Centre de documentation
scientifique

Dépouillements

Generalized composite kernel framework for hyperspectral image classification / J. Li in IEEE Transactions on geoscience and remote sensing, vol 51 n° 9 (September 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 9 (September 2013) . - pp 4816 - 4829 Titre : Generalized composite kernel framework for hyperspectral image classification Type de document : Article/Communication Auteurs : J. Li, Auteur ; Prashanth Reddy Marpu, Auteur ; Antonio Plaza, Auteur ; José M. Bioucas-Dias, Auteur ; et al., Auteur Année de publication : 2013 Conférence : MicroRad 2012, 12th specialist meeting on microwave radiometry and remote sensing applications 05/03/2012 09/03/2012 Rome Italie Proceedings IEEE Article en page(s) : pp 4816 - 4829 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification dirigée [Termes IGN] données localisées [Termes IGN] image AVIRIS [Termes IGN] image hyperspectrale [Termes IGN] image ROSIS [Termes IGN] méthode fondée sur le noyau [Termes IGN] régression logistique [Termes IGN] séparateur à vaste marge Résumé : (Auteur) This paper presents a new framework for the development of generalized composite kernel machines for hyperspectral image classification. We construct a new family of generalized composite kernels which exhibit great flexibility when combining the spectral and the spatial information contained in the hyperspectral data, without any weight parameters. The classifier adopted in this work is the multinomial logistic regression, and the spatial information is modeled from extended multiattribute profiles. In order to illustrate the good performance of the proposed framework, support vector machines are also used for evaluation purposes. Our experimental results with real hyperspectral images collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory's Airborne Visible/Infrared Imaging Spectrometer and the Reflective Optics Spectrographic Imaging System indicate that the proposed framework leads to state-of-the-art classification performance in complex analysis scenarios. Numéro de notice : A2013-536 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2230268 En ligne : https://doi.org/10.1109/TGRS.2012.2230268 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32673 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013091	RAB	Revue	Centre de documentation	En réserve L003	Disponible

A sky status indicator to detect rain-affected atmospheric thermal emissions observed at ground / Ada Vittoria Bosisio in IEEE Transactions on geoscience and remote sensing, vol 51 n° 9 (September 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 9 (September 2013) . - pp 4643 - 4649 Titre : A sky status indicator to detect rain-affected atmospheric thermal emissions observed at ground Type de document : Article/Communication Auteurs : Ada Vittoria Bosisio, Auteur ; Emanno Fionda, Auteur ; Piero Ciotti, Auteur ; Antonio Martellucci, Auteur Année de publication : 2013 Conférence : MicroRad 2012, 12th specialist meeting on microwave radiometry and remote sensing applications 05/03/2012 09/03/2012 Rome Italie Proceedings IEEE Article en page(s) : pp 4643 - 4649 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] atmosphère terrestre [Termes IGN] émission thermique [Termes IGN] image radar [Termes IGN] indicateur [Termes IGN] Pays-Bas [Termes IGN] précipitation [Termes IGN] propagation du signal [Termes IGN] radiomètre à hyperfréquence [Termes IGN] température de luminance Résumé : (Auteur) Radiometric measurements could provide continuous information about atmospheric conditions. In this paper, a sky status indicator (SSI) is proposed as a real-time recognition criterion for the detection, in particular, of the presence of rain events along the propagation path. The computation of the SSI is based on ground-based brightness temperature measurements, at 23.8 and 31.4 GHz, collected in Cabauw, Netherlands, in 2009 by the ESA Atmospheric Propagation and Profiling System (ATPROP) multichannel radiometer. A validation analysis is carried out between simulated data, which are computed by applying the radiative transfer equation to a database of radiosonde profiles collected in De Bilt, Netherlands, by the Royal Netherlands Meteorological Institute, and two data sets of radiometric observations at two elevation angles (è equal to 90° and è equal to 69.6°). The analysis based on SSI probability distribution functions has allowed for calculation of the boundary threshold values that are able to discriminate the status of the sky. Furthermore, performances of the SSI were validated against rainfall measurements collected at the ground by a rain gauge located near the ESA ATPROP multichannel radiometer. Numéro de notice : A2013-537 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2013.2272589 En ligne : https://doi.org/10.1109/TGRS.2013.2272589 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32674 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013091	RAB	Revue	Centre de documentation	En réserve L003	Disponible