References of "Poux, Florent"
     in
Bookmark and Share    
Full Text
See detailThe Smart Point Cloud: Structuring 3D intelligent point data
Poux, Florent ULiege

Doctoral thesis (2019)

Discrete spatial datasets known as point clouds often lay the groundwork for decision-making applications. E.g., we can use such data as a reference for autonomous cars and robot’s navigation, as a layer ... [more ▼]

Discrete spatial datasets known as point clouds often lay the groundwork for decision-making applications. E.g., we can use such data as a reference for autonomous cars and robot’s navigation, as a layer for floor-plan’s creation and building’s construction, as a digital asset for environment modelling and incident prediction... Applications are numerous, and potentially increasing if we consider point clouds as digital reality assets. Yet, this expansion faces technical limitations mainly from the lack of semantic information within point ensembles. Connecting knowledge sources is still a very manual and time-consuming process suffering from error-prone human interpretation. This highlights a strong need for domain-related data analysis to create a coherent and structured information. The thesis clearly tries to solve automation problematics in point cloud processing to create intelligent environments, i.e. virtual copies that can be used/integrated in fully autonomous reasoning services. We tackle point cloud questions associated with knowledge extraction – particularly segmentation and classification – structuration, visualisation and interaction with cognitive decision systems. We propose to connect both point cloud properties and formalized knowledge to rapidly extract pertinent information using domain-centered graphs. The dissertation delivers the concept of a Smart Point Cloud (SPC) Infrastructure which serves as an interoperable and modular architecture for a unified processing. It permits an easy integration to existing workflows and a multi-domain specialization through device knowledge, analytic knowledge or domain knowledge. Concepts, algorithms, code and materials are given to replicate findings and extend current applications. [less ▲]

Detailed reference viewed: 48 (18 ULiège)
Full Text
Peer Reviewed
See detailVoxel-Based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs Deep Learning Methods
Poux, Florent ULiege; Billen, Roland ULiege

in ISPRS International Journal of Geo-Information (2019), 8(5), 213

Automation in point cloud data processing is central in knowledge discovery within decision-making systems. The definition of relevant features is often key for segmentation and classification, with ... [more ▼]

Automation in point cloud data processing is central in knowledge discovery within decision-making systems. The definition of relevant features is often key for segmentation and classification, with automated workflows presenting the main challenges. In this paper, we propose a voxel-based feature engineering that better characterize point clusters and provide strong support to supervised or unsupervised classification. We provide different feature generalization levels to permit interoperable frameworks. First, we recommend a shape-based feature set (SF1) that only leverages the raw X, Y, Z attributes of any point cloud. Afterwards, we derive relationship and topology between voxel entities to obtain a three-dimensional (3D) structural connectivity feature set (SF2). Finally, we provide a knowledge-based decision tree to permit infrastructure-related classification. We study SF1/SF2 synergy on a new semantic segmentation framework for the constitution of a higher semantic representation of point clouds in relevant clusters. Finally, we benchmark the approach against novel and best-performing deep-learning methods while using the full S3DIS dataset. We highlight good performances, easy-integration, and high F1-score (> 85%) for planar-dominant classes that are comparable to state-of-the-art deep learning. [less ▲]

Detailed reference viewed: 29 (6 ULiège)
Full Text
Peer Reviewed
See detail3D Viewpoint Management and Navigation in Urban Planning: Application to the Exploratory Phase
Neuville, Romain ULiege; Pouliot, Jacynthe; Poux, Florent ULiege et al

in Remote Sensing (2019), 11(3), 236

3D geovisualization is essential in urban planning as it assists the analysis of geospatial data and decision making in the design and development of land use and built environment. However, we noted that ... [more ▼]

3D geovisualization is essential in urban planning as it assists the analysis of geospatial data and decision making in the design and development of land use and built environment. However, we noted that 3D geospatial models are commonly visualized arbitrarily as current 3D viewers often lack of design instructions to assist end users. This is especially the case for the occlusion management in most 3D environments where the high density and diversity of 3D data to be displayed require efficient visualization techniques for extracting all the geoinformation. In this paper, we propose a theoretical and operational solution to manage occlusion by automatically computing best viewpoints. Based on user’s parameters, a viewpoint management algorithm initially calculates optimal camera settings for visualizing a set of 3D objects of interest through parallel projections. Precomputed points of view are then integrated into a flythrough creation algorithm for producing an automatic navigation within the 3D geospatial model. The algorithm’s usability is illustrated within the scope of a fictive exploratory phase for the public transport services access in the European quarter of Brussels. Eventually, the proposed algorithms may also assist additional urban planning phases in achieving their purposes. [less ▲]

