ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 83-88, 2016
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-7/83/2016/
doi:10.5194/isprs-annals-III-7-83-2016
 
07 Jun 2016
BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA
M. Papadomanolaki1, M. Vakalopoulou1, S. Zagoruyko2, and K. Karantzalos1 1Remote Sensing Laboratory, National Technical University, Zographou campus, 15780, Athens, Greece
2Imagine/Ligm, Ecole des Ponts ParisTech, Cite Descartes, 77455 Champs-sur-Marne, France
Keywords: Machine Learning, Classification, Land Cover, Land Use, Convolutional, Neural Networks, Data Mining Abstract. In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the AlexNet, AlexNet-small and VGG models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates i.e., above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.
Conference paper (PDF, 4294 KB)


Citation: Papadomanolaki, M., Vakalopoulou, M., Zagoruyko, S., and Karantzalos, K.: BENCHMARKING DEEP LEARNING FRAMEWORKS FOR THE CLASSIFICATION OF VERY HIGH RESOLUTION SATELLITE MULTISPECTRAL DATA, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 83-88, doi:10.5194/isprs-annals-III-7-83-2016, 2016.

BibTeX EndNote Reference Manager XML