Centre de documentation
scientifique

Histogram curve matching approaches for object-based image classification of land cover and land use / Sory I. Toure in Photogrammetric Engineering & Remote Sensing, PERS, vol 79 n° 5 (May 2013)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 79 n° 5 (May 2013) . - pp 433 - 440 Titre : Histogram curve matching approaches for object-based image classification of land cover and land use Type de document : Article/Communication Auteurs : Sory I. Toure, Auteur ; Douglas A. Stow, Auteur ; John R. Weeks, Auteur ; Sunil Kumar, Auteur Année de publication : 2013 Article en page(s) : pp 433 - 440 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] appariement d'histogramme [Termes IGN] classificateur [Termes IGN] classification barycentrique [Termes IGN] classification orientée objet [Termes IGN] image multibande [Termes IGN] occupation du sol [Termes IGN] San Diego Résumé : (Auteur) The classification of image-objects is usually done using parametric statistical measures of central tendency and/or dispersion (e.g., mean or standard deviation). The objectives of this study were to analyze digital number histograms of image objects and evaluate classifications measures exploit-ing characteristic signatures of such histograms. Two histo-grams matching classifiers were evaluated and compared to the standard nearest neighbor to mean classifier. An ADS40 airborne multispectral image of San Diego, California was used for assessing the utility of curve matching classifiers in a geographic object-based image analysis (GEOBIA) approach. The classifications were performed with data sets having 0.5m, 2.5m, and 5m spatial resolutions. Results show that histograms are reliable features for characterizing classes. Also, both histogram matching classifiers consistently per-formed better than the one based on the standard nearest neighbor to mean rule. The highest classification accuracies were produced with images having 2.5m spatial resolution. Numéro de notice : A2013-281 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.79.5.433 En ligne : https://doi.org/10.14358/PERS.79.5.433 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32419 [article]