Supervised Pattern Classification Techniques for Oil Spill Classification in SAR Images: Preliminary Results
Andrea Montali(1) , Giorgio Giacinto(1) , Maurizio Migliaccio(2) , and Attilio Gambardella(1)
Università degli Studi di Cagliari,
Piazza D’Armi, 19,
(2) Università degli Studi di Napoli Parthenope, Via Acton, 38, 80133 Napoli, Italy
Oil spill detection by means of SAR images is possible because of the damping effect of the short wind waves caused by the presence of oil on the sea surface. As a consequence, an oil spill is physically a dark patch in SAR images. Unfortunately, several natural and atmospheric phenomena produce dark areas in SAR images, i.e. look-alikes, which make the detection of oil spills a challenging task.
It is easy to see that oil spill detection over SAR images not only requires the detection of dark patches in the image, but also requires post-processing techniques aimed at discriminating oil spills from look-alikes. Oil spill detection is thus usually framed into three fundamental phases: dark patch detection, features extraction, and oil spill/look-alike classification. Features to discriminate among oil spills and look-alikes are typically based on geometrical properties, as well as on radiometric measures and textures.
The accuracies reported in the literature for oil-spill detection techniques range from 82% to 94% of correct classification of oil-spills. These results are related to different data sets, different segmentation approaches to detect dark patches, and different feature extraction processes. On the other hand, all the studies reported in the literature are based on a classical two-class classification methodology, where examples of the two classes, i.e. oil-spills and look-alikes, must be provided to train the classification model.
The main contribution of this study is twofold: i) classical features have been examined/evaluated and ranked in function of their effectiveness; ii) the classification of dark patches has been performed using a two-class approach as well as a one-class approach. One-class approaches produce a model for the class for which reliable examples can be provided, e.g. the oil-spill class. A dark patch is classified as an oil-spill if it fits the model, otherwise it is classified as a look-alike.
In order to compare the performances of two-class classifiers and one-class classifiers, several experiments have been carried out by varying the number of training objects and the number of features.
A number of one-class and two-class classification techniques have been used: Linear discriminants, 1-Nearest Neighbour, Mixture of Gaussians, Parzen Windows and the Support Vector Machines.
The training dataset has been extracted from a set of SAR images acquired by an airborne X band SAR system mounted on board of a Laerjet 35A, during the Galitia Mission in January-February 2003 (TELAER Consortium), after the sinking of the Prestige oil tanker.
Preliminary results show that the best classification performance is always achieved by one-class classification techniques. In particular, once fixed at 2% the maximum acceptable oil-spill misclassification error, the error rate on the look-alike class was evaluated. One-class classifiers allowed attaining 1% of look-alikes incorrectly classified as oil-spills, whereas two-class classifiers attained a 3% error.
As far as the feature selection process is concerned, all the features typically used in the literature have been ranked according to their effectiveness. Results show that the highest accuracies can be attained by using either the first four or the first eight features. These features include the contrast between the background and the dark patch, the (GLCM) contrast, the outside dark patch standard deviation (as the dark patch in the image depends also on the wind speed), the inside dark patch radar backscattering, etc.