Descripteur
Documents disponibles dans cette catégorie (1887)
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
Titre : Knowledge based building facade reconstruction from laser point clouds and images Type de document : Thèse/HDR Auteurs : Shi Pu, Auteur Editeur : Delft : Netherlands Geodetic Commission NGC Année de publication : 2010 Collection : Netherlands Geodetic Commission Publications on Geodesy, ISSN 0165-1706 num. 75 Importance : 119 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-90-6132-319-3 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] B-Spline
[Termes IGN] base de connaissances
[Termes IGN] données laser
[Termes IGN] données localisées 3D
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] façade
[Termes IGN] Pays-Bas
[Termes IGN] reconstruction 3D du bâti
[Termes IGN] semis de points
[Termes IGN] système à base de connaissances
[Termes IGN] télémétrie laser terrestre
[Termes IGN] texturageIndex. décimale : 33.80 Lasergrammétrie Résumé : (Auteur) Various applications demand realistic 3D city models. For urban planning, analyzing in a 3D virtual reality world is much more efficient than imaging the 2D information on maps. For public security, accurate 3D building models are indispensable to make strategies during emergency situations. Navigation systems and virtual tourism also benefit from realistic city models. Manual creation of city models is undoubtedly a rather time consuming and expensive procedure. On one hand, images are for long the only data source for geometric modelling, while recovering of 3D geometries is not straightforward from 2D images. On the other hand, there are enormous amounts of objects (for example buildings) to be reconstructed, and their structures and shapes show a great variety. There is a lack of automated approaches to understand the building structures captured by data. The rapid development of cities even adds to the cost of manual city model updating. In recent years, laser scanning has been proven a successful technology for reverse engineering. The terrestrial laser point clouds are especially useful for documenting building facades. With the considerable high point density and the explicit 3D coordinates of terrestrial laser point clouds, it is possible to recover both large structures and fine details on building facades. The latest developments of mobile laser scanning technology also make it more cost-effective to take large-scale laser scanning over urban areas.
This PhD research aims at reconstructing photorealistic building facade models from terrestrial laser point clouds and close range images, with a largely automatic process. A knowledge base about building facade structures is established first, where several important building features (wall, door, protrusion, etc.) are defined and described with their geometric properties and spatial relationships. Then constraints for feature extraction are derived from the knowledge base. After a laser point cloud is segmented into planar segments by surface a growing segmentation algorithm, each segment is compared with the feature constraints to determine the most likely feature type for each segment. The feature extraction method works fine for all facade features except for windows, because there are usually insufficient laser points reflected from window glass. Instead, windows are reconstructed from the holes on the wall features. Then outline polygons or B-spline surfaces are fit to all feature segments, and the parts without laser points are hypothesized according to knowledge. A complete polyhedron model is combined from both fitted and hypothesized outlines.
Since laser data contains no colour information, the building models reconstructed from only laser data contain only geometric information such as vertices and edges. To obtain photorealistic results, textures must be mapped from images to the geometric models. The fusing of laser points and image requires accurate alignment between laser space and image space, which is accomplished after a semi-automated process. Because of the limitations of modelling methods, the geometry model reconstructed from laser points may contain many errors which would cause poor texturing effect. Therefore, significant line features extracted from images are compared with the initial model's edges, and necessary refinements are made to correct the model errors, or at least make the model edges consistent with the image lines. Finally, in the texturing stage, the texture of each model face is selected automatically from multiple images to ensure the optimal visibility. Texture errors caused by occlusions in front of a wall are also removed by analyzing the locations of the wall, the occlusions and the camera position.
