no code implementations • 16 Jun 2017 • Frosti Palsson, Johannes R. Sveinsson, Magnus O. Ulfarsson
In this paper, we propose a method using a three dimensional convolutional neural network (3-D-CNN) to fuse together multispectral (MS) and hyperspectral (HS) images to obtain a high resolution hyperspectral image.
no code implementations • 1 Jun 2016 • Behnood Rasti, Magnus O. Ulfarsson, Johannes R. Sveinsson
However, due to spectral and spatial redundancy the true hyperspectral signal lies on a subspace of much lower dimension than the original data.
no code implementations • 16 May 2016 • Magnus O. Ulfarsson, Frosti Palsson, Jakob Sigurdsson, Johannes R. Sveinsson
In this paper, we consider the problem of classifying p>>n data and propose a classification method based on linear discriminant analysis (LDA).
1 code implementation • 22 Mar 2018 • Burkni Palsson, Jakob Sigurdsson, Johannes R. Sveinsson, Magnus O. Ulfarsson
Also, deep encoders are tested using different activation functions.