Détail de l'auteur
Auteur Karim Hammoudi |
Documents disponibles écrits par cet auteur



A synergistic approach for recovering occlusion-free textured 3D maps of urban facades from heterogeneous cartographic data / Karim Hammoudi in International journal of advanced robotic systems, vol 10 (2013)
![]()
[article]
Titre : A synergistic approach for recovering occlusion-free textured 3D maps of urban facades from heterogeneous cartographic data Type de document : Article/Communication Auteurs : Karim Hammoudi, Auteur ; Fadi Dornaika , Auteur ; Bahman Soheilian
, Auteur ; Bruno Vallet
, Auteur ; John McDonald, Auteur ; Nicolas Paparoditis
, Auteur
Année de publication : 2013 Article en page(s) : pp 316 - 326 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] données localisées 3D
[Termes descripteurs IGN] façade
[Termes descripteurs IGN] image terrestre
[Termes descripteurs IGN] modèle numérique du bâti
[Termes descripteurs IGN] texture d'image
[Termes descripteurs IGN] zone urbaine denseRésumé : (auteur) In this paper, we present a practical approach for generating an occlusion-free textured 3D map of urban facades by the synergistic use of terrestrial images, 3D point clouds and area-based information. Particularly in dense urban environments, the high presence of urban objects in front of the facades causes significant difficulties for several stages in computational building modeling. Major challenges lie on the one hand in extracting complete 3D facade quadrilateral delimitations and on the other hand in generating occlusion-free facade textures. For these reasons, we describe a straightforward approach for completing and recovering facade geometry and textures by exploiting the data complementarity of terrestrial multi-source imagery and area-based information. Numéro de notice : A2013-804 Thématique : IMAGERIE Nature : Article DOI : 10.5772/56570 date de publication en ligne : 01/01/2013 En ligne : http://dx.doi.org/10.5772/56570 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80078
in International journal of advanced robotic systems > vol 10 (2013) . - pp 316 - 326[article]Contributions to the 3D city modeling. 3D polyhedral building model reconstruction from aerial images & 3D facade modeling from terrestrial 3D point cloud and images / Karim Hammoudi (2011)
![]()
Titre : Contributions to the 3D city modeling. 3D polyhedral building model reconstruction from aerial images & 3D facade modeling from terrestrial 3D point cloud and images Type de document : Thèse/HDR Auteurs : Karim Hammoudi, Auteur Editeur : Paris : Institut Géographique National - IGN Année de publication : 2011 Importance : 234 p. Format : 21 x 30 cm Note générale : Bibliographie
Ph.D. Thesis submitted for the degree of Doctor of Philosophy in Signal and Image Processing from the Université Paris-EstLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes descripteurs IGN] canalisation
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] données localisées 3D
[Termes descripteurs IGN] façade
[Termes descripteurs IGN] lasergrammétrie
[Termes descripteurs IGN] modèle 3D de l'espace urbain
[Termes descripteurs IGN] polyèdre
[Termes descripteurs IGN] reconstruction 3D du bâti
[Termes descripteurs IGN] route
[Termes descripteurs IGN] semis de points
[Termes descripteurs IGN] système de numérisation mobile
[Termes descripteurs IGN] texturage
[Termes descripteurs IGN] toitRésumé : (Auteur) L'objectif principal de ce travail est le développement de recherches en modélisation 3D du bâti. En particulier, la recherche en reconstruction 3D de bâtiment est un sujet très développé depuis les années 90. Malgré tout, il paraît nécessaire de poursuivre les recherches dans cet axe étant donnée que les approches actuelles consacrées à la reconstruction 3D de bâtiment (bien qu'efficaces) rencontrent encore des difficultés en terme de généralisation, de cohérence et de précision. Par ailleurs, les récents développements des systèmes d'acquisitions de rues tel que les systèmes de cartographie mobile ouvrent de nouvelles perspectives d'amélioration de la modélisation des bâtiments dans le sens ou les données terrestres (très précises et