Oil Spill Detection Based on Enhanced LBP Neural Algorithms for Noisy Satellite Images

   Introduction. Detecting oil spills in satellite imagery presents a significant challenge due to the low visual contrast between oil slicks and the sea background, particularly under varying illumination conditions and sensor noise. Traditional approaches typically convert RGB images to grayscale prior to texture analysis, discarding wavelength data critical for distinguishing oil types and thicknesses. This paper proposes a novel approach to processing each Local Binary Pattern (LBP) channel using a Pyramid Scene Parsing Network (PSPNet) architecture, which processes each RGB channel independently, preserving the spectral-textural characteristics necessary for accurate oil spill identification.

   Materials and Methods. The modified approach retains three parallel LBP streams that capture channel-specific texture patterns, which are concatenated with the original RGB input to form a six-channel tensor for deep learning processing. Training incorporates comprehensive noise augmentation strategies simulating real-world remote sensing conditions.

   Results. Experimental validation demonstrates that the proposed approach achieves a mean Intersection over Union (mIoU) of 86.05% on the test dataset, representing a 3.25% improvement over traditional grayscale LBP implementations. Critically, the presented model exhibits exceptional noise robustness compared to models based on conventional approaches.

   Discussion. The per-channel processing strategy effectively distinguishes thin oil films from spill-like phenomena (sun glint on the water surface, wind-induced disturbances).

   Conclusion. The results obtained in this study contribute to the development of operational oil spill monitoring systems requiring reliable performance under diverse environmental conditions and imaging scenarios.

1. Sukhinov A.I., Chistyakov A.E., Sidoryakina V.V., Kuznetsova I.Yu., Atayan A.M. Using parallel computing to evaluate the transport of pollutants in shallow waters. Izv. Saratov Univ. Math. Mech. Inform. 2024;24(2):298–315. (In Russ.) doi: 10.18500/1816-9791-2024-24-2-298-315

2. Sidoryakina V.V. Mathematical model of the process of oil pollution spreading in coastal marine systems. Computational Mathematics and Information Technologies. 2023;7(4):39–46. (In Russ.) doi: 10.23947/2587-8999-2023-7-4-39-46

3. Sidoryakina, V., Filina A. A set of tools for predictive modeling of the spatial distribution of oil pollution. E3S Web of Conferences. 2024;592,04017. doi: 10.1051/e3sconf/202459204017

4. Sukhinov A., Sidoryakina V., Solomakha D. Identification of plankton populations in the surface waters of the Azov Sea based on neural network structures of various architectures. BIO Web of Conferences. 2024;141,03003. doi: 10.1051/bioconf/202414103003

5. Sukhinov A.I., Sidoryakina V.V., Solomakha D.A. Identification of plankton populations on the surface of marine systems based on machine learning methods. Priority areas for the development of science and education in the context of the formation of technological sovereignty: materials of the International scientific and practical conference. Rostov-on-Don: DSTU-Print; 2024. P. 272‒277. (In Russ.)

6. Panasenko N.D. Forecasting the coastal systems state using mathematical modelling based on satellite images. Computational Mathematics and Information Technologies. 2023;7(4):32–44. (In Russ.). doi: 10.23947/2587-8999-2023-7-4-54-65

7. Struch R.E., Pulster E.L., Schreier A.D., Murawski S.A. Hepatobiliary analyses suggest chronic pah exposure in hakes (urophycis spp.) following the deepwater horizon oil spill. Environmental Toxicology and Chemistry. 2019;38(12):2740–2749. doi: 10.1002/etc.4596

8. Snyder S.M., Olin J.A., Pulster E.L., Murawski S.A. Spatial contrasts in hepatic and biliary PAHs in Tilefish (Lopholatilus chamaeleonticeps) throughout the Gulf of Mexico, with comparison to the Northwest Atlantic. Environmental Pollution. 2020;258,113775. doi: 10.1016/j.envpol.2019.113775

9. Pisano A., Bignami F., Santoleri R. Oil spill detection in glint-contaminated near-infrared modis imagery. Remote Sensing. 2015;7;1112–1134. doi: 10.3390/rs70101112

10. Brekke C., Solberg A.H. Oil spill detection by satellite remote sensing. Remote Sensing of Environment. 2005;95(1):1–13. doi: 10.1016/j.rse.2004.11.015

11. Sukhinov A.I., Solomakha D.A. Improved method of recognizing marine and coastal system objects based on combination of local binary pattern method and neural network technologies. Num. Meth. Prog. 2025;26(3):366–379. (In Russ.) doi: 10.26089/NumMet.v26r324

12. Sidoryakina V.V., Solomakha D.A. Identification of Marine Oil Spills Using Neural Network Technologies. Computational Mathematics and Information Technologies. 2024;8(4):43–48. (In Russ.) doi: 10.23947/2587-8999-2024-8-4-43-48

13. Ojala T., Pietikäinen M., Mäenpää T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 2002;24:112278. doi: 10.1109/TPAMI.2002.1017623

14. Sukhinov A.A., Ostrobrod G.B. Efficient face detection on epiphany multicore processor Epiphany. Computational Mathematics and Information Technologies. 2017;1(1):113–127. (In Russ.) URL: https://www.cmit-journal.ru/jour/article/view/85/115 (accessed: 21. 12. 2025).

15. Heikkila M., Pietikäinen M. A texture-based method for modeling the background and detecting moving objects. IEEE Trans. Pattern Anal. Mach. Intell. 2006;28:657–662. doi: 10.1109/TPAMI.2006.68

16. Ahmed S., ElGharbawi T., Salah M., El-Mewafi M. Deep neural network for oil spill detection using sentinel-1 data: application to egyptian coastal regions. Geomatics, Natural Hazards and Risk. 2023;14:76–94. doi: 10.1080/19475705.2022.2155998

17. Lee J.-S. Digital image enhancement and noise filtering by use of local statistics. IEEE Trans. Pattern Anal. Mach. Intell. 1980;2:165–168. doi: 10.1109/TPAMI.1980.4766994

18. Yu F., Sun W., Li J., Zhao Y., Zhang Y., Chen G. An improved otsu method for oil spill detection from SAR images. Oceanologia. 2017;59(3):311–317. doi: 10.1016/j.oceano.2017.03.005