Détail de l'éditeur
ICA Commission on Generalisation and Multiple Representation
|
Documents disponibles chez cet éditeur (8)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externesConstraint based evaluation of generalized images generated by deep learning / Azelle Courtial (2020)
Titre : Constraint based evaluation of generalized images generated by deep learning Type de document : Article/Communication Auteurs : Azelle Courtial Editeur : ICA Commission on Generalisation and Multiple Representation Année de publication : 2020 Projets : 1-Pas de projet / Conférence : ICA 2020, 23rd Workshop on Map Generalisation and Multiple Representation 05/11/2020 06/11/2020 Delft Pays-Bas Open Access Proceedings Importance : 3 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Français (fre) Descripteur : [Termes IGN] 1:25.000
[Termes IGN] 1:250.000
[Termes IGN] Alpes (France)
[Termes IGN] apprentissage profond
[Termes IGN] carte routière
[Termes IGN] classification pixellaire
[Termes IGN] données maillées
[Termes IGN] généralisation automatique de données
[Termes IGN] généralisation cartographique automatisée
[Termes IGN] montagne
[Termes IGN] précision cartographique
[Termes IGN] programmation par contraintes
[Termes IGN] réseau routier
[Vedettes matières IGN] GénéralisationRésumé : (Auteur) The use of deep learning techniques for map generalisation raises new problems regarding the evaluation of the results: (1) images are used as input/output instead of vector data; (2) the deep learning processes do not guarantee results that follow cartographic principles; (3) the deep learning models are black boxes that hide the causal mechanisms. Also, deep learning intern evaluation is mostly based on the realism of the images and the pixel classification accuracy, and none of these criteria is sufficient to evaluate a generalisation process. In this article, we propose an adaptation of the constraint-based evaluation to the images generated by deep learning. Six raster-based constraints are proposed for a mountain road generalisation use case. Numéro de notice : C2020-018 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans Date de publication en ligne : 17/11/2020 En ligne : https://varioscale.bk.tudelft.nl/events/icagen2020/ICAgen2020/ICAgen2020_paper_2 [...] Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96380
Titre : MapGenOnto: A shared ontology for map generalisation and multi-scale visualisation Type de document : Article/Communication Auteurs : Guillaume Touya Editeur : ICA Commission on Generalisation and Multiple Representation Année de publication : 2020 Projets : 1-Pas de projet / Conférence : ICA 2020, 23rd Workshop on Map Generalisation and Multiple Representation 05/11/2020 06/11/2020 Delft Pays-Bas Open Access Proceedings Importance : 3 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] généralisation automatique de données
[Termes IGN] ontologie
[Termes IGN] plateforme collaborative
[Termes IGN] visualisation de données
[Vedettes matières IGN] GénéralisationRésumé : (auteur) The usefulness of ontologies for map generalisation and on-demand mapping has been acknowledged by the research community for now more than ten years. But past attempts to build an ontology that shares the conceptualisation views of the community have fell short for now, maybe due to a lack of direct use cases. MapGenOnto is a new attempt to gather researchers around a shared ontology that covers the description of the geography and the map, and also the generalisation processes used to generalise this map. This short paper briefly describes the backbone concepts of this ontology, and then presents a use case to describe cross-platform ScaleMaster2.0 specifications. Numéro de notice : C2020-017 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans Date de publication en ligne : 17/11/2020 En ligne : https://varioscale.bk.tudelft.nl/events/icagen2020/ICAgen2020/ICAgen2020_paper_1 [...] Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96318
Titre : Mapping heterogeneous data: a case study on the French Green Infrastructure Type de document : Article/Communication Auteurs : Cécile Duchêne Editeur : ICA Commission on Generalisation and Multiple Representation Année de publication : 2017 Conférence : ICC 2017, 20th ICA Workshop on Generalisation and Multiple Representation 01/07/2017 02/07/2017 Washington DC Etats-Unis OA program Importance : 9 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] carte thématique
[Termes IGN] données hétérogènes
[Termes IGN] France (administrative)
[Termes IGN] généralisation cartographique automatisée
[Termes IGN] harmonisation des données
[Termes IGN] interopérabilité
[Termes IGN] trame verte et bleue
