Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection

Compressive sensing (CS) has received considerable interest in hyperspectral sensing. Recent articles have also exploited the benefits of CS in hyperspectral image classification (HSIC) in the compressively sensed band domain (CSBD). However, on many occasions, the requirement of full bands is not n...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	C. J. Della Porta, Chein-I Chang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Compressively sensed bands (CSBs) compressively sensed bands domain (CSBD) compressive sensing (CS) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/0300165fe8e54dc8aea522834b537f60
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0300165fe8e54dc8aea522834b537f60
record_format	dspace
spelling	oai:doaj.org-article:0300165fe8e54dc8aea522834b537f602021-12-02T00:00:09ZEstimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection2151-153510.1109/JSTARS.2021.3128288https://doaj.org/article/0300165fe8e54dc8aea522834b537f602021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9616398/https://doaj.org/toc/2151-1535Compressive sensing (CS) has received considerable interest in hyperspectral sensing. Recent articles have also exploited the benefits of CS in hyperspectral image classification (HSIC) in the compressively sensed band domain (CSBD). However, on many occasions, the requirement of full bands is not necessary for HSIC to perform well. So, a great challenge arises in determining the minimum number of compressively sensed bands (CSBs), <italic>n</italic><sub>CSB</sub>, needed to achieve full-band performance. Practically, the value of <italic>n</italic><sub>CSB</sub> varies with the complexity of an imaged scene. Although virtual dimensionality (VD) has been used to estimate the number of bands to be selected, <italic>n</italic><sub>BS</sub>, it is not applicable to CSBD because a CSB is actually a mixture of <italic>n</italic><sub>CSB</sub> bands sensed by a random sensing matrix, while VD is used to estimate <italic>n</italic><sub>BS</sub> which is the number of single bands to be selected. As expected, <italic>n</italic><sub>CSB</sub> will be generally smaller than <italic>n</italic><sub>BS</sub>. To estimate an optimal value of <italic>n</italic><sub>CSB</sub>, two feature selection approaches, filter and wrapper methods, are proposed to extract scene features that can be used to estimate the minimum value of <italic>n</italic><sub>CSB</sub> required to maximize performance with minimum redundancy. Specifically, these methods are fully automated by leveraging optimal partitioning schemes which enable classification to further reduce storage requirements in CSBD. Finally, a set of experiments are conducted using real-world hyperspectral images to demonstrate the viability of the proposed approach.C. J. Della PortaChein-I ChangIEEEarticleCompressively sensed bands (CSBs)compressively sensed bands domain (CSBD)compressive sensing (CS)Ocean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11775-11788 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Compressively sensed bands (CSBs) compressively sensed bands domain (CSBD) compressive sensing (CS) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Compressively sensed bands (CSBs) compressively sensed bands domain (CSBD) compressive sensing (CS) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 C. J. Della Porta Chein-I Chang Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
description	Compressive sensing (CS) has received considerable interest in hyperspectral sensing. Recent articles have also exploited the benefits of CS in hyperspectral image classification (HSIC) in the compressively sensed band domain (CSBD). However, on many occasions, the requirement of full bands is not necessary for HSIC to perform well. So, a great challenge arises in determining the minimum number of compressively sensed bands (CSBs), <italic>n</italic><sub>CSB</sub>, needed to achieve full-band performance. Practically, the value of <italic>n</italic><sub>CSB</sub> varies with the complexity of an imaged scene. Although virtual dimensionality (VD) has been used to estimate the number of bands to be selected, <italic>n</italic><sub>BS</sub>, it is not applicable to CSBD because a CSB is actually a mixture of <italic>n</italic><sub>CSB</sub> bands sensed by a random sensing matrix, while VD is used to estimate <italic>n</italic><sub>BS</sub> which is the number of single bands to be selected. As expected, <italic>n</italic><sub>CSB</sub> will be generally smaller than <italic>n</italic><sub>BS</sub>. To estimate an optimal value of <italic>n</italic><sub>CSB</sub>, two feature selection approaches, filter and wrapper methods, are proposed to extract scene features that can be used to estimate the minimum value of <italic>n</italic><sub>CSB</sub> required to maximize performance with minimum redundancy. Specifically, these methods are fully automated by leveraging optimal partitioning schemes which enable classification to further reduce storage requirements in CSBD. Finally, a set of experiments are conducted using real-world hyperspectral images to demonstrate the viability of the proposed approach.
format	article
author	C. J. Della Porta Chein-I Chang
author_facet	C. J. Della Porta Chein-I Chang
author_sort	C. J. Della Porta
title	Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
title_short	Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
title_full	Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
title_fullStr	Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
title_full_unstemmed	Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection
title_sort	estimating optimal number of compressively sensed bands for hyperspectral classification via feature selection
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/0300165fe8e54dc8aea522834b537f60
work_keys_str_mv	AT cjdellaporta estimatingoptimalnumberofcompressivelysensedbandsforhyperspectralclassificationviafeatureselection AT cheinichang estimatingoptimalnumberofcompressivelysensedbandsforhyperspectralclassificationviafeatureselection
_version_	1718403962799915008

Estimating Optimal Number of Compressively Sensed Bands for Hyperspectral Classification via Feature Selection

Ejemplares similares