Ocean Oil Spill Classification with Polarimetric SAR Based on VGG16 Multi-Feature Extraction

Fully polarimetric synthetic aperture radar (PolSAR) technology performs well in oil spill detection because of its rich target scattering information. Aiming at the problem that oil spill detection scheme based on polarization feature and deep learning has large sample requirements and high information redundancy, we propose a classification scheme combining with RBFSVM classifier and VGG16 based on transfer network. The ability of our method to distinguish different oil films is analyzed through a radarsat-2 POLSAR image of the North Sea oil spill experiment.

I. Introduction

Oil leakage events such as oil tanker collisions and drilling platform explosions occur frequently. In order to reduce environmental pollution, effective detection of oil spillages on sea surfaces are of particular importance. Due to the capability of high resolution and wide swath observation, spaceborne SAR plays a critical role in oil spill detection.