Evaluation of the potential of convolutional neural networks and random forests for multi-class segmentation of sentinel-2 imagery

Syrris, Vasileios and Hasenohr, Paul and Delipetrev, Blagoj and Kotsev, Alexander and Kempeneers, Pieter and Soille, Pierre (2019) Evaluation of the potential of convolutional neural networks and random forests for multi-class segmentation of sentinel-2 imagery. Remote Sensing, 11 (8). p. 907.

[thumbnail of 8. remotesensing-11-00907.pdf] Text
8. remotesensing-11-00907.pdf

Download (12MB)

Abstract

Motivated by the increasing availability of open and free Earth observation data through the Copernicus Sentinel missions, this study investigates the capacity of advanced computational models to automatically generate thematic layers, which in turn contribute to and facilitate the creation of land cover products. In concrete terms, we assess the practical and computational aspects of multi-class Sentinel-2 image segmentation based on a convolutional neural network and random forest approaches. The annotated learning set derives from data that is made available as result of the implementation of European Union’s INSPIRE Directive. Since this network of data sets remains incomplete in regard to some geographic areas, another objective of this work was to provide consistent and reproducible ways for machine-driven mapping of these gaps and a potential update of the existing ones. Finally, the performance analysis identifies the most important hyper-parameters, and provides hints on the models’ deployment and their transferability.

Item Type: Article
Impact Factor Value: 4
Subjects: Engineering and Technology > Electrical engineering, electronic engineering, information engineering
Divisions: Faculty of Computer Science
Depositing User: Blagoj Delipetrev
Date Deposited: 06 May 2021 13:08
Last Modified: 06 May 2021 13:08
URI: https://eprints.ugd.edu.mk/id/eprint/28045

Actions (login required)

View Item View Item