(49-6) 15 * << * >> * Russian * English * Content * All Issues

Enhancing forest cover analysis through super-resolution of Sentinel-2 multispectral images
S.V. Illarionova 1, D.G. Shadrin 1, A.V. Kedrov 2

1 Skolkovo Institute of Science and Technology,
Bolshoy Bulvar 42, bldg. 1, Skolkovo, Moscow, 143026, Russia;
2 Space technologies and services center, Ltd,
str. Lev Lavrov, 14, Perm, 614038, Russia

 PDF, 4637 kB

DOI: 10.18287/2412-6179-CO-1626

Pages: 994-1001.

Full text of article: English language.

Abstract:
Machine learning (ML) algorithms, combined with satellite observations, offer significant advantages in environmental studies, particularly in vegetation cover analysis. The varying spectral resolution and number of spectral bands of remote sensing imagery allow for different tasks to be addressed with different levels of detail and accuracy. A current limitation in advanced Geographic Information System (GIS) development is the availability and accessibility of data. High-resolution data with a wide spectral range are often expensive, while open-access data typically force researchers to choose between high spatial and temporal resolution or large number of spectral bands. In this study, we investigate this issue through a case study of forest type classification. We employed and trained a single-image super-resolution model based on the Residual Channel Attention Network (RCAN) to upscale Sentinel-2 multispectral images from 10 to 5 meters. We then compared image segmentation results from the original Sentinel-2 data, the upscaled data, and WorldView-3 images. In addition to experiments with spatial resolution, we explored the effect of number of spectral bands on segmentation quality. The results confirm our hypothesis that artificially upscaled data provide more information than low-resolution data, both for narrow and wider spectral ranges, with the increase in spatial resolution proving more significant than the increase in number of spectral bands.

Keywords:
remote sensing, computer vision, super-resolution, deep learning.

Citation:
The work was funded by the Russian Science Foundation under project No. 23-71-01122.

Acknowledgements:
Illarionova SV, Shadrin DG, Kedrov AV. Enhancing forest cover analysis through super-resolution of Sentinel-2 multispectral images. Computer Optics 2025; 49(6): 994-1001. DOI: 10.18287/2412-6179-CO-1626.

References:
  1. Lei T, et al. Review of remote sensing-based methods for forest aboveground biomass estimation: Progress, challenges, and prospects. Forests 2023; 14(6): 1086. DOI: 10.3390/f14061086.
  2. Illarionova S, Smolina A, Shadrin D. Primary forest characteristics estimation through remote sensing data and machine learning: Sakhalin case study. E3S Web of Conf 2024; 542: 04003. DOI: 10.1051/e3sconf/202454204003.
  3. Illarionova S, et al. A survey of computer vision techniques for forest characterization and carbon monitoring tasks. Remote Sens 2022; 14(22): 5861. DOI: 10.3390/rs14225861.
  4. Illarionova S, et al. Estimation of the canopy height model from multispectral satellite imagery with convolutional neural networks. IEEE Access 2022; 10: 34116-34132. DOI: 10.1109/ACCESS.2022.3161568.
  5. Liu L, et al. Hyperspectral remote sensing imagery generation from RGB images based on joint discrimination. IEEE J Sel Top Appl Earth Obs Remote Sens 2021; 14: 7624-7636. DOI: 10.1109/JSTARS.2021.3099242.
  6. Wang P, Bayram B, Sertel E. A comprehensive review on deep learning based remote sensing image super-resolution methods. Earth Sci Rev 2022; 232: 104110. DOI: 10.1016/j.earscirev.2022.104110.
  7. Dong C, et al. Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Machine Intell 2015; 38(2): 295-307. DOI: 10.1109/TPAMI.2015.2439281.
  8. Kim J, Lee JK, Lee KM. Accurate image super-resolution using very deep convolutional networks. 2016 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 1646-1654. DOI: 10.1109/CVPR.2016.182.
  9. Kim J, Lee JK, Lee KM. Deeply-recursive convolutional network for image super-resolution. 2016 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 1637-1645. DOI: 10.1109/CVPR.2016.181.
  10. Shi W, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. 2016 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 1874-1883. DOI: 10.1109/CVPR.2016.207.
  11. Liu J, et al. Residual feature aggregation network for image super-resolution. 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2020: 2356-2365. DOI: 10.1109/CVPR42600.2020.00243.
  12. Chen H, et al. Real-world single image super-resolution: A brief review. Inf Fusion 2022; 79: 124-145. DOI: 10.1016/j.inffus.2021.09.005.
  13. Ledig C, et al. Photo-realistic single image super-resolution using a generative adversarial network. 2017 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2017: 105-114. DOI: 10.1109/CVPR.2017.19.
  14. Johnson J, Alahi A, Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution. In Book: Leibe B, Matas J, Sebe N, Welling M, eds. Computer Vision – ECCV 2016. 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II. Cham, Switzerland: Springer International Publishing AG; 2016: 694-711. DOI: 10.1007/978-3-319-46475-6_43.
  15. Wang X, et al. ESRGAN: Enhanced super-resolution generative adversarial networks. In Book: Leal-Taixé L, Roth S, eds. Computer Vision – ECCV 2018 Workshops. Munich, Germany, September 8-14, 2018, Proceedings, Part V. Cham, Switzerland: Springer International Publishing AG; 2018: 63-79. DOI: 10.1007/978-3-030-11021-5_5.
  16. Wang X, et al. Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data. 2021 IEEE/CVF Int Conf on Computer Vision Workshops (ICCVW) 2021: 1905-1914. DOI: 10.1109/ICCVW54120.2021.00217.
  17. Zhang Y, et al. Image super-resolution using very deep residual channel attention networks. In Book: Ferrari V, Hebert M, Sminchisescu C, Weiss Y, eds. Computer Vision – ECCV 2018. 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VII. Cham, Switzerland: Springer International Publishing AG; 2018: 294-310. DOI: 10.1007/978-3-030-01234-2_18.
  18. Michel J, et al. SEN2VENµS, a dataset for the training of sentinel-2 super-resolution algorithms. Data 2022; 7(7): 96. DOI: 10.3390/data7070096.
  19. Illarionova S, et al. Augmentation-based methodology for enhancement of trees map detalization on a large scale. Remote Sens 2022; 14(9): 2281. DOI: 10.3390/rs14092281.
  20. Fan T, et al. MA-Net: A multi-scale attention network for liver and tumor segmentation. IEEE Access 2020; 8: 179656-179665. DOI: 10.1109/ACCESS.2020.3025372.
  21. Sharma S. Semantic segmentation for urban-scene images. arXiv Preprint. 2021. Source: <https://arxiv.org/abs/2110.13813>. DOI: 10.48550/arXiv.2110.13813.
  22. Milletari F, Navab N, Ahmadi S-A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. 2016 Fourth Int Conf on 3D Vision (3DV) 2016: 565-571. DOI: 10.1109/3DV.2016.79.
  23. Lin T-Y, Goyal P, Girshick R, He K, Dollár P. Focal loss for dense object detection. 2017 IEEE Int Conf on Computer Vision (ICCV) 2017: 2999-3007. DOI: DOI: 10.1109/ICCV.2017.324.
  24. Schepaschenko D, et al. Russian forest sequesters substantially more carbon than previously reported. Sci Rep 2021; 11: 12825. DOI: 10.1038/s41598-021-92152-9.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20