Journal "Software Engineering"
a journal on theoretical and applied science and technology
ISSN 2220-3397

Issue N6 2025 year

DOI: 10.17587/prin.16.311-319
Intelligent Processing of Remote Sensing Images of the Sea of Azov
I. F. Razveeva, Senior Lecturer, razveevai@mail.ru, Yu. V. Belova, Associate Professor, yvbelova@yandex.ru, Don State Technical University, Rostov-on-Don, 344000, Russian Federation
Corresponding author: Irina F. Razveeva, Senior Lecturer, Don State Technical University, Rostov-on-Don, 344000, Russian Federation E-mail: razveevai@mail.ru
Received on March 13, 2025
Accepted on April 04, 2025

Systems based on intelligent algorithms are currently becoming alternative sources for obtaining information in all areas of human activity. Large arrays of data coming from various sources, including satellites, unmanned aerial vehicles (UAVs) and manned aircraft, require timely and efficient processing. Computer vision technologies allow analyzing space images to solve a wide range of problems, including monitoring the state of water bodies. Algorithms based on convolutional neural networks come to the fore; they guarantee a result that is not inferior in accuracy to the cognitive abilities of a specialist. The use of such technologies minimizes the influence of the human factor and the time of information processing. This study proposes the implementation of three intelligent algorithms for analyzing remote sensing images of the Sea of Azov based on convolutional neural networks. FCN architectures with ResNet10, DeepLabV3+ and LRASPP were selected to solve the problem of segmenting areas of phytoplankton populations with subsequent creation of a water body contour. The best quality metrics were demonstrated by the FCN model with ResNet10: mIoU = 0.95, mDice = 0.97, PA = 0.98, mPrecision = 0.97. The developed segmentation algorithms are applicable as a source of additional analysis during geoinformation monitoring of water bodies. Analysis of remote sensing images allows identifying and analyzing various areas, tracking their dynamics, qualitative and quantitative indicators. Algorithms can also be used to monitor the state of the water area and identify dead water phenomena.

