Détail de l'auteur
Auteur H.M. Martine |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Application of snakes and dynamic programming optimisation technique in modeling of buildings in informal settlement areas / H. Ruther in ISPRS Journal of photogrammetry and remote sensing, vol 56 n° 4 (July - August 2002)
[article]
Titre : Application of snakes and dynamic programming optimisation technique in modeling of buildings in informal settlement areas Type de document : Article/Communication Auteurs : H. Ruther, Auteur ; H.M. Martine, Auteur ; E.G. Mtalo, Auteur Année de publication : 2002 Article en page(s) : pp 269 - 282 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] contour
[Termes IGN] détection du bâti
[Termes IGN] modèle mathématique
[Termes IGN] modèle numérique de surface
[Termes IGN] orthophotographie
[Termes IGN] photographie aérienne
[Termes IGN] processeurRésumé : (Auteur) This paper presents a novel approach to semiautomatic building extraction in informal settlement areas from aerial photographs. The proposed approach uses a strategy of delineating buildings by optimising their approximate building contour position. Approximate building contours are derived automatically by locating elevation blobs in digital surface models. Building extraction is then effected by means of the snakes algorithm and the dynamic programming optimisation technique. With dynamic programming, the building contour optimisation problem is realized through a discrete multistage process and solved by the "timedelayed" algorithm, as developed in this work. The proposed building extraction approach is a semiautomatic process, with usercontrolled operations linking fully automated subprocesses. Inputs into the proposed building extraction system are orthoimages and digital surface models, the latter being generated through image matching techniques. Buildings are modeled as "lumps" or elevation blobs in digital surface models, which are derived by altimetric thresholding of digital surface models. Initial windows for building extraction are provided by projecting the elevation blobs centre points onto an orthoimage. In the next step, approximate building contours are extracted from the orthoimage by region growing constrained by edges. Approximate building contours thus derived are inputs into the dynamic programming optimisation process in which final building contours are established. The proposed system is tested on two study areas: Marconi Beam in Cape Town, South Africa, and Manzese in Dar es Salaam, Tanzania. Sixty percent of buildings in the study areas have been extracted and verified and it is concluded that the proposed approach contributes meaningfully to the extraction of buildings in moderately complex and crowded informal settlement areas. Copyright ISPRS Numéro de notice : A2002-169 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/S0924-2716(02)00062-X En ligne : https://doi.org/10.1016/S0924-2716(02)00062-X Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22084
in ISPRS Journal of photogrammetry and remote sensing > vol 56 n° 4 (July - August 2002) . - pp 269 - 282[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-02021 SL Revue Centre de documentation Revues en salle Disponible