Centre de documentation
scientifique

Assessment of very high spatial resolution satellite image segmentations / A.P. Carleer in Photogrammetric Engineering & Remote Sensing, PERS, vol 71 n° 11 (November 2005)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 71 n° 11 (November 2005) . - pp 1285 - 1294 Titre : Assessment of very high spatial resolution satellite image segmentations Type de document : Article/Communication Auteurs : A.P. Carleer, Auteur ; O. Debeir, Auteur ; E. Wolff, Auteur Année de publication : 2005 Article en page(s) : pp 1285 - 1294 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] bruit (théorie du signal) [Termes IGN] contraste de couleurs [Termes IGN] image à résolution métrique [Termes IGN] image Ikonos [Termes IGN] image panchromatique [Termes IGN] segmentation d'image [Termes IGN] texture d'image Résumé : (Auteur) Since 1999, very high spatial resolution satellite data represent the surface of the Earth with more detail. However, information extraction by per pixel multispectral classification techniques proves to be very complex owing to the internal variability increase in land-cover units and to the weakness of spectral resolution. Image segmentation before classification was proposed as an alternative approach, but a large variety of segmentation algorithms were developed during the last 20 years, and a comparison of their implementation on very high spatial resolution images is necessary. In this study, four algorithms from the two main groups of segmentation algorithms (boundary-based and region-based) were evaluated and compared. In order to compare the algorithms, an evaluation of each algorithm was carried out with empirical discrepancy evaluation methods. This evaluation is carried out with a visual segmentation of Ikonos panchromatic images. The results show that the choice of parameters is very important and has a great influence on the segmentation results. The selected boundary-based algorithms are sensitive to the noise or texture. Better results are obtained with region-based algorithms, but a problem with the transition zones between the contrasted objects can be present. Numéro de notice : A2005-425 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.71.11.1285 En ligne : https://doi.org/10.14358/PERS.71.11.1285 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27561 [article]

Textural and contextual land-cover classification using single and multiple classifier systems / O. Debeir in Photogrammetric Engineering & Remote Sensing, PERS, vol 68 n° 6 (June 2002)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 68 n° 6 (June 2002) . - pp 597 - 605 Titre : Textural and contextual land-cover classification using single and multiple classifier systems Type de document : Article/Communication Auteurs : O. Debeir, Auteur ; I. Van Der Steen, Auteur ; P. Latinne, Auteur ; P. Van Ham, Auteur ; E. Wolff, Auteur Année de publication : 2002 Article en page(s) : pp 597 - 605 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] carte d'occupation du sol [Termes IGN] classification non dirigée [Termes IGN] image Landsat-TM [Termes IGN] occupation du sol [Termes IGN] texture d'image Résumé : (Auteur) The objective of this study was to improve the quality of the digital land-cover and land-use classification when using high-resolution (10 to 30 m) remote sensing data. Three classification techniques were compared, which can be divided into two groups : single classifiers (a five-nearest neighbour and the C4.5 decision tree classifier) and multiple classifier systems (BAGFS). Textural and contextual features (roads, hydrology, relief, etc.) were introduced during the classification process. Eleven land-cover categories, in a Belgian varied landscape, were analysed and classified using Landsat Thematic Mapper data. The accuracy assessment increased with the introduction of textural features and contextual data, between 0.60 and 0.82 for the Kappa coefficient. The best kappa value was achieved using numerous textural and contextual features with the multiple classifier system (BAGFs). Numéro de notice : A2002-133 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans En ligne : https://www.researchgate.net/publication/251430961_Textural_and_Contextual_Land- [...] Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22048 [article]