A comparative study of Deep Learning architectures for Classification of Natural and Human-made Sea Events in SAR images

Springer Science and Business Media LLC - 2022
William Mauricio Giral Ramírez1, Pedro Achanccaray1, Marco Aurélio Cavalcanti Pacheco1
1Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil

Tóm tắt

AbstractSea monitoring is essential for a better understanding of its dynamics and to measure the impact of human activities. In this context, remote sensing plays an important role by providing satellite imagery every day, even in critical climate conditions, for the detection of sea events with a potential risk to the environment. The present work proposes a comparative study of Deep Learning architectures for classification of natural and man-made sea events using SAR imagery. The evaluated architectures comprises models based on convolutional networks, inception blocks, and attention modules. Two datasets are employed for this purpose: the first one encompasses a series of natural events (geophysical phenomena), while the second describes a real oil spill scenario in the Gulf of Mexico from 2018 to 2021. As a result, through experimental analysis, it is demonstrated how the Xception and Deep Attention sampling architectures obtained the highest performance metrics, presenting Recall values of 94.2% and 87.4% for the classification of natural and human-made events, respectively.

Từ khóa


Tài liệu tham khảo

Klapp J, editor. Experimental and theoretical advances in fluid dynamics. Berlin Heidelberg: Springer; 2012.

Rabalais NN, Smith LM, Eugene-Turner R. The Deepwater Horizon oil spill and Gulf of Mexico shelf hypoxia. Continental Shelf Res. 2018;152:98–107.

Beyer J. Environmental effects of the Deepwater Horizon oil spill: a review. Mar Pollut Bull. 2016;110(1):28–51.

Wang X. Comparison of Arctic sea ice thickness from satellites, aircraft, and PIOMAS data. Remote Sens. 2016;8(9):713.

Wang, C. Labeled SAR imagery dataset of ten geophysical phenomena from Sentinel-1 wave mode (TenGeoP-SARwv). 2018.

Mahmud MS. Seasonal evolution of L-band SAR backscatter over land fast Arctic sea ice. Remote Sens Environ. 2020;251:112049.

Tong S. Multi-feature based ocean oil spill detection for polarimetric SAR data using random forest and the self-similarity parameter. Remote Sens. 2019;11(4):451.

Zhou H, Peng C. Oil spills identification in SAR image using mRMR and SVM model. In: 2018 5th International Conference on Information Science and Control Engineering (ICISCE). IEEE; 2018.

Wang C. Classification of the global Sentinel-1 SAR vignettes for ocean surface process studies. Remote Sens Environ. 2019;234:111457.

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

Song D, et al. A novel marine oil spillage identification scheme based on convolution neural network feature extraction from fully polarimetric SAR imagery. IEEE Access. 2020;8:59801–20.

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Bengio Y, LeCun Y, editors. 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings; 2015.

Sandler M, Howard A, Zhu M. Mobilenetv2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition; 2018, p. 4510–20. https://doi.org/10.1109/CVPR.2018.00474 .

Szegedy C, Vanhoucke V, Ioffe S. Rethinking the inception architecture for computer vision. In 2016 IEEE conference on computer vision and pattern recognition (CVPR); 2016, p. 2818–26; https://doi.org/10.1109/CVPR.2016.308 .

Chollet F. Xception: deep learning with depthwise separable convolutions. IEEE Conf Comput Vis Pattern Recognit. 2017;2017:1251–8.

Szegedy C, Ioffe S, Vanhoucke V. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence; 2017, vol. 31, no. 1.

Katharopoulos A, Fleuret F. Processing megapixel images with deep attention-sampling models. In: Proceedings of the International Conference on Machine Learning (ICML); 2019.

Filipponi F. Sentinel-1 GRD preprocessing workflow, 3rd international electronic conference on remote sensing. Proceedings. 2019. https://doi.org/10.3390/ECRS-3-06201.

RR Selvaraju, M Cogswell, A Das Grad-CAM. Visual explanations from deepnetworks via gradient-based localization. In: 2017 IEEE international conference on computer vision (ICCV). 2017, p. 618–626. https://doi.org/10.1109/ICCV.2017.74

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Thông tin tác giả