Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization

Visualization of multispectral images through band selection methods determines an information loss that in utmost cases proves to be critical for the adequate understanding of the represented scene. The R–G–B representation obtained by mapping the visual bands to the R, G, and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Iulia Coca Neagoe, Mihai Coca, Corina Vaduva, Mihai Datcu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Autoencoder data visualization multispectral Earth Observation (EO) images remote sensing Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/010b3aa3f8bd419f8f0fd7f52a99321b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:010b3aa3f8bd419f8f0fd7f52a99321b
record_format	dspace
spelling	oai:doaj.org-article:010b3aa3f8bd419f8f0fd7f52a99321b2021-11-17T00:00:09ZCross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization2151-153510.1109/JSTARS.2021.3123120https://doaj.org/article/010b3aa3f8bd419f8f0fd7f52a99321b2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9591292/https://doaj.org/toc/2151-1535Visualization of multispectral images through band selection methods determines an information loss that in utmost cases proves to be critical for the adequate understanding of the represented scene. The R–G–B representation obtained by mapping the visual bands to the R, G, and B channels is highly used due to its great resemblance with the natural color one and aspects perceivable by the human eye. However, despite the similarity in terms of color code, ambiguities between classes such as water and vegetation or atmospheric phenomena like fog, clouds, and smoke that have been penetrated by other bands, remain visible and hinder the process of visualization of the Earth surface. This article presents a set of five different methods to offset the effects caused by ambiguities, fog, light clouds, and smoke by transferring relevant information between bands in order to visually reconstitute those parts of the image affected by atmospheric phenomena. The general concept shared by these methods implies a stacked autoencoder that successfully encompasses the information from all spectral bands into a latent representation used for visualization. Each proposed method is defined by different combination of input and error function formula. Spectral and polar coordinates features represent the possible options for the input, while formulas based on mean squared error or angular spectral distances determine the potential choices in terms of error function definition. The property of angular spectral distance and polar coordinates transformation to obtain illuminant invariant features determined their use in three out of five methods. We evaluate the methods through spectral signature graphical comparison and visual comparison related to the R–G–B representation. We conduct experiments on multiple Sentinel 2 full images.Iulia Coca NeagoeMihai CocaCorina VaduvaMihai DatcuIEEEarticleAutoencoderdata visualizationmultispectral Earth Observation (EO) imagesremote sensingOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 11297-11310 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Autoencoder data visualization multispectral Earth Observation (EO) images remote sensing Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Autoencoder data visualization multispectral Earth Observation (EO) images remote sensing Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Iulia Coca Neagoe Mihai Coca Corina Vaduva Mihai Datcu Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
description	Visualization of multispectral images through band selection methods determines an information loss that in utmost cases proves to be critical for the adequate understanding of the represented scene. The R–G–B representation obtained by mapping the visual bands to the R, G, and B channels is highly used due to its great resemblance with the natural color one and aspects perceivable by the human eye. However, despite the similarity in terms of color code, ambiguities between classes such as water and vegetation or atmospheric phenomena like fog, clouds, and smoke that have been penetrated by other bands, remain visible and hinder the process of visualization of the Earth surface. This article presents a set of five different methods to offset the effects caused by ambiguities, fog, light clouds, and smoke by transferring relevant information between bands in order to visually reconstitute those parts of the image affected by atmospheric phenomena. The general concept shared by these methods implies a stacked autoencoder that successfully encompasses the information from all spectral bands into a latent representation used for visualization. Each proposed method is defined by different combination of input and error function formula. Spectral and polar coordinates features represent the possible options for the input, while formulas based on mean squared error or angular spectral distances determine the potential choices in terms of error function definition. The property of angular spectral distance and polar coordinates transformation to obtain illuminant invariant features determined their use in three out of five methods. We evaluate the methods through spectral signature graphical comparison and visual comparison related to the R–G–B representation. We conduct experiments on multiple Sentinel 2 full images.
format	article
author	Iulia Coca Neagoe Mihai Coca Corina Vaduva Mihai Datcu
author_facet	Iulia Coca Neagoe Mihai Coca Corina Vaduva Mihai Datcu
author_sort	Iulia Coca Neagoe
title	Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
title_short	Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
title_full	Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
title_fullStr	Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
title_full_unstemmed	Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization
title_sort	cross-bands information transfer to offset ambiguities and atmospheric phenomena for multispectral data visualization
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/010b3aa3f8bd419f8f0fd7f52a99321b
work_keys_str_mv	AT iuliacocaneagoe crossbandsinformationtransfertooffsetambiguitiesandatmosphericphenomenaformultispectraldatavisualization AT mihaicoca crossbandsinformationtransfertooffsetambiguitiesandatmosphericphenomenaformultispectraldatavisualization AT corinavaduva crossbandsinformationtransfertooffsetambiguitiesandatmosphericphenomenaformultispectraldatavisualization AT mihaidatcu crossbandsinformationtransfertooffsetambiguitiesandatmosphericphenomenaformultispectraldatavisualization
_version_	1718426027423694848

Cross-Bands Information Transfer to Offset Ambiguities and Atmospheric Phenomena for Multispectral Data Visualization

Ejemplares similares