Détail de l'auteur
Auteur Bertrand Duménieu
|
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externesCombining deep learning and mathematical morphology for historical map segmentation / Yizi Chen (2021)
Titre : Combining deep learning and mathematical morphology for historical map segmentation Type de document : Article/Communication Auteurs : Yizi Chen, Auteur ; Edwin Carlinet, Auteur ; Joseph Chazalon, Auteur ; Clément Mallet Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2021 Projets : SODUCO / Perret, Julien Note générale : bibliographie
soumis à DGMM 2021Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes descripteurs IGN] analyse diachronique
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] carte ancienne
[Termes descripteurs IGN] chaîne de traitement
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] détection d'objet
[Termes descripteurs IGN] données maillées
[Termes descripteurs IGN] morphologie mathématique
[Termes descripteurs IGN] vectorisationRésumé : (auteur) The digitization of historical maps enables the study of ancient, fragile, unique, and hardly accessible information sources. Main map features can be retrieved and tracked through the time for subsequent thematic analysis. The goal of this work is the vectorization step, i.e., the extraction of vector shapes of the objects of interest from raster images of maps. We are particularly interested in closed shape detection such as buildings, building blocks, gardens, rivers, etc. in order to monitor their temporal evolution. Historical map images present significant pattern recognition challenges. The extraction of closed shapes by using traditional Mathematical Morphology (MM) is highly challenging due to the overlapping of multiple map features and texts. Moreover, state-of-the-art Convolutional Neural Networks (CNN) are perfectly designed for content image filtering but provide no guarantee about closed shape detection. Also, the lack of textural and color information of historical maps makes it hard for CNN to detect shapes that are represented by only their boundaries. Our contribution is a pipeline that combines the strengths of CNN (efficient edge detection and filtering) and MM (guaranteed extraction of closed shapes) in order to achieve such a task. The evaluation of our approach on a public dataset shows its effectiveness for extracting the closed boundaries of objects in historical maps. Numéro de notice : P2021-001 Affiliation des auteurs : UGE-LaSTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Preprint nature-HAL : Préprint En ligne : https://arxiv.org/abs/2101.02144 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96739
Titre : Création d’une base de connaissances sur les redécoupages administratifs durant la Révolution française : l’exemple des paroisses constitutionnelles Type de document : Article/Communication Auteurs : Antoine Keller, Auteur ; Nathalie Abadie Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN Année de publication : 2019 Conférence : CHEC 2019, Séminaire Atlas historique 24/01/2019 24/01/2019 Clermont-Ferrand France programme, Journées Recherche de l'IGN 2019, 28es Journées 18/04/2019 19/04/2019 Champs-sur-Marne France Open Access Abstracts Format : 21 x 30 cm Langues : Français (fre) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes descripteurs IGN] base de connaissances
[Termes descripteurs IGN] limite administrative
[Termes descripteurs IGN] paroisse
[Termes descripteurs IGN] révolution françaiseNuméro de notice : C2019-024 Affiliation des auteurs : LaSTIG COGIT+Ext (2012-2019) Autre URL associée : vers HAL/vers la vidéo Thématique : GEOMATIQUE Nature : Conférence invitée nature-HAL : ComSansActesPubliés-Unpublished DOI : sans En ligne : https://hal.archives-ouvertes.fr/hal-03147390 Format de la ressource électronique : URL Vidéo Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94301
Titre : Engraved footprints from the past. Retrieving cartographic geohistorical data from the Cassini Carte de France, 1750-1789 Type de document : Article/Communication Auteurs : Bertrand Duménieu Editeur : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2019 Conférence : ICC 2019, 29th International Cartographic Conference ICA, Mapping everything for everyone 15/07/2019 20/07/2019 Tokyo Japon Open Access Abstracts of the ICA Importance : 2 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes descripteurs IGN] base de données localisées
[Termes descripteurs IGN] carte de Cassini
[Termes descripteurs IGN] carte de France
[Termes descripteurs IGN] code source libre
[Termes descripteurs IGN] données vectorielles
[Termes descripteurs IGN] esthétique cartographique
[Termes descripteurs IGN] extraction de données
