Contextual PolSAR image classification using fractal dimension and support vector machines

In this paper, a new classification scheme of polarimetric synthetic aperture radar (PolSAR) images using fractal dimension as contextual information is proposed. Support vector machines (SVM) due to their ability to handle the nonlinear classifier problem are applied to a new fractal feature vector...

Full description

Saved in:
Bibliographic Details
Published in:European journal of remote sensing 2013-01, Vol.46 (1), p.317-332
Main Authors: Aghababaee, Hossein, Amini, Jalal, Tzeng, Yu-Chang
Format: Article
Language:English
Subjects:
Brownian motion
Classification
Decomposition
fractal dimension
Fractal geometry
Fractals
Fuzzy logic
Image classification
PolSAR image
Radar imaging
Radar polarimetry
Support vector machines
Synthetic aperture radar
Wavelet analysis
wavelet multi-resolution
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a new classification scheme of polarimetric synthetic aperture radar (PolSAR) images using fractal dimension as contextual information is proposed. Support vector machines (SVM) due to their ability to handle the nonlinear classifier problem are applied to a new fractal feature vector, which is constructed from Pauli decomposed vector and fractal dimensions. Fractal dimension is computed based on the concepts of fractional Brownian motion (fBm) and wavelet multi-resolution analysis using a self-adaptive window approach and fuzzy logic. The experimental results on AIRSAR images prove effectiveness of the proposed vector in comparison to the Pauli decomposed vector.
ISSN:2279-7254
2279-7254
DOI:10.5721/EuJRS20134618