Experiments with three data sets show that building reconstruction are considerably accelerated by the presented methods. Our approach is more than 10 times faster than the traditional approach when reconstructing the same buildings, and the models by our approach contain more fine details such as doors and windows. The reconstruction of wall facades and roofs are fully automatic, while some manual interactions (48 percent of the total reconstruction time) are still required for editing the fine details. It should also be faster to make global statistics (number of floors, number of entrances, etc.) and modifications (deriving models with a lower level of detail, applying pre-defined textures, etc.) later on to our models, since different model parts have been associated with the semantic labels. While the reconstruction efficiency is improved by our approach, the visualization effects of our models are also comparable to the models by the traditional approach. The future work will focus on improving the knowledge base and developing a fully automated camera parameter estimation procedure. The completeness and adaptability of the knowledge base will be especially important for the further automation of our reconstruction approach.Note de contenu : 1 Introduction
1.1 State-of-the-art of terrestrial laser scanning
1.2 Related works
1.2.1 Overview
1.2.2 Frueh et al. 2005
1.2.3 Cornelis et al. 2008
1.2.4 Ripperda2008
1.2.5 Becker 2009
1.3 Method overview
1.4 Structure of the thesis
2 Knowledge engineering and reasoning
2.1 Knowledge engineering
2.1.1 Assembling the knowledge
2.1.2 Decide on a vocabulary
2.1.3 Encode general knowledge
2.1.4 The hierarchical composition
2.2 Reasoning with the knowledge
2.3 Managing uncertainty
2.3.1 Describing the uncertainty
2.3.2 Making expected decisions
2.4 Concluding remarks
3 Feature extraction
3.1 Preprocessing
3.1.1 Spatial indexing
3.1.2 Extracting points of interest
3.2 Extraction of geometric features
3.2.1 Flat surfaces
3.2.2 Curved surfaces
3.3 Extraction of semantic features
3.3.1 Solid features extraction
3.3.2 Hole-based window extraction
3.4 Discussion
4 Geometric reconstruction
4.1 Polygon fitting
4.1.1 Least squares fitting
4.1.2 Convex polygon and concave polygon fitting
4.1.3 Minimum bounding rectangle fitting
4.2 B-spline surface fitting
4.2.1 The B-spline curve and surface
4.2.2 B-spline surface approximation
4.3 Hypotheses for parts without laser data
4.4 Results and Discussion
4.4.1 Flat surfaces
4.4.2 Curved surfaces
5 Model refinement with imagery
5.1 Method overview
5.2 Registration
5.2.1 Perspective Conversion
5.2.2 Spatial Resection
5.2.3 Relative Orientation
5.3 The model refinement
5.3.1 Extraction of Significant Lines from Images
5.3.2 Matching Model Edges with Image Lines
5.3.3 Refinement Strategy
5.4 Test cases
5.4.1 The restaurant house
5.4.2 The town hall
5.4.3 The wall with high windows
5.4.4 Summary
5.5 Conclusions and outlook
6 Texture mapping
6.1 Selecting texture images
6.1.1 Optimal image selection
6.1.2 Occlusion removal
6.2 Calculating texture coordinates
6.3 Results and discussion
6.3.1 The three joined houses
6.3.2 The house with a balcony
6.3.3 The curved walls
6.3.4 Discussion
7 Method evaluation
7.1 The reconstruction approaches
7.1.1 Our approach
7.1.2 The traditional approach
7.2 The Vlaardingen case
7.3 The Enschede case
7.4 The Esslingen case
7.5 Conclusions
8 Conclusions and recommendations
8.1 Conclusions
8.2 RecommendationsNuméro de notice : 10834 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : PhD thesis : En ligne : https://www.ncgeo.nl/index.php/en/publicatiesgb/publications-on-geodesy/item/257 [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=62511 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 10834-01 33.80 Livre Centre de documentation Photogrammétrie - Lasergrammétrie Disponible Matching terrestrial images captured by a nomad system to images of a reference database for pose estimation purpose / Arnaud Le Bris (2010)
contenu dans Photogrammetric computer vision and image analysis, ISPRS Commission 3 symposium, Saint-Mandé, 1-3 septembre 2010, volume 1. Papers accepted on the basis of peer-reviewed full manuscripts / Nicolas Paparoditis (2010)
Titre : Matching terrestrial images captured by a nomad system to images of a reference database for pose estimation purpose Type de document : Article/Communication Auteurs : Arnaud Le Bris , Auteur ; Nicolas Paparoditis , Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2010 Conférence : PCV 2010, ISPRS - Commission 3 symposium Photogrammetric computer vision and image analysis 01/09/2010 03/09/2010 Saint-Mandé France ISPRS OA Archives Importance : pp 133 - 137 Note générale : Bibliographie
