Descripteur
Documents disponibles dans cette catégorie (2201)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Class-guided building extraction from imagery / D. Scott Lee in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 2 (February /2003)
[article]
Titre : Class-guided building extraction from imagery Type de document : Article/Communication Auteurs : D. Scott Lee, Auteur ; Shan Jie, Auteur ; J. Bethel, Auteur Année de publication : 2003 Article en page(s) : pp 143 - 150 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] classification non dirigée
[Termes IGN] détection de contours
[Termes IGN] détection du bâti
[Termes IGN] extraction automatique
[Termes IGN] image à résolution métrique
[Termes IGN] image Ikonos
[Termes IGN] image panchromatique
[Termes IGN] milieu urbain
[Termes IGN] reconstruction 2D du bâti
[Termes IGN] transformation de HoughRésumé : (Auteur) Recent high resolution satellite images provide a valuable new data source for geospatial information acquisition. This paper addresses building extraction from Ikonos images in urban areas. The proposed approach uses the classification results of Ikonos multispectral images to provide approximate location and shape for candidate building objects. Their fine extraction is then carried out in the corresponding panchromatic image through segmentation and squaring. The ECHO classifier is used for supervised classification while the ISODATA algorithm is used for unsupervised classification and subsequent image segmentation. The classification performance is evaluated using the classification confusion matrix, while the final building extraction results are assessed based on the manually delineated results. A building squaring approach based on the Hough transformation is developed that detects and forms the rectilinear building boundaries. A number of sample results are presented to illustrate the approach and demonstrate its efficiency. It is shown that about 64.4 percent of the buildings can be detected, extracted, and accurately formed through this process. Remaining difficulties are high percentage false alarm errors caused by the misclassification of road and building classes as well as occlusion and shadows that may mislead the extraction process. Numéro de notice : A2003-011 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.2.143 En ligne : https://doi.org/10.14358/PERS.69.2.143 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22309
in Photogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 2 (February /2003) . - pp 143 - 150[article]Semiautomated building extraction based on CSG model-image fitting / Yi-Hsing Tseng in Photogrammetric Engineering & Remote Sensing, PERS, vol 69 n° 2 (February /2003)
[article]
Titre : Semiautomated building extraction based on CSG model-image fitting Type de document : Article/Communication Auteurs : Yi-Hsing Tseng, Auteur ; Shuo Wang, Auteur Année de publication : 2003 Article en page(s) : pp 171 - 180 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] détection de contours
[Termes IGN] détection du bâti
[Termes IGN] extraction semi-automatique
[Termes IGN] géomètrie algorithmique
[Termes IGN] image aérienne
[Termes IGN] méthode des moindres carrés
[Termes IGN] point de vérification
[Termes IGN] primitive géométrique
[Termes IGN] solideRésumé : (Auteur) Building extraction based on preestablished models has been recognized as a promising idea for acquiring 3D data for buildings from aerial images. This paper proposes a novel building extraction method developed from the concept of fitting CSG (Constructive Solid Geometry) primitives to aerial images. To be practicable, this method adopts a semiautomatic procedure, carrying out highlevel tasks (building detection, model selection, and attribution) interactively by the operator and performing optimal modelimage fitting automatically with a leastsquares fitting algorithm. Buildings, represented by CSG models, can be reconstructed part by part after fitting each parameterized CSG primitive to the edge pixels of aerial images. Reconstructed building parts can then be combined using CSG Boolean set operators. Consequently, a building is represented by a CSG tree in which each node links two branches of combined parts. This paper demonstrates ten examples of building extraction from aerial photos taken at a scale of 1:5,000 and scanned at a pixel size of 25 1.um. All of the tests were performed in the prototypal system implemented in a CADbased environment cooperated with a number of specially designed programs. The process time for each primitive is about 20 seconds and the successful rate of model-image fitting was about 90 percent. Evaluated with some check points, the fitting accuracy was about 0,3 m horizontally and 1 m vertically. The test results are encouraging and promote the theory of modelbased building extraction. Numéro de notice : A2003-012 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.69.2.171 En ligne : https://doi.org/10.14358/PERS.69.2.171 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=22310
in Photogrammetric Engineering & Remote Sensing, PERS > vol 69 n° 2 (February /2003) . - pp 171 - 180[article]
contenu dans Traitement du signal et des images, 19e colloque GRETSI 2003, Paris, 8 au 11 septembre 2003, Tome 3. Actes 3 / Patrick Flandrin (2003)
