LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification
At present, the classification accuracy of high-resolution Remote Sensing Image Scene Classification (RSISC) has reached a quite high level on standard datasets. However, when coming to practical application, the intrinsic noise of satellite sensors and the disturbance of atmospheric environment oft...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/53 |
| _version_ | 1797497802543071232 |
|---|---|
| author | Weining An Xinqi Zhang Hang Wu Wenchang Zhang Yaohua Du Jinggong Sun |
| author_facet | Weining An Xinqi Zhang Hang Wu Wenchang Zhang Yaohua Du Jinggong Sun |
| author_sort | Weining An |
| collection | DOAJ |
| description | At present, the classification accuracy of high-resolution Remote Sensing Image Scene Classification (RSISC) has reached a quite high level on standard datasets. However, when coming to practical application, the intrinsic noise of satellite sensors and the disturbance of atmospheric environment often degrade real Remote Sensing (RS) images. It introduces defects to them, which affects the performance and reduces the robustness of RSISC methods. Moreover, due to the restriction of memory and power consumption, the methods also need a small number of parameters and fast computing speed to be implemented on small portable systems such as unmanned aerial vehicles. In this paper, a Lightweight Progressive Inpainting Network (LPIN) and a novel combined approach of LPIN and the existing RSISC methods are proposed to improve the robustness of RSISC tasks and satisfy the requirement of methods on portable systems. The defects in real RS images are inpainted by LPIN to provide a purified input for classification. With the combined approach, the classification accuracy on RS images with defects can be improved to the original level of those without defects. The LPIN is designed on the consideration of lightweight model. Measures are adopted to ensure a high gradient transmission efficiency while reducing the number of network parameters. Multiple loss functions are used to get reasonable and realistic inpainting results. Extensive tests of image inpainting of LPIN and classification tests with the combined approach on NWPU-RESISC45, UC Merced Land-Use and AID datasets are carried out which indicate that the LPIN achieves a state-of-the-art inpainting quality with less parameters and a faster inpainting speed. Furthermore, the combined approach keeps the comparable classification accuracy level on RS images with defects as that without defects, which will improve the robustness of high-resolution RSISC tasks. |
| first_indexed | 2024-03-10T03:24:25Z |
| format | Article |
| id | doaj.art-c76b3096ba714cc6831389f59516f5ce |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:24:25Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c76b3096ba714cc6831389f59516f5ce2023-11-23T12:12:22ZengMDPI AGRemote Sensing2072-42922021-12-011415310.3390/rs14010053LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene ClassificationWeining An0Xinqi Zhang1Hang Wu2Wenchang Zhang3Yaohua Du4Jinggong Sun5Research Department of Medical Support Technology, Academy of Military Science, Tianjin 300161, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin 300161, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin 300161, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin 300161, ChinaResearch Department of Medical Support Technology, Academy of Military Science, Tianjin 300161, ChinaInstitute of Systems Engineering, Academy of Military Science, Beijing 100171, ChinaAt present, the classification accuracy of high-resolution Remote Sensing Image Scene Classification (RSISC) has reached a quite high level on standard datasets. However, when coming to practical application, the intrinsic noise of satellite sensors and the disturbance of atmospheric environment often degrade real Remote Sensing (RS) images. It introduces defects to them, which affects the performance and reduces the robustness of RSISC methods. Moreover, due to the restriction of memory and power consumption, the methods also need a small number of parameters and fast computing speed to be implemented on small portable systems such as unmanned aerial vehicles. In this paper, a Lightweight Progressive Inpainting Network (LPIN) and a novel combined approach of LPIN and the existing RSISC methods are proposed to improve the robustness of RSISC tasks and satisfy the requirement of methods on portable systems. The defects in real RS images are inpainted by LPIN to provide a purified input for classification. With the combined approach, the classification accuracy on RS images with defects can be improved to the original level of those without defects. The LPIN is designed on the consideration of lightweight model. Measures are adopted to ensure a high gradient transmission efficiency while reducing the number of network parameters. Multiple loss functions are used to get reasonable and realistic inpainting results. Extensive tests of image inpainting of LPIN and classification tests with the combined approach on NWPU-RESISC45, UC Merced Land-Use and AID datasets are carried out which indicate that the LPIN achieves a state-of-the-art inpainting quality with less parameters and a faster inpainting speed. Furthermore, the combined approach keeps the comparable classification accuracy level on RS images with defects as that without defects, which will improve the robustness of high-resolution RSISC tasks.https://www.mdpi.com/2072-4292/14/1/53deep learningremote sensing image classificationimage inpaintingprogressive networklightweight model |
| spellingShingle | Weining An Xinqi Zhang Hang Wu Wenchang Zhang Yaohua Du Jinggong Sun LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification Remote Sensing deep learning remote sensing image classification image inpainting progressive network lightweight model |
| title | LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification |
| title_full | LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification |
| title_fullStr | LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification |
| title_full_unstemmed | LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification |
| title_short | LPIN: A Lightweight Progressive Inpainting Network for Improving the Robustness of Remote Sensing Images Scene Classification |
| title_sort | lpin a lightweight progressive inpainting network for improving the robustness of remote sensing images scene classification |
| topic | deep learning remote sensing image classification image inpainting progressive network lightweight model |
| url | https://www.mdpi.com/2072-4292/14/1/53 |
| work_keys_str_mv | AT weiningan lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification AT xinqizhang lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification AT hangwu lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification AT wenchangzhang lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification AT yaohuadu lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification AT jinggongsun lpinalightweightprogressiveinpaintingnetworkforimprovingtherobustnessofremotesensingimagessceneclassification |