[Termes descripteurs IGN] histoire de la cartographie
[Termes descripteurs IGN] système d'information géographiqueRésumé : (auteur) Antique maps are full of engraved geohistorical features. They provide representations of past states of the geographical space and are favored by historians and social scientists for their uniqueness and coherence. Working on a GIS dedicated to the history of the French territory, we extracted spatial information from the Cassini Carte de France (full name Carte Générale & Particulière de la France) as vector data. Based on the first geodetic survey of France [1, 4], this well-known and monumental map has been drawn on 182 paper sheets of size 610 x 955 mm at the scale of 1:86,400 or 1 line for 100~toises (1 inch to 1.36 miles). It depicts the French territory with fine-grained information about populated and named places, settlements, landscape features, hydrographic, ecclesiastical and road networks [3, 5, 6, 7]. As a case study, the sheet numbered 52 provided more than 6 800 spatial footprints that we have stored as a geographic database. Following the distinction made by Cassini himself between “geometric” and “topographic” entities, our geographical database is composed of two families of data, namely Triangulated Geographical Entities (“geometric” entities in Cassini’s own terms) whose geodetic properties are partly documented and Relative Geographical Entities (“topographic” in Cassini’s terms) which are dependent on and located relative to the former (Fig. 1). Those entities are analytically distinct but come together from a single artifact: the primary source they are engraved in during the mapmaking process. Because this process of embeddedness is not fully documented, retrieving both classes of entities called for a cautious cartographic visualisation with similar semiological rules and aesthetics as the original historical map (Fig. 2). This “Cassini map style” preserves the cartographic properties of the geohistorical data extracted from this primary source: generalisation, scale, spatial granularity and the overall intentions of the mapmakers [2]. Often neglected, such properties are constitutive components and dimensions of the mapping style which forms the context and gives crucial information on the accuracy and the relationships between geo-historical data enclosedin.Ourposterprovidesarenewedcartographicvisualisationofthesheet52ndsheetoftheCartedeFrance, centred on the french cities of Clermont, Riom and Thiers. It reveals unnoticed cartographic entities that were hardly legible in the original map. The historiography of cartography has been largely, and for a long time, based on critical edition of old maps published as non-georeferenced facsimile. We propose to renew this approach by producing digital maps from vector geographic databases that combine the aesthetics and semiology of old map styles with the modelling capabilities of modern GIS. Numéro de notice : C2019-036 Affiliation des auteurs : LaSTIG COGIT+Ext (2012-2019) Thématique : GEOMATIQUE Nature : Poster nature-HAL : Poster-avec-CL DOI : 10.5194/ica-abs-1-68-2019 En ligne : https://doi.org/10.5194/ica-abs-1-68-2019 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95335 
Titre : Historical collaborative geocoding Type de document : Article/Communication Auteurs : Rémi Cura, Auteur ; Bertrand Duménieu Année de publication : 2018 Projets : Belle Epoque / Riva, Angelo Article en page(s) : n° 262 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes descripteurs IGN] base de données historiques
[Termes descripteurs IGN] géocodage
[Termes descripteurs IGN] géocodage par adresse postale
[Termes descripteurs IGN] incertitude des données
[Termes descripteurs IGN] interface web
[Termes descripteurs IGN] jeu de données
[Termes descripteurs IGN] objet géohistorique
[Termes descripteurs IGN] Paris (75)
[Termes descripteurs IGN] répertoire toponymique
[Termes descripteurs IGN] science citoyenne
[Termes descripteurs IGN] sciences humaines numériques
