Opin vísindi

Browsing by Author "Sveinsson, Jóhannes Rúnar"

Browsing by Author "Sveinsson, Jóhannes Rúnar"

Sort by: Order: Results:

  • Icon
    Blind Hyperspectral Unmixing using Autoencoders : A Critical Comparison 
    Pálsson, Burkni; Sveinsson, Jóhannes Rúnar; Úlfarsson, Magnús Örn (2022-01-01)
    Deep learning has shown to be a powerful tool and has heavily impacted the data-intensive field of remote sensing. As a result, the number of published deep learning-based spectral unmixing techniques is proliferating. Blind hyperspectral unmixing (HU) ...
  • Icon
    Hyperspectral Unmixing Using a Neural Network Autoencoder 
    Palsson, Burkni; Sigurdsson, Jakob; Sveinsson, Jóhannes Rúnar; Ulfarsson, Magnus (Institute of Electrical and Electronics Engineers (IEEE), 2018)
    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 ...
  • Icon
    Sentinel-2 Image Fusion Using a Deep Residual Network 
    Palsson, Frosti; Sveinsson, Jóhannes Rúnar; Ulfarsson, Magnus (MDPI AG, 2018-08-15)
    Single sensor fusion is the fusion of two or more spectrally disjoint reflectance bands that have different spatial resolution and have been acquired by the same sensor. An example is Sentinel-2, a constellation of two satellites, which can acquire ...
  • Icon
    Unsupervised and Supervised Feature Extraction Methods for Hyperspectral Images Based on Mixtures of Factor Analyzers 
    Zhao, Bin; Ulfarsson, Magnus; Sveinsson, Jóhannes Rúnar; Chanussot, Jocelyn (MDPI AG, 2020-04-07)
    This paper proposes three feature extraction (FE) methods based on density estimation for hyperspectral images (HSIs). The methods are a mixture of factor analyzers (MFA), deep MFA (DMFA), and supervised MFA (SMFA). The MFA extends the Gaussian mixture ...