Keywords: computer vision, convolutional neural network, segmentation, phytoplankton populations, Earth remote sensing, Sea of Azov
pp. 311—319
For citation:
Razveeva I. F., Belova Yu. V. Intelligent Processing of Remote Sensing Images of the Sea of Azov, Programmnaya Ingeneria, 2025, vol. 16, no. 6, pp. 311—319. DOI: 10.17587/prin.16.311-319. (in Russian).
The research was done with the financial support of the Russian Science Foundation (grant No. 22-71-10102 "Mathematical Models and Parallel Algorithms for Predicting the Dynamics of Phytoplankton Populations in Marine Systems Taking into Account the Exchange of Oxygen and Carbon Dioxide on Supercomputer Computation Systems").
References:
  1. Postanovlenie Pravitel'stva RF ot 10 aprelya 2007 g. No. 219 "Ob utverzhdenii Polozheniya ob osushchestvlenii gosudarstvennogo monitoringa vodnykh ob'ektov" (in Russian).
  2. Kazakov M. G. Improving the Quality of 3D Geometry Extraction Using Semantic Image Analysis, Programmnaya Ingeneria, 2013, no. 8, pp. 42—47 (in Russian).
  3. Shvyrov V. V., Kapustin D. A. Analysis of modern methods and approaches to detecting objects in machine vision tasks, Programmnaya Ingeneria, 2023, vol. 14, no. 7, pp. 311—328. DOI: 10.17587/prin.14.311-328 (in Russian).
  4. Karelova R. A., Ignatov E. E. Features of the implementation of a neural network for the automation of steel defect recognition processes, Programmnaya Ingeneria, 2020, vol. 11, no. 6, pp. 330—334. DOI: 10.17587/prin.11.330-334 (in Russian).
  5. Martens M., Izzo D., Krzic A., Cox D. Super-resolution of PROBA-V images using convolutional neural networks, Astrodyn, 2019, vol. 3, pp. 387-402. DOI: 10.1007/s42064-019-0059-8.
  6. Li L., Wang W., Luo H., Ying S. Super-Resolution Reconstruction of High-Resolution Satellite ZY-3 TLC Images, Sensors, 2017, vol. 17, no. 5, article 1062. DOI: 10.3390/s17051062.
  7. Zhang X., Cui J., Wang W., Lin C. A Study for Texture Feature Extraction of High-Resolution Satellite Images Based on a Direction Measure and Gray Level Co-Occurrence Matrix Fusion Algorithm, Sensors, 2017, vol. 17, no. 7, article 1474. DOI: 10.3390/s17071474.
  8. Panasenko N. D., Poluyan A. Y., Motuz N. S. Algorithm for monitoring the plankton population dynamics based on satellite sensing data, Journal of Physics: Conference Series, 2021, vol. 2131, no. 3, article 032052. DOI: 10.1088/1742-6596/2131/3/032052.
  9. Belova Yu., Razveeva I., Rakhimbaeva E. Intelligent analysis of Earth remote sensing data on the distribution of phytoplankton and pollutants in coastal systems, E3S Web Conf., 2022, vol. 363, article 02026. DOI: 10.1051/e3sconf/202236302026.
  10. Kurganovich K. A., Shalikovskij A. V., Bosov M. A., Kochev D. V. Application of artificial intelligence algorithms to control flood-prone areas, VHR, 2021, vol. 2131, no. 3, pp. 6—24. DOI: 10.35567/1999-4508-2021-3-1 (in Russian).
  11. Ighalo J. O., Adeniyi A. G., Marques G. Artificial intelligence for surface water quality monitoring and assessment: a systematic literature analysis, Model. Earth Syst. Environ, 2021, vol. 7, pp. 669—681. DOI: 10.1007/s40808-020-01041-z.
  12. Zhao X., Wu Z., Chen Y. et al. Fine-Grained High-Resolution Remote Sensing Image Change Detection by SAM-UNet Change Detection Model, Remote Sensing, 2024, vol. 316, no. 19, article 3620. DOI: 10.3390/rs16193620.
  13. Alagialoglou L., Manakos I., Papadopoulou S. et al. Mapping Underwater Aquatic Vegetation Using Foundation Models With Air- and Space-Borne Images: The Case of Polyphytos Lake, Remote Sens., 2023, vol. 15, no. 16, article 4001. DOI: 10.3390/rs15164001.
  14. Il'ichev V. G., Dashkevich L. V., Kulygin V. V. Phytocenoses of the Sea of Azov and climate change, Priroda, 2019, vol. 8, no. 1248, pp. 54—62. DOI: 10.7868/S0032874X19080064 (in Russian).
  15. Kovaleva G. V. The problem of "blooming" water in the Sea of Azov, Trudy Yuzhnogo nauchnogo centra RAN, 2020, vol. 8, pp. 122—148. DOI: 10.23885/1993-6621-2020-8-122-148 (in Russian).
  16. Lloret L., Heredia I., Aguilar F. et al. Convolutional Neu­ral Networks for Phytoplankton identification and classification, Biodiversity Information Science and Standards, 2018, vol. 2, article e25762. DOI: 10.3897/biss.2.25762.
  17. Makarevich P. R. Pelagic phytocenoses of the Sea of Azov, Science of the South of Russia, 2022, vol. 18, no. 4, pp. 97—107. DOI: 10.7868/S25000640220410 (in Russian).
  18. Belova Yu.V., Razveeva I. F., Rakhimbaeva E. O. Development of an algorithm for semantic segmentation of Earth remote sensing data to determine phytoplankton populations, Advanced Engineering Research (Rostov-on-Don), 2024, vol. 24, no. 3, pp. 283—292. DOI: 10.23947/2687-1653-2024-24-3-283-292 (in Russian).
  19. Photos of phytoplankton populations in the Sea of Azov and Taganrog Bay: № 2023623142: zayavl. 29.09.2023: opubl. 13.10.2023 / YU. V. Belova, I. F. Razveeva, E. O. Rakhimbaeva; zayavitel' FGBOU "DGTU". Svidetel'stvo o gosudarstvennoj registracii bazy dannykh № 2023623457 RF (in Russian).
  20. A set of segmented images of phytoplankton populations in coastal systems: No. 2023620933: declared 06.04.2023: published 10.04.2023 / Yu. V. Belova, I. F. Razveeva, E. O. Rakhimbaeva; zayavitel' FGBOU "DGTU". Svidetel'stvo o gosudarstvennoj reg-istracii bazy dannykh № 2023621153 RF (in Russian).
  21. BrightnessBooster: № 2024618745: zayavl. 23.04.2024: opubl. 23.04.2024 / I. F. Razveeva, A. N. Kozhakin, B. A. Khasykov [i dr.]; zayavitel' OOO "VDK". Svidetel'stvo o gosudarstvennoj registracii programmy dlya EHVM № 2024619486 RF (in Russian).
  22. Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA, 2015, pp. 3431—3440. DOI: 10.1109/CVPR.2015.7298965.
  23. Chen L. C., Zhu Y., Papandreou G. et al. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, Lect. Notes Comput. Sci. Munich, Germany. Sept. 8—14, 2018, vol. 11211, pp. 833—851.
  24. Howard A. G., Sandler M., Chu G. et al. Searching for MobileNetV3, IEEE/CVFInternational Conference on Computer Vision (ICCV). Seoul, Korea (South). Oct. 27—Nov. 2, 2019, pp. 1314—1324.
  25. Kingma D. P., Ba J. Adam: A Method for Stochastic Optimization, International Conference on Learning Representations, San Diego, California, USA, Jan. 2015, pp. 1—13.