Chang, L.; Chen, Y.-T.; Cheng, C.-M.; Chang, Y.-L.; Ma, S.-C. Marine Oil Pollution Monitoring Based on Morphological Attention U-Net Using SAR Images. Preprints2024, 2024091041. https://doi.org/10.20944/preprints202409.1041.v1
APA Style
Chang, L., Chen, Y. T., Cheng, C. M., Chang, Y. L., & Ma, S. C. (2024). Marine Oil Pollution Monitoring Based on Morphological Attention U-Net Using SAR Images. Preprints. https://doi.org/10.20944/preprints202409.1041.v1
Chicago/Turabian Style
Chang, L., Yang-Lang Chang and Shang-Chih Ma. 2024 "Marine Oil Pollution Monitoring Based on Morphological Attention U-Net Using SAR Images" Preprints. https://doi.org/10.20944/preprints202409.1041.v1
Abstract
With the development of economy, maritime transportation has increased rapidly, which has had a significant impact on the marine environment and resources. In recent years, Synthetic Aperture Radar (SAR) has been widely used to observe maritime environmental incident. Through the large coverage area of SAR, marine environmental emergencies, especially oil pollution, can be better monitored and responded to. This study first proposed an improved Full-scale Aggregated MobileUNet (FA-MobileUNet) model to achieve more complete detection results of oil spill areas. The convolutional block attention module (CBAM) in FA-MobileUNet was modified based on morphological concepts. By introducing the morphological attention module (MAM), the improved FA-MobileUNet model can reduce the fragments and holes in the detection results, providing complete oil spill areas which were more suitable for describing the location and scope of oil pollution incidents. In addition, to overcome the inherent category imbalance of the dataset, label smoothing was applied in model training to reduce the model’s overconfidence in majority class samples while improving the model’s generalization ability. The detection performance of the improved FA-MobileUNet model reached 84.55% mIoU (mean Intersection over Union), which was 17.15% higher than that of the original U-Net model. The improved FA-MobileUNet model was then examined by some oil pollution incidents. According to the detection results, if the oil spill was suspected to be caused by a ship, the corresponding Automatic Identification System (AIS) data were collected based on the acquisition time and geo-location of the SAR image to search for the ship suspected of causing oil pollution. Finally, some oil pollution incidents in Taiwan marine area were collected to verify the effectiveness of the proposed model for marine oil pollution monitoring. Experimental results showed that the extent of the detected oil spill was consistent with the oil pollution area recorded in the incident reports.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
