Next Article in Journal
The COSMO-SkyMed Constellation Monitors the Costa Concordia Wreck
Next Article in Special Issue
A Three-Dimensional Index for Characterizing Crop Water Stress
Previous Article in Journal
Framework of Jitter Detection and Compensation for High Resolution Satellites
Previous Article in Special Issue
Estimating Fractional Shrub Cover Using Simulated EnMAP Data: A Comparison of Three Machine Learning Regression Techniques
Remote Sens. 2014, 6(5), 3965-3987; doi:10.3390/rs6053965

Automated Training Sample Extraction for Global Land Cover Mapping

1,* , 1
1 Earth and Life Institute, Université catholique de Louvain, Croix du Sud, L7.05.16, B-1348 Louvain-la-Neuve, Belgium 2 Brockmann Consult, Max-Planck-Strasse, D-21502 Geesthacht, Germany
* Author to whom correspondence should be addressed.
Received: 16 January 2014 / Revised: 10 April 2014 / Accepted: 18 April 2014 / Published: 2 May 2014
(This article belongs to the Special Issue Analysis of Remote Sensing Image Data)
View Full-Text   |   Download PDF [2530 KB, 19 June 2014; original version 19 June 2014]   |   Browse Figures


Land cover is one of the essential climate variables of the ESA Climate Change Initiative (CCI). In this context, the Land Cover CCI (LC CCI) project aims at building global land cover maps suitable for climate modeling based on Earth observation by satellite sensors.  The  challenge  is  to  generate  a  set  of  successive  maps  that  are  both  accurate and consistent over time. To do so, operational methods for the automated classification of optical images are investigated. The proposed approach consists of a locally trained classification using an automated selection of training samples from existing, but outdated land cover information. Combinations of local extraction (based on spatial criteria) and self-cleaning of training samples (based on spectral criteria) are quantitatively assessed. Two large study areas, one in Eurasia and the other in South America, are considered. The proposed morphological cleaning of the training samples leads to higher accuracies than the statistical outlier removal in the spectral domain. An optimal neighborhood has been identified for the local sample extraction. The results are coherent for the two test areas, showing an improvement of the overall accuracy compared with the original reference datasets and a significant reduction of macroscopic errors. More importantly, the proposed method partly controls the reliability of existing land cover maps as sources of training samples for supervised classification.
Keywords: global land cover; automated classification; trimming; morphological filtering; local training; MERIS global land cover; automated classification; trimming; morphological filtering; local training; MERIS
This is an open access article distributed under the Creative Commons Attribution License (CC BY) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
MDPI and ACS Style

Radoux, J.; Lamarche, C.; Van Bogaert, E.; Bontemps, S.; Brockmann, C.; Defourny, P. Automated Training Sample Extraction for Global Land Cover Mapping. Remote Sens. 2014, 6, 3965-3987.

View more citation formats

Related Articles

Article Metrics

For more information on the journal, click here


Cited By

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert