Centre dedocumentation
scientifique

Exploring the potential of deep learning segmentation for mountain roads generalisation / Azelle Courtial in ISPRS International journal of geo-information, vol 9 n° 5 (May 2020)  

Public [article]  inISPRS International journal of geo-information > vol 9 n° 5 (May 2020) . - 21 p. Titre : Exploring the potential of deep learning segmentation for mountain roads generalisation Type de document : Article/Communication Auteurs : Azelle Courtial, Auteur ; Achraf El Ayedi, Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Année de publication : 2020 Article en page(s) : 21 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] 1:25.000 [Termes descripteurs IGN] 1:250.000 [Termes descripteurs IGN] Alpes (France) [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données routières [Termes descripteurs IGN] données vectorielles [Termes descripteurs IGN] généralisation automatique de données [Termes descripteurs IGN] information géographique [Termes descripteurs IGN] montagne [Termes descripteurs IGN] route [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] symbole graphique [Termes descripteurs IGN] virage [Vedettes matières IGN] Généralisation Résumé : (auteur) Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potential on the popular mountain road generalisation problem, which requires smoothing the road, enlarging the bend summits, and schematising the bend series by removing some of the bends. We modelled the mountain road generalisation as a deep learning problem by generating an image from input vector road data, and tried to generate it as an output of the model a new image of the generalised roads. Similarly to previous studies on building generalisation, we used a U-Net architecture to generate the generalised image from the ungeneralised image. The deep learning model was trained and evaluated on a dataset composed of roads in the Alps extracted from IGN (the French national mapping agency) maps at 1:250,000 (output) and 1:25,000 (input) scale. The results are encouraging as the output image looks like a generalised version of the roads and the accuracy of pixel segmentation is around 65%. The model learns how to smooth the output roads, and that it needs to displace and enlarge symbols but does not always correctly achieve these operations. This article shows the ability of deep learning to understand and manage the geographic information for generalisation, but also highlights challenges to come. Numéro de notice : A2020-295 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9050338 date de publication en ligne : 25/05/2020 En ligne : https://doi.org/10.3390/ijgi9050338 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95131 [article]

Extending Processing Toolbox for assessing the logical consistency of OpenStreetMap data / Sukhjit Singh Sehra in Transactions in GIS, Vol 24 n° 1 (February 2020)  

Public [article]  inTransactions in GIS > Vol 24 n° 1 (February 2020) . - pp 44 - 71 Titre : Extending Processing Toolbox for assessing the logical consistency of OpenStreetMap data Type de document : Article/Communication Auteurs : Sukhjit Singh Sehra, Auteur ; Jaiteg Singh, Auteur ; Hardeep Singh Rai, Auteur Année de publication : 2020 Article en page(s) : pp 44 - 71 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes descripteurs IGN] cartographie collaborative [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] données localisées libres [Termes descripteurs IGN] données routières [Termes descripteurs IGN] Inde [Termes descripteurs IGN] information sémantique [Termes descripteurs IGN] intégrité topologique [Termes descripteurs IGN] morphologie urbaine [Termes descripteurs IGN] OpenStreetMap [Termes descripteurs IGN] QGIS [Termes descripteurs IGN] qualité des données Résumé : (auteur) OpenStreetMap (OSM) produces a huge amount of labeled spatial data, but its quality has always been a deep concern. Numerous quality issues have been discussed in the vast literature, while the fitness of OSM for road navigability is only partly explored. Navigability depends on logical consistency, which focuses on the existence of logical contradictions within a data set. Researchers have discussed the insufficiency of established methods and the lack of a computational paradigm to assess the quality of the OSM data. To address the research gaps, the current work extended the capabilities of the Quantum GIS Processing Toolbox for assessment of spatial data. The models and scripts developed are able to assess logical consistency based on geographical topological consistency, semantic information, and morphological consistency. The established and proxy indicators are selected for measuring the logical consistency of OSM data for navigability. For empirical validation, OSM Punjab data are compared with authoritative data from HERE (proprietary) and the Remote Sensing Centre (RSC), Punjab, India. The results conclude that even the proprietary road data sets are not free from logical inconsistencies and data contributed by the masses are credible and navigable. OSM has produced better results than the RSC, but needs more crowd contributions to improve its quality. Numéro de notice : A2020-101 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12587 date de publication en ligne : 08/11/2019 En ligne : https://doi.org/10.1111/tgis.12587 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94692 [article]

Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning / Yann Méneroux in International Journal of Data Science and Analytics JDSA, vol inconnu ([01/10/2019])  

