Centre de documentation
scientifique

Geographic Information Systems in Geospatial Intelligence, ch. 5. Spectral optimization of airborne multispectral camera for land cover classification: automatic feature selection and spectral band clustering / Arnaud Le Bris (2019)  

Public Titre de série : Geographic Information Systems in Geospatial Intelligence, ch. 5 Titre : Spectral optimization of airborne multispectral camera for land cover classification: automatic feature selection and spectral band clustering Type de document : Chapitre/Contribution Auteurs : Arnaud Le Bris , Auteur ; Nesrine Chehata , Auteur ; Xavier Briottet , Auteur ; Nicolas Paparoditis , Auteur Editeur : London [UK] : IntechOpen Année de publication : 2019 Projets : 1-Pas de projet / Importance : 4 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] bande spectrale [Termes IGN] carte d'occupation du sol [Termes IGN] classification multibande [Termes IGN] image hyperspectrale [Termes IGN] optimisation (mathématiques) Résumé : (auteur) Hyperspectral imagery consists of hundreds of contiguous spectral bands. However, most of them are redundant. Thus a subset of well-chosen bands is generally sufficient for a specific problem, enabling to design adapted superspectral sensors dedicated to specific land cover classification. Related both to feature selection and extraction, spectral optimization identifies the most relevant band subset for specific applications, involving a band subset relevance score as well as a method to optimize it. This study first focuses on the choice of such relevance score. Several criteria are compared through both quantitative and qualitative analyses. To have a fair comparison, all tested criteria are compared to classic hyperspectral data sets using the same optimization heuristics: an incremental one to assess the impact of the number of selected bands and a stochastic one to obtain several possible good band subsets and to derive band importance measures out of intermediate good band subsets. Last, a specific approach is proposed to cope with the optimization of bandwidth. It consists in building a hierarchy of groups of adjacent bands, according to a score to decide which adjacent bands must be merged, before band selection is performed at the different levels of this hierarchy. Numéro de notice : H2019-008 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Chapître / contribution nature-HAL : ChOuvrScient DOI : 10.5772/intechopen.88507 Date de publication en ligne : 20/12/2019 En ligne : http://dx.doi.org/10.5772/intechopen.88507 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95734