Titre : Analyse et représentation ensembles-échelle d'une image Type de document : Article/Communication Auteurs : Laurent Guigues , Auteur ; Hervé Le Men , Auteur ; Jean-Pierre Cocquerez, Auteur Editeur : Saint-Mandé : Institut Géographique National - IGN (2008-2011) Année de publication : 2003 Conférence : GRETSI 2003, 19th Symposium on Signal and Image Processing 08/09/2003 11/09/2003 Paris France OA proceedings Importance : pp 126 - 129 Note générale : bibliographie Langues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] segmentation d'imageRésumé : (auteur) Cet article propose une approche multi-échelles de la segmentation d’image qui s’appuie sur un principe d’optimisation. Notre objectif est de calculer une séquence complète de partitions monotones qui approxime les minima d’une fonctionnelle dépendant d’un paramètre réel qui se comporte comme un paramètre d’échelle. Pour pouvoir manipuler toutes ces solutions, nous introduisons la représentation ensembles-échelles, qui constitue le pendant orienté régions des représentations scale-space issues du filtrage. Nous aboutissons à un algorithme efficace et sans paramètre, baptisé escalade, qui produit une description ensembles-échelle d’une image dont les coupes correspondent à toute une famille de partitions de finesse variable. Numéro de notice : C2003-038 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésNat DOI : sans En ligne : http://documents.irevues.inist.fr/bitstream/handle/2042/13727/A401.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85968
Titre : Automatic bridge detection in high-resolution satellite images Type de document : Article/Communication Auteurs : Roger Trias-Sanz , Auteur ; Nicolas Lomenie, Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2003 Collection : Lecture notes in Computer Science, ISSN 0302-9743 num. 2626 Conférence : ICVS 2003, 3rd International Conference Computer Vision Systems 01/04/2003 03/04/2003 Graz Autriche Proceedings Springer Importance : pp 172 - 181 Note générale : bibliographie Langues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification par réseau neuronal
[Termes IGN] détection d'objet
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image à haute résolution
[Termes IGN] image panchromatiqueRésumé : (auteur) A set of methodologies and techniques for automatic detection of bridges in pan-chromatic, high-resolution satellite images is presented. These methods rely on (a) radiometric features and neural networks to classify each pixel into several terrain types, and (b) fixed rules to find bridges in this classification. They can be easily extended to other kinds of geographical objects, and integrated with existing techniques using geometric features. The proposed method has been tested in a number of experiments. Numéro de notice : C2003-046 Affiliation des auteurs : MATIS+Ext (1993-2011) Thématique : IMAGERIE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/3-540-36592-3_17 Date de publication en ligne : 14/03/2003 En ligne : https://doi.org/10.1007/3-540-36592-3_17 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101126
Titre : Automation in architectural photogrammetry : Line photogrammetry for the reconstruction from single and multiple images Type de document : Thèse/HDR Auteurs : Frank van den Heuvel, Auteur ; M. George Vosselman, Auteur Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2003 Collection : Netherlands Geodetic Commission Publications on Geodesy, ISSN 0165-1706 num. 54 Importance : 190 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-90-6132-281-8 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie terrestre
[Termes IGN] automatisation
[Termes IGN] caméra numérique
[Termes IGN] détection de contours
[Termes IGN] méthode des moindres carrés
[Termes IGN] métrologie
[Termes IGN] patrimoine culturel
[Termes IGN] photogrammétrie architecturale
[Termes IGN] photogrammétrie métrologique
[Termes IGN] photogrammétrie terrestre
[Termes IGN] reconstruction 3D du bâti
[Termes IGN] traitement d'image
[Termes IGN] vision par ordinateurIndex. décimale : 33.70 Photogrammétrie terrestre Résumé : (Auteur) Architectural photogrammetry has been practised for more than a century with the documentation of cultural heritage as its main objective. Since the introduction of the computer, and later the digital camera, research in photogrammetry aims at automation. This thesis reports on research on automation in architectural photogrammetry for efficient reconstruction of detailed building models from one or more possibly widely separated digital closerange images. This research is on the fringes of photogrammetry and computer vision. It treats topics frequently studied in computer vision in a photogrammetric way and offers new solutions. This approach is characterised by:
- Robust and direct solutions for approximate value computation Statistical testing of consistency of redundant information
- Integral leastsquares adjustment of all information for optimal parameter estimation Quality control by statistical testing and error propagation
- Semiautomatic processing, aiming at a reliable solution with a minimum of user interaction
- Precalibration of the camera's used
- Exploitation of generic knowledge of the object shape Use of image lines as the basic type of observations.
