Paper Info
Title
Information-theoretic heterogeneity measurement for SAR imagery
Abstract
A heterogeneity feature, calculable from synthetic aperture radar (SAR) images on a per-pixel basis, but relying on global image statistics, is defined and discussed. Starting from the multiplicative speckle and texture models relating the amount of texture and speckle to the local mean and variance at every pixel, such a feature is rigorously derived from Shannon's information theory as the conditional information of local standard deviation to local mean. Thanks to robust statistical estimation, it is very little sensitive to the noise affecting SAR data, and thus capable of capturing subtle variations of texture whenever they are embedded in a heavy speckle. Experimental results carried out on two SAR images with different degrees of noisiness demonstrate that the proposed feature is likely to be useful for a variety of automated segmentation and classification tasks.
Year
DOI
Venue
2005
10.1109/TGRS.2004.837328
Geoscience and Remote Sensing, IEEE Transactions
Keywords
Field
DocType
geophysical signal processing,image classification,image segmentation,image texture,radar imaging,remote sensing by radar,speckle,synthetic aperture radar,terrain mapping,vegetation mapping,global image statistics,image classification,image segmentation,information theory,information-theoretic signal processing,land cover classification,multiplicative speckle model,multivariate analysis,statistical estimation,synthetic aperture radar imagery,textural features,variation coefficient
Information theory,Computer vision,Radar imaging,Speckle pattern,Synthetic aperture radar,Image texture,Remote sensing,Image segmentation,Artificial intelligence,Contextual image classification,Standard deviation,Mathematics
Journal
Volume
Issue
ISSN
43
3
0196-2892
Citations 
PageRank 
References 
15
0.98
7
Authors
3
Name
Order
Citations
PageRank
B. Aiazzi152849.43
Luciano Alparone290180.27
Stefano Baronti355950.87