Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD

A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them a p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thomas Hänel, Thomas Jarmer, Nils Aschenbruck
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	compressed sensing multispectral imaging precision agriculture wireless sensor networks Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/b283b747ac1d4a198fde12ac970048a5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b283b747ac1d4a198fde12ac970048a5
record_format	dspace
spelling	oai:doaj.org-article:b283b747ac1d4a198fde12ac970048a52021-11-11T19:14:57ZLearning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD10.3390/s212172961424-8220https://doaj.org/article/b283b747ac1d4a198fde12ac970048a52021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7296https://doaj.org/toc/1424-8220A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them a promising solution for the calibration of satellite data. In this paper, we explore an alternative approach for processing data from such a network. Hyperspectral sensors were found to be too complex for such a network. While previous work considered fusing the data from different multispectral sensors in order to derive hyperspectral data, we shift the assessment of the hyperspectral modeling in a separate preprocessing step based on machine learning. We then use the learned data as additional input while using identical multispectral sensors, further reducing the complexity of the sensors. Despite requiring careful parametrization, the approach delivers hyperspectral data of similar and in some cases even better quality.Thomas HänelThomas JarmerNils AschenbruckMDPI AGarticlecompressed sensingmultispectral imagingprecision agriculturewireless sensor networksChemical technologyTP1-1185ENSensors, Vol 21, Iss 7296, p 7296 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	compressed sensing multispectral imaging precision agriculture wireless sensor networks Chemical technology TP1-1185
spellingShingle	compressed sensing multispectral imaging precision agriculture wireless sensor networks Chemical technology TP1-1185 Thomas Hänel Thomas Jarmer Nils Aschenbruck Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
description	A promising low-cost solution for monitoring spectral information, e.g., on agricultural fields, is that of wireless sensor networks. In contrast to remote sensing, these can achieve more continuous monitoring due to their long-term deployment and are less impacted by the atmosphere, making them a promising solution for the calibration of satellite data. In this paper, we explore an alternative approach for processing data from such a network. Hyperspectral sensors were found to be too complex for such a network. While previous work considered fusing the data from different multispectral sensors in order to derive hyperspectral data, we shift the assessment of the hyperspectral modeling in a separate preprocessing step based on machine learning. We then use the learned data as additional input while using identical multispectral sensors, further reducing the complexity of the sensors. Despite requiring careful parametrization, the approach delivers hyperspectral data of similar and in some cases even better quality.
format	article
author	Thomas Hänel Thomas Jarmer Nils Aschenbruck
author_facet	Thomas Hänel Thomas Jarmer Nils Aschenbruck
author_sort	Thomas Hänel
title	Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
title_short	Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
title_full	Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
title_fullStr	Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
title_full_unstemmed	Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD
title_sort	learning a transform base for the multi- to hyperspectral sensor network with k-svd
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b283b747ac1d4a198fde12ac970048a5
work_keys_str_mv	AT thomashanel learningatransformbaseforthemultitohyperspectralsensornetworkwithksvd AT thomasjarmer learningatransformbaseforthemultitohyperspectralsensornetworkwithksvd AT nilsaschenbruck learningatransformbaseforthemultitohyperspectralsensornetworkwithksvd
_version_	1718431605535539200

Learning a Transform Base for the Multi- to Hyperspectral Sensor Network with K-SVD

Ejemplares similares