Restoration of Semantic-Based Super-Resolution Aerial Images
Keywords:
aerial images, super-resolution, semantic segmentation, convolutional neural networks, visual transformers, generative adversarial networksAbstract
Currently, technologies for remote sensing image processing are actively developing, including both satellite images and aerial images obtained from video cameras of unmanned aerial vehicles. Often such images have artifacts such as low resolution, blurred image fragments, noise, etc. One way to overcome such limitations is to use modern technologies to restore super-resolution images based on deep learning methods. The specificity of aerial images is the presentation of texture and structural elements in a higher resolution than in satellite images, which objectively contributes to better results of restoration. The article provides a classification of super-resolution methods based on the main architectures of deep neural networks, namely convolutional neural networks, visual transformers and generative adversarial networks. The article proposes a method for reconstructing super-resolution aerial images SemESRGAN taking into account semantic features by using an additional deep network for semantic segmentation during the training stage. The total loss function, including adversarial losses, pixel-level losses, and perception losses (feature similarity), is minimized. Six annotated aerial and satellite image datasets CLCD, DOTA, LEVIR-CD, UAVid, AAD, and AID were used for the experiments. The results of image restoration using the proposed SemESRGAN method were compared with the basic architectures of convolutional neural networks, visual transformers and generative adversarial networks. Comparative results of image restoration were obtained using objective metrics PSNR and SSIM, which made it possible to evaluate the quality of restoration using various deep network models.
References
2. Lepcha D.C., Goyal B., Dogra A., Goyal V. Image super-resolution: A comprehensive review, recent trends, challenges and applications. Information Fusion. 2023. vol. 91. pp. 230–260.
3. Goodfellow I., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y. Generative adversarial nets. Advances in Neural Information Processing Systems (NIPS 2014). 2014. vol. 27. pp. 1–9.
4. Favorskaya M.N., Pakhirka A.I. [GAN-based remote sensing single-image resolution improvement] Obrabotka prostranstvennyx dannyx v zadachax monitoringa pripodnyx i antropogennyx prozessov (SDM-2023): Sb. tr. Vserossijskoj nkonf. s mezhdunar. Uchast. [Processing of spatial data in tasks of monitoring natural and anthropogenic processes: Collected papers]. 2023. pp. 163–168. (In Russ.).
5. Conde M.V., Choi U.J., Burchi M., Timofte R. Swin2SR: SwinV2 transformer for compressed image super-resolution and restoration. Computer Vision – ECCV 2022 Workshops. LNCS. Springer, Cham. 2023. vol. 13802. pp. 669–687.
6. Wang P., Bayram B., Sertel E. A comprehensive review on deep learning based remote sensing image super-resolution methods. Earth-Science Reviews. 2022. vol. 232(15). DOI: 10.1016/j.earscirev.2022.104110.
7. Qiu D., Cheng Y., Wang X. Medical image super-resolution reconstruction algorithms based on deep learning: A survey. Computer Methods and Programs in Biomedicine. 2023. vol. 238. DOI: 10.1016/j.cmpb.2023.107590.
8. Jiang J., Wang C., Liu X., Ma J. Deep learning-based face super-resolution: A survey. ACM Computing Surveys. 2021. vol. 55. no. 1. pp. 1–36.
9. Liu H., Ruan Z., Zhao P., Dong C., Shang F., Liu Y., Yang L., Timofte R. Video super-resolution based on deep learning: A comprehensive survey. Artificial Intelligence Review. 2022. vol. 55. no. 8. pp. 5981–6035.
10. Sun Y., Deng K., Ren K., Liu J., Deng C., Jin Y. Deep learning in statistical downscaling for deriving high spatial resolution gridded meteorological data: A systematic review. ISPRS Journal of Photogrammetry and Remote Sensing. 2024. vol. 208. pp. 14–38.
11. Wang T., Sun W., Qi H., Ren P. Aerial image super resolution via wavelet multiscale convolutional neural networks. IEEE Geoscience and Remote Sensing Letters. 2018. vol. 15. no. 5. pp. 769–773.
12. Xu W.-J., Xu G.-L., Wang Y., Sun X., Lin D.-Y., Wu Y.-R. High quality remote sensing image super-resolution using deep memory connected network. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2018). 2018. pp. 8889-8892.
13. Tang J., Zhang J., Chen D., Al-Nabhan N., Huang C. Single-frame super-resolution for remote sensing images based on improved deep recursive residual network. EURASIP J Image Video Proc. 2021. vol. 2021. DOI: 10.1186/s13640-021-00560-8.
14. Tang S., Liu J., Xie X., Yang S., Zeng W., Wang X. A stage-mutual-affine network for single remote sensing image super-resolution. Chinese Conference on Pattern Recognition and Computer Vision (PRCV). 2022. pp. 249–261.