[Termes descripteurs IGN] traitement de données localiséesRésumé : (auteur) The latest developments in the field of digital humanities have increasingly enabled the construction of large data sets which can be easily accessed and used. These data sets often contain indirect spatial information, such as historical addresses. Historical geocoding is the process of transforming indirect spatial information into direct locations which can be placed on a map, thus allowing for spatial analysis and cross-referencing. There are many geocoders that work efficiently for current addresses. However, these do not tackle temporal information, and usually follow a strict hierarchy (country, city, street, house number, etc.) which is difficult—if not impossible—to use with historical data. Historical data is filled with uncertainty (pertaining to temporal, textual, and positional accuracy, as well as to the reliability of historical sources) which can neither be ignored nor entirely resolved. Our open source, open data, and extensible solution for geocoding is based on extracting a large number of simple gazetteers composed of geohistorical objects, from historical maps. Geocoding a historical address becomes the process of finding one or several geohistorical objects in the gazetteers which best match the historical address searched by the user. The matching criteria are customisable, weighted, and include several dimensions (fuzzy string, fuzzy temporal, level of detail, positional accuracy). Since our goal is to facilitate historical work, we also put forward web-based user interfaces which help geocode (one address or batch mode) and display results over current or historical maps. Geocoded results can then be checked and edited collaboratively (no source is modified). The system was tested on the city of Paris, France, for the 19th and 20th centuries. It showed high response rates and worked quickly enough to be used interactively. Numéro de notice : A2018-389 Affiliation des auteurs : LaSTIG COGIT+Ext (2012-2019) Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi7070262 date de publication en ligne : 04/07/2018 En ligne : https://doi.org/10.3390/ijgi7070262 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90804
in ISPRS International journal of geo-information > vol 7 n° 7 (July 2018) . - n° 262[article]Documents numériques
en open access
Historical collaborative geocoding - pdf éditeurAdobe Acrobat PDF
Titre : Assessing the planimetric accuracy of Paris atlases from the late 18th and 19th centuries Type de document : Article/Communication Auteurs : Bertrand Duménieu Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2018 Projets : 1-Pas de projet / Conférence : KEGeod 2018, Knowledge Extraction from Geographical Data, Technical tracks of SAC 2018 09/04/2018 13/04/2018 Pau France , SAC 2018, 33rd Annual ACM Symposium on Applied Computing 09/04/2018 13/04/2018 Pau France Proceedings ACM Importance : pp 876 - 883 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes descripteurs IGN] carte ancienne
[Termes descripteurs IGN] dix-huitième siècle
[Termes descripteurs IGN] dix-neuvième siècle
[Termes descripteurs IGN] géoréférencement
[Termes descripteurs IGN] géoréférencement indirect
[Termes descripteurs IGN] Paris (75)
[Termes descripteurs IGN] point d'appui
[Termes descripteurs IGN] précision planimétrique
[Termes descripteurs IGN] projectionRésumé : (auteur) The recent initiatives to digitize cultural heritage resources and publish them on the Web have renewed interest in historical maps for the diachronic analysis of territories in GIS applications. However, such analyses should not be done without a good understanding of the possibilities and limitations of geographical information provided by historical maps, i.e. their quality. One of the major concerns regarding historical maps quality is their positional planimetric accuracy which highly depends on survey techniques used at the time. As these techniques are not always thoroughly known and as ground truth is most of the time not sufficiently available, direct absolute evaluation approaches have been proposed to assess historical maps positional planimetric accuracy. In this article, we follow the intuition that the most widely adopted georeferencing-based approach for assessing the positional planimetric accuracy of historical maps can be adapted to provide an evaluation of the error caused by the survey process in cases like Paris atlases where the georeferencing transformation can be estimated with ground control points based on geodetic features and where the projection of the map can be approximated by a well known projected coordinate reference system. We apply this tuned approach on the Verniquet atlas and evaluate the validity of our hypothesis about projection approximation. Numéro de notice : C2018-019 Affiliation des auteurs : LaSTIG COGIT+Ext (2012-2019) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3167132.3167228 date de publication en ligne : 15/04/2018 En ligne : https://doi.org/10.1145/3167132.3167228 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90481 Documents numériques
en open access
Assessing the planimetric accuracy of Paris atlases ... - postprintAdobe Acrobat PDFUn système d'information géographique pour le suivi d'objets historiques urbaines à travers l'espace et le temps / Bertrand Duménieu (2015)
PermalinkPermalink