Paper accepted on the basis of peer-reviewed full manuscriptLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s)
[Termes IGN] géoréférencement direct
[Termes IGN] image panoramique
[Termes IGN] intégration de données
[Termes IGN] points homologues
[Termes IGN] SIFT (algorithme)
[Termes IGN] Stéréopolis
[Termes IGN] système de numérisation mobileRésumé : (Auteur) Mobile mapping systems have been developed to achieve a fast automated acquisition of huge quantity of georeferenced terrestrial images in urban cities. Stereopolis is such a system making it possible to capture panoramic groups of images. These georeferenced photos are then stored in urban images street scale reference databases. The issue investigated in this paper is the problem of tie points extraction between new images captured with an approximate georeferencement by a ”nomad system” and images from the reference database in order to estimate a precise pose for these new images. Because of several difficulties (diachronism, viewpoint change, scale variation, repetitive patterns) extracting enough correct well distributed tie points is difficult and directly extracted and matched SIFT keypoints from original images are most of the time not sufficient. Nevertheless, results can be improved using ortho-rectified images on the facade plane instead of original images. Rectification parameters (3D rotation) are obtained from the coordinates of vanishing points corresponding to the two main directions of the facade. These points can indeed be extracted from linear features of the facade on the images. However, many point matches remain false and difficult to detect using only their image coordinates. The use of both image coordinates and scale and orientation associated to the matched SIFT keypoints makes it possible to detect outliers and to obtain an approximate similitude model between the two ortho-images. A more accurate model can then be computed from correct tie points. Numéro de notice : C2010-003 Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Communication DOI : sans En ligne : https://www.isprs.org/proceedings/XXXVIII/part3/a/pdf/133_XXXVIII-part3A.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=65058 Modélisation de façades par analyse conjointe d'images terrestres et de données laser / Antoine Pinte (2010)
Titre : Modélisation de façades par analyse conjointe d'images terrestres et de données laser Type de document : Mémoire Auteurs : Antoine Pinte, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2010 Importance : 92 p. Format : 21 x 30 cm Note générale : Bibliographie
Rapport de Travail de Fin d’Etude, Cycle des Ingénieurs diplômés de l’ENSG 3ème année (IT3), Mastère PPMD, option PhotogrammétrieLangues : Français (fre) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] analyse texturale
[Termes IGN] données lidar
[Termes IGN] façade
[Termes IGN] fenêtre (bâtiment)
[Termes IGN] image terrestre
[Termes IGN] modèle 3D de l'espace urbain
[Termes IGN] modélisation 3D
[Termes IGN] morphologie mathématique
[Termes IGN] orthoimage
[Termes IGN] segmentation d'image
[Termes IGN] système de numérisation mobileIndex. décimale : MPPMD Mémoires du mastère spécialisé Photogrammétrie, Positionnement et Mesures de Déformation Résumé : (Auteur) Afin d'affiner les modèles 3D urbains, Siradel est intéressée par une méthode de modélisation de façades. L'objectif de ce stage de fin d'études est de développer une méthode automatique de recadrage de façade et de détection de fenêtres, portes, balcons et formes arrondies, à partir de données issues d'un véhicule d'acquisition terrestre. Un état de l'art montre que de nombreuses solutions existent pour modéliser les façades à partir de données photographiques seules ou avec des données laser en complément. L'algorithme développé est basé principalement sur une méthode de projections d'images de gradient. Des traitements morphologiques, la transformée de Hough ou encore le détecteur de Harris permettent d'améliorer la robustesse de l'algorithme. Des données laser (nuages de points laser projetés sur la façade) sont utilisées pour affiner la modélisation. La méthode mise en place se décompose en quatre étapes : recadrage de la façade, découpage en tuiles, détection de fenêtres et amélioration de la modélisation. Des tests permettent d'évaluer quantitativement les différentes étapes de l'algorithme d'un point de vue classification et précision. Note de contenu : 1) Analyse de l'existant
