Centre de documentation
scientifique

Knowledge based system for the automatic extraction of road intersections from aerial images / Nicolas Boichis (2000)  

Public Titre : Knowledge based system for the automatic extraction of road intersections from aerial images Type de document : Article/Communication Auteurs : Nicolas Boichis , Auteur ; Jean-Marc Viglino , Auteur ; Jean-Pierre Cocquerez, Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2000 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 33-B3 Conférence : ISPRS 2000, 19th ISPRS Congress Technical Commission 3, Systems for Data Processing, Analysis and Representation 16/07/2000 23/07/2000 Amsterdam Pays-Bas OA Proceedings archives Importance : pp 27 - 34 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] extraction automatique [Termes IGN] extraction du réseau routier [Termes IGN] image aérienne [Termes IGN] reconstruction de route [Termes IGN] transformation de Hough Résumé : (auteur) A National Geographic Agency is a mapmaker and a database producer. The current manual stereoplotting of cartographic objects is time consuming. To reduce this production cost, we are working on problems related to the photogrammetric data capture automation. Based on our experience of road network systems and on our cartographic requirements, we consider road intersection extraction as a specific problem. In this article, the complete architecture of our system is presented in three steps: a specific intersection model description, the interpretation strategy and a decision-making process. We detail the simple intersection and roundabout process and evaluate the system behaviour on a large set of data. © 2000 International Society for Photogrammetry and Remote Sensing. Numéro de notice : C2000-020 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.isprs.org/proceedings/XXXIII/congress/part3/27_XXXIII-part3s.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102890

Surface reconstruction in urban areas from multiple views of aerial digital frame cameras / Nicolas Paparoditis (2000)  

Public Titre : Surface reconstruction in urban areas from multiple views of aerial digital frame cameras Type de document : Article/Communication Auteurs : Nicolas Paparoditis , Auteur ; Christian Thom , Auteur ; Hassan Jibrini , Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2000 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 33-B3 Conférence : ISPRS 2000, 19th ISPRS Congress Technical Commission 3, Systems for Data Processing, Analysis and Representation 16/07/2000 23/07/2000 Amsterdam Pays-Bas OA Proceedings archives Importance : pp 43 - 50 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] corrélation d'images [Termes IGN] couple stéréoscopique [Termes IGN] image aérienne [Termes IGN] reconstruction d'objet [Termes IGN] zone urbaine Résumé : (auteur) This paper describes an original approach and strategy for the automatic surface reconstruction of urban areas from digital aerial multiple views (across track as well as along track). The general reconstruction approach is based on a concept of multi-image matching guided from object space which provides the DSM and the corresponding orthoimage at the same time. The general idea is to match all the images at the same time with a multi-image correlation function instead of merging all elementary DSM computed on all stereopairs. This multi-image correlation function has very interesting properties, we can use very small templates (windows) in the image matching process, the correlation scores give a real reliability indicator of the matches and the false matches can be filtered with a deterministic threshold. All discarded areas are filled with a hierarchical matching strategy aiming at building the surface step by step. Numéro de notice : C2000-014 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.isprs.org/proceedings/Xxxiii/congress/part3/43_XXXIII-part3s.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102891