Title
Characterization of local regularity in SAR Imagery by means of multiscale techniques: application to oil spill detection
Abstract
Thanks to their capability to cover large areas, in all weather conditions, during the day as well as during the night, spaceborne Synthetic Aperture Radar (SAR) techniques constitute an extremely promising alternative to traditional surveillance methods. Nevertheless, in order to assure further usability of SAR images, specific data mining tools are still to be developed to provide an efficient automatic interpretation of SAR data. The aim of this paper is to introduce texture analysis performed in the framework of time - frequency theory, as a means to detect oil spills in the sea surface. In particular, an algorithm permitting a precise quantitative characterization of the border between the oil spill candidate and the sea, will allow a novel classification of oil spills and look-alikes.
Year
DOI
Venue
2007
10.1109/IGARSS.2007.4424040
Barcelona
Keywords
Field
DocType
data mining,image texture,remote sensing by radar,spaceborne radar,synthetic aperture radar,SAR imagery,data interpretation,data mining,local regularity,oil spill detection,spaceborne synthetic aperture radar,texture analysis,Hölder exponent,multiresolution analysis,wavelet transform
Spaceborne radar,Computer vision,Oil spill,Holder exponent,Synthetic aperture radar,Image texture,Computer science,Usability,Remote sensing,Multiresolution analysis,Artificial intelligence,Wavelet transform
Conference
ISBN
Citations 
PageRank 
978-1-4244-1212-9
0
0.34
References 
Authors
1
4
Name
Order
Citations
PageRank
Tello, M.100.34
Lopez-Martinez, C.252.86
Jordi Mallorquí314217.69
Danisi, A.400.34