|
MUM (Merge Using Moments) Segmentation for SAR Images
Presented at EUROPTO (Rome, Italy) 1994.
Cite this paper as:
Rod Cook, Ian McConnell, Chris Oliver and Edward Welbourne,
`MUM (Merge Using Moments) segmentation for SAR images',
in SAR Data Processing for Remote Sensing,
edited by G. Franceschetti,
Proc. SPIE 2316 (1994) pp92-103.
Abstract
In Synthetic Aperture Radar (SAR) and other systems employing coherent
illumination to form high-resolution images, the resulting image is generally
corrupted by a form of multiplicative noise, known as coherent speckle,
with a signal-to-noise ratio of unity.
This severe form of noise presents singular problems for image processing
software of all kinds.
This paper describes a segmentation scheme, Merge Using Moments (MUM), for
images corrupted by coherent speckle.
The image is initially massively over-segmented.
A scheme based on examination of the statistical properties of
adjoining regions is employed to improve an over-fine segmentation by merging
regions to produce a coarser segmentation.
This scheme is employed iteratively until no remaining merge appears valid,
at which time a good segmentation is obtained.
The results of using it on typical SAR images illustrate its potential.
|
|
|
