Descripteur
Documents disponibles dans cette catégorie (1304)
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
contenu dans AutoCarto 2006, Vancouver, Washington, Volume 2. Papers / Cartography and geographic information society (2006)
Titre : Methods for improving and updating the knowledge of a generalization system Type de document : Article/Communication Auteurs : Anne Ruas , Auteur ; Aurélie Dyèvre, Auteur ; Cécile Duchêne , Auteur ; Patrick Taillandier , Auteur Editeur : Cartography and Geographic Information Society Année de publication : 2006 Conférence : Auto-Carto 2006, international symposium on cartography and computing 26/06/2006 28/06/2006 Vancouver Colombie britannique - Canada OA Proceedings Importance : 11 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] agent (intelligence artificielle)
[Termes IGN] apprentissage dirigé
[Termes IGN] base de connaissances
[Termes IGN] base de règles
[Termes IGN] bati
[Termes IGN] généralisation cartographique automatisée
[Vedettes matières IGN] GénéralisationRésumé : (Auteur) In this paper we present a method to improve and to update the knowledge used for the automation of the generalization of buildings based on agent paradigm. We propose to store 1/ each building decision, 2/ the reason why the decision was taken (the conflicts) 3/ the result of each algorithm (an improvement or not) and 4/ the successful process chain within all trials. At the end, the processes of all buildings are compared in order to identify the weakness (for example the case where a specific algorithm is often used but never succeeds). When a deficiency is identified we introduce new rules and we study the effect of this change on the efficiency of the process. It can be used either to improve existing knowledge or to introduce new rules associate to the use of a new measure or a new algorithm. The first study has been made on building independent generalization to set the learning methodology. We wish now to apply it on more complex cases such as contextual generalization which still needs knowledge improvement. Numéro de notice : 14347 Affiliation des auteurs : COGIT (1988-2011) Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication DOI : sans En ligne : https://cartogis.org/docs/proceedings/2006/ruas_dyevre_duchene_taillandier.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=64342 Documents numériques
en open access
14347_auto-carto_2006_ruas_dyevre_duchene_taillandier.pdfAdobe Acrobat PDF
Titre : Modeling and visualizing dynamic landscape objects and their qualities Type de document : Thèse/HDR Auteurs : Daniel van de Vlag, Auteur ; Alfred Stein, Directeur de thèse ; Menno-Jan Kraak, Directeur de thèse Editeur : Enschede [Pays Bas] : University of Twente Année de publication : 2006 Collection : ITC Dissertation num. 132 Importance : 170 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-90-8504-384-3 Note générale : bibliographie Langues : Français (fre) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] analyse multivariée
[Termes IGN] arbre de décision
[Termes IGN] classification ascendante hiérarchique
[Termes IGN] données spatiotemporelles
[Termes IGN] incertitude des données
[Termes IGN] objet géographique
[Termes IGN] ontologieIndex. décimale : THESE Thèses et HDR Résumé : (auteur) This thesis focuses on modeling and visualizing dynamic landscape objects and their qualities. It contains ontologies to characterize and model dynamic landscape features using spatial data. It considers their spatial data qualities and visualizes them by explorative methods. In this study, the dynamic landscape features are derived from a coastal movement application within the Netherlands, whereby beaches are subject to nourishment due to severe erosion. The description and classification of beach objects and their processes essentially grounds on the perception of the coastal landscape. Modeling a landscape is a basic agreement on the conceptualization of these features and processes. The aim is to develop a framework for conceptualization of dynamic beach objects, to understand the physical processes involved and to illustrate decision rules adopted in classification of these objects. Also, quality issues related to beach nourishments are studied, visualized and explored, using new visualization techniques. A domain-specific ontology can serve as a framework for the conceptualization of beach objects and their processes. The discrimination into product and problem ontology supports the guidance for classification of these objects and to elucidate which data ‘fit for use’. Data qualities are assessed using