Centre de documentation
scientifique

GeoRec: Geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes / Linxi Huan in ISPRS Journal of photogrammetry and remote sensing, vol 186 (April 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 186 (April 2022) . - pp 301 - 314 Titre : GeoRec: Geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes Type de document : Article/Communication Auteurs : Linxi Huan, Auteur ; Xianwei Zheng, Auteur ; Jianya Gong, Auteur Année de publication : 2022 Article en page(s) : pp 301 - 314 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] données localisées 3D [Termes IGN] géométrie [Termes IGN] image RVB [Termes IGN] maillage [Termes IGN] modélisation sémantique [Termes IGN] objet 3D [Termes IGN] reconstruction 3D [Termes IGN] reconstruction d'objet [Termes IGN] scène intérieure Résumé : (auteur) Semantic indoor 3D modeling with multi-task deep neural networks is an efficient and low-cost way for reconstructing an indoor scene with geometrically complete room structure and semantic 3D individuals. Challenged by the complexity and clutter of indoor scenarios, the semantic reconstruction quality of current methods is still limited by the insufficient exploration and learning of 3D geometry information. To this end, this paper proposes an end-to-end multi-task neural network for geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes (termed as GeoRec). In the proposed GeoRec, we build a geometry extractor that can effectively learn geometry-enhanced feature representation from depth data, to improve the estimation accuracy of layout, camera pose and 3D object bounding boxes. We also introduce a novel object mesh generator that strengthens the reconstruction robustness of GeoRec to indoor occlusion with geometry-enhanced implicit shape embedding. With the parsed scene semantics and geometries, the proposed GeoRec reconstructs an indoor scene by placing reconstructed object mesh models with 3D object detection results in the estimated layout cuboid. Extensive experiments conducted on two benchmark datasets show that the proposed GeoRec yields outstanding performance with mean chamfer distance error for object reconstruction on the challenging Pix3D dataset, 70.45% mAP for 3D object detection and 77.1% 3D mIoU for layout estimation on the commonly-used SUN RGB-D dataset. Especially, the mesh reconstruction sub-network of GeoRec trained on Pix3D can be directly transferred to SUN RGB-D without any fine-tuning, manifesting a high generalization ability. Numéro de notice : A2022-235 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2022.02.014 Date de publication en ligne : 03/03/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.02.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100139 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022041	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2022043	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2022042	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

From point clouds to high-fidelity models - advanced methods for image-based 3D reconstruction / Audrey Richard (2021)  

Public Titre : From point clouds to high-fidelity models - advanced methods for image-based 3D reconstruction Type de document : Thèse/HDR Auteurs : Audrey Richard, Auteur Editeur : Zurich : Eidgenossische Technische Hochschule ETH - Ecole Polytechnique Fédérale de Zurich EPFZ Année de publication : 2021 Note générale : bibliographie A thesis submitted to attain the degree of Doctor of Sciences of ETH Zurich Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] compréhension de l'image [Termes IGN] démonstration de faisabilité [Termes IGN] discrétisation spatiale [Termes IGN] jeu de données localisées [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modélisation sémantique [Termes IGN] optimisation (mathématiques) [Termes IGN] Pays-Bas [Termes IGN] reconstruction 3D [Termes IGN] reconstruction d'objet [Termes IGN] Rhénanie du Nord-Wesphalie (Allemagne) [Termes IGN] semis de points [Termes IGN] texturage [Termes IGN] Zurich (Suisse) Résumé : (auteur) Capturing automatically a virtual 3D model of an object or a scene from a collection of images is a useful capability with a wide range of applications, including virtual/augmented reality, heritage preservation, consumer digital entertainment, autonomous robotics, navigation, industrial vision or metrology, and many more. Since the early days of photogrammetry and computer vision, it has been a topic of intensive research but has eluded a general solution for it. 3D modeling requires more than reconstructing a cloud of 3D points from images; it requires a high-fidelity representation whose form is often dependent on individual objects. This thesis guides you in the journey of image-based 3D reconstruction through several advanced methods that aims to push its boundaries, from precise and complete geometry to detailed appearance, using both theory with elegant mathematics and more recent breakthroughs in deep learning. To evaluate these methods, thorough experiments are conducted at scene level (and large-scale) where efficiency is of key importance, and at object level where accuracy, completeness and photorealism can be better appreciated. To show the individual potential of each of these methods, as well as the possible wide coverage in terms of applications, different scenarios are considered and serve as a proof-of-concept. Thereby, the journey starts with large-scale city modeling using aerial photography from the cities of Zürich (Switzerland), Enschede (Netherlands) and Dortmund (Germany), followed by single object completion using the synthetic dataset ShapeNet, that includes objects like cars, benches or planes that can be found in every city, to finish with the embellishment of these digital models via high-resolution texture mapping using a multi-view 3D dataset of real and synthetic objects, like for example statues and fountains that also dress the landscape of cities. Combining them together into an incremental pipeline dedicated to a specific application would require further tailoring but is quite possible. Numéro de notice : 17650 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : PhD : Sciences : ETH Zurich : 2021 En ligne : http://dx.doi.org/10.3929/ethz-b-000461735 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97892

