Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/55448
Title: Supervised classification of fully PolSAR images using active contour models
Authors: Santana Cedres, Daniel Elias 
Gómez Déniz, Luis 
Trujillo Pino, Agustín Rafael 
Alemán Flores, Miguel 
Deriche, Rachid
Alvarez, Luis 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
120601 Construcción de algoritmos
120602 Ecuaciones diferenciales
120326 Simulación
Keywords: Active contours
Classification
Polarimetric synthetic aperture radar (PolSAR) snakes
Statistical learning
Issue Date: 2019
Journal: IEEE Geoscience and Remote Sensing Letters 
Abstract: In this letter, we propose a supervised method for the classification of fully polarimetric synthetic aperture radar (PolSAR) images based on active contour models. We use an ``a priori'' estimation, obtained from training data, of the complex Wishart distributions of the different types of regions in the image (for instance, water, crops, grass, forest or urban). The information of the Wishart distributions is included in the active contour models to guide the level set evolution. We study the case of two classes and the case of three or more classes separately. We present some experimental results on the synthetic data and real PolSAR images to show the performance of the proposed model. The results are compared with other well-known supervised classification methods, and, for actual PolSAR data, our method shows an overall precision of 94.31% and a κ coefficient of 0.937.
URI: http://hdl.handle.net/10553/55448
ISSN: 1545-598X
DOI: 10.1109/LGRS.2019.2892524
Source: IEEE Geoscience and Remote Sensing Letters [ISSN 1545-598X], v. 16(7), p. 1165-1169
Appears in Collections:Artículos
Show full item record

SCOPUSTM   
Citations

3
checked on Aug 7, 2022

WEB OF SCIENCETM
Citations

3
checked on Aug 7, 2022

Page view(s)

108
checked on Jun 19, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.