a quality matrix, where ontological features are portrayed against quality elements. Elements of positional, thematic and temporal accuracy and data completeness are considered of high importance for the beach nourishment application. The problem and product ontology helps to define two scenarios; the first determined by the regulations from the Ministry for Public Works; the second grounded on the abilities from an existing spatial dataset. A comparison between them shows that 72.8% of the objects suitable and non-suitable for nourishment are correctly classified. A higher overlap is found in areas where actual beach nourishments were carried out. Inaccuracies in attributes, i.e. altitude, vegetation and wetness, influence the determination of the objects. A sensitivity analysis applied on altitude shows that determinate boundaries for beach nourishment objects are not reasonable and consequently should be treated as vague objects. The ontology for beach objects is extended with a spatio-temporal ontology that considers objects to be vague and dynamic. It contains full membership functions for crisp objects, partial membership functions for fuzzy objects and temporal membership functions for dynamic fuzzy objects. The temporal membership functions include seasonal changes of vegetation and daily changes in wetness. A sensitivity analysis shows that the calculated beach nourishment volumes are practically insensitive in relation to assumptions on the temporal membership functions. A spatio-temporal ontology, as an extent of a spatial ontology, is shown to model dynamic processes in landscape studies in a more realistic way. To classify a coastal landscape, I also consider the level of scale. Object hierarchy is essential but is often ignored when collecting and classifying landscape features. A fuzzy decision tree considers a hierarchical structure for classification based on decision rules on object attributes. These attributes are defined on the basis of uncertain parameters that may change in space and time. A Bayesian hierarchical model deals with modeling and handling this uncertainty. In the beach management application, Bayesian hierarchical modeling is applied to obtain posterior probability distributions for several boundary regions. The posterior distributions yield lower and upper limits of membership functions describing boundaries between object classes. In this way, a proper fuzzy decision tree is build that includes the inherent dynamic uncertainty. The spatial information of the application contains large multivariate and multi-temporal datasets. An integrated prototype for visualization and exploration of multivariate spatiotemporal datasets is introduced. It is applied to understand and explain the behaviour of dynamic beach objects and their uncertainties. It consists of the map environment (MAP), a parallel coordinate plot environment (PCP) for visualizing attributes of the dataset, and a temporal ordered space matrix environment (TOSM) for presenting spatio-temporal patterns. The TOSM is a new exploration method and can be seen as a schematized map, whereby the rows in the TOSM environment represent time, the columns represent geographic units, and individual cells are colored according to the value of user defined attributes. The prototype is applied on four case studies. A usability test is performed to test for the differences in the ability to detect patterns in multivariate spatio-temporal datasets for each environment. Test measures are efficiency, effectiveness and user’s satisfaction. Results show that the TOSM environment and the integrated prototype have significantly better performances in efficiency and user’s satisfaction than the MAP and PCP environment. Note de contenu : 1: Introduction
2: Ameland case study
3: An application of problem and product ontologies for the revision of beach nourishments
4: Modeling Dynamic Beach Objects Using Spatio-temporal Ontologies
5: Incorporating Uncertainty via Hierarchical Classification using Fuzzy Decision Trees
6: Temporal Ordered Space Matrix: Representation of Multivariate Spatio-temporal Data
7: ConclusionsNuméro de notice : 17248 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Thèse étrangère Note de thèse : PhD thesis : Géomatique : ITC : 2006 En ligne : http://library.wur.nl/WebQuery/wurpubs/348623 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81878 Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 17248-01 THESE Livre Centre de documentation Thèses Disponible SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 3. Conférenciers invités, Journées Ontologie et textes juridiques, Indexation des connaissances en sciences humaines / Mounira Harzallah (2006)
