Centre de documentation
scientifique

Textural classification of remotely sensed images using multiresolution techniques / Rizwan Ahmed Ansari in Geocarto international, vol 35 n° 14 ([15/10/2020])  

Public [article]  inGeocarto international > vol 35 n° 14 [15/10/2020] . - pp 1580 - 1602 Titre : Textural classification of remotely sensed images using multiresolution techniques Type de document : Article/Communication Auteurs : Rizwan Ahmed Ansari, Auteur ; Krishna Mohan Buddhiraju, Auteur ; Avik Bhattacharya, Auteur Année de publication : 2020 Article en page(s) : pp 1580 - 1602 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] analyse multirésolution [Termes IGN] analyse texturale [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection de contours [Termes IGN] distance euclidienne [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] image RVB [Termes IGN] image satellite [Termes IGN] texture d'image [Termes IGN] transformation en ondelettes Résumé : (auteur) Multiresolution analysis (MRA) methods have been successfully used in texture analysis. Texture analysis is widely discussed in literature, but most of the methods which do not employ multiresolution strategy cannot exploit the fact that texture occurs at various spatial scales. This paper proposes a methodology to identify different classes in satellite images using texture features from newly developed multiresolution methods. The proposed method is tested on remotely sensed optical images and a Pauli RGB decomposed version of synthetic aperture radar image. The textural information is extracted at various scales and in different directions from curvelet and contourlet transforms. The results are compared with wavelet-based features. Accuracy assessment is performed and comparative analysis is carried out using minimum distance to mean, support vector machine and random forest classifiers. It is found that the proposed method shows better class discriminating power and classification capability as compared to existing wavelet-based method. Numéro de notice : A2020-618 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1581263 Date de publication en ligne : 15/04/2019 En ligne : https://doi.org/10.1080/10106049.2019.1581263 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95994 [article]