RT Journal Article
T1 Caffe CNN-based Classification of Hyperspectral Images on GPU
A1 Suárez Garea, Jorge Alberto
A1 Blanco Heras, Dora
A1 Argüello Pedreira, Francisco
K1 Superpixel segmentation
K1 Watershed transform
K1 Waterpixel segmentation
K1 Hyperspectral image
K1 Remote sensing
K1 CUDA
AB Deep learning techniques based on Convolutional Neural Networks (CNNs) are extensively used for the classification of hyperspectral images. These techniques present high computational cost. In this paper, a GPU (Graphics Processing Unit) implementation of a spatial-spectral supervised classification scheme based on CNNs and applied to remote sensing datasets is presented. In particular, two deep learning libraries, Caffe and CuDNN, are used and compared. In order to achieve an efficient GPU projection, different techniques and optimizations have been applied. The implemented scheme comprises Principal Component Analysis (PCA) to extract the main features, a patch extraction around each pixel to take the spatial information into account, one convolutional layer for processing the spectral information, and fully connected layers to perform the classification. To improve the initial GPU implementation accuracy, a second convolutional layer has been added. High speedups are obtained together with competitive classification accuracies.
PB Springer
SN 1573-0484
YR 2018
FD 2018-03-09
LK https://hdl.handle.net/10347/38536
UL https://hdl.handle.net/10347/38536
LA eng
NO Garea, A. S., Heras, D. B., & Argüello, F. (2019). Caffe CNN-based classification of hyperspectral images on GPU. The Journal of Supercomputing, 75, 1065-1077.
NO This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s11227-018-2300-2
NO Consellerı́a de Cultura, Educación e Ordenación Universitaria, Xunta de Galicia, GRC2014/008 y ED431G/08.
NO Ministerio de Educación, Cultura y Deportes, Gobierno de España, TIN2013-41129-P y TIN2016-76373-P.
NO European Regional Development Fund, European Union, ERDF
DS Minerva
RD 24 abr 2026