résolues) peuvent être exploitées avec davantage de cohérence (en comparaison à l'aérien) pour enrichir les modèles de bâtiments au niveau des façades (la géométrie, la texture). Ainsi, des approches de modélisation aériennes et terrestres sont individuellement proposées. Au niveau aérien, nous décrivons une approche directe et dépourvu d'extraction et d'assemblage de primitives géométriques en vue de la reconstruction 3D de modèles polyédriques simples de bâtiments à partir d'un jeu d'images aériennes calibrées. Au niveau terrestre, plusieurs approches qui décrivent essentiellement un pipeline pour la modélisation 3D des façades urbaines sont proposées; à savoir, la segmentation et classification de nuage de rues urbaines, la modélisation géométrique des façades urbaines et le texturage des façades urbaines comportant des occultations causées par d'autres objets du mobilier urbain. Note de contenu : I Introduction
1 Introduction
1.1 Global context
1.1.1 Towards 3D Mapping
1.2 Specific Context of the Thesis
1.1.1 Positioning of the Thesis in the IGN Research
1.3 Problem Statement
1.4 Major Contributions
1.5 Organization of the Thesis
II Aerial Building Modeling
2 Extracting 3D Polyhedral Building Models from Aerial Images
2.1 Introduction and Motivation
2.1.1 Chapter Contribution
2.2 Related Work
2.3 Problem Statement and Model Parametrization
2.4 Proposed Approach
2.4.1 Multiscopic Context and 3D to 2D Projection
2.4.2 Measuring Model-to-Data Consistency
2.4.3 Computing the Polyhedral Building Model
2.5 Experimental Results and Performance Study
2.5.1 Input Dataset
2.5.2 Reconstructed 3D Models and Convergence Study
2.5.3 Accuracy Evaluation
2.5.4 Performance in the Presence of Image Noise
2.5.5 Performance according to the Image Resolution
2.5.6 Performance in the Presence of Superstructures
2.5.7 Performance in the Presence of Significant Shadows
2.6 Conclusions
2.6.1 Contribution
2.6.2 Future Work
III Terrestrial Facade Modeling
3 Properties of Terrestrial Urban Laser Data
3.1 Urban Street Facades Modeling
3.1.1 A Priori Knowledge on Street Facades
3.2 Dataset Acquired by the Mobile Mapping System
3.2.1 The IGN Street Mobile Mapping System
3.2.2 Acquisition Protocol, Collected Data and their Management
3.3 Exploiting Laser Data: Challenges and Difficulties
3.3.1 Laser Reflectance
3.3.2 Variability of Point Density
3.3.3 Data Redundancy
3.3.4 Static and Mobile Occlusions
3.3.5 Visibility and Coverage of Urban Objects
3.3.6 3D Data Misalignment
3.4 Conclusion
4 Segmenting and Classifying Terrestrial Urban Street Point Cloud
4.1 Introduction and motivation
4.2 Related Work
4.3 Proposed Approaches
4.3.1 3D Data Pre-processing
4.3.2 Accumulation Map Generation (Euclidean)
4.3.3 Map-based Segmentation into Vertical and Surface Clusters
4.3.4 Approach 1: Direct Urban Point Cloud Segmentation from the Cadastral Map
4.3.5 Approach 2: Model-less Urban Point Cloud Segmentation
4.4 Experimental Results and Performance Study
4.4.1 Experimental setup
4.4.2 Performance of Major Segmentation Stages
4.4.3 Overall Analysis and Accuracy Assessment
4.5 Conclusions
4.5.1 Contribution
5 Facade Modeling and Occlusion-free Texturing from Image and Laser Data
5.1 Introduction and Motivation
5.1.1 Compatibility and Divergence between Aerial-based Building Modeling and Ground-based Facade Modeling
5.1.2 Related Work
5.2 Terrestrial-based Facade Modeling
5.2.1 Problem Statement and Main Objectives
5.2.2 Related Work
5.3 Proposed approach
5.3.1 Parametrization of Street Facade Models vs. Facade LOD
5.3.2 Generating Aerial/Terrestrial Compatible Facade Models
5.3.3 Limitations of Laser Data in Facade Top Delimitation
5.3.4 Investigations for Generating Facade Models adapted for the Walk-through Street Visualization
5.3.5 Generating Occlusion-free Facade Textures
5.4 Experimental Results and Performance Study
5.4.1 Generated Wire-Frame 3D mode
5.4.2 Accuracy Evaluation
5.4.3 Performance in Enhancing Facade LOD from Laser Data
5.4.4 Image-based Skyline Detection
5.4.5 Generated Occlusion-free Texture
5.5 Conclusions
5.5.1 Contribution
5.5.2 Future Works
IV Conclusion and Future Works
6 Conclusion and Future Works
6.1 Synthesis of Researches and Contributions
