Centre de documentation
scientifique

Strategies for integrating information from multiple resolutions into land-use/land-cover classification routines / D.M. Chen in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 11 (November 2003)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 11 (November 2003) . - pp 1279 - 1287 Titre : Strategies for integrating information from multiple resolutions into land-use/land-cover classification routines Type de document : Article/Communication Auteurs : D.M. Chen, Auteur ; D. Stow, Auteur Année de publication : 2003 Article en page(s) : pp 1279 - 1287 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] banlieue [Termes IGN] classification barycentrique [Termes IGN] classification multidimensionnelle [Termes IGN] image à très haute résolution [Termes IGN] intégration de données [Termes IGN] métropole [Termes IGN] milieu urbain [Termes IGN] occupation du sol [Termes IGN] précision de la classification [Termes IGN] résolution multiple [Termes IGN] San Diego Résumé : (Auteur) With the development of new remote sensing systems, very high spatial and spectral resolution images now provide a source for detailed and continuous sampling of the Earth's surface from local to regional scales. This paper presents three strategies for selecting and integrating information from different spatial resolutions into classification routines. One strategy is to combine layers of image varying resolution. A second strategy involves comparing the a posteriori probabilities of each class at different resolutions. Another strategy is based on a top-down approach stating with the coarsest resolution. The multiresolution strategies are tested using simulated multiresolution images for a portion of the rural-urban fringe of the SanDiego Metropolitan Area. The classification accuracy obtained from using three multiple strategies was greater when compared with that from a conventional single-resolution approach. Among the three strategies, the top-down approach resulted in the highest classification accuracy with a Kappa value of 0,648 compared to a Kappa of 0,566 for the conventional classifier. Numéro de notice : A2003-294 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.11.1279 En ligne : https://doi.org/10.14358/PERS.69.11.1279 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22589 [article]

Scale and texture in digital image classification / J.S. Ferro in Photogrammetric Engineering & Remote Sensing, PERS, vol 68 n° 1 (January 2002)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 68 n° 1 (January 2002) . - pp 51 - 63 Titre : Scale and texture in digital image classification Type de document : Article/Communication Auteurs : J.S. Ferro, Auteur ; T.A. Warner, Auteur Année de publication : 2002 Article en page(s) : pp 51 - 63 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] accentuation de contours [Termes IGN] analyse d'image numérique [Termes IGN] classification dirigée [Termes IGN] classification multidimensionnelle [Termes IGN] classification non dirigée [Termes IGN] classification par maximum de vraisemblance [Termes IGN] image ADAR [Termes IGN] image multibande [Termes IGN] incertitude des données [Termes IGN] qualité d'image [Termes IGN] superposition d'images Résumé : (Auteur) Classification errors using texture are most likely associated with class edges, but investigators often avoid edges when evaluating textures for classification. The large window needed to produce a stable texture measure produce large edge effects. Small windows minimize edge effects, but often do not provide stable texture measures. Simulated data experiments showed that class separability increased when texture was used in addition to spectral information. Texture separability improved with larger windows. This improvement was over estimated when pixels were chosen away from class edges. Airborne Data Acquisition and Registration (ADAR) data showed that separability of class interiors improved with the addition of texture, but that, for the whole class, separability fell. Maximum-likelihood classification of the ADAR data demonstrated the effect of edges and multiple scales in reducing the accuracy of classification incorporating texture. Numéro de notice : A2002-010 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans En ligne : https://www.asprs.org/wp-content/uploads/pers/2002journal/january/2002_jan_51-63 [...] Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21927 [article]