15. Wang S., Zhou T., Lu Y., Di H. Contextual transformation network for lightweight remote-sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing. 2022. vol. 60. pp. 1–13. DOI: 10.1109/TGRS.2021.3132093.
16. Lei S., Shi Z., Mo W. Transformer-based multistage enhancement for remote sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing. 2022. vol. 60. pp. 1–11. DOI: 10.1109/TGRS.2021.3136190.
17. Shang J., Gao M., Li Q., Pan J., Zou G., Jeon G. Hybrid-scale hierarchical transformer for remote sensing image super-resolution. Remote Sens. 2023. vol. 15. no. 13. pp. 1–20.
18. Peng G., Xie M., Fang L. Context-aware lightweight remote-sensing image super-resolution network. Frontiers in Neurorobotics. 2023. vol. 17. DOI: 10.3389/fnbot.2023.1220166.
19. Li Y., Mavromatis S., Zhang F., Du Z., Sequeira J., Wang Z., Zhao X., Liu R. Single-image super-resolution for remote sensing images using a deep generative adversarial network with local and global attention mechanisms. IEEE Transactions on Geoscience and Remote Sensing. 2021. vol. 60. pp. 1–24. DOI: 10.1109/TGRS.2021.3093043.
20. Guo M., Zhang Z., Liu H., Huang Y. NDSRGAN: A novel dense generative adversarial network for real aerial imagery super-resolution reconstruction. Remote Sens. 2022. vol. 14. no. 7. pp. 1–23. DOI: 10.3390/rs14071574.
21. Zhang J., Xu T., Li J., Jiang S., Zhang Y. Single-image super resolution of remote sensing images with real-world degradation modeling. Remote Sens. 2022. vol. 14. no. 12. pp. 1–22. DOI: 10.3390/rs14122895.
22. Haykır A.A., Oksuz I. Transfer learning based super resolution of aerial images. 2022 30th Signal Processing and Communications Applications Conference (SIU). 2022. pp. 1–4.
23. Haykir A.A., Öksuz I. Super-resolution with generative adversarial networks for improved object detection in aerial images. Information Discovery and Delivery. 2023. vol. 51. no. 4. pp. 349–357.
24. Tuna C., Unal G., Sertel E. Single-frame super resolution of remote-sensing images by convolutional neural networks. Int. J. Remote Sens. 2018. vol. 39. no. 8. pp. 2463–2479.
25. Dong C., Loy C.C., He K., Tang, X. Learning a deep convolutional network for image super-resolution // Computer Vision – ECCV 2014: 13th European Conference. 2014. pp. 184–199.
26. Wang J., Wang B., Wang X., Zhao Y., Long T. Hybrid attention-based U-shaped network for remote sensing image super-resolution. IEEE Transactions on Geoscience and Remote Sensing. 2023. vol. 61. pp. 1–15.
27. Gu J., Dong C. Interpreting super-resolution networks with local attribution maps. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. pp. 9199–9208.
28. Wang X., Yu K., Wu S., Gu J., Liu Y., Dong C., Qiao Y., Loy C.C. ESRGAN: Enhanced super-resolution generative adversarial networks. Computer Vision – ECCV 2018 Workshops. 2019. pp. 63–79.
29. Johnson J., Alahi A., Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution. Computer Vision – ECCV 2016: 14th European Conference. 2016. pp. 694–711.
30. Liu M., Chai Z., Deng H., Liu R. A CNN-transformer network with multiscale context aggregation for fine-grained cropland change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2022. vol. 15. pp. 4297–4306.
31. Xia G., Bai X., Ding J., Zhu Z., Belongie S., Luo J., Datcu M., Pelillo M., Zhang L. DOTA: A large-scale dataset for object detection in aerial images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. pp. 3974–3983.
32. Chen H., Shi Z. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection. Remote Sens. 2020. vol. 12. no. 10. DOI: 10.3390/rs12101662.
33. Lyu Y., Vosselman G., Xia G-S., Yilmaz A., Yang M.Y. UAVid: A semantic segmentation dataset for UAV imagery. ISPRS Journal of Photogrammetry and Remote Sensing. 2020. vol. 165. pp. 108–119.
34. Airbus Aircraft Detection. Available at: www.kaggle.com/datasets/airbusgeo/airbus-aircrafts-sample-dataset (accessed 04.03.2024).
35. Xia G.-S., Hu J., Hu F., Shi B., Bai X., Zhong Y., Zhang L. AID: A benchmark dataset for performance evaluation of aerial scene classification. IEEE Transactions on Geoscience and Remote Sensing. 2017. vol. 55. no. 7. pp. 3965–3981.
36. Zhang R., Isola P., Efros A.A., Shechtman E., Wang O. The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE: Salt Lake City, UT, USA. 2018. pp. 586–595.
Published
How to Cite
Section
Copyright (c) Маргарита Николаевна Фаворская, Андрей Иванович Пахирка

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms: Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).