Détail de l'autorité
|
PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision 20/09/2006 22/09/2006 Bonn Allemagne OA ISPRS Archives
nom du congrès :
PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision
début du congrès :
20/09/2006
fin du congrès :
22/09/2006
ville du congrès :
Bonn
pays du congrès :
Allemagne
site des actes du congrès :
|
Documents disponibles (4)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Titre : 3D road mark reconstruction from multiple calibrated aerial images Type de document : Article/Communication Auteurs : Olivier Tournaire , Auteur ; Nicolas Paparoditis
Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2006 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 36-3 Conférence : PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision 20/09/2006 22/09/2006 Bonn Allemagne OA ISPRS Archives Importance : pp 73 - 78 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement de formes
[Termes IGN] corrélation à l'aide de traits caractéristiques
[Termes IGN] détection d'objet
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image aérienne
[Termes IGN] reconstruction 3D
[Termes IGN] signalisation routièreRésumé : (auteur) A method for accurate 3D reconstruction of road features from multiple calibrated aerial images of urban areas is proposed in this paper. We here focus on road-marks and in particular on zebra-crossings and discontinuous road-marks separating circulation lanes. The approaches used here are generic and based on a-priori external knowledge and thus constrain the extraction of image features. As we will explain, two strategies are adopted depending on the object size. For zebra-crossings, we first build 3D segments representing stripes’ borders by 2D segments matching. For discontinuous lanes, we build a graph describing the network in each image and then match nodes in order to obtain 3D position of stripes’ centers. This provides in both cases an initial solution in 3D space. Using geometric and radiometric modeling to obtain a set of plausible models, e then look for an optimal solution. The last step yields us to choose the best one in adequacy with images data. A correlation based energy and template matching strategy achieve this in a hierarchical frame. The algorithm is finally evaluated with ground control points surveyed with a millimetric precision. Numéro de notice : C2006-010 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : https://www.isprs.org/proceedings/XXXVI/part3/singlepapers/P_09.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86190 Documents numériques
en open access
3D road mark reconstruction - pdf éditeurAdobe Acrobat PDFAutomatic building reconstruction from a digital elevation model and cadastral data : an operational approach / Mélanie Durupt (2006)
Titre : Automatic building reconstruction from a digital elevation model and cadastral data : an operational approach Type de document : Article/Communication Auteurs : Mélanie Durupt, Auteur ; Franck Taillandier Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2006 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 36-3 Conférence : PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision 20/09/2006 22/09/2006 Bonn Allemagne OA ISPRS Archives Importance : pp 142 - 147 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] données cadastrales
[Termes IGN] méthode robuste
[Termes IGN] modèle numérique de surface
[Termes IGN] modélisation 3D
[Termes IGN] primitive géométrique
[Termes IGN] Ransac (algorithme)
[Termes IGN] reconstruction 3D du bâti
[Termes IGN] toit
[Termes IGN] zone urbaine denseRésumé : (auteur) In this paper, we tackle the problem of automatic building reconstruction using digital elevation model and cadastral data. We aim at massive production of 3D urban models and present thus an algorithm, that is an adaptation of a more general and semi-automatic strategy to an operational context where robustness is essential. We present two approaches relying on two different techniques for non-vertical planes extraction using constraints inferred by cadastral limits. The first one consists in inferring planar primitives by estimating only two parameters for each building: the height of gutter and the slope of roofs. The other idea is to extract planar primitives directly from the cadastral limits and from the DEM, using a robust RANSAC estimation algorithm. The results of an evaluation carried out on 620 buildings on a dense urban centre are promising and enables to compare both approaches. Numéro de notice : C2006-013 Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : http://www.isprs.org/proceedings/XXXVI/part3/singlepapers/O_14.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86193 Documents numériques
en open access
Automatic building reconstruction - pdf éditeurAdobe Acrobat PDF
Titre : A robust algorithm for estimating digital terrain models from digital surface models in dense urban areas Type de document : Article/Communication Auteurs : Nicolas Champion Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2006 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 36-3 Conférence : PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision 20/09/2006 22/09/2006 Bonn Allemagne OA ISPRS Archives Importance : pp 111 - 116 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] méthode de réduction d'énergie
[Termes IGN] méthode robuste
[Termes IGN] modèle numérique de surface
[Termes IGN] modèle numérique de sursol
[Termes IGN] modèle numérique de terrain
[Termes IGN] zone urbaine denseRésumé : (auteur) This paper describes an algorithm in order to derive DTMs (Digital Terrain Models) from correlation DSMs (Digital Surface Models) and above-ground (buildings and vegetation) masks in dense urban areas. Among all the methods found in literature, the Elastic Grid method shows a good capability to reconstruct the topographic surface. This method consists in interpolating height values under above-ground masks by minimizing an energy. Nevertheless, this method is ill-adapted to outliers in input data (above-ground points out of above-ground masks). The main contribution of our study is the use of a method based on robust statistics in order to reject outliers from calculation so that the nal DTM ts the true topographic surface for the best. For that purpose, the initial Elastic Grid has been noticeably changed. The results of the new method for 2 test sites with a pixel ground size of 20 cm (the rst one is relatively at and the second one is hilly) show the quality of the nal DTM and the robustness of our method. Tests have been carried out with lower resolution DSMs and without any mask and show the feasability of extending the method to a more general context. Numéro de notice : C2006-011 Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : http://www.isprs.org/proceedings/XXXVI/part3/singlepapers/O_09.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86191
Titre : A supervised classification approach towards quality self-diagnosis of 3D building models using digital aerial imagery Type de document : Article/Communication Auteurs : Laurence Boudet Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2006 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 36-3 Conférence : PCV 2006, ISPRS - Commission 3 symposium Photogrammetric Computer vision 20/09/2006 22/09/2006 Bonn Allemagne OA ISPRS Archives Importance : pp 136 - 141 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] bati
[Termes IGN] classification dirigée
[Termes IGN] image aérienne
[Termes IGN] méthode robuste
[Termes IGN] modélisation 3D
[Termes IGN] toit
[Termes IGN] zone urbaine denseRésumé : (auteur) In the context of 3D building model production or updating, the models have to be manually checked one by one by a human operator in order to ensure their quality. In this paper, we investigate a new approach to perform a quality self-diagnosis of building models in dense urban areas from high resolution aerial images. Hence, we aim at reliably identifying roof facets that do not comply with quality specifications. The self-diagnosis process will highlight potential incorrect facets for their inspection by a human operator. A set of calibrated aerial images enable us to collect positive or negative evidences of roof facet existence and consistency. A particular attention has been paid to the definition of a set of low-level, complementary, robust and consistent image processing measures. Four quality classes have been defined and are used to classify roof facet quality. A supervised classifier and robust decision rules are then applied to perform an effective self-diagnosis according to the traffic light paradigm. Finally, the work in progress leads to a promising quantitative and qualitative evaluation in the context of dense urban areas. Numéro de notice : C2006-012 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE/POSITIONNEMENT Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : http://www.isprs.org/proceedings/XXXVI/part3/singlepapers/O_13.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86192 Documents numériques
en open access
A supervised classification approach - pdf éditeurAdobe Acrobat PDF