[Termes IGN] utilisation du solRésumé : (auteur) To achieve a preservation and restoration of ecosystems, public environmental policies at the international level are fostering the implementation of Green Infrastructures, i.e. networks composed of areas where animal and vegetal species can live (habitat patches), and corridors to circulate between them. In France, defining existing habitat patches and corridors was ensured in a distributed manner by the Regions, the first subnational administrative level, with flexible guidelines. It resulted in very heterogeneous data in terms of level of detail, raising the question: “How to map such heterogeneous data at a supra-regional level, making them understandable while respecting the work of Regions, and with a reasonable amount of human work?”. Our study focuses on habitat patches of two adjacent Regions. After making a “rough” map directly from the provided data, we explore three ways for homogenizing the map. The first method consists in generalizing the more detailed data using simple morphologic operators. The second method consists in graphically refining the less detailed data by filling the areas with a pattern taken from the more detailed data. The third method consists in drastically changing the level of abstraction of the data on both regions, while rasterizing the space. Although it would be necessary to test the resulting maps on potential users, we think the third approach is probably the only one usable. Numéro de notice : C2017-035 Affiliation des auteurs : LASTIG COGIT+Ext (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89950 Documents numériques
en open access
Mapping heterogeneous data ... - pdf éditeurAdobe Acrobat PDF
Titre : Progressive block graying and landmarks enhancing as intermediate representations between buildings and urban areas Type de document : Article/Communication Auteurs : Guillaume Touya Editeur : ICA Commission on Generalisation and Multiple Representation Année de publication : 2017 Conférence : ICC 2017, 20th ICA Workshop on Generalisation and Multiple Representation 01/07/2017 02/07/2017 Washington DC Etats-Unis OA program Importance : 10 p. Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse multicritère
[Termes IGN] apprentissage automatique
[Termes IGN] base de données cartographiques
[Termes IGN] estompage automatique
[Termes IGN] généralisation du bâti
[Termes IGN] point de repère
[Termes IGN] relation spatiale
[Termes IGN] zone urbaine
[Termes IGN] zoom
[Vedettes matières IGN] GénéralisationRésumé : (Auteur) Geovisualization applications that allow the navigation between maps at different scales while zooming in and out often provide no smooth transition between the individual building level of abstraction and the representation of whole urban areas as polygons. In order to reduce the cognitive load of the user, we seek to add intermediate zoom levels with intermediate and progressive abstractions between buildings and urban areas. This paper proposes a method based on progressive block graying while enhancing building landmarks, to derive these intermediate representations from the individual buildings. Block graying is based on an automatic building classification, and a multiple criteria decision technique to infer inner city blocks. The landmarks identification relies on machine learning and several criteria based on geometry and spatial relations. The method is tested with real cartographic data between the 1:25k (with individual buildings) and the 1:100k scale (with urban areas): transitions with one, two, or three intermediate representations are derived and tested. Numéro de notice : C2017-007 Affiliation des auteurs : LASTIG COGIT (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86201 Documents numériques
en open access
Progressive_Block_Graying_and_Landmarks_Enhancing - postprintAdobe Acrobat PDF
Titre : Collaboration on an ontology for generalisation Type de document : Article/Communication Auteurs : Nick Gould, Auteur ; William A Mackaness, Auteur ; Guillaume Touya Editeur : ICA Commission on Generalisation and Multiple Representation Année de publication : 2014 Conférence : ICA 2014, 17th workshop on Generalisation and Multiple Representation 22/09/2014 26/09/2014 Vienne Autriche Open access proceedings Importance : 9 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] algorithme de généralisation
[Termes IGN] base de connaissances
[Termes IGN] cartographie collaborative
[Termes IGN] généralisation cartographique automatisée
[Termes IGN] ontologie
[Vedettes matières IGN] GénéralisationRésumé : (auteur) To move beyond the current plateau in automated cartography, we need greater sophistication in the process of selecting generalisation algorithms. This is particularly so in the context of machine comprehension. We also need to build on existing algorithm development instead of duplication. More broadly, we need to model the geographical context that drives the selection, sequencing and degree of application of generalisation algorithms. We argue that a collaborative effort is required to create and share an ontology for cartographic generalisation focused on supporting the algorithm selection process. The benefits of developing a collective ontology will be the increased sharing of algorithms and support for on-demand mapping and generalisation web services. Numéro de notice : C2014-011 Affiliation des auteurs : LASTIG COGIT+Ext (2012-2019) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : http://generalisation.icaci.org/index.php/prevevents/11-previous-events-details/ [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78486 Documents numériques
en open access
Collaboration on an Ontology for GeneralisationAdobe Acrobat PDF
