Centre de documentation
scientifique

A multiple-cascade-classifier system for a robust and partially unsupervised updating of land-cover maps / Lorenzo Bruzzone in IEEE Transactions on geoscience and remote sensing, vol 40 n° 9 (September 2002)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 40 n° 9 (September 2002) . - pp 1984 - 1996 Titre : A multiple-cascade-classifier system for a robust and partially unsupervised updating of land-cover maps Type de document : Article/Communication Auteurs : Lorenzo Bruzzone, Auteur ; R. Cossu, Auteur Année de publication : 2002 Article en page(s) : pp 1984 - 1996 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] carte d'occupation du sol [Termes IGN] classification non dirigée [Termes IGN] classification par maximum de vraisemblance [Termes IGN] classification par réseau neuronal [Termes IGN] image multitemporelle [Termes IGN] mise à jour cartographique Résumé : (Auteur) A system for a regular updating of landcover maps is proposed that is based on the use of multitemporal remote sensing images. Such a system is able to address the updating problem under the realistic but critical constraint that, for the image to be classified (i.e., the most recent of the considered multitemporal dataset no ground truth information is available. The system is composed of an ensemble of partially unsupervised classifiers integrated in a multipleclassifier architecture. Each classifier of the ensemble exhibits the following novel characteristics: 1) it is developed in the framework of the cascade-classification approach to exploit the temporal correlation existing between images acquired at different times in the considered area; and 2) it is based on a partially unsupervised methodology capable of accomplishing the classification process under the aforementioned critical constraint. Both a parametric maximumlikelihood (ML) classification approach and a nonparametric radial basis function (RBF) neuralnetwork classification approach are used as basic methods for the development of partially unsupervised cascade classifiers. In addition, in order to generate an effective ensemble of classification algorithms, hybrid ML and RBF neuralnetwork cascade classifiers are defined by exploiting the characteristics of the cascadeclassification methodology. The results yielded by the different classifiers are combined by using standard unsupervised combination strategies. This allows the definition of a robust and accurate partially unsupervised classification system capable of analyzing a wide typology of remote sensing data (e.g., images acquired by passive sensors, synthetic aperture radar images, and multisensor and multisource data). Experimental results obtained on a real multitemporal and multisource dataset confirm the effectiveness of the proposed system. Numéro de notice : A2002-287 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2002.803794 En ligne : https://doi.org/10.1109/TGRS.2002.803794 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22198 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-02081	RAB	Revue	Centre de documentation	En réserve L003	Disponible