Centre de documentation
scientifique

Roof boundary extraction using multiple images / Ahmed F. Elaksher in Photogrammetric record, vol 18 n° 101 (March - May 2003)  

Public [article]  inPhotogrammetric record > vol 18 n° 101 (March - May 2003) . - pp 27 - 40 Titre : Roof boundary extraction using multiple images Type de document : Article/Communication Auteurs : Ahmed F. Elaksher, Auteur ; J.S. Bethel, Auteur ; E. Mikhail, Auteur Année de publication : 2003 Article en page(s) : pp 27 - 40 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] appariement géométrique [Termes IGN] classification dirigée [Termes IGN] cohérence géométrique [Termes IGN] contour [Termes IGN] courbe épipolaire [Termes IGN] détection de contours [Termes IGN] exhaustivité des données [Termes IGN] image aérienne [Termes IGN] méthode robuste [Termes IGN] milieu urbain [Termes IGN] photo-interprétation assistée par ordinateur [Termes IGN] polygone [Termes IGN] reconstruction 3D du bâti [Termes IGN] segmentation d'image Résumé : (Auteur) Urban area building extraction is one of the most challenging problems in photogrammetry. Wellextracted buildings are needed for a variety of applications, such as cartography, building GIS databases for cities, and urban planning. This paper presents a new technique to extract 3D building wireframes using a robust multiimage linematching algorithm. Although one pair of images is adequate to find the 3D position of two visibly corresponding image, features, it is not sufficient to solve the general building extraction problem due to obscured parts in the building. Four images are used in this research to extract the building wireframes. First the images are segmented into regions. Regions are then classified into roof regions and nonroof regions based on their size, shape, and intensity values. The roof region boundary pixels are located and used to find the region perimeters. Region correspondence is solved in a pairwise mode over all images using the epipolar constraint, region size, region shape, and region intensity values. Image lines within the corresponding regions are matched over all images simultaneously by first creating a plane for each region line. Planes are then intersected simultaneously and geometric consistency is used to determine acceptance or rejection. Results with high overlap and sidelap aerial images are presented and evaluated. The results show the completeness and accuracy that this method can provide for extracting complex urban buildings. The average coordinate accuracy is about 08 m using 1:4000 scale aerial photographs scanned at 30 um Six buildings were examined; the line detection rate is 98%. Numéro de notice : A2003-091 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/0031-868X.t01-1-00003 En ligne : https://doi.org/10.1111/0031-868X.t01-1-00003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22387 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
106-03011	RAB	Revue	Centre de documentation	En réserve L003	Disponible