Oil spills detection: Challenges addressed in the scope of the SEAGULL project

Abstract

The development of intelligent systems to support maritime situation awareness is the main goal of the SEAGULL project. By equipping unmanned aerial vehicles (UAVs) with different types of optical sensors we target an intelligent maritime surveillance system. In this paper we present experiments performed with an hyperspectral camera to detect oil spills. We have developed a detection algorithm that automatically informs the base station of an oil spill in case a spectral signature recognized as oil is found on open sea. This contributes significantly to the generation of situational awareness of maritime events such as detection and georeferencing of oil spills or hazardous and noxious substances. After a brief overview of the SEAGULL platform and architecture, we focus on presenting the algorithms for automatic detection of oil spills with a hyperspectral camera on board an UAV.