3 October 2017 Vessel and oil spill early detection using COSMO satellite imagery
Author Affiliations +
Abstract
Oil spillage is one of the most common sources of environmental damage in places where coastal wild life is found in natural reservoirs. This is especially the case in the Patagonian coast, with a littoral more than 5000 km long and a surface above a million and half square km. In addition, furtive fishery activities in Argentine waters are depleting the food supplies of several species, altering the ecological equilibrium. For this reason, early oil spills and vessel detection is an imperative surveillance task for environmental and governmental authorities. However, given the huge geographical extension, human assisted monitoring is unfeasible, and therefore real time remote sensing technologies are the only operative and economically feasible solution. In this work we describe the theoretical foundations and implementation details of a system specifically designed to take advantage of the SAR imagery delivered by two satellite constellations (the SAOCOM mission, developed by the Argentine Space Agency, and the COSMO mission, developed by the Italian Space Agency), to provide real-time detection of vessels and oil spills. The core of the system is based on pattern recognition over a statistical characterization of the texture patterns arising in the positive and negative conditions (i.e., vessel, oil, or plain sea surfaces). Training patterns were collected from a large number of previously reported contacts tagged by experts in the National Commission on Space Activities (CONAE). The resulting system performs well above the sensitivity and specificity of other avalilable systems.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Natalia V. Revollo, Claudio A. Delrieux, "Vessel and oil spill early detection using COSMO satellite imagery", Proc. SPIE 10422, Remote Sensing of the Ocean, Sea Ice, Coastal Waters, and Large Water Regions 2017, 1042203 (3 October 2017); doi: 10.1117/12.2279545; https://doi.org/10.1117/12.2279545
PROCEEDINGS
9 PAGES


SHARE
Back to Top