Vol. 6 No. 1 (2025)

Standard Journal Issues

Hybrid Deep Learning Approach for Marine Debris Detection in Satellite Imagery Using UNet with ResNext50 Backbone

Published 2025-06-24

  • Marada Srinivasa Rao

Marada Srinivasa Rao
Department of Information Technology, MVGR College of Engineering (A), Vizianagaram, Andhra Pradesh, India

Abstract

Marine debris is persistent solid stuff in the water. Oceans include several varieties of organic marine debris, but massive levels of man-made marine trash threaten their biological equilibrium. Manually scanning the ocean for garbage is time-consuming and inefficient, making it uneconomical. Deep learning, which is more efficient than manual methods, is used to detect marine debris in satellite imagery in our work. Deep learning algorithms have been successful in semantic segmentation, however marine debris detection using satellite imagery has been underexplored. The lack of comprehensive marine debris datasets until recently and the complexity of multispectral satellite photos are to blame. Our segmentation method using the UNet architecture and a ResNext50 backbone exceeds the existing state of the art on the Marine Debris Archive Dataset (MARIDA), a dataset of 11 band sentinel 2 Satellite image patches. The hybrid solution combines ResNext50's increased feature extraction with UNet's global and local context preservation, which is crucial in satellite photos of floating bodies due to marine debris' movement pattern. We achieved benchmark mean pixel accuracy, IoU, and F1 scores. We achieved an 88% recall, a 10% improvement over the state of the art, in categorizing marine trash pixels in photos. This work attempts to advance deep learning algorithms for remote sensing and move closer to cleaner oceans.