Detailed reference viewed: 62 (20 ULiège)
Full Text
Peer Reviewed
See detail3D Point Cloud Semantic Modelling: Integrated Framework for Indoor Spaces and Furniture
Poux, Florent ULiege; Neuville, Romain ULiege; Nys, Gilles-Antoine ULiege et al

in Remote Sensing (2018), 10(9), 1412

3D models derived from point clouds are useful in various shapes to optimize the trade-off between precision and geometric complexity. They are defined at different granularity levels according to each ... [more ▼]

3D models derived from point clouds are useful in various shapes to optimize the trade-off between precision and geometric complexity. They are defined at different granularity levels according to each indoor situation. In this article, we present an integrated 3D semantic reconstruction framework that leverages segmented point cloud data and domain ontologies. Our approach follows a part-to-whole conception which models a point cloud in parametric elements usable per instance and aggregated to obtain a global 3D model. We first extract analytic features, object relationships and contextual information to permit better object characterization. Then, we propose a multi-representation modelling mechanism augmented by automatic recognition and fitting from the 3D library ModelNet10 to provide the best candidates for several 3D scans of furniture. Finally, we combine every element to obtain a consistent indoor hybrid 3D model. The method allows a wide range of applications from interior navigation to virtual stores. [less ▲]

Detailed reference viewed: 65 (19 ULiège)
Full Text
See detailLa transition numérique dans le domaine du patrimoine bâti: un retour d'expériences
Billen, Roland ULiege; Jonlet, Benoît ULiege; Luczfalvy Jancsó, Andrea ULiege et al

in Bulletin de la commission royale des monuments, sites et fouilles - Tome 30 (2018)

Detailed reference viewed: 121 (16 ULiège)
Full Text
See detailSmart Point Clouds for information modelling: application in Cultural Heritage
Poux, Florent ULiege; Hallot, Pierre ULiege

Conference (2018, June 01)

Le travail présenté décrit un modèle interopérable pour la gestion des nuages de points volumineux tout en intégrant la sémantique. Les routines de traitement et les modèles de données actuels manquent de ... [more ▼]

Le travail présenté décrit un modèle interopérable pour la gestion des nuages de points volumineux tout en intégrant la sémantique. Les routines de traitement et les modèles de données actuels manquent de connaissances pour raisonner à partir de l’extraction d’information plutôt que de l’interprétation. Le modèle conceptuel de nuages de points intelligents développé permet d'apporter l'intelligence aux nuages de points via 3 méta-modèles connectés, tout en reliant les connaissances disponibles et les procédures de classification qui permettent l'injection sémantique.L'interopérabilité conduit l'adaptation du modèle à de nombreuses applications grâce à des ontologies de domaines spécialisés. Un premier prototype est implémenté dans la base de données Python et PostgreSQL et permet de combiner des concepts sémantiques et spatiaux pour des requêtes hybrides de base sur différents nuages de points. Une application du modèle est proposée dans la détermination de tesselles de la voute de l’oratoire carolorégien de Germigny-des-prés. Les tesselles sont identifiées de façon automatique sur une interaction entre 18 caractéristiques, dont les données biaisées du capteur, chaque tesselles dans le nuage de points à haute densité des mosaïques complexes capturées en 3D. Les connaissances sont ensuite utilisées pour classer chaque tesselles en fonction de leur taille, de leur surface, de leur forme, de leurs propriétés matérielles et de la classe de leur voisins. La méthode de détection et d'enrichissement sémantique montre des résultats prometteurs avec 94 % de sémantisation correcte, première étape vers la création d'un nuage de point archéologique intelligent. [less ▲]

