DOI: https://doi.org/10.26089/NumMet.v26r324

Improved method of recognizing marine and coastal system objects based on combination of local binary pattern method and neural network technologies

Authors

  • Alexander I. Sukhinov
  • Denis A. Solomakha

Keywords:

PSPNet
LBP
oil spill detection
image segmentation

Abstract

The work proposes a hybrid model LBP+PSPNet to increase the accuracy of oil spill segmentation on RGB-images of remote sensing of the Earth, especially in conditions of low contrast between pollution and marine background. The model combines local texture feature extraction (LBP) with global context analysis based on Pyramid Scene Parsing Network (PSPNet). LBP enhances the detail of the texture features of oil film, which are often masked by solar flares or small spots. PSPNet provides large-scale image analysis, which allows for the precise segmentation of both large spills and low-level pollution. Experiments showed that LBP integration increases the IoU metric by 4.6% compared to the basic PSPNet architecture. The proposed model reaches F1-measure 0.85 when tested on low contrast scenarios, demonstrating resistance to noise and atmospheric distortions. The results confirm the effectiveness of synthesis of classical methods of texture analysis and deep learning for environmental monitoring tasks.


Downloads

Published

2025-09-21

Issue

Vol. 26 (2025): Issue 3.

Section

Methods and algorithms of computational mathematics and their applications

Authors

Alexander I. Sukhinov

Don State Technical University

• Professor, Head of Department

Denis A. Solomakha

Don State Technical University

• Masterʼs student

References

  1. J. Beyer, H. C. Trannum, T. Bakke, et al., “Environmental Effects of the Deepwater Horizon Oil Spill: A Review,” Marine Pollution Bulletin 110 (1), 28-51. (2016).
    doi 10.1016/j.marpolbul.2016.06.027
  2. J. W. Farrington, “Oil Pollution in the Marine Environment II: Fates and Effects of Oil Spills,” Environment: Science and Policy for Sustainable Development 56 (4), 16-31 (2014).
    doi 10.1080/00139157.2014.922382
  3. N. A. Bui, Y. Oh, I. Lee, “Oil Spill Detection and Classification through Deep Learning and Tailored Data Augmentation,” International Journal of Applied Earth Observation and Geoinformation 129 (3-4), Article Number 103845. (2024).
    doi 10.1016/j.jag.2024.103845
  4. M. N. Pangilinan, R. Anacan, and R. Garcia, “Design and Development of an Oil Spill Detection and Transmission System Using Artificial Illumination Using LEDs,” in Proceedings of the 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS) , Bangkok, Thailand, 2016, pp. 407-412.
    doi 10.1109/ISMS.2016.61
  5. O. N. Gershenzon, V. E. Gershenzon, and S. V. Osheyko, “Integral Solution for Oil Spill Detection Using SAR Data,” Proceedings of the 2007 3rd International Conference on Recent Advances in Space Technologies (RAST 2007), 361-365 (2007).
    doi 10.1109/RAST.2007.4284013
  6. D.-W. Shin, C.-S. Yang, and W.-J. Choi, “Oil Spill Detection Technique with Automatic Updating Using Deep Learning and Oil Spill Index,” Proceedings of the 2023 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2023), 4019-4022 (2023).
    doi 10.1109/IGARSS52108.2023.10281425
  7. Z. Ghorbani and A. H. Behzadan, “Monitoring Offshore Oil Pollution Using Multi-Class Convolutional Neural Networks,” Environmental Pollution 289, Article Number 117884 (2021).
    doi 10.1016/j.envpol.2021.117884
  8. V. Bondur, T. Chimitdorzhiev, I. Kirbizhekova, and A. Dmitriev, “A Novel Method of Boreal Zone Reforestation/Afforestation Estimation Using PALSAR-1, 2 and Landsat-5, 8 Data,” Forests 15 (1), Article Number 132 (2024).
    doi 10.3390/f15010132
  9. H. Guo, G. Wei, and J. An, “Dark Spot Detection in SAR Images of Oil Spill Using Segnet,” Applied Sciences 8 (12), Article Number 2670 (2018).
    doi 10.3390/app8122670
  10. A. Pisano, F. Bignami, and R. Santoleri, “Oil Spill Detection in Glint-Contaminated Near-Infrared MODIS Imagery,” Remote Sensing 7 (1), 1112-1134 (2015).