Spatial decision support in urban environments using machine learning, 3D geo-visualization and semantic integration of multi-source data / Nikolaos Sideris (2019)  

Public Titre : Spatial decision support in urban environments using machine learning, 3D geo-visualization and semantic integration of multi-source data Type de document : Thèse/HDR Auteurs : Nikolaos Sideris, Auteur ; Georgios Miaoulis, Directeur de thèse ; Djamchid Ghazanfarpour, Directeur de thèse Editeur : Limoges : Université de Limoges Année de publication : 2019 Importance : 136 p. Format : 21 x 30 cm Note générale : bibliographie Thèse pour obtenir le grade de Docteur de l'Université de Limoges spécialité Informatique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] aide à la décision [Termes IGN] apprentissage automatique [Termes IGN] classification barycentrique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] données multisources [Termes IGN] géoréférencement [Termes IGN] géovisualisation [Termes IGN] image 3D [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modélisation sémantique [Termes IGN] ontologie [Termes IGN] planification urbaine [Termes IGN] système d'information urbain [Termes IGN] urbanisme Index. décimale : THESE Thèses et HDR Résumé : (auteur) The constantly increasing amount and availability of urban data derived from varying sources leads to an assortment of challenges that include, among others, the consolidation, visualization, and maximal exploitation prospects of the aforementioned data. A preeminent problem affecting urban planning is the appropriate choice of location to host a particular activity (either commercial or common welfare service) or the correct use of an existing building or empty space. In this thesis we propose an approach to address the preceding challenges availed with machine learning techniques with the random forests classifier as its dominant method in a system that combines, blends and merges various types of data from different sources, encode them using a novel semantic model that can capture and utilize both low-level geometric information and higher level semantic information and subsequently feeds them to the random forests classifier. The data are also forwarded to alternative classifiers and the results are appraised to confirm the prevalence of the proposed method. The data retrieved stem from a multitude of sources, e.g. open data providers and public organizations dealing with urban planning. Upon their retrieval and inspection at various levels (e.g. import, conversion, geospatial) they are appropriately converted to comply with the rules of the semantic model and the technical specifications of the corresponding subsystems. Geometrical and geographical calculations are performed and semantic information is extracted. Finally, the information from individual earlier stages along with the results from the machine learning techniques and the multicriteria methods are integrated into the system and visualized in a front-end web based environment able to execute and visualize spatial queries, allow the management of three-dimensional georeferenced objects, their retrieval, transformation and visualization, as a decision support system. Note de contenu : Introduction 1- Theorical background and State of the Art 2- Thesis contribution to semantic querying, navigation and spatial decision Making of 3D Urban Scenes using Machine Learning 3- Evaluation discussion et conclusions Numéro de notice : 25995 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE/URBANISME Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Université de Limoges : 2019 Organisme de stage : XLIM (Limoges) nature-HAL : Thèse DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-02449667/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96808

Social networks with rich edge semantics / Quan Zheng (2017)  

