A hyperspectral image denoising method based on land cover spectral autocorrelation
Developing denoising algorithms for hyperspectral remote sensing images (HSIs) can alleviate noise problem, improve data utilization as well as the accuracy of subsequent applications. However, existing denoising techniques are usually unstable due to the variations of landscapes, resulting in local...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223003059 |
| _version_ | 1797677717202665472 |
|---|---|
| author | Shuheng Zhao Xiaolin Zhu Denghong Liu Fei Xu Yan Wang Liupeng Lin Xuehong Chen Qiangqiang Yuan |
| author_facet | Shuheng Zhao Xiaolin Zhu Denghong Liu Fei Xu Yan Wang Liupeng Lin Xuehong Chen Qiangqiang Yuan |
| author_sort | Shuheng Zhao |
| collection | DOAJ |
| description | Developing denoising algorithms for hyperspectral remote sensing images (HSIs) can alleviate noise problem, improve data utilization as well as the accuracy of subsequent applications. However, existing denoising techniques are usually unstable due to the variations of landscapes, resulting in local distortion of HSIs, especially in heterogeneous areas. To tackle this issue, we propose a spatial–spectral interactive restoration (SSIR) framework by exploiting the complementarity of model-based and data-driven methods. Specifically, a deep learning-based denoising module that incorporates both convolutional neural networks (CNN) and Swin Transformer (TF) blocks is designed. This denoiser can achieve local–global dependencies modeling and content-based interactions to better capture global heterogeneity differences in HSIs. Moreover, we introduce an unsupervised unmixing module that utilizes spectral autocorrelation as prior information to effectively capture the differences in reflectance characteristics among different land cover components. This parameter-free module further improves the generalization ability of SSIR and enables stable denoising performance across different scenarios. Both modules are iteratively updated and fuel each other in SSIR. The proposed SSIR is shown to outperform others in preserving spatial details, maintaining spectral fidelity, and adapting to different landscapes based on simulated and real experiments conducted on various HSIs under diverse noise conditions. |
| first_indexed | 2024-03-11T22:49:16Z |
| format | Article |
| id | doaj.art-f2370e14fb7a4ff6b89e125b2d46e727 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-03-11T22:49:16Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-f2370e14fb7a4ff6b89e125b2d46e7272023-09-22T04:38:20ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-09-01123103481A hyperspectral image denoising method based on land cover spectral autocorrelationShuheng Zhao0Xiaolin Zhu1Denghong Liu2Fei Xu3Yan Wang4Liupeng Lin5Xuehong Chen6Qiangqiang Yuan7Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, China; Corresponding author.Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, ChinaState Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan 430079, ChinaDeveloping denoising algorithms for hyperspectral remote sensing images (HSIs) can alleviate noise problem, improve data utilization as well as the accuracy of subsequent applications. However, existing denoising techniques are usually unstable due to the variations of landscapes, resulting in local distortion of HSIs, especially in heterogeneous areas. To tackle this issue, we propose a spatial–spectral interactive restoration (SSIR) framework by exploiting the complementarity of model-based and data-driven methods. Specifically, a deep learning-based denoising module that incorporates both convolutional neural networks (CNN) and Swin Transformer (TF) blocks is designed. This denoiser can achieve local–global dependencies modeling and content-based interactions to better capture global heterogeneity differences in HSIs. Moreover, we introduce an unsupervised unmixing module that utilizes spectral autocorrelation as prior information to effectively capture the differences in reflectance characteristics among different land cover components. This parameter-free module further improves the generalization ability of SSIR and enables stable denoising performance across different scenarios. Both modules are iteratively updated and fuel each other in SSIR. The proposed SSIR is shown to outperform others in preserving spatial details, maintaining spectral fidelity, and adapting to different landscapes based on simulated and real experiments conducted on various HSIs under diverse noise conditions.http://www.sciencedirect.com/science/article/pii/S1569843223003059Hyperspectral remote sensingImage restorationConvolutional neural networkTransformerSpectral unmixing analysisNoise removal |
| spellingShingle | Shuheng Zhao Xiaolin Zhu Denghong Liu Fei Xu Yan Wang Liupeng Lin Xuehong Chen Qiangqiang Yuan A hyperspectral image denoising method based on land cover spectral autocorrelation International Journal of Applied Earth Observations and Geoinformation Hyperspectral remote sensing Image restoration Convolutional neural network Transformer Spectral unmixing analysis Noise removal |
| title | A hyperspectral image denoising method based on land cover spectral autocorrelation |
| title_full | A hyperspectral image denoising method based on land cover spectral autocorrelation |
| title_fullStr | A hyperspectral image denoising method based on land cover spectral autocorrelation |
| title_full_unstemmed | A hyperspectral image denoising method based on land cover spectral autocorrelation |
| title_short | A hyperspectral image denoising method based on land cover spectral autocorrelation |
| title_sort | hyperspectral image denoising method based on land cover spectral autocorrelation |
| topic | Hyperspectral remote sensing Image restoration Convolutional neural network Transformer Spectral unmixing analysis Noise removal |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223003059 |
| work_keys_str_mv | AT shuhengzhao ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT xiaolinzhu ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT denghongliu ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT feixu ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT yanwang ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT liupenglin ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT xuehongchen ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT qiangqiangyuan ahyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT shuhengzhao hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT xiaolinzhu hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT denghongliu hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT feixu hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT yanwang hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT liupenglin hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT xuehongchen hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation AT qiangqiangyuan hyperspectralimagedenoisingmethodbasedonlandcoverspectralautocorrelation |