Hyperspectral Data Dimensionality Reduction: A Comparative Study Between PCA and Autoencoder Methods

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60162694%3AG43__%2F26%3A00563811" target="_blank" >RIV/60162694:G43__/26:00563811 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-71397-2_20" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-71397-2_20</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-71397-2_20" target="_blank" >10.1007/978-3-031-71397-2_20</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Hyperspectral Data Dimensionality Reduction: A Comparative Study Between PCA and Autoencoder Methods

Popis výsledku v původním jazyce

Hyperspectral imaging has emerged as a powerful tool for remote sensing providing detection and identification of objects of interest using their unique spectral signature. Accurate information obtained can reveal details about the physical properties of materials that are relevant to intelligence gathering. Those interesting characteristics coupled with Unmanned Aerial Vehicles (UAVs) offer the perspective of easier detection of camouflaged army gear on the battlefield. This paper presents some aspect of hyperspectral measurements and processing and focuses on workload reduction and latent data representation using Principal Component Analysis (PCA) and autoencoder techniques. Both techniques are compared through a simple segmentation method that shows their efficiency in reducing the dimensionality of the hyperspectral data, spectrum-wise and image-wise.

Název v anglickém jazyce

Hyperspectral Data Dimensionality Reduction: A Comparative Study Between PCA and Autoencoder Methods

Popis výsledku anglicky

Hyperspectral imaging has emerged as a powerful tool for remote sensing providing detection and identification of objects of interest using their unique spectral signature. Accurate information obtained can reveal details about the physical properties of materials that are relevant to intelligence gathering. Those interesting characteristics coupled with Unmanned Aerial Vehicles (UAVs) offer the perspective of easier detection of camouflaged army gear on the battlefield. This paper presents some aspect of hyperspectral measurements and processing and focuses on workload reduction and latent data representation using Principal Component Analysis (PCA) and autoencoder techniques. Both techniques are compared through a simple segmentation method that shows their efficiency in reducing the dimensionality of the hyperspectral data, spectrum-wise and image-wise.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Modelling and Simulation for Autonomous Systems MESAS

ISBN

978-3-031-71397-2

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

21

Strana od-do

314-334

Název nakladatele

Springer Nature Switzerland

Místo vydání

Cham

Místo konání akce

Palermo

Datum konání akce

17. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001419689800020