Title :
Fast SAR image restoration, segmentation, and detection of high-reflectance regions
Author :
Bratsolis, E. ; Sigelle, M.
Author_Institution :
Dept. Traitement du Signal et des Images, Ecole Nat. Superieure des Telecommun., Paris, France
Abstract :
An iterative filter that can be used for speckle reduction and restoration of synthetic aperture radar (SAR) images is presented here. This method can be considered as a first step in the extraction of other important information. The second step is the detection of high-reflectance regions and continues with the segmentation of the total image. We have worked in three-look simulated and real European Remote Sensing 1 satellite amplitude images. The iterative filter is based on a membrane model Markov random field approximation optimized by a synchronous local iterative method. The final form of restoration gives a total sum-preserving regularization for the pixel values of our image. The high-reflectance regions are defined as the brightest regions of the restored image. After the separation of this extreme class, we give a fast segmentation method using the histogram of the restored image.
Keywords :
Markov processes; digital filters; image restoration; image segmentation; iterative methods; radar detection; radar imaging; spaceborne radar; synthetic aperture radar; fast SAR image restoration; high-reflectance regions; iterative filter; membrane model Markov random field approximation; segmentation; speckle reduction; synchronous local iterative method; synthetic aperture radar images; three-look images; total sum-preserving regularization; Data mining; Filters; Image restoration; Image segmentation; Iterative methods; Radar detection; Remote sensing; Satellites; Speckle; Synthetic aperture radar;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
DOI :
10.1109/TGRS.2003.817222