Detailed reference viewed: 44 (3 ULiège)
Full Text
Peer Reviewed
See detailA Formalized 3D Geovisualization Illustrated to Selectivity Purpose of Virtual 3D City Model
Neuville, Romain ULiege; Pouliot, Jacynthe; Poux, Florent ULiege et al

in ISPRS International Journal of Geo-Information (2018), 7(5),

Virtual 3D city models act as valuable central information hubs supporting many aspects of cities, from management to planning and simulation. However, we noted that 3D city models are still ... [more ▼]

Virtual 3D city models act as valuable central information hubs supporting many aspects of cities, from management to planning and simulation. However, we noted that 3D city models are still underexploited and believe that this is partly due to inefficient visual communication channels across 3D model producers and the end-user. With the development of a formalized 3D geovisualization approach, this paper aims to support and make the visual identification and recognition of specific objects in the 3D models more efficient and useful. The foundation of the proposed solution is a knowledge network of the visualization of 3D geospatial data that gathers and links mapping and rendering techniques. To formalize this knowledge base and make it usable as a decision-making system for the selection of styles, second-order logic is used. It provides a first set of efficient graphic design guidelines, avoiding the creation of graphical conflicts and thus improving visual communication. An interactive tool is implemented and lays the foundation for a suitable solution for assisting the visualization process of 3D geospatial models within CAD and GIS-oriented software. Ultimately, we propose an extension to OGC Symbology Encoding in order to provide suitable graphic design guidelines to web mapping services. [less ▲]

Detailed reference viewed: 65 (23 ULiège)
Full Text
See detailNumérisation 3D par lasergrammétrie et photogrammétrie: applications à la Réalité Virtuelle
Poux, Florent ULiege; Luczfalvy Jancsó, Andrea ULiege; Jonlet, Benoît ULiege et al

Conference (2018, March 08)

Alors que les copies virtuelles du monde réel ont tendance à être créées plus rapidement que jamais sous forme de nuages de points et produits dérivés, leur utilisation par tous les professionnels demande ... [more ▼]

Alors que les copies virtuelles du monde réel ont tendance à être créées plus rapidement que jamais sous forme de nuages de points et produits dérivés, leur utilisation par tous les professionnels demande de nouveaux outils pour faciliter la diffusion des connaissances. Les analyses numériques changent la manière dont les chercheurs, les archéologues et les conservateurs du patrimoine travaillent et collaborent pour combiner progressivement leur expertise grâce à une plate-forme commune. Néanmoins, l’adjonction d'information sémantique pour compléter les nuages de points est essentielle pour permettre une utilisation complète comme donnée de référence. Les concepts et les outils qui simplifient ce processus sont rares, ce qui complique la mise en commun des analyses. Différentes méthodes seront présentées permettant d'extraire des informations archéologiques aux nuages de points et créer une connexion avec les connaissances structurées sous forme d'ontologie. Les outils de communication et de visualisation 3D développés pour permettre plusieurs interactions seront illustrées sur le château de Jehay. Un partenariat a été établi entre cette association et l’Unité de Géomatique de l’Université de Liège. Il porte non seulement sur l’acquisition de données 3D mais aussi sur l’accompagnement de l’association dans ses projets de recherches archéologiques, de réhabilitation du site et de valorisation. Plusieurs campagnes de mesures ont été réalisées à différents stades de la rénovation. De nouvelles missions sont prévues notamment par des étudiants de l’Université. Outre plusieurs vidéos promotionnelles et quelques produits dérivés utiles à la rénovation, une exploitation en réalité virtuelle retient pour le moment l’attention de nos développeurs. En effet, le Château étant actuellement en grande partie fermé au public, il est prévu cet été d’offrir sur le site des visites en réalité virtuelle basées sur des levés lasergrammétriques et photogrammétriques. À plus long terme, il est prévu d’établir un système d’information spatialisée dédié au Château ; les bases conceptuelles de ce système ont déjà été dressées lors d’une récente étude. [less ▲]

Detailed reference viewed: 119 (8 ULiège)
Full Text
See detailFusion de données lasergrammétriques/photogrammétriques et techniques d'extraction d'information archéologique sur base de nuage de points 3D
Poux, Florent ULiege; Billen, Roland ULiege; Hallot, Pierre ULiege et al

Conference (2018, March 08)

While virtual copies of the real world tend to be created faster than ever in the form of point clouds and derived products, their use by all professionals requires new tools to facilitate the ... [more ▼]

