Catalogue en ligne IGN

Semantic aware quality evaluation of 3D building models : Modeling and simulation / Oussama Ennafii (2019)

Public

Titre :	Semantic aware quality evaluation of 3D building models : Modeling and simulation
Titre original :	Evaluation de la qualité des modèles 3D de bâtiments
Type de document :	Thèse/HDR
Auteurs :	Oussama Ennafii , Auteur ; Clément Mallet , Directeur de thèse ; Florent Lafarge, Directeur de thèse
Editeur :	Champs/Marne : Université Paris-Est
Année de publication :	2019
Importance :	238 p.
Format :	21 x 30 cm
Note générale :	bibliographie Dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy delivered by Université Paris-Est, Speciality Geographical Information Sciences and Technologies Thèse récompensée par le prix 2020 EuroSDR PhD Award.
Langues :	Anglais (eng)
Descripteur :	[Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection d'erreur [Termes IGN] généralisation [Termes IGN] image à très haute résolution [Termes IGN] information sémantique [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modèle numérique de surface [Termes IGN] modélisation 3D [Termes IGN] modélisation du bâti [Termes IGN] scène urbaine [Termes IGN] taxinomie
Index. décimale :	THESE Thèses et HDR
Résumé :	(auteur) The automatic generation of 3D building models from geospatial data is now a standard procedure. An abundant literature covers the last two decades and several softwares are now available. However, urban areas are very complex environments. Inevitably, practitioners still have to visually assess, at city-scale, the correctness of these models and detect frequent reconstruction errors. Such a process relies on experts, and is highly time-consuming with approximately two hours/km² per expert. This work proposes an approach for automatically evaluating the quality of 3D building models. Potential errors are compiled in a novel hierarchical and modular taxonomy. This allows, for the first time, to disentangle fidelity and modeling errors, whatever the level of details of the modeled buildings. The quality of models is predicted using the geometric properties of buildings and, when available, Very High Resolution images and Digital Surface Models. A baseline of handcrafted, yet generic, features is fed into a Random Forest or Support Vector Machine classifiers. Richer features, relying on graph kernels as well as Scattering Networks, were proposed to better take into consideration structure. Both multi-class and multi-label cases are studied: due to the interdependence between classes of errors, it is possible to retrieve all errors at the same time while simply predicting correct and erroneous buildings. The proposed framework was tested on three distinct urban areas in France with more than 3,000 buildings. 80%-99% F-score values are attained for the most frequent errors. For scalability purposes, the impact of the urban area composition on the error prediction was also studied, in terms of transferability, generalization, and representativeness of the classifiers. It shows the necessity of multi-modal remote sensing data and mixing training samples from various cities to ensure a stability of the detection ratios, even with very limited training set sizes.
Note de contenu :	1- Introduction 2- State of the art 3- Semantic evaluation of 3D models 4- A learning approach for quality evaluation 5- Assessing the learned approach 6- Computing a better representation 7- Assessing the advanced features 8- Conclusion
Numéro de notice :	25860
Affiliation des auteurs :	LASTIG MATIS (2012-2019)
Thématique :	IMAGERIE
Nature :	Thèse française
Note de thèse :	Thèse de Doctorat : Spécialité : Sciences et Technologies de l'Information Géographique : Paris-Est, 2019
Organisme de stage :	Lastig (IGN)
nature-HAL :	Thèse
DOI :	sans
En ligne :	https://hal.science/tel-02879809
Format de la ressource électronique :	URL
Permalink :	https://documentation.ensg.eu/index.php?lvl=notice_display&id=95395

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
25860-02	THESE	Livre	Centre de documentation	Thèses	Disponible
25860-01	THESE	Livre	Centre de documentation	Thèses	Disponible
25860-03	THESE	Livre	Centre de documentation	Thèses	Disponible

IGN

Centre de documentation
scientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! Horaires du CDOS

Informations pratiques

Exemplaires(3)

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

IGN

Centre de documentationscientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! Horaires du CDOS

Informations pratiques

Exemplaires(3)

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

Centre de documentation
scientifique