Centre de documentation
scientifique

A very quick neural network algorithm for cloud detection / K.R. Al-Rawi in Geocarto international, vol 18 n° 1 (March - May 2003)  

Public [article]  inGeocarto international > vol 18 n° 1 (March - May 2003) . - pp 45 - 50 Titre : A very quick neural network algorithm for cloud detection Type de document : Article/Communication Auteurs : K.R. Al-Rawi, Auteur ; José Luis Casanova, Auteur ; A. Vasileisky, Auteur Année de publication : 2003 Article en page(s) : pp 45 - 50 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] classification par réseau neuronal [Termes IGN] image NOAA-AVHRR [Termes IGN] nuage [Termes IGN] radiance Résumé : (Auteur) A very quick neural network algorithm for cloud detection, based on a neural network, is developed. Cloud detection is speeded up through the use of the Class Assigning Space (CAS). The CAS is a classified Radiance Space (RS), which has been built using the trained neural network. The GAS is used to assign a class for each pixel in the image instead of using the ANN to treat every single pixel. The detection time is approximately one second. Channel 1 and channel 5 of N0AA-AVHRR images have been used. The Supervised ARTII artificial neural network has been employed. The system performance has been tested with different training sets and different input data. Numéro de notice : A2003-101 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040308542262 En ligne : https://doi.org/10.1080/10106040308542262 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22397 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-03011	RAB	Revue	Centre de documentation	En réserve L003	Disponible