A. Présentation de la société
B. Données disponibles.
1. Ortho-photographies des façades
2. Imagettes laser
3. Modèle 3D
C. Etat de l'art
1. Modélisation à partir d'images terrestres
2. Modélisation à partir d'images terrestres et de points laser
2) Description de l'algorithme
A. Présentation de la méthode
1. Choix adoptés
2. Présentation fonctionnelle
3. Présentation technique
B. Recadrage de la façade
1. Limites latérales
2. Limite supérieure
3. Limite inférieure
C. Découpage en tuiles
1. Découpage en colonnes
2. Découpage en lignes (étages)
3. Cas du rez-de-chaussée
D. Détection des fenêtres
1. Les étages
2. Le rez-de-chaussée
E. Amélioration du modèle
1. Détection des bords arrondis des fenêtres
2. Détection des balcons
3. Détection des portes
3) Résultats
A. Présentation
1. Paramétrage
2. Echantillon de test
3. Méthodes d'évaluation
B. Classification
C. Précision
1. Redécoupage de la façade
2. Découpage en tuiles
3. Détection de fenêtres
4. Autres fonctionnalités
D. Résultats finaux
ConclusionNuméro de notice : 10900 Affiliation des auteurs : IGN (1940-2011) Thématique : IMAGERIE Nature : Mémoire masters divers Organisme de stage : Siradel Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=49404 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 10900-01 MPPMD Livre Centre de documentation Travaux d'élèves Disponible Documents numériques
peut être téléchargé
10900_mem_modelisation_facades_pinte.pdfAdobe Acrobat PDF Object-based image analysis / E.A. Addink in GIM international, vol 24 n° 1 (January 2010)
[article]
Titre : Object-based image analysis Type de document : Article/Communication Auteurs : E.A. Addink, Auteur ; F. Can Coillie, Auteur Année de publication : 2010 Article en page(s) : pp 12 - 15 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse d'image numérique
[Termes IGN] classification automatique
[Termes IGN] reconnaissance de formesRésumé : (Auteur) Looking at a satellite image one sees squares (i.e. pixels) representing landscape, although the actual shapes of roads, rivers, lakes, forest and nature reserve might more accurately be represented by lines, circles or irregularly shaped polygons. Over recent years earth observation has become an important data source, while image interpretation has been limited to squares the features of which are spectral variables : colours and invisible radiance determined by reflection-absorption behaviour of landscape objects, as observed by satellite sensors. Copyright Reed Business Numéro de notice : A2009-600 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30131
in GIM international > vol 24 n° 1 (January 2010) . - pp 12 - 15[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 061-2010011 RAB Revue Centre de documentation En réserve L003 Disponible Photogrammetric computer vision and image analysis, ISPRS Commission 3 symposium, Saint-Mandé, 1-3 septembre 2010, volume 1. Papers accepted on the basis of peer-reviewed full manuscripts / Nicolas Paparoditis (2010)
Titre de série : Photogrammetric computer vision and image analysis, ISPRS Commission 3 symposium, Saint-Mandé, 1-3 septembre 2010, volume 1 Titre : Papers accepted on the basis of peer-reviewed full manuscripts Type de document : Actes de congrès Auteurs : Nicolas Paparoditis , Éditeur scientifique ; Marc Pierrot-Deseilligny , Éditeur scientifique ; Clément Mallet , Éditeur scientifique ; Olivier Tournaire , Éditeur scientifique Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2010 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 38-3A Conférence : PCV 2010, ISPRS - Commission 3 symposium Photogrammetric computer vision and image analysis 01/09/2010 03/09/2010 Saint-Mandé France ISPRS OA Archives Importance : 308 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique
[Termes IGN] analyse d'image numérique
[Termes IGN] caméra numérique
[Termes IGN] données lidar
[Termes IGN] étalonnage de capteur (imagerie)
[Termes IGN] extraction de données
[Termes IGN] image aérienne
[Termes IGN] image oblique
[Termes IGN] système de numérisation mobile
