A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization

When dealing with multivariate remotely sensed records collected by multiple sensors, an accurate selection of information at the data, feature, or decision level is instrumental in improving the scenes’ characterization. This will also enhance the system’s efficiency and provi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Eduard Khachatrian, Saloua Chlaily, Torbjorn Eltoft, Andrea Marinoni
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Gaussian kernel (GK) graph Laplacians multimodal remote sensing mutual information (MI) unsupervised information selection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/bfd7abd088b9463b9a186e91f96fc3e1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bfd7abd088b9463b9a186e91f96fc3e1
record_format	dspace
spelling	oai:doaj.org-article:bfd7abd088b9463b9a186e91f96fc3e12021-11-23T00:00:37ZA Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization2151-153510.1109/JSTARS.2021.3124308https://doaj.org/article/bfd7abd088b9463b9a186e91f96fc3e12021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9599440/https://doaj.org/toc/2151-1535When dealing with multivariate remotely sensed records collected by multiple sensors, an accurate selection of information at the data, feature, or decision level is instrumental in improving the scenes’ characterization. This will also enhance the system’s efficiency and provide more details on modeling the physical phenomena occurring on the Earth’s surface. In this article, we introduce a flexible and efficient method based on graph Laplacians for information selection at different levels of data fusion. The proposed approach combines data structure and information content to address the limitations of existing graph-Laplacian-based methods in dealing with heterogeneous datasets. Moreover, it adapts the selection to each homogenous area of the considered images according to their underlying properties. Experimental tests carried out on several multivariate remote sensing datasets show the consistency of the proposed approach.Eduard KhachatrianSaloua ChlailyTorbjorn EltoftAndrea MarinoniIEEEarticleGaussian kernel (GK)graph Laplaciansmultimodal remote sensingmutual information (MI)unsupervised information selectionOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11546-11566 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Gaussian kernel (GK) graph Laplacians multimodal remote sensing mutual information (MI) unsupervised information selection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Gaussian kernel (GK) graph Laplacians multimodal remote sensing mutual information (MI) unsupervised information selection Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Eduard Khachatrian Saloua Chlaily Torbjorn Eltoft Andrea Marinoni A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
description	When dealing with multivariate remotely sensed records collected by multiple sensors, an accurate selection of information at the data, feature, or decision level is instrumental in improving the scenes’ characterization. This will also enhance the system’s efficiency and provide more details on modeling the physical phenomena occurring on the Earth’s surface. In this article, we introduce a flexible and efficient method based on graph Laplacians for information selection at different levels of data fusion. The proposed approach combines data structure and information content to address the limitations of existing graph-Laplacian-based methods in dealing with heterogeneous datasets. Moreover, it adapts the selection to each homogenous area of the considered images according to their underlying properties. Experimental tests carried out on several multivariate remote sensing datasets show the consistency of the proposed approach.
format	article
author	Eduard Khachatrian Saloua Chlaily Torbjorn Eltoft Andrea Marinoni
author_facet	Eduard Khachatrian Saloua Chlaily Torbjorn Eltoft Andrea Marinoni
author_sort	Eduard Khachatrian
title	A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
title_short	A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
title_full	A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
title_fullStr	A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
title_full_unstemmed	A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization
title_sort	multimodal feature selection method for remote sensing data analysis based on double graph laplacian diagonalization
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/bfd7abd088b9463b9a186e91f96fc3e1
work_keys_str_mv	AT eduardkhachatrian amultimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT salouachlaily amultimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT torbjorneltoft amultimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT andreamarinoni amultimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT eduardkhachatrian multimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT salouachlaily multimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT torbjorneltoft multimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization AT andreamarinoni multimodalfeatureselectionmethodforremotesensingdataanalysisbasedondoublegraphlaplaciandiagonalization
_version_	1718417399927013376

A Multimodal Feature Selection Method for Remote Sensing Data Analysis Based on Double Graph Laplacian Diagonalization

Ejemplares similares