Public [article]  inInternational Journal of Data Science and Analytics JDSA > vol inconnu [01/10/2019] Titre : Traffic signal detection from in-vehicle GPS speed profiles using functional data analysis and machine learning Type de document : Article/Communication Auteurs : Yann Méneroux , Auteur ; Arnaud Le Guilcher , Auteur ; Guillaume Saint Pierre, Auteur ; Mohammad Ghasemi Hamed, Auteur ; Sébastien Mustière , Auteur ; O. Orfila, Auteur Année de publication : 2019 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes descripteurs IGN] analyse fonctionnelle (mathématiques) [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] carte routière [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] contenu généré par les utilisateurs [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données routières [Termes descripteurs IGN] feu de circulation [Termes descripteurs IGN] inférence [Termes descripteurs IGN] reconnaissance de formes [Termes descripteurs IGN] signalisation routière [Termes descripteurs IGN] trace GPS [Termes descripteurs IGN] trafic routier [Termes descripteurs IGN] transformation en ondelettes [Termes descripteurs IGN] vitesse Résumé : (auteur) The increasing availability of large-scale global positioning system data stemming from in-vehicle-embedded terminal devices enables the design of methods deriving road network cartographic information from drivers’ recorded traces. Some machine learning approaches have been proposed in the past to train automatic road network map inference, and recently this approach has been successfully extended to infer road attributes as well, such as speed limitation or number of lanes. In this paper, we address the problem of detecting traffic signals from a set of vehicle speed profiles, under a classification perspective. Each data instance is a speed versus distance plot depicting over a hundred profiles on a 100-m-long road span. We proposed three different ways of deriving features: The first one relies on the raw speed measurements; the second one uses image recognition techniques; and the third one is based on functional data analysis. We input them into most commonly used classification algorithms, and a comparative analysis demonstrated that a functional description of speed profiles with wavelet transforms seems to outperform the other approaches with most of the tested classifiers. It also highlighted that random forests yield an accurate detection of traffic signals, regardless of the chosen feature extraction method, while keeping a remarkably low confusion rate with stop signs. Numéro de notice : A2019-497 Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s41060-019-00197-x date de publication en ligne : 04/10/2019 En ligne : https://doi.org/10.1007/s41060-019-00197-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93755 [article]

Geospatial information integration for authoritative and crowd sourced road vector data / H. Du in Transactions in GIS, vol 16 n° 4 (August 2012)  

Public [article]  inTransactions in GIS > vol 16 n° 4 (August 2012) . - pp 455 - 476 Titre : Geospatial information integration for authoritative and crowd sourced road vector data Type de document : Article/Communication Auteurs : H. Du, Auteur ; Natasha Alechina, Auteur ; G. Hart, Auteur ; et al., Auteur Année de publication : 2012 Article en page(s) : pp 455 - 476 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes descripteurs IGN] appariement de données localisées [Termes descripteurs IGN] conflation [Termes descripteurs IGN] données localisées de référence [Termes descripteurs IGN] données localisées des bénévoles [Termes descripteurs IGN] données routières [Termes descripteurs IGN] données vectorielles [Termes descripteurs IGN] intégration de données [Termes descripteurs IGN] ontologie Résumé : (Auteur) This article describes results from a research project undertaken to explore the technical issues associated with integrating unstructured crowd sourced data with authoritative national mapping data. The ultimate objective is to develop methodologies to ensure the feature enrichment of authoritative data, using crowd sourced data. Users increasingly find that they wish to use data from both kinds of geographic data sources. Different techniques and methodologies can be developed to solve this problem. In our previous research, a position map matching algorithm was developed for integrating authoritative and crowd sourced road vector data, and showed promising results (Anand et al. 2010). However, especially when integrating different forms of data at the feature level, these techniques are often time consuming and are more computationally intensive than other techniques available. To tackle these problems, this project aims at developing a methodology for automated conflict resolution, linking and merging of geographical information from disparate authoritative and crowd-sourced data sources. This article describes research undertaken by the authors on the design, implementation, and evaluation of algorithms and procedures for producing a coherent ontology from disparate geospatial data sources. To integrate road vector data from disparate sources, the method presented in this article first converts input data sets to ontologies, and then merges these ontologies into a new ontology. This new ontology is then checked and modified to ensure that it is consistent. The developed methodology can deal with topological and geometry inconsistency and provide more flexibility for geospatial information merging. Numéro de notice : A2012-362 Thématique : GEOMATIQUE/INFORMATIQUE/SOCIETE NUMERIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/j.1467-9671.2012.01303.x date de publication en ligne : 03/05/2012 En ligne : https://doi.org/10.1111/j.1467-9671.2012.01303.x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31808 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
040-2012041	SL	Revue	Centre de documentation	Revues en salle	Disponible