An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning
Shadows inevitably exist in remote sensing images (RSIs) and are characterized by lower resolution, mixed-pixel, and diverse background information. These characteristics pose a great challenge to the automatic compensation of shadows in RSIs. To address these issues, this paper proposes a training...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/15481603.2025.2487334 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850213348758519808 |
|---|---|
| author | Xingyu Shen Yungang Cao Baikai Sui Shuang Zhang Dejun Feng |
| author_facet | Xingyu Shen Yungang Cao Baikai Sui Shuang Zhang Dejun Feng |
| author_sort | Xingyu Shen |
| collection | DOAJ |
| description | Shadows inevitably exist in remote sensing images (RSIs) and are characterized by lower resolution, mixed-pixel, and diverse background information. These characteristics pose a great challenge to the automatic compensation of shadows in RSIs. To address these issues, this paper proposes a training method using automatically simulated data to achieve real shadow compensation. In the process of data simulation, we take into comprehensive account the distribution, spatial extent, morphology, and other properties of shadows in RSIs, along with the reflectivity differences of ground features. And a lightweight shadow compensation framework is proposed to compensate shadows. Specifically, a Stair-step Hierarchical Context Aggregation Module is employed in the primary stage to integrate global and local texture information that is more important for shadow compensation. After that, a U-shaped end-to-end structure is used to perceive shadows and image features. Then, a Buffer-based mask attention Module is proposed to enhance the network’s attentiveness to both shadows and shadow boundaries. Finally, an additional high-resolution residual connection is utilized to get the final output. This connection effectively maintains the continuity of the image. This method was validated by two remote sensing image datasets with different resolutions and achieved favorable results. |
| format | Article |
| id | doaj-art-8ca12e346a8b484da8910fe05a2f75a4 |
| institution | OA Journals |
| issn | 1548-1603 1943-7226 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj-art-8ca12e346a8b484da8910fe05a2f75a42025-08-20T02:09:10ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262025-12-0162110.1080/15481603.2025.2487334An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learningXingyu Shen0Yungang Cao1Baikai Sui2Shuang Zhang3Dejun Feng4Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu, ChinaShadows inevitably exist in remote sensing images (RSIs) and are characterized by lower resolution, mixed-pixel, and diverse background information. These characteristics pose a great challenge to the automatic compensation of shadows in RSIs. To address these issues, this paper proposes a training method using automatically simulated data to achieve real shadow compensation. In the process of data simulation, we take into comprehensive account the distribution, spatial extent, morphology, and other properties of shadows in RSIs, along with the reflectivity differences of ground features. And a lightweight shadow compensation framework is proposed to compensate shadows. Specifically, a Stair-step Hierarchical Context Aggregation Module is employed in the primary stage to integrate global and local texture information that is more important for shadow compensation. After that, a U-shaped end-to-end structure is used to perceive shadows and image features. Then, a Buffer-based mask attention Module is proposed to enhance the network’s attentiveness to both shadows and shadow boundaries. Finally, an additional high-resolution residual connection is utilized to get the final output. This connection effectively maintains the continuity of the image. This method was validated by two remote sensing image datasets with different resolutions and achieved favorable results.https://www.tandfonline.com/doi/10.1080/15481603.2025.2487334Remote sensing imageShadow compensationdeep learninghierarchical context aggregationmask attention |
| spellingShingle | Xingyu Shen Yungang Cao Baikai Sui Shuang Zhang Dejun Feng An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning GIScience & Remote Sensing Remote sensing image Shadow compensation deep learning hierarchical context aggregation mask attention |
| title | An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| title_full | An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| title_fullStr | An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| title_full_unstemmed | An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| title_short | An automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| title_sort | automatic remote sensing image shadow compensation method utilizing reflectance differences and transfer learning |
| topic | Remote sensing image Shadow compensation deep learning hierarchical context aggregation mask attention |
| url | https://www.tandfonline.com/doi/10.1080/15481603.2025.2487334 |
| work_keys_str_mv | AT xingyushen anautomaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT yungangcao anautomaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT baikaisui anautomaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT shuangzhang anautomaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT dejunfeng anautomaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT xingyushen automaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT yungangcao automaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT baikaisui automaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT shuangzhang automaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning AT dejunfeng automaticremotesensingimageshadowcompensationmethodutilizingreflectancedifferencesandtransferlearning |