[Termes IGN] visualisation 3DNote de contenu : voir site Numéro de notice : 15528A Affiliation des auteurs : MATIS (1993-2011) Thématique : IMAGERIE Nature : Actes nature-HAL : DirectOuvrColl/Actes DOI : sans En ligne : http://www.isprs.org/proceedings/XXXVIII/part3/a/default.aspx Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=34773 Voir aussiContient
- Panorama-based camera calibration / Bertrand Cannelle (2010)
- Extracting wire-frame models of street facades from 3D point clouds and the corresponding cadastral map / Karim Hammoudi (2010)
- Matching terrestrial images captured by a nomad system to images of a reference database for pose estimation purpose / Arnaud Le Bris (2010)
- A formulation for unsupervised hierarchical segmentation of facade images with periodic models / Jean-Pascal Burochin (2010)
- Motion blur detection in aerial images shot with channel-dependent exposure time / Lâmân Lelégard (2010)
Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 15528-01A CG2010 Livre Centre de documentation Congrès Disponible 15528-01 DEP-RECP Cédérom LASTIG Dépôt en unité Exclu du prêt 15528-04A K317 Livre LASTIG Dépôt en unité Exclu du prêt Photogrammetric computer vision and image analysis: ISPRS Commission 3 symposium, Saint-Mandé, 1-3 septembre 2010, volume 2. Papers accepted on the basis of abstracts / Nicolas Paparoditis (2010)PermalinkPermalinkPermalinkSemiology of graphics / Jacques Bertin (2010)PermalinkTraitement des données de télédétection / Michel-Claude Girard (2010)PermalinkTraitement de l'image et de la vidéo / Rachid Belaroussi (2010)PermalinkDetection of unregistered buildings for updating 2D databases / Nicolas Champion (01/12/2009)PermalinkContribution of airborne full-waveform Lidar and image data for urban scene classification / Nesrine Chehata (07/11/2009)PermalinkA geometric stochastic approach based on marked point processes for road mark detection from high resolution aerial images / Olivier Tournaire in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 6 (November - December 2009)PermalinkA matching algorithm for detecting land use changes using case-based reasoning / X. Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 75 n° 11 (November 2009)Permalinkvol 30 n° 20 - October 2009 - Accuracy 2008, [actes], spatial accuracy in remote sensing, Shangai, 25 - 27 June 2008 (Bulletin de International Journal of Remote Sensing IJRS) / Jingxiong ZhangPermalinkvol 30 n° 19 - October 2009 - ForestSat 2007, [actes], operational tools in forestry using remote sensing techniques, Montpellier, 5 - 7 November 2007 (Bulletin de International Journal of Remote Sensing IJRS) / Ronald E. McRobertsPermalinkSmall-footprint laser scanning simulator for system validation, error assessment, and algorithm development / Antero Kukko in Photogrammetric Engineering & Remote Sensing, PERS, vol 75 n° 10 (October 2009)PermalinkAutomated extraction of buildings from Ikonos imagery by integrating spectral and spatial information / X. Wang in Geomatica, vol 63 n° 3 (September 2009)PermalinkRapid mapping of high resolution SAR scenes / F. Dell'acqua in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 5 (September - October 2009)PermalinkStereo analysis of high-resolution SAR images for building height estimation in cases of orthogonal aspect directions / Uwe Soergel in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 5 (September - October 2009)PermalinkApplications of remote sensing and geographic information systems for urban land-cover change studies in Mongolia / D. Amarsaikhan in Geocarto international, vol 24 n° 4 (August - September 2009)PermalinkA disturbance inventory framework for flexible and reliable landscape monitoring / J. Linke in Photogrammetric Engineering & Remote Sensing, PERS, vol 75 n° 8 (August 2009)PermalinkRange of categorical associations for comparison of maps with mixed pixels / Robert Gilmore Pontius in Photogrammetric Engineering & Remote Sensing, PERS, vol 75 n° 8 (August 2009)PermalinkObservations of urban and suburban environments with global satellite scatterometer data / Son V. Nghiem in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 4 (July - August 2009)Permalink