User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Automated Training Sample Extraction for Global Land Cover Mapping

Primary tabs

download
  • Open access
  • PDF
  • 2.42 M
Radoux, Julien Lamarche, Céline Van Bogaert, Eric Bontemps, Sophie Brockmann, Carsten Defourny, Pierre

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consists of a locally trained classification using an automated selection of training samples from existing, but outdated land cover information.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.

Document type Article de périodique (Journal article) – Article de recherche
Access type Accès libre
Publication date 2014
Language Anglais
Journal information "Remote Sensing" - Vol. 6, no.5, p. 3965-3987 (2014)
Peer reviewed yes
Publisher MDPI (Switzerland)
issn 2072-4292
e-issn 2072-4292
Publication status Publié
Affiliation UCL - SST/ELI/ELIE - Environmental Sciences
Keywords global land cover ; automated classification ; trimming ; morphological filtering ; local training ; MERIS
Links
  1. Hollmann R., Merchant C. J., Saunders R., Downy C., Buchwitz M., Cazenave A., Chuvieco E., Defourny P., de Leeuw G., Forsberg R., Holzer-Popp T., Paul F., Sandven S., Sathyendranath S., van Roozendael M., Wagner W., The ESA Climate Change Initiative: Satellite Data Records for Essential Climate Variables, 10.1175/bams-d-11-00254.1
  2. DEFRIES R. S., TOWNSHEND J. R. G., NDVI-derived land cover classifications at a global scale, 10.1080/01431169408954345
  3. De Fries R. S., Hansen M., Townshend J. R. G., Sohlberg R., Global land cover classifications at 8 km spatial resolution: The use of training data derived from Landsat imagery in decision tree classifiers, 10.1080/014311698214235
  4. Loveland T. R., Reed B. C., Brown J. F., Ohlen D. O., Zhu Z., Yang L., Merchant J. W., Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data, 10.1080/014311600210191
  5. Friedl Mark A., Sulla-Menashe Damien, Tan Bin, Schneider Annemarie, Ramankutty Navin, Sibley Adam, Huang Xiaoman, MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets, 10.1016/j.rse.2009.08.016
  6. Bontemps, 243 (2012)
  7. Colditz R.R., Schmidt M., Conrad C., Hansen M.C., Dech S., Land cover classification with coarse spatial resolution data to derive continuous and discrete maps for complex regions, 10.1016/j.rse.2011.07.010
  8. Hansen M. C., Defries R. S., Townshend J. R. G., Sohlberg R., Global land cover classification at 1 km spatial resolution using a classification tree approach, 10.1080/014311600210209
  9. Muchoney, Photogramm. Eng. Remote Sens, 65, 1061 (1999)
  10. Pal Mahesh, Mather P. M., Some issues in the classification of DAIS hyperspectral data, 10.1080/01431160500185227
  11. Foody G. M., Arora M. K., An evaluation of some factors affecting the accuracy of classification by an artificial neural network, 10.1080/014311697218764
  12. Tuia D., Pasolli E., Emery W.J., Using active learning to adapt remote sensing image classifiers, 10.1016/j.rse.2011.04.022
  13. Brodley, 1, 799 (1996)
  14. Vancutsem C., Bicheron P., Cayrol P., Defourny P., An assessment of three candidate compositing methods for global MERIS time series, 10.5589/m07-056
  15. Di Gregorio, 1 (2000)
  16. Herold M., Mayaux P., Woodcock C.E., Baccini A., Schmullius C., Some challenges in global land cover mapping: An assessment of agreement and accuracy in existing 1 km datasets, 10.1016/j.rse.2007.11.013
  17. Bontemps Sophie, Bogaert Patrick, Titeux Nicolas, Defourny Pierre, An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution, 10.1016/j.rse.2008.03.013
  18. Hansen Matthew C., Loveland Thomas R., A review of large area monitoring of land cover change using Landsat data, 10.1016/j.rse.2011.08.024
  19. Vancutsem C., Defourny P., A decision support tool for the optimization of compositing parameters, 10.1080/01431160802036375
  20. Bruzzone L., Roli F., Serpico S.B., An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection, 10.1109/36.477187
  21. Cortes Corinna, Vapnik Vladimir, Support-vector networks, 10.1007/bf00994018
  22. Chih-Wei Hsu, Chih-Jen Lin, A comparison of methods for multiclass support vector machines, 10.1109/72.991427
  23. Soille (1999)
  24. Desclée Baudouin, Bogaert Patrick, Defourny Pierre, Forest change detection by statistical object-based method, 10.1016/j.rse.2006.01.013
  25. Radoux Julien, Defourny Pierre, Automated Image-to-Map Discrepancy Detection using Iterative Trimming, 10.14358/pers.76.2.173
  26. Colditz René R., López Saldaña Gerardo, Maeda Pedro, Espinoza Jesús Argumedo, Tovar Carmen Meneses, Hernández Arturo Victoria, Benítez Carlos Zermeño, Cruz López Isabel, Ressl Rainer, Generation and analysis of the 2005 land cover map for Mexico using 250m MODIS data, 10.1016/j.rse.2012.04.021
  27. Defourny, 207 (2012)
  28. DeFries R, Multiple Criteria for Evaluating Machine Learning Algorithms for Land Cover Classification from Satellite Data, 10.1016/s0034-4257(00)00142-5
  29. Mayaux P., Eva H., Gallego J., Strahler A.H., Herold M., Agrawal S., Naumov S., De Miranda E.E., Di Bella C.M., Ordoyne C., Kopin Y., Roy P.S., Validation of the global land cover 2000 map, 10.1109/tgrs.2006.864370
  30. Strahler, GOFC-GOLD Rep, 25, 1 (2006)
  31. Blanco Paula D., Colditz Rene R., López Saldaña Gerardo, Hardtke Leonardo A., Llamas Ricardo M., Mari Nicolás A., Fischer Angeles, Caride Constanza, Aceñolaza Pablo G., del Valle Héctor F., Lillo-Saavedra Mario, Coronato Fernando, Opazo Sergio A., Morelli Fabiano, Anaya Jesús A., Sione Walter F., Zamboni Pamela, Arroyo Victor Barrena, A land cover map of Latin America and the Caribbean in the framework of the SERENA project, 10.1016/j.rse.2012.12.025
  32. Schneider Annemarie, Friedl Mark A., Potere David, Mapping global urban areas using MODIS 500-m data: New methods and datasets based on ‘urban ecoregions’, 10.1016/j.rse.2010.03.003
  33. Pal M., Mather P. M., Support vector machines for classification in remote sensing, 10.1080/01431160512331314083
  34. Mountrakis Giorgos, Im Jungho, Ogole Caesar, Support vector machines in remote sensing: A review, 10.1016/j.isprsjprs.2010.11.001
  35. Foody G.M., Mathur A., A relative evaluation of multiclass image classification by support vector machines, 10.1109/tgrs.2004.827257
Bibliographic reference Radoux, Julien ; Lamarche, Céline ; Van Bogaert, Eric ; Bontemps, Sophie ; Brockmann, Carsten ; et. al. Automated Training Sample Extraction for Global Land Cover Mapping. In: Remote Sensing, Vol. 6, no.5, p. 3965-3987 (2014)
Permanent URL http://hdl.handle.net/2078.1/143085