DAEN: Deep Autoencoder Networks for Hyperspectral Unmixing

Spectral unmixing is a technique for remotely sensed image interpretation that expresses each (possibly mixed) pixel as a combination of pure spectral signatures (endmembers) and their fractional abundances. In this paper, we develop a new technique for unsupervised unmixing which is based on a deep...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on geoscience and remote sensing Ročník 57; číslo 7; s. 4309 - 4321
Hlavní autori: Su, Yuanchao, Li, Jun, Plaza, Antonio, Marinoni, Andrea, Gamba, Paolo, Chakravortty, Somdatta
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.07.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Computers
Deep autoencoder network (DAEN)
deep learning
endmember identification
Estimation
Hyperspectral imaging
hyperspectral unmixing
Noise reduction
Outliers (statistics)
Remote sensing
Signal processing
Signal to noise ratio
Spectra
Spectral signatures
Training
variational autoencoder (VAE)
ISSN:0196-2892, 1558-0644
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Spectral unmixing is a technique for remotely sensed image interpretation that expresses each (possibly mixed) pixel as a combination of pure spectral signatures (endmembers) and their fractional abundances. In this paper, we develop a new technique for unsupervised unmixing which is based on a deep autoencoder network (DAEN). Our newly developed DAEN consists of two parts. The first part of the network adopts stacked autoencoders (SAEs) to learn spectral signatures, so as to generate a good initialization for the unmixing process. In the second part of the network, a variational autoencoder (VAE) is employed to perform blind source separation, aimed at obtaining the endmember signatures and abundance fractions simultaneously. By taking advantage from the SAEs, the robustness of the proposed approach is remarkable as it can unmix data sets with outliers and low signal-to-noise ratio. Moreover, the multihidden layers of the VAE ensure the required constraints (nonnegativity and sum-to-one) when estimating the abundances. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data. When compared with other unmixing methods, the proposed approach demonstrates very competitive performance.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2018.2890633