Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms
As super-resolution techniques continue to evolve, there is a growing requirement for more advanced methods to capture finer details, particularly when dealing with the smaller pixels within an image. In remote sensing, enhanced spatial details can find utility in diverse applications, such as disas...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10497594/ |
| _version_ | 1797201335697801216 |
|---|---|
| author | Allen Patnaik Narendra Chaudhary M. K. Bhuyan Sultan Alfarhood Mejdl Safran |
| author_facet | Allen Patnaik Narendra Chaudhary M. K. Bhuyan Sultan Alfarhood Mejdl Safran |
| author_sort | Allen Patnaik |
| collection | DOAJ |
| description | As super-resolution techniques continue to evolve, there is a growing requirement for more advanced methods to capture finer details, particularly when dealing with the smaller pixels within an image. In remote sensing, enhanced spatial details can find utility in diverse applications, such as disaster management, urban planning, and environmental change detection. Many existing image super-resolution algorithms are there to improve image resolution. However, they are not explicitly crafted to accommodate the distinctive attributes of remote-sensing images, rendering them less effective in restoring the details of the images. Therefore, we proposed a convolutional block attention residual network with joint adversarial mechanisms (CRNJAM) to capture finer details in remote sensing images. We first designed a generator based on the residual network and attention mechanism. This has the ability to produce high-quality images with superior resolution, even when the input is of low quality. Then, we train the super-resolved images with high-resolution images with the help of two types of discriminators to generate more realistic images. The first discriminator evaluates an input sample’s local regions or patches. On the other hand, the second discriminator evaluates the entire input sample as a whole. The result shows that the proposed model can significantly reduce the noise in the generated super-resolved image; also, the SR image generated using the proposed method provides competitive advantages over the images generated using other models. |
| first_indexed | 2024-04-24T07:45:55Z |
| format | Article |
| id | doaj.art-8b383a82d99049588f877fef095ccd91 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T07:45:55Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8b383a82d99049588f877fef095ccd912024-04-18T23:00:37ZengIEEEIEEE Access2169-35362024-01-0112534245343510.1109/ACCESS.2024.338798110497594Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial MechanismsAllen Patnaik0https://orcid.org/0009-0009-1418-9805Narendra Chaudhary1https://orcid.org/0009-0005-2574-1512M. K. Bhuyan2https://orcid.org/0000-0003-2152-5466Sultan Alfarhood3https://orcid.org/0009-0001-1268-9613Mejdl Safran4https://orcid.org/0000-0002-7445-7121Indian Institute of Technology Guwahati, Guwahati, IndiaVE Commercial Vehicle, Bangalore, IndiaIndian Institute of Technology Guwahati, Guwahati, IndiaDepartment of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaAs super-resolution techniques continue to evolve, there is a growing requirement for more advanced methods to capture finer details, particularly when dealing with the smaller pixels within an image. In remote sensing, enhanced spatial details can find utility in diverse applications, such as disaster management, urban planning, and environmental change detection. Many existing image super-resolution algorithms are there to improve image resolution. However, they are not explicitly crafted to accommodate the distinctive attributes of remote-sensing images, rendering them less effective in restoring the details of the images. Therefore, we proposed a convolutional block attention residual network with joint adversarial mechanisms (CRNJAM) to capture finer details in remote sensing images. We first designed a generator based on the residual network and attention mechanism. This has the ability to produce high-quality images with superior resolution, even when the input is of low quality. Then, we train the super-resolved images with high-resolution images with the help of two types of discriminators to generate more realistic images. The first discriminator evaluates an input sample’s local regions or patches. On the other hand, the second discriminator evaluates the entire input sample as a whole. The result shows that the proposed model can significantly reduce the noise in the generated super-resolved image; also, the SR image generated using the proposed method provides competitive advantages over the images generated using other models.https://ieeexplore.ieee.org/document/10497594/Adversarial mechanismsattention modulesuper-resolution |
| spellingShingle | Allen Patnaik Narendra Chaudhary M. K. Bhuyan Sultan Alfarhood Mejdl Safran Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms IEEE Access Adversarial mechanisms attention module super-resolution |
| title | Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms |
| title_full | Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms |
| title_fullStr | Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms |
| title_full_unstemmed | Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms |
| title_short | Remote Sensing Single-Image Super-Resolution Using Convolutional Block Attention Residual Network With Joint Adversarial Mechanisms |
| title_sort | remote sensing single image super resolution using convolutional block attention residual network with joint adversarial mechanisms |
| topic | Adversarial mechanisms attention module super-resolution |
| url | https://ieeexplore.ieee.org/document/10497594/ |
| work_keys_str_mv | AT allenpatnaik remotesensingsingleimagesuperresolutionusingconvolutionalblockattentionresidualnetworkwithjointadversarialmechanisms AT narendrachaudhary remotesensingsingleimagesuperresolutionusingconvolutionalblockattentionresidualnetworkwithjointadversarialmechanisms AT mkbhuyan remotesensingsingleimagesuperresolutionusingconvolutionalblockattentionresidualnetworkwithjointadversarialmechanisms AT sultanalfarhood remotesensingsingleimagesuperresolutionusingconvolutionalblockattentionresidualnetworkwithjointadversarialmechanisms AT mejdlsafran remotesensingsingleimagesuperresolutionusingconvolutionalblockattentionresidualnetworkwithjointadversarialmechanisms |