Titre de série : SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 3 Titre : Conférenciers invités, Journées Ontologie et textes juridiques, Indexation des connaissances en sciences humaines Type de document : Actes de congrès Auteurs : Mounira Harzallah, Éditeur scientifique ; Jean Charlet, Éditeur scientifique ; Nathalie Aussenac-Gilles, Éditeur scientifique Editeur : Nantes : Université de Nantes Année de publication : 2006 Conférence : SdC 2006, Semaine de la connaissance 26/06/2006 30/06/2006 Nantes France OA Proceedings Importance : 86 p. Format : 21 x 30 cm Langues : Français (fre) Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] analyse des risques
[Termes IGN] analyse du discours
[Termes IGN] apprentissage automatique
[Termes IGN] droit
[Termes IGN] ingénierie des connaissances
[Termes IGN] ontologie
[Termes IGN] recherche interdisciplinaire
[Termes IGN] science de l'information
[Termes IGN] sciences humaines et sociales
[Termes IGN] système de gestion de connaissances
[Termes IGN] terminologieIndex. décimale : CG2006 Actes de congrès en 2006 Note de contenu : - Conférenciers invités
- Ontologies et textes juridiques
- Indexation et connaissances en sciences humainesNuméro de notice : 24699C Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Actes Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92547 Voir aussi
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 4. Applications industrielles des technologies de la connaisance ; Pratiques et méthodes de classification du savoir à l'heure d'internet ; Récit et gestion des connaissances ; Représentation et raisonnement sur le temps et l'espace / Mounira Harzallah (2006)
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 1. IC 2006, 17es Journées francophones d'ingénierie des connaissances / Mounira Harzallah (2006)
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 2. Coopération, Innovation, Technologie ; Connaissances et compétences en entreprise industrielle ; activité collective et connaissance dans les organisations / Mounira Harzallah (2006)
Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 24699-01C CG2006 Livre Centre de documentation Congrès Disponible SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 4. Applications industrielles des technologies de la connaisance ; Pratiques et méthodes de classification du savoir à l'heure d'internet ; Récit et gestion des connaissances ; Représentation et raisonnement sur le temps et l'espace / Mounira Harzallah (2006)
Titre de série : SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 4 Titre : Applications industrielles des technologies de la connaisance ; Pratiques et méthodes de classification du savoir à l'heure d'internet ; Récit et gestion des connaissances ; Représentation et raisonnement sur le temps et l'espace Type de document : Actes de congrès Auteurs : Mounira Harzallah, Éditeur scientifique ; Jean Charlet, Éditeur scientifique ; Nathalie Aussenac-Gilles, Éditeur scientifique Editeur : Nantes : Université de Nantes Année de publication : 2006 Conférence : SdC 2006, Semaine de la connaissance 26/06/2006 30/06/2006 Nantes France OA Proceedings Importance : 180 p. Format : 21 x 30 cm Langues : Français (fre) Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] analyse syntaxique
[Termes IGN] apprentissage automatique
[Termes IGN] classification à base de connaissances
[Termes IGN] classification automatique
[Termes IGN] information géographique
[Termes IGN] ingénierie des connaissances
[Termes IGN] ontologie
[Termes IGN] référentiel sémantique
[Termes IGN] science de l'information
[Termes IGN] système de gestion de connaissances
[Termes IGN] terminologie
[Termes IGN] web sémantiqueIndex. décimale : CG2006 Actes de congrès en 2006 Note de contenu : - Applications industrielles des technologies de la connaissance
- Pratiques et méthodes de classification du savoir à l'heure d'Internet
- Récit et gestion des connaissances
- Représentation et raisonnement sur le temps et l'espaceNuméro de notice : 24699D Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Actes Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92548 Voir aussi
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 1. IC 2006, 17es Journées francophones d'ingénierie des connaissances / Mounira Harzallah (2006)
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 3. Conférenciers invités, Journées Ontologie et textes juridiques, Indexation des connaissances en sciences humaines / Mounira Harzallah (2006)
