Texture descriptors for robust SAR image segmentation

Mostrar todas las versiones(2)

"SAR (synthetic aperture radar) and PolSAR (polarimetric synthetic aperture radar) images fulfill a fundamental role in Earth observation, due to their advantages over optical images. However, the presence of speckle noise hinders their automatic interpretation and unsupervised use, rendering t...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rey, Andrea, Gambini, Juliana, Delrieux, Claudio
Formato: Artículo de publicación periódica
Lenguaje:Inglés
Publicado: 2022
Acceso en línea:https://ri.itba.edu.ar/handle/20.500.14769/3976
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-20.500.14769-3976
record_format dspace
spelling I32-R138-20.500.14769-39762026-01-15T15:29:43Z Texture descriptors for robust SAR image segmentation Rey, Andrea Gambini, Juliana Delrieux, Claudio "SAR (synthetic aperture radar) and PolSAR (polarimetric synthetic aperture radar) images fulfill a fundamental role in Earth observation, due to their advantages over optical images. However, the presence of speckle noise hinders their automatic interpretation and unsupervised use, rendering traditional segmentation tools ineffective. For this reason, advanced image segmentation models are sought to overcome the limitations that make an adequate treat ment of speckled images difficult. We propose a procedure for SAR and PolSAR image clas sification, based on texture descriptors, that combines fractal dimension, a specific probability distribution function, Tsallis entropy, and the entropic index. A vector of local texture features is built using a set of reference regions, then a support vector machine classifier is applied. The proposed algorithm is tested with synthetic and actual monopolarimetric and polarimetric SAR imagery, exhibiting visually remarkable and robust results in coincidence with quantitative qual ity metrics as accuracy and F1-score." 2022-11-08T19:38:16Z 2022-11-08T19:38:16Z 2022-12-28 Artículo de publicación periódica 1931-3195 https://ri.itba.edu.ar/handle/20.500.14769/3976 en info:eu-repo/semantics/reference/doi/10.1117/1.JRS.15.046511 application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Inglés
description "SAR (synthetic aperture radar) and PolSAR (polarimetric synthetic aperture radar) images fulfill a fundamental role in Earth observation, due to their advantages over optical images. However, the presence of speckle noise hinders their automatic interpretation and unsupervised use, rendering traditional segmentation tools ineffective. For this reason, advanced image segmentation models are sought to overcome the limitations that make an adequate treat ment of speckled images difficult. We propose a procedure for SAR and PolSAR image clas sification, based on texture descriptors, that combines fractal dimension, a specific probability distribution function, Tsallis entropy, and the entropic index. A vector of local texture features is built using a set of reference regions, then a support vector machine classifier is applied. The proposed algorithm is tested with synthetic and actual monopolarimetric and polarimetric SAR imagery, exhibiting visually remarkable and robust results in coincidence with quantitative qual ity metrics as accuracy and F1-score."
format Artículo de publicación periódica
author Rey, Andrea
Gambini, Juliana
Delrieux, Claudio
spellingShingle Rey, Andrea
Gambini, Juliana
Delrieux, Claudio
Texture descriptors for robust SAR image segmentation
author_facet Rey, Andrea
Gambini, Juliana
Delrieux, Claudio
author_sort Rey, Andrea
title Texture descriptors for robust SAR image segmentation
title_short Texture descriptors for robust SAR image segmentation
title_full Texture descriptors for robust SAR image segmentation
title_fullStr Texture descriptors for robust SAR image segmentation
title_full_unstemmed Texture descriptors for robust SAR image segmentation
title_sort texture descriptors for robust sar image segmentation
publishDate 2022
url https://ri.itba.edu.ar/handle/20.500.14769/3976
work_keys_str_mv AT reyandrea texturedescriptorsforrobustsarimagesegmentation
AT gambinijuliana texturedescriptorsforrobustsarimagesegmentation
AT delrieuxclaudio texturedescriptorsforrobustsarimagesegmentation
_version_ 1865139244366823424

Ejemplares similares