6.1.1 The Generation of Simple Polyhedral Building Models from Aerial Images
6.1.2 The Segmentation of Urban Street in Terrestrial Laser Data
6.1.3 The Facade Modeling from Terrestrial Multi-source Data
6.2 Future Works
6.2.1 An Unified Pipeline for the Facade Modeling
6.2.2 The Full Enfranchisement of the Conventional Cadastral Map (Man-made) in the Facade Model Generation
6.2.3 The Fusing of Generated Aerial-based Building Models and Terrestrial-based Facade Models
6.2.4 The Enhancement of LoD in the Facade Models
6.3 Work Outcomes
V AppendixNuméro de notice : 14432 Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de doctorat : Signal and Image Processing : Paris Est : 2011 Organisme de stage : MATIS (IGN) nature-HAL : Thèse Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=45250 Documents numériques
peut être téléchargé
14432_these2011_hammoudi.pdfAdobe Acrobat PDFA featureless approach to 3D polyhedral building modeling from aerial images / Karim Hammoudi in Sensors, vol 11 n° 1 (January 2011)
![]()
[article]
Titre : A featureless approach to 3D polyhedral building modeling from aerial images Type de document : Article/Communication Auteurs : Karim Hammoudi, Auteur ; Fadi Dornaika , Auteur
Année de publication : 2011 Article en page(s) : pp 228 - 259 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] image aérienne
[Termes descripteurs IGN] luminance lumineuse
[Termes descripteurs IGN] mesure de similitude
[Termes descripteurs IGN] méthode robuste
[Termes descripteurs IGN] orthoimage
[Termes descripteurs IGN] reconstruction 3D du bâtiRésumé : (auteur) This paper presents a model-based approach for reconstructing 3D polyhedral building models from aerial images. The proposed approach exploits some geometric and photometric properties resulting from the perspective projection of planar structures. Data are provided by calibrated aerial images. The novelty of the approach lies in its featurelessness and in its use of direct optimization based on image rawbrightness. The proposed framework avoids feature extraction and matching. The 3D polyhedral model is directly estimated by optimizing an objective function that combines an image-based dissimilarity measure and a gradient score over several aerial images. The optimization process is carried out by the Differential Evolution algorithm. The proposed approach is intended to provide more accurate 3D reconstruction than feature-based approaches. Fast 3D model rectification and updating can take advantage of the proposed method. Several results and evaluations of performance from real and synthetic images show the feasibility and robustness of the proposed approach. Numéro de notice : A2011-611 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/s110100228 date de publication en ligne : 28/12/2010 En ligne : https://doi.org/10.3390/s110100228 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91711
in Sensors > vol 11 n° 1 (January 2011) . - pp 228 - 259[article]Extracting wire-frame models of street facades from 3D point clouds and the corresponding cadastral map / Karim Hammoudi (01/10/2010)
contenu dans Photogrammetric computer vision and image analysis, ISPRS Commission 3 symposium, Saint-Mandé, 1-3 septembre 2010, 1. Volume 1 [Papers accepted on the basis of peer-reviewed full manuscripts] / Marc Pierrot-Deseilligny (2010)
Titre : Extracting wire-frame models of street facades from 3D point clouds and the corresponding cadastral map Type de document : Article/Communication Auteurs : Karim Hammoudi, Auteur ; Fadi Dornaika , Auteur ; Bahman Soheilian
, Auteur ; Nicolas Paparoditis
, Auteur
Congrès : PCV 2010, ISPRS - Commission 3 symposium Photogrammetric computer vision and image analysis (1 - 3 septembre 2010; Saint-Mandé, France), Auteur Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 01/10/2010 Importance : pp 91 - 96 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes descripteurs IGN] façade
[Termes descripteurs IGN] modèle 3D de l'espace urbain
[Termes descripteurs IGN] photogrammétrie terrestre
[Termes descripteurs IGN] segmentation d'image
[Termes descripteurs IGN] semis de points
