Centre de documentation
scientifique

CrossroadsDescriber, automatic textual description of OpenStreetMap intersections / Jérémy Kalsron (2022)  

Public Titre : CrossroadsDescriber, automatic textual description of OpenStreetMap intersections Type de document : Article/Communication Auteurs : Jérémy Kalsron, Auteur ; Jean-Marie Favreau, Auteur ; Guillaume Touya , Auteur Editeur : AGILE Alliance Année de publication : 2022 Projets : ACTIVmap / Favreau, Jean-Marie Conférence : AGILE 2022, 25th international AGILE Conference on Geographic Information Science, Artificial intelligence in the service of geospatial technologies 14/06/2022 17/06/2022 Vilnius Lithuanie OA Proceedings Importance : 6 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] implémentation (informatique) [Termes IGN] intersection spatiale [Termes IGN] modèle conceptuel de données localisées [Termes IGN] OpenStreetMap Résumé : (Auteur) Crossing an intersection is a challenge for visually impaired people. While tactile maps can be a medium for appropriating this complex space, they benefit from being complemented by audio information. In this paper we propose a data model to describe an intersection, the paths that allow to cross it, and their accessibility attributes. We also present methods to generate this model automatically from OpenStreetMap, by inferring missing data through graph analysis techniques. Finally, we present an implementation, the evaluation of which confirms the ability of the model to generate a compliant description for intersections with enough data. Numéro de notice : C2022-025 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : https://agile-giss.copernicus.org/articles/3/40/2022/ Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-3-40-2022 Date de publication en ligne : 10/06/2022 En ligne : https://hal.science/hal-03694759v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100927

A method to produce metadata describing and assessing the quality of spatial landmark datasets in mountain area / Marie-Dominique Van Damme (2022)  

Public Titre : A method to produce metadata describing and assessing the quality of spatial landmark datasets in mountain area Type de document : Article/Communication Auteurs : Marie-Dominique Van Damme , Auteur ; Ana-Maria Olteanu-Raimond , Auteur Editeur : Göttingen : Copernicus publications Année de publication : 2022 Projets : CHOUCAS / Olteanu-Raimond, Ana-Maria Conférence : AGILE 2022, 25th international AGILE Conference on Geographic Information Science, Artificial intelligence in the service of geospatial technologies 14/06/2022 17/06/2022 Vilnius Lithuanie OA Proceedings Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Infrastructure de données [Termes IGN] Alpes (France) [Termes IGN] appariement de données localisées [Termes IGN] données localisées [Termes IGN] données ouvertes [Termes IGN] jeu de données localisées [Termes IGN] loisir [Termes IGN] métadonnées géographiques [Termes IGN] montagne [Termes IGN] norme ISO [Termes IGN] ontologie [Termes IGN] qualité des données Résumé : (auteur) The increase of recreational activities in the mountains and a growing amount of websites proposing geographic data, offer new opportunities for societal needs such as mountain rescue, biodiversity monitoring, outdoor activities. However, the main issue with the websites data is the lack of metadata that minimizes its reuse outside the community that produced the data. The goal of this paper is to study and generate quality and descriptive metadata using ISO standards. To this end, we propose a method based on a common vocabulary such as an ontology and a data matching process. The first one allows to associate to each type of feature from an available geographic dataset an ontology class that will facilitate data matching, reproducibility of results and minimize semantic heterogeneity. The second one allows to define matching links between features representing the same entity in the real world and compute quality indicators based on the validated links. Finally, at the end of this process, we are able to generate descriptive and quality metadata. By following ISO standards and using the QualityML dictionary for measures, the metadata is serialized to XML and can finally be published as open source. Our approach was applied to five different landmark datasets in the French Alps region. New insights were acquired regarding positional accuracy and semantic granularity. Numéro de notice : C2022-027 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-3-17-2022 Date de publication en ligne : 10/06/2022 En ligne : https://doi.org/10.5194/agile-giss-3-17-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100928

Representing vector geographic information as a tensor for deep learning based map generalisation / Azelle Courtial (2022)  

Public Titre : Representing vector geographic information as a tensor for deep learning based map generalisation Type de document : Article/Communication Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Editeur : AGILE Alliance Année de publication : 2022 Projets : 1-Pas de projet / Olteanu-Raimond, Ana-Maria Conférence : AGILE 2022, 25th international AGILE Conference on Geographic Information Science, Artificial intelligence in the service of geospatial technologies 14/06/2022 17/06/2022 Vilnius Lithuanie OA Proceedings Importance : 8 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] alignement des données [Termes IGN] apprentissage profond [Termes IGN] architecture de réseau [Termes IGN] bati [Termes IGN] carte topographique [Termes IGN] couche [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données vectorielles [Termes IGN] information sémantique [Termes IGN] milieu urbain [Termes IGN] route [Termes IGN] tenseur [Vedettes matières IGN] Généralisation Résumé : (auteur) Recently, many researchers tried to generate (generalised) maps using deep learning, and most of the proposed methods deal with deep neural network architecture choices. Deep learning learns to reproduce examples, so we think that improving the training examples, and especially the representation of the initial geographic information, is the key issue for this problem. Our article extracts some representation issues from a literature review and proposes different ways to represent vector geographic information as a tensor. We propose two kinds of contributions: 1) the representation of information by layers; 2) the representation of additional information. Then, we demonstrate the interest of some of our propositions with experiments that show a visual improvement for the generation of generalised topographic maps in urban areas. Numéro de notice : C2022-024 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-3-32-2022 En ligne : https://doi.org/10.5194/agile-giss-3-32-2022 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100921

When is a ring road a ’ring road’? A brief perceptual study / Quentin Potié (2022)  

Public Titre : When is a ring road a ’ring road’? A brief perceptual study Type de document : Article/Communication Auteurs : Quentin Potié , Auteur ; William A Mackaness, Auteur ; Guillaume Touya , Auteur Editeur : Göttingen : Copernicus publications Année de publication : 2022 Projets : LostInZoom / Touya, Guillaume Conférence : AGILE 2022, 25th international AGILE Conference on Geographic Information Science, Artificial intelligence in the service of geospatial technologies 14/06/2022 17/06/2022 Vilnius Lithuanie OA Proceedings Importance : 7 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] amer visuel [Termes IGN] caractérisation [Termes IGN] cognition [Termes IGN] étude préliminaire [Termes IGN] route [Termes IGN] ville [Termes IGN] vision [Vedettes matières IGN] Cartologie Résumé : (auteur) The shapes and patterns of the road network of a topographic map provide important visual cues when interpreting the map and moving between scales in interactive environments. The ’city ring road’ is an example of a road structure we might use in the recognition and characterisation of a city. Our goal is the automatic identification (and preservation) of such structures through changing scales. In this preliminary study, we conducted an online survey and face to face interviews in order to obtain and prioritise the structural, topological and semantic properties that define ’ring road-ness’. We then created a practical ontology of ring roads, with a view to algorithm implementation that mirrors the human perception of ring roads. Numéro de notice : C2022-026 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-3-54-2022 Date de publication en ligne : 11/06/2022 En ligne : https://doi.org/10.5194/agile-giss-3-54-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100929