Public Titre : Social networks with rich edge semantics Type de document : Monographie Auteurs : Quan Zheng, Auteur ; David Skillicorn, Auteur Editeur : Boca Raton, New York, ... : CRC Press Année de publication : 2017 Importance : 230 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-1-315-39062-8 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Société de l'information [Termes IGN] intégration de données [Termes IGN] modèle relationnel [Termes IGN] modélisation sémantique [Termes IGN] réseau social [Termes IGN] réseautage social [Termes IGN] science des données Résumé : (éditeur) Social Networks with Rich Edge Semantics introduces a new mechanism for representing social networks in which pairwise relationships can be drawn from a range of realistic possibilities, including different types of relationships, different strengths in the directions of a pair, positive and negative relationships, and relationships whose intensities change with time. For each possibility, the book shows how to model the social network using spectral embedding. It also shows how to compose the techniques so that multiple edge semantics can be modeled together, and the modeling techniques are then applied to a range of datasets. Features: - Introduces the reader to difficulties with current social network analysis, and the need for richer representations of relationships among nodes, including accounting for intensity, direction, type, positive/negative, and changing intensities over time - Presents a novel mechanism to allow social networks with qualitatively different kinds of relationships to be described and analyzed - Includes extensions to the important technique of spectral embedding, shows that they are mathematically well motivated and proves that their results are appropriate - Shows how to exploit embeddings to understand structures within social networks, including subgroups, positional significance, link or edge prediction, consistency of role in different contexts, and net flow of properties through a node - Illustrates the use of the approach for real-world problems for online social networks, criminal and drug smuggling networks, and networks where the nodes are themselves groups Suitable for researchers and students in social network research, data science, statistical learning, and related areas, this book will help to provide a deeper understanding of real-world social networks. Note de contenu : 1- Introduction 2- The core model 3- Background 4- Modelling relationships of different types 5- Modelling asymmetric relationships 6- Modelling asymmetric relationships with multiple types 7- Modelling relationships that change over time 8- Modelling positive and negative relationships 9- Signed graph-based semi-supervised learning 10- Combining directed and signed embeddings 11- Summary Numéro de notice : 25843 Affiliation des auteurs : non IGN Thématique : SOCIETE NUMERIQUE Nature : Monographie En ligne : https://www.taylorfrancis.com/books/9781315390628 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95250

Geospatial human-environment simulation through integration of massive multiplayer online games and geographic information systems / O. Ahlqvist in Transactions in GIS, vol 16 n° 3 (June 2012)  

Public [article]  inTransactions in GIS > vol 16 n° 3 (June 2012) . - pp 331 - 350 Titre : Geospatial human-environment simulation through integration of massive multiplayer online games and geographic information systems Type de document : Article/Communication Auteurs : O. Ahlqvist, Auteur ; J. Ramanathan, Auteur ; T. Loffing, Auteur ; A. Kocher, Auteur Année de publication : 2012 Article en page(s) : pp 331 - 350 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] artefact [Termes IGN] intégration de données [Termes IGN] jeu en ligne [Termes IGN] modélisation sémantique [Termes IGN] système d'information géographique [Termes IGN] visualisation cartographique Résumé : (Auteur) This article reports on the initial development of a generic framework for integrating Geographic Information Systems (GIS) with Massive Multi-player Online Gaming (MMOG) technology to support the integrated modeling of human-environment resource management and decision-making. We review Web 2.0 concepts, online maps, and games as key technologies to realize a participatory construction of spatial simulation and decision making practices. Through a design-based research approach we develop a prototype framework, “GeoGame”, that allows users to play board-game-style simulations on top of an online map. Through several iterations, we demonstrate the implementation of a range of design artifacts including: real-time, multi-user editing of online maps, web services, game lobby, user-modifiable rules and scenarios building, chat, discussion, and market transactions. Based on observational, analytical, experimental and functional evaluations of design artifacts as well as a literature review, we argue that a MMO GeoGame-framework offers a viable approach to address the complex dynamics of human-environmental systems that require a simultaneous reconciliation of both top-down and bottom-up decision making where stakeholders are an integral part of a modeling environment. Further research will offer additional insight into the development of social-environmental models using stakeholder input and the use of such models to explore properties of complex dynamic systems. Numéro de notice : A2012-280 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/j.1467-9671.2012.01340.x Date de publication en ligne : 28/05/2012 En ligne : https://doi.org/10.1111/j.1467-9671.2012.01340.x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31726 [article]

A semantic and language-based representation of an environmental scene / J.M. Le Yaouanc in Geoinformatica, vol 14 n° 3 (July 2010)  

Permalink

vol 14 n° 5 - septembre - octobre 2009 - Système d'information et géolocalisation (Bulletin de Ingénierie des systèmes d'information, ISI : Revue des sciences et technologies de l'information, RSTI) / Sylvie Servigne

Permalink

Semantic modeling for the acquisition of topographic information from images and maps, SMATI 99 / Wolfgang Förstner (1999)

Permalink