Automatic detection of oil spills from SAR images

A probabilistic method has been developed that distinguishes oil spills from other similar sea surface features in synthetic aperture radar (SAR) images. It considers both the radiometric and the geometric characteristics of the areas being tested. In order to minimize the operator intervention, it adopts automatic selection criteria to extract the potentially polluted areas from the images. The method has an a priori percentage of correct classification higher than 90% on the training dataset; the performance is confirmed on a different dataset of verified slicks. Some analyses have been conducted using images with different radiometric and geometric resolutions to test its suitability with SAR images different from European Remote Sensing (ERS) satellite ones. The system and its ability to detect and classify oil and non‐oil surface features are described. Starting from a set of verified oil spills detected offshore and over the coastline, the ability of SAR to reveal oil spills is tested by analysing wind intensity, deduced from the image itself, and the distance from the coast.

[1]  P. Lombardini,et al.  Damping effect of monolayers on surface wave motion in a liquid , 1978 .

[2]  F. Sabins.  Remote Sensing: Principles and Interpretation , 1987 .

[3]  Heinrich Hühnerfuss,et al.  Attenuation of wind waves by artificial surface films of different chemical structure , 1981 .

[4]  Renato Cini,et al.  Experimental evidence of a maximum in the frequency domain of the ratio of ripple attenuation in monolayered water to that in pure water , 1981 .

[5]  P. Lombardini,et al.  The Marangoni wave in ripples on an air-water interface covered by a spreading film , 1982 .

[6]  Heinrich Hühnerfuss,et al.  Remote sensing of marine slicks utilizing their influence on wave spectra , 1983 .

[7]  P. Trivero,et al.  Measurements of the damping effect of a spreading film on wind-excited sea ripples using a two-frequency radar , 1985 .

[8]  G. J. St-Cyr,et al.  A radar ocean imaging model for small to moderate incidence angles , 1986 .

[9]  S. G. Salashin,et al.  Surface film effect on short wind waves , 1986 .

[10]  Claudia Manfredi,et al.  Ripples damping due to monomolecular films , 1987 .

[11]  Heinrich Hühnerfuss,et al.  Radar signatures of oil films floating on the sea surface and the Marangoni effect , 1988 .

[12]  P. Trivero,et al.  Modulation of the Spectra of Short Gravity Waves by Sea Surface Films: Slick Detection and Characterization with a Microwave Probe , 1989 .

[13]  R. Reuter,et al.  Lidar fluorosensing of mineral oil spills on the sea surface. , 1990, Applied optics.

[14]  Keinosuke Fukunaga,et al.  Introduction to statistical pattern recognition (2nd ed.) , 1990 .

[15]  K. Fukunaga.  Chapter 11 – CLUSTERING , 1990 .

[16]  W. Alpers,et al.  The Damping Of Ocean Surface Waves By Monomolecular Sea Slicks Measured By Airborne Multi-frequency Radars During The Saxon-fpn experiment , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[17]  Ian S. F. Jones,et al.  Satellite remote sensing of the oceanic environment , 1993 .

[18]  P. Trivero,et al.  Ocean surface films measured by interferential microwave probe , 1995 .

[19]  Jochen Horstmann,et al.  Wind measurements using ERS-1 SAR , 1995 .

[20]  Henri Laur,et al.  Derivation of the backscattering coefficient s0 in ESA ERS SAR PRI products , 1996 .

[21]  H. A. Espedal,et al.  Operational use of wind data for slick detection , 1997 .

[22]  P. Trivero,et al.  SAR detection and characterization of sea surface slicks , 1998 .

[23]  Fabio Del Frate,et al.  Neural networks for oil spill detection using ERS-SAR data , 2000, IEEE Trans. Geosci. Remote. Sens..

[24]  A. Palucci,et al.  LASER SPECTROSCOPY OF MINERAL OILS ON THE WATER SURFACE , 2000 .

[25]  B. Fiscella,et al.  Oil spill detection using marine SAR images , 2000 .

[26]  P. Trivero,et al.  Sea surface slicks measured by SAR , 2001 .

[27]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .