Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer
Deep learning methods have been widely studied for Polarimetric synthetic aperture radar (PolSAR) land cover classification. The scarcity of PolSAR labeled samples and the small receptive field of the model limit the performance of deep learning methods for land cover classification. In this paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/18/4656 |
| _version_ | 1827657062363955200 |
|---|---|
| author | Hongmiao Wang Cheng Xing Junjun Yin Jian Yang |
| author_facet | Hongmiao Wang Cheng Xing Junjun Yin Jian Yang |
| author_sort | Hongmiao Wang |
| collection | DOAJ |
| description | Deep learning methods have been widely studied for Polarimetric synthetic aperture radar (PolSAR) land cover classification. The scarcity of PolSAR labeled samples and the small receptive field of the model limit the performance of deep learning methods for land cover classification. In this paper, a vision Transformer (ViT)-based classification method is proposed. The ViT structure can extract features from the global range of images based on a self-attention block. The powerful feature representation capability of the model is equivalent to a flexible receptive field, which is suitable for PolSAR image classification at different resolutions. In addition, because of the lack of labeled data, the Mask Autoencoder method is used to pre-train the proposed model with unlabeled data. Experiments are carried out on the Flevoland dataset acquired by NASA/JPL AIRSAR and the Hainan dataset acquired by the Aerial Remote Sensing System of the Chinese Academy of Sciences. The experimental results on both datasets demonstrate the superiority of the proposed method. |
| first_indexed | 2024-03-09T22:38:02Z |
| format | Article |
| id | doaj.art-b88f4c2704754210a7883553bb8fa575 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T22:38:02Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b88f4c2704754210a7883553bb8fa5752023-11-23T18:46:21ZengMDPI AGRemote Sensing2072-42922022-09-011418465610.3390/rs14184656Land Cover Classification for Polarimetric SAR Images Based on Vision TransformerHongmiao Wang0Cheng Xing1Junjun Yin2Jian Yang3Department of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaDeep learning methods have been widely studied for Polarimetric synthetic aperture radar (PolSAR) land cover classification. The scarcity of PolSAR labeled samples and the small receptive field of the model limit the performance of deep learning methods for land cover classification. In this paper, a vision Transformer (ViT)-based classification method is proposed. The ViT structure can extract features from the global range of images based on a self-attention block. The powerful feature representation capability of the model is equivalent to a flexible receptive field, which is suitable for PolSAR image classification at different resolutions. In addition, because of the lack of labeled data, the Mask Autoencoder method is used to pre-train the proposed model with unlabeled data. Experiments are carried out on the Flevoland dataset acquired by NASA/JPL AIRSAR and the Hainan dataset acquired by the Aerial Remote Sensing System of the Chinese Academy of Sciences. The experimental results on both datasets demonstrate the superiority of the proposed method.https://www.mdpi.com/2072-4292/14/18/4656land cover classificationpolarimetric SARdeep learningvision transformer |
| spellingShingle | Hongmiao Wang Cheng Xing Junjun Yin Jian Yang Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer Remote Sensing land cover classification polarimetric SAR deep learning vision transformer |
| title | Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer |
| title_full | Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer |
| title_fullStr | Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer |
| title_full_unstemmed | Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer |
| title_short | Land Cover Classification for Polarimetric SAR Images Based on Vision Transformer |
| title_sort | land cover classification for polarimetric sar images based on vision transformer |
| topic | land cover classification polarimetric SAR deep learning vision transformer |
| url | https://www.mdpi.com/2072-4292/14/18/4656 |
| work_keys_str_mv | AT hongmiaowang landcoverclassificationforpolarimetricsarimagesbasedonvisiontransformer AT chengxing landcoverclassificationforpolarimetricsarimagesbasedonvisiontransformer AT junjunyin landcoverclassificationforpolarimetricsarimagesbasedonvisiontransformer AT jianyang landcoverclassificationforpolarimetricsarimagesbasedonvisiontransformer |