SAR marine oil spill detection based on an encoder-decoder network

ABSTRACT

Marine oil spills are currently among the most challenging problems in marine environments. Synthetic Aperture Radar (SAR), with all-day and all-weather observation, has demonstrated great potential in oil disaster monitoring. A simple encoder-decoder network model was proposed by using SAR images for effective oil spill detection. The proposed model incorporates an optimized U-Net architecture that reduces computational requirements while maintaining detection performance. This is achieved through shortened encoder and decoder stages, depthwise separable convolutions, group normalization, and bilinear interpolation-based upsampling. To improve the model’s generalization, the auto-learning rate and focal loss function are also included. Two public SAR datasets acquired by different sensors have been used to illustrate the efficiency of the proposed model. In addition, the polarimetric information has also been assessed for the detection of oil spill monitoring. The results show that the model can achieve high efficiency at a small model size. The sub-dataset with polarimetric features also achieves a high F1-score of 91.65% and an IoU of 84.59%.

KEYWORDS:

• SAR
• oil spill detection
• encoder-decoder network
• U-Net model
• polarization

Acknowledgements

The oil spill open-source dataset used in this research is from two research papers. We would like to express our heartfelt thanks! Thanks to Qiqi Zhu et al. and Xiaoshuang Ma et al. for sharing such a helpful dataset.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data Availability statement

Upon a reasonable request, the corresponding author is willing to share the datasets analysed in this research.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China under Grant 61971318, U2033216 and 42371367; Natural Science Foundation of Hubei Province, No. 2022CFB193, and Shenzhen Fundamental Research Program under Grant JCYJ20200109150833977.