TY - JOUR
T1 - Automatic detection of oil spills from SAR images
AU - Nirchio, F.
AU - Sorgente, M.
AU - Giancaspro, A.
AU - Biamino, W.
AU - Parisato, E.
AU - Ravera, R.
AU - Trivero, P.
N1 - Funding Information:
This work has been done using the data provided by ESA in the framework of ERS A.O.3. All the data used are ERS data on which there is an ESA copyright. The data processing has been carried out at Italian PAF. Some of the analysis presented in this paper is part of the DISMAR project funded by the EU in the IST programme. We want to thank the Italian Environment Ministry, Department of Marine Resources Protection, for the data provided of the identified oil spills.
PY - 2005/3/20
Y1 - 2005/3/20
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/17144429725
U2 - 10.1080/01431160512331326558
DO - 10.1080/01431160512331326558
M3 - Article
SN - 0143-1161
VL - 26
SP - 1157
EP - 1174
JO - International Journal of Remote Sensing
JF - International Journal of Remote Sensing
IS - 6
ER -