[Termes descripteurs IGN] système de numérisation mobile
[Termes descripteurs IGN] texturageRésumé : (Auteur) This paper presents an operational approach for extracting wire-frame models of street facades. Georeferenced terrestrial laser rawdata are acquired by a Mobile Mapping System (MMS). The MMS constitutes an adapted tool to massively collect accurate data at street level. After a filtering step of the 3D raw point cloud of street, the street point cloud is segmented into a cloud of dominant facade walls. Piecewise quasi-planar facade cloud are then extracted using an adapted Progressive Probabilistic Hough Transform (PPHT). At the planimetric level, a cadastral map issue from an urban database is employed to segment the cloud of planar clusters into residential facade portion. Finally, each portion is vertically delimited using heuristic approaches. The adapted PPHT allows the automatic modeling of facade outlines with a fine facade line detection and a low computation time. The adapted approach has been tested on a set of point clouds acquired in the city of Paris under real conditions. Examples and experimental results show the efficiency of the proposed approach. Numéro de notice : C2010-002 Thématique : IMAGERIE Nature : Communication Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=65057 Extracting building footprint from 3D point clouds using terrestrial laser scanning at street level / Karim Hammoudi (01/12/2009)
![]()
contenu dans CMRT09 Object extraction for 3D city models, road databases and traffic monitoring-concepts, algorithms and evaluation / Uwe Stilla (2009)
Titre : Extracting building footprint from 3D point clouds using terrestrial laser scanning at street level Type de document : Article/Communication Auteurs : Karim Hammoudi, Auteur ; Fadi Dornaika , Auteur ; Nicolas Paparoditis
, Auteur
Congrès : Congrès: CMRT 2009, City Models, Roads and Traffic Object extraction for 3D city models, road databases, traffic monitoring (3 - 4 septembre 2009; Paris, France), Auteur Année de publication : 01/12/2009 Importance : pp 65 - 70 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] empreinte
[Termes descripteurs IGN] extraction de traits caractéristiques
[Termes descripteurs IGN] modélisation 3D
[Termes descripteurs IGN] semis de points
[Termes descripteurs IGN] système de numérisation mobile
[Termes descripteurs IGN] télémétrie laser terrestre
[Termes descripteurs IGN] zone urbaineRésumé : (Auteur) In this paper, we address the problem of generating building footprints using terrestrial laser scanning from a Mobile Mapping System (MMS). The MMS constitutes a fast and adapted tool to extract precise data for 3D city modeling. Urban environments evolve over time due to human activities and other factors. Buildings are constructed or destroyed and the urban areas are extended. Therefore, the structures of the cities are constantly modified. Currently, building footprints can be generated using aerial data. However, aerial based footprints lack precision due to the nature of the data and to the associated extraction methods. The use of MMS is proposed as an alternative to perform this complex task. In this work, we propose an operational approach for automatic extraction of accurate building footprints. We describe the challenges associated with the terrestrial laser raw data acquired in realistic and dense urban environments. After a filtering stage on the 3D laser cloud point, we extract and reconstruct the dominant facade planes by combining the Hough transform, the k-means clustering algorithm and the RANSAC method. The building footprint is then estimated from these dominant planes. Preliminary experimental results are presented and discussed. The assessments show that this approach is very promising for the automation of building footprints extraction. Numéro de notice : C2009-008 Thématique : IMAGERIE Nature : Communication Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=65048 Documents numériques
en open access
c2009-008_cmrt09_hammoudi_et_al.pdfAdobe Acrobat PDFExtracting 3D polyhedral building models from aerial images using a featureless and direct approach / Fadi Dornaika (20/05/2009)
Permalink