While virtual copies of the real world tend to be created faster than ever in the form of point clouds and derived products, their use by all professionals requires new tools to facilitate the dissemination of knowledge. Digital analyses are changing the way researchers, archaeologists and heritage curators work and collaborate to gradually combine their expertise through a common platform. Nevertheless, the addition of semantic information to complete the point clouds is essential to allow a complete use as reference data. There are few concepts and tools that simplify this process, making it difficult to share analyses. Different methods will be presented to extract archaeological information from the point clouds and create a connection with the structured knowledge in the form of ontology. Classification and structuring procedures for reasoning from the data will be discussed. These methodologies will be illustrated at the Germigny-des-prés (France) and Château de Jehay (Belgium) sites. The communication and 3D visualization tools developed to allow several interactions will also be presented. While the Germigny-des-prés site (France) is almost exclusively dedicated to research, the same is not true for the Jehay site. This exceptional site belongs to the Province of Liège and is managed by a non-profit association. A partnership has been established between this association and the Geomatics Unit of the University of Liège. It concerns not only the acquisition of 3D data but also the support of the association in its archaeological research, site rehabilitation and enhancement projects. Several measurement campaigns were carried out at different stages of the renovation. New missions are planned, notably by students from the University. In addition to several promotional videos and a few derivative products useful for renovation, a virtual reality operation is currently attracting the attention of our developers. Indeed, the Castle is currently largely closed to the public, it is planned this summer to offer virtual reality tours based on lasergrammetric and photogrammetric surveys. In the longer term, it is planned to establish a spatialized information system dedicated to the Castle; the conceptual bases of this system have already been established during a recent study. [less ▲]

Detailed reference viewed: 95 (17 ULiège)
Peer Reviewed
See detailRecherches récentes sur le site de Germigny-des-Prés (Loiret, France).
Van Wersch, Line ULiege; Hocquet, François-Philippe ULiege; Strivay, David ULiege et al

Conference (2018)

Restauré au XIXe siècle, l'église de Germigny-des-Prés est actuellement la seule au nord des Alpes à abriter des mosaïques alto-médiévales. L’édifice de culte, bâti au début du IXe siècle, faisait partie ... [more ▼]

Restauré au XIXe siècle, l'église de Germigny-des-Prés est actuellement la seule au nord des Alpes à abriter des mosaïques alto-médiévales. L’édifice de culte, bâti au début du IXe siècle, faisait partie de la villa de Théodulphe, proche conseiller de Charlemagne, abbé de Fleury et évêque d’Orléans. Ce site est donc exceptionnel à plus d’un titre. D’une part, l’église est une des plus anciennes de France et, en dépit de restaurations, elle reste un témoignage singulier de l’architecture religieuse alto-médiévale. D’autre part, ses mosaïques nous permettent d’aborder ce type de décoration et plus largement le verre, matériaux rares pour cet époque. Enfin, le site devrait receler les vestiges d’une villa carolingienne dont la réalité matérielle pose encore de nombreuses interrogations. Depuis trois ans, en collaboration avec une équipe internationale, des recherches utilisant des méthodes diverses ont été entreprises. Les mosaïques ont fait l’objet d’un premier examen macroscopique et d’analyses pXRF In situ pour distinguer les parties originales de la restauration du XIXe siècle. 15 échantillons de verre ont ensuite été analysés en EMP-WDS et LA-ICP-MS afin d'identifier leurs matériaux, recettes et provenances. Malgré la restauration plus vaste qu'on ne le pensait auparavant, des parties originales subsistent sur la voûte orientale. Si, des tesselles colorées antiques ont été réutilisés, les cubes couverts d’or et d’argent proviennent d'une production originale. Aucune correspondance n’existant dans le monde italien et byzantin, ils pourraient être issus d’une production spécifique, peut-être régionale. Des prospections géoradars ont été effectuées sur le site afin de localiser de potentiels vestiges alto-médiévaux. Elles ont mis en évidence l’existence de structures en différents emplacements. A l’intérieur du bâtiment, elles ont identifié l’abside occidentale confirmant la restitution du plan original proposé en 1930. A l’extérieur, elles ont permis de détecter les zones sur lesquelles devraient se concentrer les recherches archéologiques. Enfin, un scan 3D a permis un relevé précis du bâtiment. Il sera utilisé pour la gestion de l'information et la visualiser des résultats des recherches que nous espérons poursuivre sur le site de Germigny-des-Prés. [less ▲]

