Détail de l'auteur
Auteur T. Macri Pellizzei |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Multitemporal/multiband SAR classification of urban areas using spatial analysis: statistical versus neural kernel-based approach / T. Macri Pellizzei in IEEE Transactions on geoscience and remote sensing, vol 41 n° 10 (October 2003)
[article]
Titre : Multitemporal/multiband SAR classification of urban areas using spatial analysis: statistical versus neural kernel-based approach Type de document : Article/Communication Auteurs : T. Macri Pellizzei, Auteur ; Paolo Gamba, Auteur ; P. Lombardo, Auteur ; F. Dell'acqua, Auteur Année de publication : 2003 Article en page(s) : pp 2338 - 2353 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] analyse comparative
[Termes IGN] classification dirigée
[Termes IGN] classification floue
[Termes IGN] classification par réseau neuronal
[Termes IGN] image radar moirée
[Termes IGN] image SIR-C
[Termes IGN] milieu urbain
[Termes IGN] réalité de terrain
[Termes IGN] segmentation d'image
[Termes IGN] test de performanceRésumé : (Auteur) In this paper, we derive two techniques for the classification of Multifrequency/multitemporal polarimetric SAR images, based respectively on a statistical and on a neural approach. Both techniques are especially designed to exploit the spatial structure of the observed scene, thus allowing more stable classification results. Such techniques are useful when looking at medium - to - scale features, like the boundaries between urban and non-urban areas. They are applied to a set of SIR-C images of a urban area, to test their effectiveness in the identification of the different classes that compose the observed scene. A lower and an upper bound to the classification performance are introduced to characterise their limits. They correspond respectively to pixel-by-pixel classification and to the joint classification of the pixels belonging to the different classes identified in the ground truth. The results achieved with the two approaches are quantitatively analysed by comparing them to the ground truth. Moreover, a hybrid approach is presented, where the homogeneous regions identified through statistical segmentation are classified using a neuro-fuzzy technique. Finally, a quantitative analysis of the results achieved with all the proposed techniques is carried out, showing that their classification performance is much higher than the lower bound and reasonably close to the upper bound. This is a consequence of their effectiveness in the exploitation of the spatial information. Numéro de notice : A2003-356 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2003.818762 En ligne : https://doi.org/10.1109/TGRS.2003.818762 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=26436
in IEEE Transactions on geoscience and remote sensing > vol 41 n° 10 (October 2003) . - pp 2338 - 2353[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-03101 RAB Revue Centre de documentation En réserve L003 Disponible