Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method
Medium-resolution remote sensing satellites have provided a large amount of long time series and full coverage data for Earth surface monitoring. However, the different objects may have similar spectral values and the same objects may have different spectral values, which makes it difficult to impro...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3382 |
| _version_ | 1827626971770650624 |
|---|---|
| author | Junyuan Yao Shuanggen Jin |
| author_facet | Junyuan Yao Shuanggen Jin |
| author_sort | Junyuan Yao |
| collection | DOAJ |
| description | Medium-resolution remote sensing satellites have provided a large amount of long time series and full coverage data for Earth surface monitoring. However, the different objects may have similar spectral values and the same objects may have different spectral values, which makes it difficult to improve the classification accuracy. Semantic segmentation of remote sensing images is greatly facilitated via deep learning methods. For medium-resolution remote sensing images, the convolutional neural network-based model does not achieve good results due to its limited field of perception. The fast-emerging vision transformer method with self-attentively capturing global features well provides a new solution for medium-resolution remote sensing image segmentation. In this paper, a new multi-class segmentation method is proposed for medium-resolution remote sensing images based on the improved Swin UNet model as a pure transformer model and a new pre-processing, and the image enhancement method and spectral selection module are designed to achieve better accuracy. Finally, 10-categories segmentation is conducted with 10-m resolution Sentinel-2 MSI (Multi-Spectral Imager) images, which is compared with other traditional convolutional neural network-based models (DeepLabV3+ and U-Net with different backbone networks, including VGG, ResNet50, MobileNet, and Xception) with the same sample data, and results show higher Mean Intersection Over Union (MIOU) (72.06%) and better accuracy (89.77%) performance. The vision transformer method has great potential for medium-resolution remote sensing image segmentation tasks. |
| first_indexed | 2024-03-09T13:06:00Z |
| format | Article |
| id | doaj.art-bb1c8409b7834952ad17ec19308c68f7 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T13:06:00Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-bb1c8409b7834952ad17ec19308c68f72023-11-30T21:49:11ZengMDPI AGRemote Sensing2072-42922022-07-011414338210.3390/rs14143382Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet MethodJunyuan Yao0Shuanggen Jin1School of Communication and Information Engineering, Shanghai University, Shanghai 200444, ChinaShanghai Astronomical Observatory, Chinese Academy of Sciences, Shanghai 200030, ChinaMedium-resolution remote sensing satellites have provided a large amount of long time series and full coverage data for Earth surface monitoring. However, the different objects may have similar spectral values and the same objects may have different spectral values, which makes it difficult to improve the classification accuracy. Semantic segmentation of remote sensing images is greatly facilitated via deep learning methods. For medium-resolution remote sensing images, the convolutional neural network-based model does not achieve good results due to its limited field of perception. The fast-emerging vision transformer method with self-attentively capturing global features well provides a new solution for medium-resolution remote sensing image segmentation. In this paper, a new multi-class segmentation method is proposed for medium-resolution remote sensing images based on the improved Swin UNet model as a pure transformer model and a new pre-processing, and the image enhancement method and spectral selection module are designed to achieve better accuracy. Finally, 10-categories segmentation is conducted with 10-m resolution Sentinel-2 MSI (Multi-Spectral Imager) images, which is compared with other traditional convolutional neural network-based models (DeepLabV3+ and U-Net with different backbone networks, including VGG, ResNet50, MobileNet, and Xception) with the same sample data, and results show higher Mean Intersection Over Union (MIOU) (72.06%) and better accuracy (89.77%) performance. The vision transformer method has great potential for medium-resolution remote sensing image segmentation tasks.https://www.mdpi.com/2072-4292/14/14/3382Swin UNetSwin Transformerremote sensingsemantic segmentationSentinel-2 |
| spellingShingle | Junyuan Yao Shuanggen Jin Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method Remote Sensing Swin UNet Swin Transformer remote sensing semantic segmentation Sentinel-2 |
| title | Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method |
| title_full | Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method |
| title_fullStr | Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method |
| title_full_unstemmed | Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method |
| title_short | Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method |
| title_sort | multi category segmentation of sentinel 2 images based on the swin unet method |
| topic | Swin UNet Swin Transformer remote sensing semantic segmentation Sentinel-2 |
| url | https://www.mdpi.com/2072-4292/14/14/3382 |
| work_keys_str_mv | AT junyuanyao multicategorysegmentationofsentinel2imagesbasedontheswinunetmethod AT shuanggenjin multicategorysegmentationofsentinel2imagesbasedontheswinunetmethod |