DGNet: Distribution Guided Efficient Learning for Oil Spill Image Segmentation
- 30 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-17
Abstract
Successful implementation of oil spill segmentation in Synthetic Aperture Radar (SAR) images is vital for marine environmental protection. In this paper, we develop an effective segmentation framework named DGNet, which performs oil spill segmentation by incorporating the intrinsic distribution of backscatter values in SAR images. Specifically, our proposed segmentation network is constructed with two deep neural modules running in an interactive manner, where one is the inference module to achieve latent feature variable inference from SAR images, and the other is the generative module to produce oil spill segmentation maps by drawing the latent feature variables as inputs. Thus, to yield accurate segmentation, we take into account the intrinsic distribution of backscatter values in SAR images and embed it in our segmentation model. The intrinsic distribution originates from SAR imagery, describing the physical characteristics of oil spills. In the training process, the formulated intrinsic distribution guides efficient learning of optimal latent feature variable inference for oil spill segmentation. The efficient learning enables the training of our proposed DGNet with a small amount of image data. This is economically beneficial to oil spill segmentation where the availability of oil spill SAR image data is limited in practice. Additionally, benefiting from optimal latent feature variable inference, our proposed DGNet performs accurate oil spill segmentation. We evaluate the segmentation performance of our proposed DGNet with different metrics, and experimental evaluations demonstrate its effective segmentations.Keywords
All Related Versions
Funding Information
- China Scholarship Council (201806450015)
- Ph.D. Studentship from the University of Leicester
This publication has 49 references indexed in Scilit:
- Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentationMagnetic Resonance Imaging, 2014
- A Modified Level Set Approach for Segmentation of Multiband Polarimetric SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2014
- Oil Spill Detection in Hybrid-Polarimetric SAR ImagesIEEE Transactions on Geoscience and Remote Sensing, 2014
- A tutorial on variational Bayesian inferenceArtificial Intelligence Review, 2011
- Dark-spot detection from SAR intensity imagery with spatial density thresholding for oil-spill monitoringRemote Sensing of Environment, 2010
- Active contours driven by local image fitting energyPattern Recognition, 2010
- Impact of oil pollution and increased sea surface temperatures on marine ecosystems and biota in the Gulf2008
- Fish and oil in the Lofoten–Barents Sea system: synoptic review of the effect of oil spills on fish populationsMarine Ecology Progress Series, 2007
- Long-term Environmental Impact of Oil SpillsSpill Science & Technology Bulletin, 2002
- Introduction to Modern Statistical MechanicsPhysics Today, 1988