Abstract
The frequency of marine oil spills has increased in recent years. The growing exploitation of marine oil and continuous increase in marine crude oil transportation has caused tremendous damage to the marine ecological environment. Using synthetic aperture radar (SAR) images to monitor marine oil spills can help control the spread of oil spill pollution over time and reduce the economic losses and environmental pollution caused by such spills. However, it is a significant challenge to distinguish between oil-spilled areas and oil-spill-like in SAR images. Semantic segmentation models based on deep learning have been used in this field to address this issue. In addition, this study is dedicated to improving the accuracy of the U-Shape Network (UNet) model in identifying oil spill areas and oil-spill-like areas and alleviating the overfitting problem of the model; a feature merge network (FMNet) is proposed for image segmentation. The global features of SAR image, which are high-frequency component in the frequency domain and represents the boundary between categories, are obtained by a threshold segmentation method. This can weaken the impact of spot noise in SAR image. Then high-dimensional features are extracted from the threshold segmentation results using convolution operation. These features are superimposed with to the down sampling and combined with the high-dimensional features of original image. The proposed model obtains more features, which allows the model to make more accurate decisions. The overall accuracy of the proposed method increased by 1.82% and reached 61.90% compared with the UNet. The recognition accuracy of oil spill areas and oil-spill-like areas increased by approximately 3% and reached 56.33%. The method proposed in this paper not only improves the recognition accuracy of the original model, but also alleviates the overfitting problem of the original model and provides a more effective monitoring method for marine oil spill monitoring. More importantly, the proposed method provides a design principle that opens up new development ideas for the optimization of other deep learning network models.
Highlights
The architecture is characterized by end-to-end image segmentation technology, and in the up sampling process, the depth features obtained by convolution operation are used as an important basis for each up sampling decision
After analyzing the effects of the fusion model in the training and verification stages, the model was evaluated on the test set, and 110 Synthetic aperture radar (SAR) images in the test set were segmented using the network structure obtained through training
The segmentation results obtained by the feature merge network (FMNet) algorithm combining ToZero and U-Shape Network (UNet) are more detailed than the baseline model, and the recognition results of some areas are even more accurate than the shape in the label
Summary
Oil spills in the ocean have become a serious environmental problem causing, longlasting financial costs and threats to marine life [1]. The continuous increase of pollutants from marine oil spills will have an increasingly negative impact on the environment, biodiversity will be reduced, and eventually the ecosystem imbalance will endanger human survival and sustainable development. In 2015, Ronneberger et al [32] proposed a UNet network structure, which greatly promoted research on medical image segmentation. The entire network has 19 convolution operations, 4 pooling operations, 4 up-sampling operations, and 4 cropping and copying operations. The entire network has 19 convolution operations, 4 pooling operations, 4 up-sampling operations, and 4 cropping and copying the “same” mode for processing, theuses output the same as the original operations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
