Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models
Optical remote sensing images have a wide range of applications but are often affected by cloud cover, which interferes with subsequent analysis. Therefore, cloud removal has become indispensable in remote sensing data processing. The Tibetan Plateau, as a sensitive region to climate change, plays a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/23/7848 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850060120212373504 |
|---|---|
| author | Guoqiang Zheng Tianle Zhao Yaohui Liu |
| author_facet | Guoqiang Zheng Tianle Zhao Yaohui Liu |
| author_sort | Guoqiang Zheng |
| collection | DOAJ |
| description | Optical remote sensing images have a wide range of applications but are often affected by cloud cover, which interferes with subsequent analysis. Therefore, cloud removal has become indispensable in remote sensing data processing. The Tibetan Plateau, as a sensitive region to climate change, plays a crucial role in the East Asian water cycle and regional climate due to its snow cover. However, the rich ice and snow resources, rapid snow condition changes, and active atmospheric convection in the plateau as well as its surrounding mountainous areas, make optical remote sensing prone to cloud interference. This is particularly significant when monitoring snow cover changes, where cloud removal becomes essential considering the complex terrain and unique snow characteristics of the Tibetan Plateau. This paper proposes a novel Multi-Scale Attention-based Cloud Removal Model (MATT). The model integrates global and local information by incorporating multi-scale attention mechanisms and local interaction modules, enhancing the contextual semantic relationships and improving the robustness of feature representation. To improve the segmentation accuracy of cloud- and snow-covered regions, a cloud mask is introduced in the local-attention module, combined with the local interaction module to modulate and reconstruct fine-grained details. This enables the simultaneous representation of both fine-grained and coarse-grained features at the same level. With the help of multi-scale fusion modules and selective attention modules, MATT demonstrates excellent performance on both the Sen2_MTC_New and XZ_Sen2_Dataset datasets. Particularly on the XZ_Sen2_Dataset, it achieves outstanding results: PSNR = 29.095, SSIM = 0.897, FID = 125.328, and LPIPS = 0.356. The model shows strong cloud removal capabilities in cloud- and snow-covered areas in mountainous regions while effectively preserving snow information, and providing significant support for snow cover change studies. |
| format | Article |
| id | doaj-art-a44cbc14fdbd4619ace727d8be6d9cc9 |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-a44cbc14fdbd4619ace727d8be6d9cc92025-08-20T02:50:41ZengMDPI AGSensors1424-82202024-12-012423784810.3390/s24237848Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention ModelsGuoqiang Zheng0Tianle Zhao1Yaohui Liu2School of Surveying and Geo-Informatics, Shandong Jianzhu University, Fengming Road, Jinan 250101, ChinaSchool of Surveying and Geo-Informatics, Shandong Jianzhu University, Fengming Road, Jinan 250101, ChinaSchool of Surveying and Geo-Informatics, Shandong Jianzhu University, Fengming Road, Jinan 250101, ChinaOptical remote sensing images have a wide range of applications but are often affected by cloud cover, which interferes with subsequent analysis. Therefore, cloud removal has become indispensable in remote sensing data processing. The Tibetan Plateau, as a sensitive region to climate change, plays a crucial role in the East Asian water cycle and regional climate due to its snow cover. However, the rich ice and snow resources, rapid snow condition changes, and active atmospheric convection in the plateau as well as its surrounding mountainous areas, make optical remote sensing prone to cloud interference. This is particularly significant when monitoring snow cover changes, where cloud removal becomes essential considering the complex terrain and unique snow characteristics of the Tibetan Plateau. This paper proposes a novel Multi-Scale Attention-based Cloud Removal Model (MATT). The model integrates global and local information by incorporating multi-scale attention mechanisms and local interaction modules, enhancing the contextual semantic relationships and improving the robustness of feature representation. To improve the segmentation accuracy of cloud- and snow-covered regions, a cloud mask is introduced in the local-attention module, combined with the local interaction module to modulate and reconstruct fine-grained details. This enables the simultaneous representation of both fine-grained and coarse-grained features at the same level. With the help of multi-scale fusion modules and selective attention modules, MATT demonstrates excellent performance on both the Sen2_MTC_New and XZ_Sen2_Dataset datasets. Particularly on the XZ_Sen2_Dataset, it achieves outstanding results: PSNR = 29.095, SSIM = 0.897, FID = 125.328, and LPIPS = 0.356. The model shows strong cloud removal capabilities in cloud- and snow-covered areas in mountainous regions while effectively preserving snow information, and providing significant support for snow cover change studies.https://www.mdpi.com/1424-8220/24/23/7848deep learningcloud removalattention modelmulti-scale fusion moduleSentinel-2 |
| spellingShingle | Guoqiang Zheng Tianle Zhao Yaohui Liu Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models Sensors deep learning cloud removal attention model multi-scale fusion module Sentinel-2 |
| title | Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models |
| title_full | Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models |
| title_fullStr | Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models |
| title_full_unstemmed | Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models |
| title_short | Cloud Removal in the Tibetan Plateau Region Based on Self-Attention and Local-Attention Models |
| title_sort | cloud removal in the tibetan plateau region based on self attention and local attention models |
| topic | deep learning cloud removal attention model multi-scale fusion module Sentinel-2 |
| url | https://www.mdpi.com/1424-8220/24/23/7848 |
| work_keys_str_mv | AT guoqiangzheng cloudremovalinthetibetanplateauregionbasedonselfattentionandlocalattentionmodels AT tianlezhao cloudremovalinthetibetanplateauregionbasedonselfattentionandlocalattentionmodels AT yaohuiliu cloudremovalinthetibetanplateauregionbasedonselfattentionandlocalattentionmodels |