Centre dedocumentation
scientifique

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks / Mahmoud Saeedimoghaddam in International journal of geographical information science IJGIS, vol 34 n° 5 (May 2020)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 34 n° 5 (May 2020) . - pp 947 - 968 Titre : Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks Type de document : Article/Communication Auteurs : Mahmoud Saeedimoghaddam, Auteur ; Tomasz F. Stepinski, Auteur Année de publication : 2020 Article en page(s) : pp 947 - 968 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] carrefour [Termes descripteurs IGN] carte ancienne [Termes descripteurs IGN] carte numérisée [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données localisées [Termes descripteurs IGN] Etats-Unis [Termes descripteurs IGN] extraction du réseau routier [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] numérisation automatique [Termes descripteurs IGN] représentation cartographique [Termes descripteurs IGN] système d'information géographique [Termes descripteurs IGN] vision par ordinateur Résumé : (auteur) Road intersection data have been used across a range of geospatial analyses. However, many datasets dating from before the advent of GIS are only available as historical printed maps. To be analyzed by GIS software, they need to be scanned and transformed into a usable (vector-based) format. Because the number of scanned historical maps is voluminous, automated methods of digitization and transformation are needed. Frequently, these processes are based on computer vision algorithms. However, the key challenges to this are (1) the low conversion accuracy for low quality and visually complex maps, and (2) the selection of optimal parameters. In this paper, we used a region-based deep convolutional neural network-based framework (RCNN) for object detection, in order to automatically identify road intersections in historical maps of several cities in the United States of America. We found that the RCNN approach is more accurate than traditional computer vision algorithms for double-line cartographic representation of the roads, though its accuracy does not surpass all traditional methods used for single-line symbols. The results suggest that the number of errors in the outputs is sensitive to complexity and blurriness of the maps, and to the number of distinct red-green-blue (RGB) combinations within them. Numéro de notice : A2020-205 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1696968 date de publication en ligne : 28/11/2019 En ligne : https://doi.org/10.1080/13658816.2019.1696968 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94882 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2020051	SL	Revue	Centre de documentation	Revues en salle	Disponible