Centre de documentation
scientifique

Impact of topographic normalization on land-cover classification accuracy / S.R. Hale in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 7 (July 2003)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 7 (July 2003) . - pp 785 - 791 Titre : Impact of topographic normalization on land-cover classification accuracy Type de document : Article/Communication Auteurs : S.R. Hale, Auteur ; B.N. Rock, Auteur Année de publication : 2003 Article en page(s) : pp 785 - 791 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification dirigée [Termes IGN] image Landsat-ETM+ [Termes IGN] modèle numérique de terrain [Termes IGN] occupation du sol [Termes IGN] précision de la classification Résumé : (Auteur) For pixel classifying algorithms to perform effectively, effects of topographic relief must be minimized or removed. In areas of high topographic relief, problems arise when spectral variations in ground target illumination and radiance, owing to differences in incident radiation and nonLambertian reflectance behavior, respectively, cause identical landcover types to reflect differently, or different cover types to reflect similarly. A Landsat Enhanced Thematic Mapper image was processed using band ratios, the Minnaert Correction, aspect partitioning, and combinations of these treatments to generate independent landcover classifications. Treatment classification accuracy was determined using error matrices and the Kappa statistic. Producer's and User's Accuracies were examined to determine if treatments were superior at producing greater class specific accuracy. None of the treatments produced a significantly more accurate classification; however, assessment of classspecific accuracies indicated accuracy gains using aspect partitioning alone or in combination with the Minnaert Correction. Numéro de notice : A2003-154 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.7.785 En ligne : https://doi.org/10.14358/PERS.69.7.785 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22450 [article]