Keywords

UNet, ResNext, Encoder Blocks, Decoder Blocks, Marine Debris, ResUNext

PDF

References

  1. Perumal, K. et al. (2021) ‘Sources, spatial distribution, and abundance of marine debris on Thondi Coast, Palk Bay, Southeast Coast of India’, Environmental Sciences Europe, 33(1). doi:10.1186/s12302-021-00576-x.
  2. Schuyler, Q.A. et al. (2014) ‘Mistaken identity? Visual similarities of marine debris to natural prey items of sea turtles’, BMC Ecology, 14(1). doi:10.1186/1472-6785-14-14.
  3. Ryan, P.G. (2015) ‘Birds and plastic pollution: recent advances’, Marine Pollution Bulletin, 105(1), pp. 25–26. doi:10.1016/j.marpolbul.2016.02.011.
  4. Hidayaturrahman, H. and Lee, T.G. (2019) ‘Microplastics in Digestive System of Little-black cormorant (Phalacrocorax sulcirostris) in Pulau Rambut Sanctuary’, Marine Pollution Bulletin, 149, p. 110566. doi:10.1016/j.marpolbul.2019.110566.
  5. Thompson, R.C. et al. (2011) ‘Marine Debris as a Global Environmental Problem: Introducing a solutions based framework focused on plastic’, STAP Information Document, Global Environment Facility. doi : hegef.org sites/default/files/publications/STAP_MarineDebris_-_website_1.pdf.
  6. Barboza, L.G.A. et al. (2018) ‘Microplastics in Fish and Fishery Products and Risks for Human Health: A Review’, Environmental International, 114, pp. 200–212. doi:10.1016/j.envint.2018.02.017.
  7. Chae, Y. and An, Y.J. (2017) ‘Health Effects of Microplastic Exposures: Current Issues and Perspectives in South Korea’, Environmental Research, 158, pp. 754–762. doi:10.1016/j.envres.2017.06.002.
  8. Raymond-Yakoubian, J. et al. (2017) ‘An Indigenous approach to ocean planning and policy in the Bering Strait region of Alaska’, Marine Policy, 97, pp. 101–108. doi:10.1016/j.marpol.2018.05.007.
  9. Kikaki, K. et al. (2022) 'MARIDA: A Benchmark for Marine Debris Detection from Sentinel-2 Remote Sensing Data', PLOS ONE, 17(1), e0262247. doi:10.1371/journal.pone.0262247.
  10. Zhao, P. et al. (2024) 'Object Detection in Multispectral Remote Sensing Images Based on Cross-Modal Cross-Attention', Sensors, 24(13), p. 4098. doi:10.3390/s24134098.
  11. Yuan, K. et al. (2021) 'Deep-Learning-Based Multispectral Satellite Image Segmentation for Water Body Detection', IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, pp. 7422–7434. doi:10.1109/JSTARS.2021.3098678.
  12. Uehara, K. et al. (2017) 'Multi-Channel Higher-Order Local Autocorrelation for Object Detection in Multispectral Imagery', Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 123–130. doi:10.1109/CVPRW.2017.123.
  13. Hu, C. (2022) 'Remote Detection of Marine Debris Using Sentinel-2 Imagery: A Cautious Note on Spectral Interpretations', Remote Sensing, 14(5), p. 1123. doi:10.3390/rs14051123.
  14. Rußwurm, M. et al. (2023) 'Large-scale Detection of Marine Debris in Coastal Areas with Sentinel-2', ISPRS Journal of Photogrammetry and Remote Sensing, 192, pp. 49–60. doi:10.1016/j.isprsjprs.2023.04.012.
  15. Anjaneyulu, S.S.S.R. et al. (2020) 'An Overview of Technological Revolution in Satellite Image Analysis', Journal of the Indian Society of Remote Sensing, 48, pp. 497–513. doi:10.1007/s12524-019-01068-7.
  16. Zhao, F., Huang, B., Wang, J., Shao, X., Wu, Q., Xi, D., Liu, Y., Chen, Y., Zhang, G., Ren, Z., Chen, J., & Mizuno, K. (2025) ‘Seafloor debris detection using underwater images and deep learning-driven image restoration: A case study from Koh Tao, Thailand’, Marine Pollution Bulletin, 214, 117710. https://doi.org/10.1016/j.marpolbul.2025.117710.
  17. ?uraš, A., Wolf, B. J., Ilioudi, A., Palunko, I., & De Schutter, B. (2024) ‘A dataset for detection and segmentation of underwater marine debris in shallow waters’, Scientific Data, 11(1). https://doi.org/10.1038/s41597-024-03759-2.
  18. Ma, B., Zhao, F., Xi, D., Wang, J., Shao, X., Wang, S., Tabeta, S., & Mizuno, K. (2024) ‘A New Coral Classification Method Using Speed Sea Scanner-Portable and Deep Learning-Based Point Cloud Semantic Segmentation’, In OCEANS 2024 - Halifax, Halifax, NS, Canada, 2024 (pp. 1–4). https://doi.org/10.1109/oceans55160.2024.10753899.
  19. Shen, A., Zhu, Y., Angelov, P., & Jiang, R. (2024) ‘Marine debris detection in satellite surveillance using attention mechanisms’, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 4320–4330. https://doi.org/10.1109/jstars.2024.3349489.
  20. Nivedita, V., Begum, S. S., Aldehim, G., Alashjaee, A. M., Arasi, M. A., Sikkandar, M. Y., Jayasankar, T., & Vivek, S. (2024) ‘Plastic debris detection along coastal waters using Sentinel-2 satellite data and machine learning techniques’, Marine Pollution Bulletin, 209, 117106. https://doi.org/10.1016/j.marpolbul.2024.117106
  21. Topouzelis, K. et al. (2019) 'Floating Marine Litter Detection Algorithms and Techniques Using Optical Remote Sensing Data: A Review', Marine Pollution Bulletin, 145, pp. 429–442. doi:10.1016/j.marpolbul.2019.06.011.
  22. Ronneberger, O., Fischer, P., and Brox, T. (2015) 'U-Net: Convolutional Networks for Biomedical Image Segmentation', Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 234–241. doi:10.1007/978-3-319-24574-4_28.
  23. Xie, S. et al. (2017) 'Aggregated Residual Transformations for Deep Neural Networks', Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987–5995. doi:10.1109/CVPR.2017.634.
  24. Phan, T.H. and Yamamoto, K. (2020) 'Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses', arXiv preprint, arXiv:2006.01413. doi: https://arxiv.org/pdf/2006.01413.
  25. Lin, T.Y. et al. (2017) 'Focal Loss for Dense Object Detection', Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988. doi:10.1109/ICCV.2017.324.
  26. Kingma, D.P. and Ba, J. (2015) 'Adam: A Method for Stochastic Optimization', arXiv preprint, arXiv:1412.6980. doi: /arxiv.org/abs/1412.6980.
  27. Qian, J. et al. (2021) 'Understanding Gradient Clipping in Incremental Gradient Methods', Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), pp. 3645–3683.
  28. Booth, H., Ma, W. and Karaku?, O. (2023) ‘High-precision density mapping of marine debris and floating plastics via satellite imagery’, Scientific Reports, 13(1). doi:10.1038/s41598-023-33612-2.
  29. Schaum, A. (2009) ‘Remote spectral detection using a laboratory signature’, 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, pp. 1–4. doi:10.1109/whispers.2009.5289061.
  30. Piryonesi, S.M. (2019) 'The Application of Data Analytics to Asset Management: Deterioration and Climate Change Adaptation in Ontario Roads', Doctoral dissertation, University of Toronto. Available at: https://tspace.library.utoronto.ca/handle/1807/97601.
  31. Piryonesi, S.M. and El-Diraby, T.E. (2021) 'Using Machine Learning to Examine Impact of Type of Performance Indicator on Flexible Pavement Deterioration Modeling', Journal of Infrastructure Systems, g27(2), 04021005. doi:10.1061/(ASCE)IS.1943-555X.0000602.
  32. Smith, P.F., Ganesh, S., and Liu, P. (2013) 'A Comparison of Random Forest Regression and Multiple Linear Regression for Prediction in Neuroscience', Journal of Neuroscience Methods, 220(1), pp. 85–91. doi:10.1016/j.jneumeth.2013.08.024.
  33. Azhan, Mohammed. (2022) ’ResAttUNet: Detecting Marine Debris using an Attention activated Residual UNet.’, ArXiv abs/2210.08506 (2022).

Downloads

Download data is not yet available.