Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising
Remote sensing images are widely applied in instance segmentation and objetive recognition; however, they often suffer from noise, influencing the performance of subsequent applications. Previous image denoising works have only obtained restored images without preserving detailed texture. To address...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/24/6300 |
| _version_ | 1797455478235594752 |
|---|---|
| author | Huiqing Qi Shengli Tan Zhichao Li |
| author_facet | Huiqing Qi Shengli Tan Zhichao Li |
| author_sort | Huiqing Qi |
| collection | DOAJ |
| description | Remote sensing images are widely applied in instance segmentation and objetive recognition; however, they often suffer from noise, influencing the performance of subsequent applications. Previous image denoising works have only obtained restored images without preserving detailed texture. To address this issue, we proposed a novel model for remote sensing image denoising, called the anisotropic weighted total variation feature fusion network (AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net), consisting of four novel modules (WTV-Net, SOSB, AuEncoder, and FB). AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net combines traditional total variation with a deep neural network, improving the denoising ability of the proposed approach. Our proposed method is evaluated by PSNR and SSIM metrics on three benchmark datasets (NWPU, PatternNet, UCL), and the experimental results show that AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net can obtain 0.12∼19.39 dB/0.0237∼0.5362 higher on PSNR/SSIM values in the Gaussian noise removal and mixed noise removal tasks than State-of-The-Art (SoTA) algorithms. Meanwhile, our model can preserve more detailed texture features. The SSEQ, BLIINDS-II, and BRISQUE values of AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net on the three real-world datasets (AVRIS Indian Pines, ROSIS University of Pavia, HYDICE Urban) are 3.94∼12.92 higher, 8.33∼27.5 higher, and 2.2∼5.55 lower than those of the compared methods, respectively. The proposed framework can guide subsequent remote sensing image applications, regarding the pre-processing of input images. |
| first_indexed | 2024-03-09T15:54:55Z |
| format | Article |
| id | doaj.art-df27f84e817b4cf78682b92dafe56278 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T15:54:55Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-df27f84e817b4cf78682b92dafe562782023-11-24T17:47:25ZengMDPI AGRemote Sensing2072-42922022-12-011424630010.3390/rs14246300Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image DenoisingHuiqing Qi0Shengli Tan1Zhichao Li2School of Mathematical Sciences, East China Normal University, Shanghai 200241, ChinaSchool of Mathematical Sciences, East China Normal University, Shanghai 200241, ChinaKey Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaRemote sensing images are widely applied in instance segmentation and objetive recognition; however, they often suffer from noise, influencing the performance of subsequent applications. Previous image denoising works have only obtained restored images without preserving detailed texture. To address this issue, we proposed a novel model for remote sensing image denoising, called the anisotropic weighted total variation feature fusion network (AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net), consisting of four novel modules (WTV-Net, SOSB, AuEncoder, and FB). AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net combines traditional total variation with a deep neural network, improving the denoising ability of the proposed approach. Our proposed method is evaluated by PSNR and SSIM metrics on three benchmark datasets (NWPU, PatternNet, UCL), and the experimental results show that AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net can obtain 0.12∼19.39 dB/0.0237∼0.5362 higher on PSNR/SSIM values in the Gaussian noise removal and mixed noise removal tasks than State-of-The-Art (SoTA) algorithms. Meanwhile, our model can preserve more detailed texture features. The SSEQ, BLIINDS-II, and BRISQUE values of AWTV<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>F</mi><mn>2</mn></msup></semantics></math></inline-formula>Net on the three real-world datasets (AVRIS Indian Pines, ROSIS University of Pavia, HYDICE Urban) are 3.94∼12.92 higher, 8.33∼27.5 higher, and 2.2∼5.55 lower than those of the compared methods, respectively. The proposed framework can guide subsequent remote sensing image applications, regarding the pre-processing of input images.https://www.mdpi.com/2072-4292/14/24/6300remote sensing imagenoise removalweighted total variationfeature fusionconvolutional neural network |
| spellingShingle | Huiqing Qi Shengli Tan Zhichao Li Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising Remote Sensing remote sensing image noise removal weighted total variation feature fusion convolutional neural network |
| title | Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising |
| title_full | Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising |
| title_fullStr | Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising |
| title_full_unstemmed | Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising |
| title_short | Anisotropic Weighted Total Variation Feature Fusion Network for Remote Sensing Image Denoising |
| title_sort | anisotropic weighted total variation feature fusion network for remote sensing image denoising |
| topic | remote sensing image noise removal weighted total variation feature fusion convolutional neural network |
| url | https://www.mdpi.com/2072-4292/14/24/6300 |
| work_keys_str_mv | AT huiqingqi anisotropicweightedtotalvariationfeaturefusionnetworkforremotesensingimagedenoising AT shenglitan anisotropicweightedtotalvariationfeaturefusionnetworkforremotesensingimagedenoising AT zhichaoli anisotropicweightedtotalvariationfeaturefusionnetworkforremotesensingimagedenoising |