Détail de l'autorité
|
IGARSS 2004, International Geoscience And Remote Sensing Symposium, Science for society: exploring and manging a changing planet 20/09/2004 24/09/2004 Anchorage Alaska - Etats-Unis Proceedings IEEE
nom du congrès :
IGARSS 2004, International Geoscience And Remote Sensing Symposium, Science for society: exploring and manging a changing planet
début du congrès :
20/09/2004
fin du congrès :
24/09/2004
ville du congrès :
Anchorage
pays du congrès :
Alaska - Etats-Unis
site des actes du congrès :
|
Documents disponibles (3)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externesvol 43 n° 11 - November 2005 - Special issue on the 2004 international geosciences and remote sensing symposium (IGARSS): "Science for society: exploring and manging a changing planet" (Bulletin de IEEE Transactions on geoscience and remote sensing) / Geoscience and remote sensing society
ContientExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-05111 RAB Revue Centre de documentation En réserve L003 Disponible Supervised image classification by contextual adaboost based on posteriors in neighborhoods / Ryuei Nishii in IEEE Transactions on geoscience and remote sensing, vol 43 n° 11 (November 2005)
Titre : Supervised image classification by contextual adaboost based on posteriors in neighborhoods Type de document : Article/Communication Auteurs : Ryuei Nishii, Auteur ; Shinto Eguchi, Auteur Année de publication : 2005 Conférence : IGARSS 2004, International Geoscience And Remote Sensing Symposium, Science for society: exploring and manging a changing planet 20/09/2004 24/09/2004 Anchorage Alaska - Etats-Unis Proceedings IEEE Article en page(s) : pp 2547 - 2554 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage automatique
[Termes IGN] axiome de Bayes
[Termes IGN] classification contextuelle
[Termes IGN] classification dirigée
[Termes IGN] géostatistique
[Termes IGN] probabilités
[Termes IGN] segmentation d'imageRésumé : (Auteur) AdaBoost, a machine learning technique, is employed for supervised classification of land-cover categories of geostatistical data. We introduce contextual classifiers based on neighboring pixels. First, posterior probabilities are calculated at all pixels. Then averages of the log posteriors are calculated in different neighborhoods and are then used as contextual classification functions. Weights for the classification functions can be determined by minimizing the empirical risk with multiclass. Finally, a convex combination of classification functions is obtained. The classification is performed by a noniterative maximization procedure. The proposed method is applied to artificial multispectral images and benchmark datasets. The performance of the proposed method is excellent and similar to Markov-random-field-based classifier, which requires an iterative maximization procedure. Numéro de notice : A2005-495 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2005.848693 En ligne : https://doi.org/10.1109/TGRS.2005.848693 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27631
in IEEE Transactions on geoscience and remote sensing > vol 43 n° 11 (November 2005) . - pp 2547 - 2554[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-05111 RAB Revue Centre de documentation En réserve L003 Disponible
Titre : Detection of systematic error areas on a DTM by comparison with a high resolution LIDAR DTM Type de document : Article/Communication Auteurs : Frédéric Rousseaux, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2004 Conférence : IGARSS 2004, International Geoscience And Remote Sensing Symposium, Science for society: exploring and manging a changing planet 20/09/2004 24/09/2004 Anchorage Alaska - Etats-Unis Proceedings IEEE Importance : pp 4160 - 4163 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie
[Termes IGN] analyse comparative
[Termes IGN] données altimétriques
[Termes IGN] interpolation spatiale
[Termes IGN] modèle numérique de terrain
[Termes IGN] Triangulated Irregular NetworkRésumé : (auteur) The spatial repartition and the impacts of the errors on a Digital Terrain Model (DTM) were studied. It was found that the spatial repartition of the biggest errors does not depend on the interpolation choice but on the relief type. Interpolation was shown to influence the raster DTMs (matrix with regular cells). It was also found that on the raster DTM, as on the TIN DTM, the bias are due to a lack of altimetric information on some of the interpolated areas. Those areas are usually located inside the last maximal or minimal contour line. Numéro de notice : C2004-038 Affiliation des auteurs : COGIT (1988-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IGARSS.2004.1370050 Date de publication en ligne : 27/12/2004 En ligne : https://doi.org/10.1109/IGARSS.2004.1370050 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102629