Detailed reference viewed: 14 (0 ULiège)
Peer Reviewed
See detailThe carolingian site of Germigny-des-Prés (Loiret, France), micro and macro-scales methods for the identification of a mosaic production.
Van Wersch, Line ULiege; Hocquet, François-Philippe ULiege; Strivay, David ULiege et al

Poster (2018)

The church of Germigny-des-Prés is one of the oldest in France. It holds the only early medieval mosaics preserved north of the Alps, ordered by Theodulph, close counselor of Charlemagne, at the beginning ... [more ▼]

The church of Germigny-des-Prés is one of the oldest in France. It holds the only early medieval mosaics preserved north of the Alps, ordered by Theodulph, close counselor of Charlemagne, at the beginning of the 9th century AD to decorate the oratory of his villa 1. Restored in the 19th century, it still conserved a part of the original material. These tesserae are a great opportunity to reach the glass from the early Middle Ages, period of change for glass production. Moreover, this site could have hold a mosaic workshop and it could be the first settlement of this type ever discovered 2. In situ, a macroscopic exam and pXRF analyses done on the tesserae from the vault and arches allow to distinguish original material and restored area. 15 glass samples were analysed using EMP-WDS and LA-ICP-MS in order to identify their materials and techniques as well as their origins. A 3D scan of the building makes possible to quantify accurately the materials, to manage the information and to view the results. Finally, ground penetrating radar prospections were done on the site in order to locate a potential workshop. The concentrations of lead, potassium and iron allow us to distinguish the early medieval tesserae from the new ones. Thanks to this, the original part of the mosaic can be precisely differentiated from the restoration of the 19th century that is vaster than previously thought. Still, the figures of the vault appear to be original. The analysed cubes show that some were re-used roman tesserae but the ones with gold and silver, the most numerous in the mosaic of the vault, come from an original production, specific to this site. Structures were found by prospections in different locations around the church and excavations will now take place in order to identify this remains and a potential workshop. Acknowledgements: to the council of Germigny-des-Prés and the DRAC Centre Val-de-Loire for the research authorizations. The missions were financed by the FRS-FNRS, The Comhaire prize of the foundation Roi Baudouin and by ARCHEA. 1 A. Freeman, P. Meyvaert, Gesta (2001), 125- 139. 2 L. James, E. Soproni, B. Bjornholt, in «Mosaics by numbers, (2013), 310-328. [less ▲]

Detailed reference viewed: 20 (0 ULiège)
Full Text
See detailCASTLE4D : The Castle of Franchimont (Theux, Province of Liège, Belgium)
Luczfalvy Jancsó, Andrea ULiege; Hoffsummer, Patrick ULiege; Billen, Roland ULiege et al

in Ettel, Peter; Flambard Héricher, Anne-Marie; O'Conor, Kieran (Eds.) Château Gaillard 28 - L'environnement du château (2018)

This paper presents the CASTLE4D project and its application to the castle of Franchimont (Theux, Province of Liège, Belgium). The combination of traditional archaeological methods and new technologies ... [more ▼]

This paper presents the CASTLE4D project and its application to the castle of Franchimont (Theux, Province of Liège, Belgium). The combination of traditional archaeological methods and new technologies (3D digitisation) will result in the development of an Archaeological Information System (AIS), based on Geographic Information systems (GIS). This AIS is going to gather all types of available documents for the study of this castle whilst organising them spatially and chronologically around the 3D model. This tool will then help to create a historic geovisualisation, which should modify its appearance according to the selected time period and the data linked to this phase. This way, the establishment and the verification of hypothesis is going to have a visual support (the three-dimensional digitisation) and a collection of the sources on which the different theories were elaborated on. [less ▲]

Detailed reference viewed: 219 (34 ULiège)
Full Text
Peer Reviewed
See detailMODEL FOR REASONING FROM SEMANTICALLY RICH POINT CLOUD DATA
Poux, Florent ULiege; Neuville, Romain ULiege; Hallot, Pierre ULiege et al

in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2017, October 26), IV-4/W5

