Title :
Synthetic aperture Radar oil spill segmentation by stochastic complexity minimization
Author :
Galland, Frédéric ; Réfrégier, Philippe ; Germain, Olivier
Author_Institution :
Phys. & Image Process. Group, Domaine Univ. de St.-Jerome, Marseille, France
Abstract :
We present a new algorithm for oil spill segmentation in synthetic aperture radar (SAR) images, using the minimum description length (MDL) principle and a polygonal active grid. This algorithm is based on two steps: a first partitioning step into homogeneous regions and a second classification step with an automatic MDL thresholding. The obtained method allows one to segment the different candidate oil spills in an image automatically and in a few seconds.
Keywords :
geophysical signal processing; image segmentation; radar imaging; synthetic aperture radar; SAR images; automatic MDL thresholding; first partitioning step; homogeneous regions; minimum description length principle; oil spill segmentation; polygonal active grid; second classification step; stochastic complexity minimization; synthetic aperture radar; Active contours; Data mining; Hazards; Image segmentation; Minimization methods; Oil pollution; Partitioning algorithms; Petroleum; Stochastic processes; Synthetic aperture radar; MDL; Minimum description length; SAR; oil spill segmentation; polygonal active grid; synthetic aperture radar;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2004.835346
