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]

Is deep learning the new agent for map generalization? / Guillaume Touya in International journal of cartography, vol 5 n° 2-3 (July - November 2019)  

Public [article]  inInternational journal of cartography > vol 5 n° 2-3 (July - November 2019) . - pp 142 - 157 Titre : Is deep learning the new agent for map generalization? Type de document : Article/Communication Auteurs : Guillaume Touya , Auteur ; Xiang Zhang, Auteur ; Imran Lokhat , Auteur Congrès : Congrès: ICC 2019, 29th International Cartographic Conference ICA Mapping everything for everyone (15 - 20 juillet 2019; Tokyo, Japon) , Commanditaire Année de publication : 2019 Projets : 1-Pas de projet / Article en page(s) : pp 142 - 157 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] généralisation cartographique automatisée [Termes descripteurs IGN] système multi-agents [Vedettes matières IGN] Généralisation Résumé : (Auteur) The automation of map generalization has been keeping researchers in cartography busy for years. Particularly great progress was made in the late 90s with the use of the multi-agent paradigm. Although the current use of automatic processes in some national mapping agencies is a great achievement, there are still many unsolved issues and research seems to stagnate in the recent years. With the success of deep learning in many fields of science, including geographic information science, this paper poses the controversial question of the title: is deep learning the new agent, i.e. the technique that will make generalization research bridge the gap to fully automated generalization processes? The paper neither responds a clear yes nor a clear no but discusses what issues could be tackled with deep learning and what the promising perspectives. Some preliminary experiments with building generalization or data enrichments are presented to support the discussion. Numéro de notice : A2019-235 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/23729333.2019.1613071 date de publication en ligne : 09/05/2019 En ligne : https://doi.org/10.1080/23729333.2019.1613071 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92932 [article]

Cropland extraction based on OBIA and adaptive scale pre-estimation / Ming Dongping in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 8 (August 2016)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 82 n° 8 (August 2016) . - pp 635 - 644 Titre : Cropland extraction based on OBIA and adaptive scale pre-estimation Type de document : Article/Communication Auteurs : Ming Dongping, Auteur ; Xiang Zhang, Auteur ; Min Wang, Auteur ; Wen Zhou, Auteur Année de publication : 2016 Article en page(s) : pp 635 - 644 Langues : Anglais (eng) Numéro de notice : A2016-609 Nature : Article En ligne : http://dx.doi.org/10.14358/PERS.82.8.635 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81809 [article]

Réservation

Réserver ce document

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2016082	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
105-2016081	SL	Revue	Centre de documentation	Revues en salle	Disponible

A vector field model to handle the displacement of multiple conflicts in building generalization / Tinghua Ai in International journal of geographical information science IJGIS, vol 29 n° 8 (August 2015)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 29 n° 8 (August 2015) . - pp 1310 - 1331 Titre : A vector field model to handle the displacement of multiple conflicts in building generalization Type de document : Article/Communication Auteurs : Tinghua Ai, Auteur ; Xiang Zhang, Auteur ; Qi Zhou, Auteur ; Min Yang, Auteur Année de publication : 2015 Article en page(s) : pp 1310 - 1331 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] conflit d'espace [Termes descripteurs IGN] détection de conflit [Termes descripteurs IGN] généralisation cartographique automatisée [Termes descripteurs IGN] généralisation du bâti [Termes descripteurs IGN] partition des données [Termes descripteurs IGN] relation spatiale [Termes descripteurs IGN] triangulation de Delaunay [Vedettes matières IGN] Généralisation Résumé : (Auteur) In map generalization, the displacement operation attempts to resolve proximity conflicts to guarantee map legibility. Owing to the limited representation space, conflicts may occur between both the same and different features under different contexts. A successful displacement should settle multiple conflicts, suppress the generation of secondary conflicts after moving some objects, and preserve the distribution patterns. The effect of displacement can be understood as a force that pushes related objects away with properties of propagation and distance decay. This study borrows the idea of vector fields from physics discipline and establishes a vector field model to handle the displacement of multiple conflicts in building generalization. A scalar field is first constructed based on a Delaunay triangulation skeleton to partition the buildings being examined (e.g., a street block). Then, we build a vector field to conduct displacement measurements through the detection of conflicts from multiple sources. The direction and magnitude of the displacement force are computed based on an iso-line model of vector field. The experiment shows that this global method can settle multiple conflicts and preserve the spatial relations and important building patterns. Numéro de notice : A2015-604 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2015.1019886 En ligne : https://doi.org/10.1080/13658816.2015.1019886 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78025 [article]

Detection and correction of inconsistencies between river networks and contour data by spatial constraint knowledge / Tinghua Ai in Cartography and Geographic Information Science, Vol 42 n° 1 (January 2015)  

Public [article]  inCartography and Geographic Information Science > Vol 42 n° 1 (January 2015) . - pp 79 - 93 Titre : Detection and correction of inconsistencies between river networks and contour data by spatial constraint knowledge Type de document : Article/Communication Auteurs : Tinghua Ai, Auteur ; Min Yang, Auteur ; Xiang Zhang, Auteur ; Jing Tian, Auteur Année de publication : 2015 Article en page(s) : pp 79 - 93 Note générale : Bibliographie Langues : Anglais (eng) Résumé : (auteur) In the representation of topographic data, the distribution of hydrographic networks should be constrained by the contour model’s landform features. During the integration of topographic databases, however, spatial conflicts may destroy these constraints, generating inconsistencies. This study presents a method to detect and correct inconsistencies between river networks and contour data by spatial knowledge. First, structured terrain features are extracted from the contour-based geometric representation and matching relationships between rivers and contours are constructed based on spatial knowledge of the distribution of rivers and talwegs. We then propose a distance metric for measuring differences and identifying inconsistencies between the matched river and contour features. Three correction approaches are provided for different inconsistency situations, including river adjustment referenced to the contour, contour adjustment referenced to the river and adjustment of both river and contour to middle positions. We apply the proposed method to the integration and maintenance of national topographic infrastructure in order to demonstrate its effectiveness. Numéro de notice : A2015-235 Nature : Article DOI : 10.1080/15230406.2014.956673 En ligne : https://doi.org/10.1080/15230406.2014.956673 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76228 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
032-2015011	SL	Revue	Centre de documentation	Revues en salle	Disponible

Formalization and data enrichment for automated evaluation of building pattern preservation / Xiang Zhang (2010) 

Permalink