Centre dedocumentation
scientifique

Extraction of built-up areas from Landsat-8 OLI data based on spectral-textural information and feature selection using support vector machine method / Vijendra Singh Bramhe in Geocarto international, vol 35 n° 10 ([01/08/2020])  

Public [article]  inGeocarto international > vol 35 n° 10 [01/08/2020] . - pp 1067 - 1087 Titre : Extraction of built-up areas from Landsat-8 OLI data based on spectral-textural information and feature selection using support vector machine method Type de document : Article/Communication Auteurs : Vijendra Singh Bramhe, Auteur ; Sanjay Kumar Ghosh, Auteur ; Pradeep Kumar Garg, Auteur Année de publication : 2020 Article en page(s) : pp 1067 - 1087 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse spectrale [Termes IGN] analyse texturale [Termes IGN] bati [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] extraction de traits caractéristiques [Termes IGN] image Landsat-OLI [Termes IGN] image multibande [Termes IGN] matrice de co-occurrence [Termes IGN] niveau de gris (image) [Termes IGN] plus proche voisin, algorithme du [Termes IGN] réseau neuronal artificiel [Termes IGN] texture d'image Résumé : (auteur) Information of built-up area is essential for various applications, such as sustainable development or urban planning. Built-up area extraction using optical data is challenging due to spectral confusion between built-up and other classes (bare land or river sand, etc.). Here an automated approach has been proposed to generate built-up maps using spectral-textural features and feature selection techniques. Eight Grey-Level Co-Occurrence Matrix based texture features are extracted using Landsat-8 Operational Land Imager bands and combined with multispectral data. The most informative features are selected from combined spectral-textural dataset using feature selection techniques. Further, Support Vector Machine (SVM) classifiers are trained on labelled samples using optimal features and results are compared with Back Propagation-Neural Network (BP-NN) and k-Nearest Neighbour (k-NN). The results show that inclusion of textural features and applying feature selection methods increases the highest overall accuracy of Linear-SVM, RBF-SVM, BP-NN, and k-NN by 9.20%, 9.09%, 8.42%, and 7.39%, respectively. Numéro de notice : A2020-425 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1566406 Date de publication en ligne : 18/03/2019 En ligne : https://doi.org/10.1080/10106049.2019.1566406 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95489 [article]