Centre de documentation
scientifique

Feature selection by genetic algorithms in object-based classification of Ikonos imagery for forest mapping in Flanders, Belgium / F.M.B. Van Coillie in Remote sensing of environment, vol 110 n° 4 (30/10/2007)  

Public [article]  inRemote sensing of environment > vol 110 n° 4 (30/10/2007) . - pp 476 - 487 Titre : Feature selection by genetic algorithms in object-based classification of Ikonos imagery for forest mapping in Flanders, Belgium Type de document : Article/Communication Auteurs : F.M.B. Van Coillie, Auteur ; L.P.C. Verbeke, Auteur ; R.R. DE Wulf, Auteur Année de publication : 2007 Conférence : ForestSat 2007, forests and remote sensing : methods and operational tools 05/11/2007 07/11/2007 Montpellier France Article en page(s) : pp 476 - 487 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] algorithme génétique [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal [Termes IGN] détection d'objet [Termes IGN] Flandre (Belgique) [Termes IGN] forêt tempérée [Termes IGN] image Ikonos [Termes IGN] segmentation d'image Résumé : (Auteur) Obtaining detailed information about the amount of forest cover is an important issue for governmental policy and forest management. This paper presents a new approach to update the Flemish Forest Map using IKONOS imagery. The proposed method is a three-step object-oriented classification routine that involves the integration of 1) image segmentation, 2) feature selection by Genetic Algorithms (GAs) and 3) joint Neural Network (NN) based object-classification. The added value of feature selection and neural network combination is investigated. Results show that, with GA-feature selection, the mean classification accuracy (in terms of Kappa Index of Agreement) is significantly higher (p Numéro de notice : A2007-412 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2007.03.020 En ligne : https://doi.org/10.1016/j.rse.2007.03.020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28775 [article]