Skip to main content

Advertisement

SpringerLink
Log in

Oil spill detection over ocean surface using deep learning: a comparative study

  • Original Paper
  • Published:
Marine Systems & Ocean Technology Aims and scope Submit manuscript

Abstract

Marine pollution poses a humongous threat to oceanic life especially large scale oil spills. The paper addresses this concern by offering a comparative study of novel deep learning architectures trained on identical datasets and computational conditions. We explore the concept of dataset amplification through non-learning image manipulations techniques like Horizontal and Vertical flipping along with random rotations. The models are thoroughly attested using parameters like Mean-IoU, F1 scores and percentage accuracy. The paper concludes by showing V-Net supremacy, as it outperforms it’s fellow implementations with an accuracy of 90.65% and a Dice-Coefficient of 90.34.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. D. Lan, B. Liang, C. Bao, M. Ma, Y. Xu, C. Yu, Marine oil spill risk mapping for accidental pollution and its application in a coastal city. Mar. Pollut. Bull. 96(1–2), 220–225 (2015). https://doi.org/10.1016/j.marpolbul.2015.05.023

    Article  Google Scholar 

  2. USEPA. Understanding oil spills and oil spill response. https://www.epa.gov/sites/production/files/2018-01/documents/ospguide99.pdf (2009)

  3. M. Fingas, C.E. Brown, A review of oil spill remote sensing. Sensors 18(1), 91 (2018)

    Google Scholar 

  4. W. Pu, Deep SAR imaging and motion compensation. IEEE Trans. Image Process. 30, 2232–2247 (2021). https://doi.org/10.1109/tip.2021.3051484

    Article  Google Scholar 

  5. P. Marzialetti, G. Laneve, Oil spill monitoring on water surfaces by radar l, c and x band SAR imagery: a comparison of relevant characteristics. in 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE, pp. 7715–7717 (2016)

  6. ITOPH. Oil tanker spill statistics. https://www.itopf.org/knowledge-resources/data-statistics/statistics/ (2020)

  7. M. Krestenitis, G. Orfanidis, K. Ioannidis, K. Avgerinakis, S. Vrochidis, I. Kompatsiaris, Oil spill identification from satellite images using deep neural networks. Remote Sens. 11(15), 1762 (2019)

    Article  Google Scholar 

  8. F. Milletari, N. Navab, S.A. Ahmadi. V-net: fully convolutional neural networks for volumetric medical image segmentation. in 2016 fourth international conference on 3D vision (3DV), IEEE, pp. 565–571 (2016)

  9. J.M. Hancock. Jaccard distance (jaccard index, jaccard similarity coefficient) https://doi.org/10.1002/9780471650126.dob0956 (2004)

  10. I.T. Jolliffe, The dice co-efficient: a neglected verification performance measure for deterministic forecasts of binary events. Meteorol. Appl. 23(1), 89–90 (2015). https://doi.org/10.1002/met.1532

    Article  Google Scholar 

  11. Z. Zhi-gang, Z. Jian-xue, Z. Yong-gang, Research on the influence of ocean environment on sea clutter. Procedia Environ. Sci. 11, 1108–1112 (2011). https://doi.org/10.1016/j.proenv.2011.12.167

    Article  Google Scholar 

  12. P. Liu, C. Zhao, X. Li, M. He, W. Pichel, Identification of ocean oil spills in SAR imagery based on fuzzy logic algorithm. Int. J. Remote Sens. 31(17–18), 4819–4833 (2010)

    Article  Google Scholar 

  13. M.F. Fingas, C.E. Brown, Review of oil spill remote sensing. Spill Sci. Technol. Bull. 4(4), 199–208 (1997)

    Article  Google Scholar 

  14. K. Topouzelis, A. Psyllos, Oil spill feature selection and classification using decision tree forest on SAR image data. ISPRS J. Photogramm. Remote Sens. 68, 135–143 (2012)

    Article  Google Scholar 

  15. D. Mera, V. Bolon-Canedo, J.M. Cotos, A. Alonso-Betanzos, On the use of feature selection to improve the detection of sea oil spills in SAR images. Comput. Geosci. 100, 166–178 (2017)

    Article  Google Scholar 

  16. A. Taravat, N. Oppelt, Adaptive weibull multiplicative model and multilayer perceptron neural networks for dark-spot detection from SAR imagery. Sensors 14(12), 22798–22810 (2014)

    Article  Google Scholar 

  17. S. Chehresa, A. Amirkhani, G.A. Rezairad, M.R. Mosavi, Optimum features selection for oil spill detection in SAR image. J. Indian Soc. Remote Sens. 44(5), 775–787 (2016)

    Article  Google Scholar 

  18. L. Xu, J. Li, A. Brenning, A comparative study of different classification techniques for marine oil spill identification using radarsat-1 imagery. Remote Sens. Environ. 141, 14–23 (2014)

    Article  Google Scholar 

  19. F. Del Frate, A. Petrocchi, J. Lichtenegger, G. Calabresi, Neural networks for oil spill detection using ERS-SAR data. IEEE Trans. Geosci. Remote Sens. 38(5), 2282–2287 (2000)

    Article  Google Scholar 

  20. S. Singha, T.J. Bellerby, O. Trieschmann, Satellite oil spill detection using artificial neural networks. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 6(6), 2355–2363 (2013)

    Article  Google Scholar 

  21. L. Zuo, P. He, C. Zhang, Z. Zhang, A robust approach to reading recognition of pointer meters based on improved mask-RCNN. Neurocomputing 388, 90–101 (2020)

    Article  Google Scholar 

  22. S.T. Yekeen, A.L. Balogun, K.B.W. Yusof, A novel deep learning instance segmentation model for automated marine oil spill detection. ISPRS J. Photogramm. Remote Sens. 167, 190–200 (2020)

