Opin vísindi

Hyperspectral Unmixing Using a Neural Network Autoencoder

Hyperspectral Unmixing Using a Neural Network Autoencoder

Title: Hyperspectral Unmixing Using a Neural Network Autoencoder
Author: Palsson, Burkni   orcid.org/0000-0001-9821-8320
Sigurdsson, Jakob   orcid.org/0000-0002-4978-9722
Sveinsson, Jóhannes Rúnar
Ulfarsson, Magnus   orcid.org/0000-0002-0461-040X
Date: 2018
Language: English
Scope: 25646-25656
University/Institute: Háskóli Íslands
University of Iceland
School: Verkfræði- og náttúruvísindasvið (HÍ)
School of Engineering and Natural Sciences (UI)
Department: Rafmagns- og tölvuverkfræðideild (HÍ)
Faculty of Electrical and Computer Engineering (UI)
Series: IEEE Access;6
ISSN: 2169-3536
DOI: 10.1109/ACCESS.2018.2818280
Subject: Hyperspectral unmixing; Autoencoder; Deep learning; Neural network; Spectral angle distance; Endmember extraction; Hugbúnaðarverkfræði
URI: https://hdl.handle.net/20.500.11815/854

Show full item record


Palsson, B., Sigurdsson, J., Sveinsson, J. R., & Ulfarsson, M. O. (2018). Hyperspectral Unmixing Using a Neural Network Autoencoder. IEEE Access, 6, 25646-25656. doi:10.1109/ACCESS.2018.2818280


In this paper, we present a deep learning based method for blind hyperspectral unmixing in the form of a neural network autoencoder. We show that the linear mixture model implicitly puts certain architectural constraints on the network, and it effectively performs blind hyperspectral unmixing. Several different architectural configurations of both shallow and deep encoders are evaluated. Also, deep encoders are tested using different activation functions. Furthermore, we investigate the performance of the method using three different objective functions. The proposed method is compared to other benchmark methods using real data and previously established ground truths of several common data sets. Experiments show that the proposed method compares favorably to other commonly used hyperspectral unmixing methods and exhibits robustness to noise. This is especially true when using spectral angle distance as the network's objective function. Finally, results indicate that a deeper and a more sophisticated encoder does not necessarily give better results.

Files in this item

This item appears in the following Collection(s)