A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing
Open Access
- 9 May 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (10) , 1684
Abstract
The efficient and timely identification of oil spill areas is crucial for ocean environmental protection. Synthetic aperture radar (SAR) is widely used in oil spill detection due to its all-weather monitoring capability. Meanwhile, existing deep learning-based oil spill detection methods mainly rely on the classical U-Net framework and have achieved impressive results. However, SAR images exhibit high noise, blurry boundaries, and irregular shapes of target areas, as well as speckles and shadows, which lead to the loss of performance in existing algorithms. In this paper, we propose a novel network architecture to achieve more precise segmentation of oil spill areas by reintroducing rich semantic contextual information before obtaining the final segmentation mask. Specifically, the proposed architecture can re-fuse feature maps from different levels at the decoder end. We design a multi-convolutional layer (MCL) module to extract basic feature information from SAR images, and a feature extraction module (FEM) module further extracts and fuses feature maps generated by the U-Net decoder at different levels. Through these operations, the network can learn rich global and local contextual information, enable sufficient interaction of feature information at different stages, enhance the model’s contextual awareness, and improve its ability to recognize complex textures and blurry boundaries, thereby enhancing the segmentation accuracy of SAR images. Compared to many U-Net based segmentation networks, our method shows promising results and achieves state-of-the-art performance on multiple evaluation metrics.Keywords
Funding Information
- a Major Scientific and Technological Innovation Project of Shandong Province of China (2021ZLGX05, 2020CXGC010705, 62301174, 2024A04J2081)
- National Natural Science Foundation of China (2021ZLGX05, 2020CXGC010705, 62301174, 2024A04J2081)
- Guangzhou Basic and Applied Basic Research Topic (Young Doctor “Sailing” Project) (2021ZLGX05, 2020CXGC010705, 62301174, 2024A04J2081)
This publication has 48 references indexed in Scilit:
- Absorbed dose rate for marine biota due to the oil spilled using ICRP reference animal and Monte Carlo simulationApplied Radiation and Isotopes, 2022
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- On the use of feature selection to improve the detection of sea oil spills in SAR imagesComputers & Geosciences, 2017
- An oceanographic survey for oil spill monitoring and model forecasting validation using remote sensing and in situ data in the Mediterranean SeaDeep Sea Research Part II: Topical Studies in Oceanography, 2016
- Optimum Features Selection for oil Spill Detection in SAR ImageJournal of the Indian Society of Remote Sensing, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Oil Spill Monitoring Based on SAR Remote Sensing ImageryAquatic Procedia, 2015
- A cloud-integrated web platform for marine monitoring using GIS and remote sensing. Application to oil spill detection through SAR imagesFuture Generation Computer Systems, 2014
- Oil spill feature selection and classification using decision tree forest on SAR image dataISPRS Journal of Photogrammetry and Remote Sensing, 2012
- Study on the hyperspectral polarized reflection characteristics of oil slicks on sea surfacesChinese Science Bulletin, 2011