- SdC 2006, Semaine de la connaissance, 26 - 30 juin 2006, Nantes, France, Volume 2. Coopération, Innovation, Technologie ; Connaissances et compétences en entreprise industrielle ; activité collective et connaissance dans les organisations / Mounira Harzallah (2006)
Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 24699-01D CG2006 Livre Centre de documentation Congrès Disponible
Titre : Tree detection in aerial LIDAR and image data Type de document : Article/Communication Auteurs : John Secord, Auteur ; Avideh Zahkor, Auteur Editeur : New York [Etats-Unis] : IEEE Signal Processing Society Année de publication : 2006 Conférence : ICIP 2006, 13th IEEE International Conference on Image Processing 08/10/2006 11/10/2006 Atlanta Géorgie - Etats-Unis Proceedings IEEE Importance : 35 p. Format : 21 x 30 cm Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] apprentissage dirigé
[Termes IGN] classification dirigée
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] détection d'arbres
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] image aérienne
[Termes IGN] modélisation 3D
[Termes IGN] segmentationRésumé : (auteur) In this paper, we present an approach to detecting trees in registered aerial image and range data obtained via LiDAR. The motivation for this problem comes from automated city modeling, in which such data is used to generate textured 3-D models. Representing the trees in these models is problematic because the data is usually too sparsely sampled in tree regions to create an accurate 3-D model of the trees. Furthermore, including the tree data points interferes with the polygonization step of the building roof top models. Therefore, it is advantageous to detect and remove points that represent trees in both LiDAR and aerial imagery. In this paper, we propose a two-step method for tree detection consisting of segmentation followed by classification. The segmentation is done using a simple region-growing algorithm using weighted features from aerial image and LiDAR, such as height, texture map, height variation, and normal vector estimates. The weights for the features are determined using a learning method on random walks. The classification is done using weighted support vector machines (SVM), allowing us to control the misclassification rate. The overall problem is formulated as a binary detection problem, and receiver operating characteristic curves are shown to validate our approach. Numéro de notice : C2006-024 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Communication DOI : 10.1109/ICIP.2006.312850 En ligne : https://doi.org/10.1109/ICIP.2006.312850 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90963 Integrating LIDAR elevation data, multi-spectral imagery and neural network modelling for marsh characterization / J.T. Morris in International Journal of Remote Sensing IJRS, vol 26 n° 23 (December 2005)PermalinkA change detection model based on neighborhood correlation image analysis and decision tree classification / J. Im in Remote sensing of environment, vol 99 n° 3 (30/11/2005)PermalinkAn application of problem and product ontologies for the revision beach nourishments / Daniel van de Vlag in International journal of geographical information science IJGIS, vol 19 n° 10 (november 2005)PermalinkSupervised image classification by contextual adaboost based on posteriors in neighborhoods / Ryuei Nishii in IEEE Transactions on geoscience and remote sensing, vol 43 n° 11 (November 2005)PermalinkAn artificial-neural-network-based, constrained CA model for simulating urban growth / Q. Guan in Cartography and Geographic Information Science, vol 32 n° 4 (October 2005)PermalinkExploring the hidden potential of common spatial data models to visualize uncertainty / J. Kardos in Cartography and Geographic Information Science, vol 32 n° 4 (October 2005)PermalinkCartographic generalization of roads in a local and adaptive approach: A knowledge acquistion problem / Sébastien Mustière in International journal of geographical information science IJGIS, vol 19 n° 8 - 9 (september 2005)PermalinkAutomatic 3D object recognition and reconstruction based on neuro-fuzzy modelling / F. Samadzadegan in ISPRS Journal of photogrammetry and remote sensing, vol 59 n° 5 (August - October 2005)PermalinkA statistical self-organizing learning system for remote sensing classification / H.M. Chi in IEEE Transactions on geoscience and remote sensing, vol 43 n° 8 (August 2005)PermalinkAssessment of simulated cognitive maps: the influence of prior knowledge from cartographic maps / R.E. Lloyd in Cartography and Geographic Information Science, vol 32 n° 3 (July 2005)Permalink