The research is presented in the form of a collection of papers published between 1997 and 2002. Furthermore, the methods described in the papers have also been applied to a reference set of images. The results of these experiments are presented in a separate chapter.
The demand for models of the built environment has increased due to the development of computer applications such as virtual and augmented reality, and computer games. In these applications the required accuracy of the models is not as high as in traditional applications of architectural photogrammetry, such as documentation of cultural heritage. Emphasis in research has shifted towards efficient production of computer models that show a high level of realism. [...]
The processing of images of the CIPA reference data set has demonstrated the capabilities and limitations of the developed methods for camera calibration, image orientation, and object reconstruction. Calibration of the camera was performed semiautomatically with five images of the reference data set. The results were compared with the camera information available from the reference data set. The maximum parameter difference was three times its standard deviation.
The two different methods for image orientation have been applied on four images taken at the corners of the building. The first one is based on the reconstruction of rectangles from a single image. Resulting orientations differ less than 4 degrees from the adjusted values derived in a bundle adjustment. With the second more automated method a correct approximate solution was obtained for all image pairs using two or three manually measured corresponding points. Full automation of relative orientation was not possible for all image pairs due to the repeating structures in the fagades and for imagery where image scale differences were large.
An object model was reconstructed based on a linephotogrammetric bundle adjustment of manual fine measurements in the same four images. Geometric object constraints made the reconstruction of occluded object points possible, improved regularity of the building model and strengthened the geometry of the network.
The research presented in this thesis contributes to the fields of photogrammetry and computer vision. However, emphasis is on photogrammetry where manual or semiautomatic measurement methods prevail and leastsquares adjustment is the tool commonly applied for parameter estimation. The developed linephotogrammetric bundle adjustment model that allows the incorporation of object shape knowledge is the main contribution to this field. Computer vision is generally more focussed on automation, single image processing, and the use of uncalibrated cameras. Therefore, the methods developed for vanishing point detection, used for image orientation and camera calibration, and the methods developed for reconstruction from a single image are primarily in the field of computer vision. In conclusion, this thesis contributes to bringing photogrammetry and computer vision closer together, which will be beneficial to both fields.Numéro de notice : 15053 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère En ligne : https://www.ncgeo.nl/downloads/54VandenHeuvel.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=55055 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 15053-01 33.70 Livre Centre de documentation Photogrammétrie - Lasergrammétrie Disponible PermalinkAutomatische Extraktion von Straßen aus digitalen Luftbildern / Andreas Baumgartner (2003)PermalinkPermalinkBauaufnahme als Modellierungsaufgabe / U. Weferling (2003)PermalinkEléments de géométrie qualitative pour la description structurale d'objets / Pierre Gambarotto (2003)PermalinkL'évaluation de la généralisation / Sylvain Bard in Géomatique expert, n° 22 (01/01/2003)PermalinkExploitation des images RSO multi-temporelles et multi-incidences dans une zone urbaine / A. Boudyaf (2003)PermalinkExtracting 3D free-form surface boundaries of man-made objects from multiple calibrated images : a robust, accurate and high resolving power edgel matching and chaining approach / Franck Jung (2003)PermalinkExtraction de réseaux de rues en milieu urbain à partir d'images satellites à très haute résolution spatiale / Renaud Péteri (2003)PermalinkFabrication de vraies ortho-images et correction des ombres / Didier Boldo in Géomatique expert, n° 22 (01/01/2003)Permalink