    doi 10.3390/rs70101112
  11. N. Kitajima, R. Seto, D. Yamazaki, et al., “Potential of a SAR Small-Satellite Constellation for Rapid Monitoring of Flood Extent,” Remote Sensing 13 (10), Article Number 1959 (2021).
    doi 10.3390/rs13101959
  12. V. V. Sidoryakina and D. A. Solomakha, “Identification of Marine Oil Spills Using Neural Network Technologies,” Computational Mathematics and Information Technologies 8 (4), 43-48 (2024).
    doi 10.23947/2587-8999-2024-8-4-43-48
  13. S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering 22 (10), 1345-1359 (2010).
    doi 10.1109/TKDE.2009.191
  14. N. Kitajima, R. Seto, D. Yamazaki, et al., “Potential of a SAR Small-Satellite Constellation for Rapid Monitoring of Flood Extent,” Remote Sensing 13 (10), Article Number 1959 (2021).
    doi 10.3390/rs13101959
  15. S. Ahmed, T. ElGharbawi, M. Salah, and M. El-Mewafi, “Deep Neural Network for Oil Spill Detection Using Sentinel-1 Data: Application to Egyptian Coastal Regions,” Geomatics, Natural Hazards and Risk 14 (1), 76-94 (2022).
    doi 10.1080/19475705.2022.2155998
  16. H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid Scene Parsing Network,” Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6230-6239 (2017).
    doi 10.1109/CVPR.2017.660
  17. T. Ojala, M. Pietik854inen, and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Featured Distributions,” Pattern Recognition 29 (1), 51-59 (1996).
    doi 10.1016/0031-3203(95)00067-4
  18. C. Brekke and A. H. S. Solberg, “Oil Spill Detection by Satellite Remote Sensing,” Remote Sensing of Environment 95 (1), 1-13 (2005).
    doi 10.1016/j.rse.2004.11.015
  19. N. A. Firsov, V. V. Podlipnov, N. A. Ivliev, et al., “Ensembles of Spectral-Spatial Convolutional Neural Network Models for Classifying Soil Types in Hyperspectral Images,” Computer Optics 47 (5), 795-805 (2023).
    doi 10.18287/2412-6179-CO-1260
  20. A. B. Whetten and H. J. Demler, “Detection of Multidecadal Changes in Vegetation Dynamics and Association with Intra-Annual Climate Variability in the Columbia River Basin,” Remote Sensing 14 (3), Article Number 569 (2022).
    doi 10.3390/rs14030569
  21. S. T. Yekeen and A.-L. Balogun, “Automated Marine Oil Spill Detection Using Deep Learning Instance Segmentation Model,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B3-2020, 1271-1276 (2020).
    doi 10.5194/isprs-archives-XLIII-B3-2020-1271-2020
  22. K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” arXiv: 1512.03385 [cs.CV] (2015).
    doi 10.48550/arXiv.1512.03385
  23. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015, in Lecture Notes in Computer Science 9351, pp. 234-241 (2015).
    doi 10.1007/978-3-319-24574-4_28
  24. Y. Chen, Y. Sun, W. Yu, Y. Liu, and H. Hu, “A Novel Lightweight Bilateral Segmentation Network for Detecting Oil Spills on the Sea Surface,” Marine Pollution Bulletin 175 (1), Article Number 113343 (2022).
    doi 10.1016/j.marpolbul.2022.113343
  25. T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence 24 (7), 971-987 (2002).
    doi 10.1109/TPAMI.2002.1017623
  26. N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05) 1, 886-893 (2005).
    doi 10.1109/CVPR.2005.177
  27. D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision 60 (2), 91-110 (2004).
    doi 10.1023/B: VISI.0000029664.99615.94.
  28. T. Bouwmans, “Traditional and Recent Approaches in Background Modeling for Foreground Detection: An Overview,” Computer Science Review 11-12, 31-66 (2014).
    doi 10.1016/j.cosrev.2014.04.001
  29. S. Brahnam, L. C. Jain, L. Nanni, and A. Lumini, Local Binary Patterns: New Variants and Applications. Studies in Computational Intelligence. (Springer, Berlin, 2014).
    doi 10.1007/978-3-642-39289-4
  30. M. Heikkil854 and M. Pietik854inen, “A Texture-Based Method for Modeling the Background and Detecting Moving Objects,” IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (4), 657-662 (2006).
    doi 10.1109/TPAMI.2006.68

License

Copyright (c) 2025 А. И. Сухинов, Д. А. Соломаха

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.