Convolutional Autoencoder for Spectral-Spatial Hyperspectral Unmixing

Blind hyperspectral unmixing is the process of expressing the measured spectrum of a pixel as a combination of a set of spectral signatures called endmembers and simultaneously determining their fractional abundances in the pixel. Most unmixing methods are strictly spectral and do not exploit the sp...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on geoscience and remote sensing Ročník 59; číslo 1; s. 535 - 549
Hlavní autoři: Palsson, Burkni, Ulfarsson, Magnus O., Sveinsson, Johannes R.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Abundance
Artificial neural networks
Convolutional codes
Data mining
deep neural network learning
Estimation
Feature maps
Hyperspectral data unmixing
Hyperspectral imaging
image processing
Indexes
Methods
Neural networks
Pixels
Spatial resolution
Spectra
Spectral signatures
spectral–spatial model
ISSN:0196-2892, 1558-0644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Blind hyperspectral unmixing is the process of expressing the measured spectrum of a pixel as a combination of a set of spectral signatures called endmembers and simultaneously determining their fractional abundances in the pixel. Most unmixing methods are strictly spectral and do not exploit the spatial structure of hyperspectral images (HSIs). In this article, we present a new spectral-spatial linear mixture model and an associated estimation method based on a convolutional neural network autoencoder unmixing (CNNAEU). The CNNAEU technique exploits the spatial and the spectral structure of HSIs both for endmember and abundance map estimation. As it works directly with patches of HSIs and does not use any pooling or upsampling layers, the spatial structure is preserved throughout and abundance maps are obtained as feature maps of a hidden convolutional layer. We compared the CNNAEU method to four conventional and three deep learning state-of-the-art unmixing methods using four real HSIs. Experimental results show that the proposed CNNAEU technique performs particularly well and consistently when it comes to endmembers' extraction and outperforms all the comparison methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2020.2992743