Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze
The haze in remote sensing images can cause the decline of image quality and bring many obstacles to the applications of remote sensing images. Considering the non-uniform distribution of haze in remote sensing images, we propose a single remote sensing image dehazing method based on the encoder–dec...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/5e5850c7cc3c4325bd3429f7f1b30656 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:5e5850c7cc3c4325bd3429f7f1b30656 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:5e5850c7cc3c4325bd3429f7f1b306562021-11-11T18:56:53ZDeep Dehazing Network for Remote Sensing Image with Non-Uniform Haze10.3390/rs132144432072-4292https://doaj.org/article/5e5850c7cc3c4325bd3429f7f1b306562021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4443https://doaj.org/toc/2072-4292The haze in remote sensing images can cause the decline of image quality and bring many obstacles to the applications of remote sensing images. Considering the non-uniform distribution of haze in remote sensing images, we propose a single remote sensing image dehazing method based on the encoder–decoder architecture, which combines both wavelet transform and deep learning technology. To address the clarity issue of remote sensing images with non-uniform haze, we preliminary process the input image by the dehazing method based on the atmospheric scattering model, and extract the first-order low-frequency sub-band information of its 2D stationary wavelet transform as an additional channel. Meanwhile, we establish a large-scale hazy remote sensing image dataset to train and test the proposed method. Extensive experiments show that the proposed method obtains greater advantages over typical traditional methods and deep learning methods qualitatively. For the quantitative aspects, we take the average of four typical deep learning methods with superior performance as a comparison object using 500 random test images, and the peak-signal-to-noise ratio (PSNR) value using the proposed method is improved by 3.5029 dB, and the structural similarity (SSIM) value is improved by 0.0295, respectively. Based on the above, the effectiveness of the proposed method for the problem of remote sensing non-uniform dehazing is verified comprehensively.Bo JiangGuanting ChenJinshuai WangHang MaLin WangYuxuan WangXiaoxuan ChenMDPI AGarticleremote sensing imagesnon-uniform hazedeep learningimage dehazingScienceQENRemote Sensing, Vol 13, Iss 4443, p 4443 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
remote sensing images non-uniform haze deep learning image dehazing Science Q |
| spellingShingle |
remote sensing images non-uniform haze deep learning image dehazing Science Q Bo Jiang Guanting Chen Jinshuai Wang Hang Ma Lin Wang Yuxuan Wang Xiaoxuan Chen Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| description |
The haze in remote sensing images can cause the decline of image quality and bring many obstacles to the applications of remote sensing images. Considering the non-uniform distribution of haze in remote sensing images, we propose a single remote sensing image dehazing method based on the encoder–decoder architecture, which combines both wavelet transform and deep learning technology. To address the clarity issue of remote sensing images with non-uniform haze, we preliminary process the input image by the dehazing method based on the atmospheric scattering model, and extract the first-order low-frequency sub-band information of its 2D stationary wavelet transform as an additional channel. Meanwhile, we establish a large-scale hazy remote sensing image dataset to train and test the proposed method. Extensive experiments show that the proposed method obtains greater advantages over typical traditional methods and deep learning methods qualitatively. For the quantitative aspects, we take the average of four typical deep learning methods with superior performance as a comparison object using 500 random test images, and the peak-signal-to-noise ratio (PSNR) value using the proposed method is improved by 3.5029 dB, and the structural similarity (SSIM) value is improved by 0.0295, respectively. Based on the above, the effectiveness of the proposed method for the problem of remote sensing non-uniform dehazing is verified comprehensively. |
| format |
article |
| author |
Bo Jiang Guanting Chen Jinshuai Wang Hang Ma Lin Wang Yuxuan Wang Xiaoxuan Chen |
| author_facet |
Bo Jiang Guanting Chen Jinshuai Wang Hang Ma Lin Wang Yuxuan Wang Xiaoxuan Chen |
| author_sort |
Bo Jiang |
| title |
Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| title_short |
Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| title_full |
Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| title_fullStr |
Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| title_full_unstemmed |
Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze |
| title_sort |
deep dehazing network for remote sensing image with non-uniform haze |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/5e5850c7cc3c4325bd3429f7f1b30656 |
| work_keys_str_mv |
AT bojiang deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT guantingchen deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT jinshuaiwang deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT hangma deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT linwang deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT yuxuanwang deepdehazingnetworkforremotesensingimagewithnonuniformhaze AT xiaoxuanchen deepdehazingnetworkforremotesensingimagewithnonuniformhaze |
| _version_ |
1718431647685148672 |