Fisher Vectors for PolSAR Image Classification

Mostrar todas las versiones(2)

In this letter, we study the application of the Fisher vector (FV) to the problem of pixelwise supervised classification of polarimetric synthetic aperture radar images. This is a challenging problem since information in those images is encoded as complex-valued covariance matrices. We observe that...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Redolfi, Javier, Sánchez, Jorge, Flesia, Ana Georgina
Formato: Documento de conferencia publishedVersion
Lenguaje:Inglés
Publicado: SADIO 2019
Materias:
Fisher vectors
image classification
polarimetric synthetic aperture radar
Acceso en línea:http://hdl.handle.net/20.500.12272/3889
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-3889
record_format dspace
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
topic Fisher vectors
image classification
polarimetric synthetic aperture radar
spellingShingle Fisher vectors
image classification
polarimetric synthetic aperture radar
Redolfi, Javier
Sánchez, Jorge
Flesia, Ana Georgina
Fisher Vectors for PolSAR Image Classification
topic_facet Fisher vectors
image classification
polarimetric synthetic aperture radar
description In this letter, we study the application of the Fisher vector (FV) to the problem of pixelwise supervised classification of polarimetric synthetic aperture radar images. This is a challenging problem since information in those images is encoded as complex-valued covariance matrices. We observe that the real parts of these matrices preserve the positive semidefiniteness property of their complex counterpart. Based on this observation, we derive an FV from a mixture of real Wishart densities and integrate it with a Potts-like energy model in order to capture spatial dependencies between neighboring regions. Experimental results on two challenging data sets show the effectiveness of the approach.
format Documento de conferencia
publishedVersion
Documento de conferencia
author Redolfi, Javier
Sánchez, Jorge
Flesia, Ana Georgina
author_facet Redolfi, Javier
Sánchez, Jorge
Flesia, Ana Georgina
author_sort Redolfi, Javier
title Fisher Vectors for PolSAR Image Classification
title_short Fisher Vectors for PolSAR Image Classification
title_full Fisher Vectors for PolSAR Image Classification
title_fullStr Fisher Vectors for PolSAR Image Classification
title_full_unstemmed Fisher Vectors for PolSAR Image Classification
title_sort fisher vectors for polsar image classification
publisher SADIO
publishDate 2019
url http://hdl.handle.net/20.500.12272/3889
work_keys_str_mv AT redolfijavier fishervectorsforpolsarimageclassification
AT sanchezjorge fishervectorsforpolsarimageclassification
AT flesiaanageorgina fishervectorsforpolsarimageclassification
bdutipo_str Repositorios
_version_ 1764820552391852033

Ejemplares similares