for more resources
This study developed a deep learning model, DAU-Net, to classify sea ice and open water from SAR images with high accuracy. By integrating the dual-attention mechanism into U-Net, improvements in pixel-level classification and IoU were achieved. Experimental results showed that DAU-Net outperformed the original U-Net and DenseNetFCN models.
This study develops a deep learning (DL) model to classify the sea ice and open water from synthetic aperture radar (SAR) images. We use the U-Net, a well-known fully convolutional network (FCN) for pixel-level segmentation, as the model backbone. We employ a DL-based feature extracting model, ResNet-34, as the encoder of the U-Net. To achieve high accuracy classifications, we integrate the dual-attention mechanism into the original U-Net to improve the feature representations, forming a dual-attention U-Net model (DAU-Net). The SAR images are obtained from Sentinel-1A. The dual-polarized information and the incident angle of SAR images are model inputs. We used 15 dual-polarized images acquired near the Bering Sea to train the model and employ the other three images to test the model. Experiments show that the DAU-Net could achieve pixel-level classification; the dual-attention mechanism can improve the classification accuracy. Compared with the original U-Net, DAU-Net improves the intersection over union (IoU) by 7.48.% points, 0.96.% points, and 0.83.% points on three test images. Compared with the recently published model DenseNetFCN, the three improvement IoU values of DAU-Net are 3.04.% points, 2.53.% points, and 2.26.% points, respectively.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available