    Article  Google Scholar 

  23. T. De Kerf, J. Gladines, S. Sels, S. Vanlanduit, Oil spill detection using machine learning and infrared images. Remote Sens. 12(24), 4090 (2020)

    Article  Google Scholar 

  24. G. Chen, Y. Li, G. Sun, Y. Zhang, Application of deep networks to oil spill detection using polarimetric synthetic aperture radar images. Appl. Sci. 7(10), 968 (2017)

    Article  Google Scholar 

  25. Y. Li, X. Yang, Y. Ye, L. Cui, B. Jia, Z. Jiang, S. Wang. Detection of oil spill through fully convolutional network. in International Conference on Geo-Spatial Knowledge and Intelligence (Springer, New York, 2017), pp. 353–362

  26. X. Zhu, Y. Li, Q. Zhang, B. Liu, Oil film classification using deep learning-based hyperspectral remote sensing technology. ISPRS Int. J. Geo-Inf. 8(4), 181 (2019)

    Article  Google Scholar 

  27. D. Cantorna, C. Dafonte, A. Iglesias, B. Arcay, Oil spill segmentation in SAR images using convolutional neural networks: a comparative analysis with clustering and logistic regression algorithms. Appl. Soft Comput. 84, 105716 (2019)

    Article  Google Scholar 

  28. G. Orfanidis, K. Ioannidis, K. Avgerinakis, S. Vrochidis, I. Kompatsiaris. A deep neural network for oil spill semantic segmentation in sar images. in 2018 25th IEEE International Conference on Image Processing (ICIP), IEEE, pp. 3773–3777 (2018)

  29. F. Gao, Y. Yang, J. Wang, J. Sun, E. Yang, H. Zhou, A deep convolutional generative adversarial networks (DCGANS)- based semi-supervised method for object recognition in synthetic aperture radar (sar) images. Remote Sens. 10(6), 846 (2018)

    Article  Google Scholar 

  30. F. Del Frate, D. Latini, V. Scappiti. On neural networks algorithms for oil spill detection when applied to c-and x-band SAR. in 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), IEEE pp. 5249–5251 (2017)

  31. H. Guo, G. Wei, J. An, Dark spot detection in SAR images of oil spill using segnet. Appl. Sci. 8(12), 2670 (2018)

    Article  Google Scholar 

  32. J. Zhang, H. Feng, Q. Luo, Y. Li, J. Wei, J. Li, Oil spill detection in quad-polarimetric SAR images using an advanced convolutional neural network based on superpixel model. Remote Sens. 12(6), 944 (2020)

    Article  Google Scholar 

  33. K. Zeng, Y. Wang, A deep convolutional neural network for oil spill detection from spaceborne SAR images. Remote Sens. 12(6), 1015 (2020)

    Article  Google Scholar 

  34. F.M. Bianchi, M.M. Espeseth, N. Borch, Large-scale detection and categorization of oil spills from SAR images with deep learning. Remote Sens. 12(14), 2260 (2020)

    Article  Google Scholar 

  35. O. Ronneberger. Invited talk: U-net convolutional networks for biomedical image segmentation. in Informatik aktuell, (Springer, Berlin, 2017), pp. 3–3. https://doi.org/10.1007/978-3-662-54345-0_3

  36. A. Carpenter European maritime safety agency cleanseanet activities in the north sea. in The Handbook of Environmental Chemistry (Springer International Publishing, New York, 2015), pp. 33–47. https://doi.org/10.1007/6982015429

  37. L.C. Chen, G. Papandreou, F. Schroff, H. Adam. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:abs/170605587 (2017)

  38. M. Goyal, A. Oakley, P. Bansal, D. Dancey, MH. Yap. Automatic lesion boundary segmentation in dermoscopic images with ensemble deep learning methods. arXiv preprint arXiv:190200809 (2019)

  39. M. Liu, H. Luo, Y. Tan, X. Wang, W. Chen. Improved v-net based image segmentation for 3d neuron reconstruction. in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE, pp. 443–448 (2018)

  40. C.S. Chang, J.J. Ding, P.H. Chen, Y.F. Wu, S.J. Lin. 3-d cell segmentation by improved v-net architecture using edge and boundary labels. in 2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP). IEEE, pp. 435–439 (2019)

  41. P.X. Nguyen, Z. Lu, W. Huang, S. Huang, A. Katsuki, Z. Lin. Medical image segmentation with stochastic aggregated loss in a unified u-net. in 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), IEEE, pp. 1–4 (2019)

  42. C. Shorten, T.M. Khoshgoftaar, A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)

    Article  Google Scholar 

Download references

Acknowledgements

We are thankful to Dr. Anup Das from Space Applications Center, ISRO for his constant guidance and support. We also extend our gratitude towards Institute of Technology, Nirma University for providing the apt ambience and infrastructure to carry out this research. We acknowledge the computational empowerment that we could avail in terms of supercomputing facility of Param Shavak funded by GUJCOST Computer Science and Engineering Department.

Author information

Authors and Affiliations

  1. Institute of Technology, Nirma University, Ahmedabad, India

    Naishadh Mehta, Pooja Shah & Pranshav Gajjar

Authors
  1. Naishadh Mehta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pooja Shah
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Pranshav Gajjar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Naishadh Mehta.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mehta, N., Shah, P. & Gajjar, P. Oil spill detection over ocean surface using deep learning: a comparative study. Mar Syst Ocean Technol 16, 213–220 (2021). https://doi.org/10.1007/s40868-021-00109-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40868-021-00109-4

Keywords

Search

Navigation