This paper proposes an interoperable model for managing high dimensional point clouds while integrating semantics. Point clouds from sensors are a direct source of information physically describing a 3D ... [more ▼]

This paper proposes an interoperable model for managing high dimensional point clouds while integrating semantics. Point clouds from sensors are a direct source of information physically describing a 3D state of the recorded environment. As such, they are an exhaustive representation of the real world at every scale: 3D reality-based spatial data. Their generation is increasingly fast but processing routines and data models lack of knowledge to reason from information extraction rather than interpretation. The enhanced smart point cloud developed model allows to bring intelligence to point clouds via 3 connected meta-models while linking available knowledge and classification procedures that permits semantic injection. Interoperability drives the model adaptation to potentially many applications through specialized domain ontologies. A first prototype is implemented in Python and PostgreSQL database and allows to combine semantic and spatial concepts for basic hybrid queries on different point clouds. [less ▲]

Detailed reference viewed: 116 (25 ULiège)
Full Text
Peer Reviewed
See detailTOWARDS A DECISION SUPPORT TOOL FOR 3D VISUALISATION: APPLICATION TO SELECTIVITY PURPOSE OF SINGLE OBJECT IN A 3D CITY SCENE
Neuville, Romain ULiege; Pouliot, Jacynthe; Poux, Florent ULiege et al

in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2017, October 26), IV-4/W5

This paper deals with the establishment of a comprehensive methodological framework that defines 3D visualisation rules and its application in a decision support tool. Whilst the use of 3D models grows in ... [more ▼]

This paper deals with the establishment of a comprehensive methodological framework that defines 3D visualisation rules and its application in a decision support tool. Whilst the use of 3D models grows in many application fields, their visualisation remains challenging from the point of view of mapping and rendering aspects to be applied to suitability support the decision making process. Indeed, there exists a great number of 3D visualisation techniques but as far as we know, a decision support tool that facilitates the production of an efficient 3D visualisation is still missing. This is why a comprehensive methodological framework is proposed in order to build decision tables for specific data, tasks and contexts. Based on the second-order logic formalism, we define a set of functions and propositions among and between two collections of entities: on one hand static retinal variables (hue, size, shape…) and 3D environment parameters (directional lighting, shadow, haze…) and on the other hand their effect(s) regarding specific visual tasks. It enables to define 3D visualisation rules according to four categories: consequence, compatibility, potential incompatibility and incompatibility. In this paper, the application of the methodological framework is demonstrated for an urban visualisation at high density considering a specific set of entities. On the basis of our analysis and the results of many studies conducted in the 3D semiotics, which refers to the study of symbols and how they relay information, the truth values of propositions are determined. 3D visualisation rules are then extracted for the considered context and set of entities and are presented into a decision table with a colour coding. Finally, the decision table is implemented into a plugin developed with three.js, a cross-browser JavaScript library. The plugin consists of a sidebar and warning windows that help the designer in the use of a set of static retinal variables and 3D environment parameters. [less ▲]

Detailed reference viewed: 61 (15 ULiège)
Full Text
Peer Reviewed
See detail3D Point Clouds in Archaeology: Advances in Acquisition, Processing and Knowledge Integration Applied to Quasi-Planar Objects
Poux, Florent ULiege; Neuville, Romain ULiege; Van Wersch, Line ULiege et al

in Geosciences (2017), 7(4), 96

Digital investigations of the real world through point clouds and derivatives are changing how curators, cultural heritage researchers and archaeologists work and collaborate. To progressively aggregate ... [more ▼]

Digital investigations of the real world through point clouds and derivatives are changing how curators, cultural heritage researchers and archaeologists work and collaborate. To progressively aggregate expertise and enhance the working proficiency of all professionals, virtual reconstructions demand adapted tools to facilitate knowledge dissemination. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. In this paper, we review the state of the art of point cloud integration within archaeological applications, giving an overview of 3D technologies for heritage, digital exploitation and case studies showing the assimilation status within 3D GIS. Identified issues and new perspectives are addressed through a knowledge-based point cloud processing framework for multi-sensory data, and illustrated on mosaics and quasi-planar objects. A new acquisition, pre-processing, segmentation and ontology-based classification method on hybrid point clouds from both terrestrial laser scanning and dense image matching is proposed to enable reasoning for information extraction. Experiments in detection and semantic enrichment show promising results of 94% correct semantization. Then, we integrate the metadata in an archaeological smart point cloud data structure allowing spatio-semantic queries related to CIDOC-CRM. Finally, a WebGL prototype is presented that leads to efficient communication between actors by proposing optimal 3D data visualizations as a basis on which interaction can grow. [less ▲]

Detailed reference viewed: 214 (47 ULiège)
See detailLiDAR aérien et autres nuages de points pour la cartographie multi-échelles
Poux, Florent ULiege; Neuville, Romain ULiege; Kasprzyk, Jean-Paul ULiege et al

Conference (2017, September 12)

Utilisation de nuage de points pour la cartographie 3D multi-échelles. Exemples d'utilisation et définition de workflows pour assurer l'interopérabilité lors de la fusion de données issues de différents ... [more ▼]

Utilisation de nuage de points pour la cartographie 3D multi-échelles. Exemples d'utilisation et définition de workflows pour assurer l'interopérabilité lors de la fusion de données issues de différents capteurs. [less ▲]

Detailed reference viewed: 86 (26 ULiège)
Full Text
Peer Reviewed
See detailPOINT CLOUD CLASSIFICATION OF TESSERAE FROM TERRESTRIAL LASER DATA COMBINED WITH DENSE IMAGE MATCHING FOR ARCHAEOLOGICAL INFORMATION EXTRACTION
Poux, Florent ULiege; Neuville, Romain ULiege; Hallot, Pierre ULiege et al

in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2017, August 16), IV-2/W2

Reasoning from information extraction given by point cloud data mining allows contextual adaptation and fast decision making. However, to achieve this perceptive level, a point cloud must be semantically ... [more ▼]

Reasoning from information extraction given by point cloud data mining allows contextual adaptation and fast decision making. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. This paper presents an automatic knowledge-based method for pre-processing multi-sensory data and classifying a hybrid point cloud from both terrestrial laser scanning and dense image matching. Using 18 features including sensor’s biased data, each tessera in the high-density point cloud from the 3D captured complex mosaics of Germigny-des-prés (France) is segmented via a colour multi-scale abstraction-based featuring extracting connectivity. A 2D surface and outline polygon of each tessera is generated by a RANSAC plane extraction and convex hull fitting. Knowledge is then used to classify every tesserae based on their size, surface, shape, material properties and their neighbour’s class. The detection and semantic enrichment method shows promising results of 94% correct semantization, a first step toward the creation of an archaeological smart point cloud. [less ▲]

Detailed reference viewed: 127 (23 ULiège)
Full Text
Peer Reviewed
See detailDIGITAL INVESTIGATIONS OF AN ARCHAEOLOGICAL SMART POINT CLOUD: A REAL TIME WEB-BASED PLATFORM TO MANAGE THE VISUALISATION OF SEMANTICAL QUERIES
Poux, Florent ULiege; Neuville, Romain ULiege; Hallot, Pierre ULiege et al

in Conservation of Cultural Heritage in the Digital Era (2017, May 16)

While virtual copies of the real world tend to be created faster than ever through point clouds and derivatives, their working proficiency by all professionals’ demands adapted tools to facilitate ... [more ▼]

While virtual copies of the real world tend to be created faster than ever through point clouds and derivatives, their working proficiency by all professionals’ demands adapted tools to facilitate knowledge dissemination. Digital investigations are changing the way cultural heritage researchers, archaeologists, and curators work and collaborate to progressively aggregate expertise through one common platform. In this paper, we present a web application in a WebGL framework accessible on any HTML5-compatible browser. It allows real time point cloud exploration of the mosaics in the Oratory of Germigny-des-Prés, and emphasises the ease of use as well as performances. Our reasoning engine is constructed over a semantically rich point cloud data structure, where metadata has been injected a priori. We developed a tool that directly allows semantic extraction and visualisation of pertinent information for the end users. It leads to efficient communication between actors by proposing optimal 3D viewpoints as a basis on which interactions can grow. [less ▲]

Detailed reference viewed: 106 (18 ULiège)