Descripteur
Documents disponibles dans cette catégorie (1373)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Titre : Representing shape collections with alignment-aware linear models Type de document : Article/Communication Auteurs : Romain Loiseau , Auteur ; Tom Monnier, Auteur ; Loïc Landrieu , Auteur ; Mathieu Aubry, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2021 Autre Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Projets : READY3D / Landrieu, Loïc Conférence : 3DV 2021, International Conference on 3D Vision 01/12/2021 03/12/2021 Londres online Royaume-Uni Proceedings IEEE Importance : pp 1044 - 1053 Format : 21 x 30 cm Note générale : bibliographie
This work was supported in part by ANR project READY3D ANR-19-CE23-0007 and HPC resources from GENCI-IDRIS (Grant 2020-AD011012096).Langues : Anglais (eng) Descripteur : [Termes IGN] analyse de données
[Termes IGN] apprentissage profond
[Termes IGN] données localisées 3D
[Termes IGN] modèle linéaire
[Termes IGN] réseau neuronal profond
[Termes IGN] segmentation
[Termes IGN] semis de points
[Termes IGN] transformation affineRésumé : (auteur) In this paper, we revisit the classical representation of 3D point clouds as linear shape models. Our key insight is to leverage deep learning to represent a collection of shapes as affine transformations of low-dimensional linear shape models. Each linear model is characterized by a shape prototype, a low-dimensional shape basis and two neural networks. The networks take as input a point cloud and predict the coordinates of a shape in the linear basis and the affine transformation which best approximate the input. Both linear models and neural networks are learned end-to-end using a single reconstruction loss. The main advantage of our approach is that, in contrast to many recent deep approaches which learn feature-based complex shape representations, our model is explicit and every operation occurs in 3D space. As a result, our linear shape models can be easily visualized and annotated, and failure cases can be visually understood. While our main goal is to introduce a compact and interpretable representation of shape collections, we show it leads to state of the art results for few-shot segmentation. Code and data are available at: https://romainloiseau.github.io/deep-linear-shapes Numéro de notice : C2021-036 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers ArXiv Thématique : INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/3DV53792.2021.00112 Date de publication en ligne : 03/12/2021 En ligne : https://doi.org/10.1109/3DV53792.2021.00112 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98385 Sherloc: a knowledge-driven algorithm for geolocating microblog messages at sub-city level / Laura Di Rocco in International journal of geographical information science IJGIS, vol 35 n° 1 (January 2021)
[article]
Titre : Sherloc: a knowledge-driven algorithm for geolocating microblog messages at sub-city level Type de document : Article/Communication Auteurs : Laura Di Rocco, Auteur ; Michela Bertolotto, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 84 - 115 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] données localisées
[Termes IGN] géolocalisation
[Termes IGN] inférence
[Termes IGN] microblogue
[Termes IGN] répertoire toponymique
[Termes IGN] segmentation sémantique
[Termes IGN] système à base de connaissances
[Termes IGN] toponyme
[Termes IGN] zone urbaineRésumé : (auteur) Many solutions for coarse geolocating of users at the time they post a message exist. However, for many important applications, like traffic monitoring and event detection, finer geolocation at the level of city neighborhoods, i.e., at a sub-city level, is needed. Data-driven approaches often do not guarantee good accuracy and efficiency due to the higher number of sub-city level positions to be estimated and the low availability of balanced and large training sets. We claim that external information sources overcome limitations of data-driven approaches in achieving good accuracy for sub-city level geolocation and we present a knowledge-driven approach achieving good results once the reference area of a message is known. Our algorithm, called Sherloc, exploits toponyms in the message, extracts their semantic from a geographic gazetteer, and embeds them into a metric space that captures the semantic distance among them. We identify the semantically closest toponyms to a message and then cluster them with respect to their spatial locations. Sherloc requires no prior training, it can infer the location at sub-city level with high accuracy, and it is not limited to geolocating on a fixed spatial grid. Numéro de notice : A2021-021 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1764003 Date de publication en ligne : 16/06/2020 En ligne : https://doi.org/10.1080/13658816.2020.1764003 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96521
in International journal of geographical information science IJGIS > vol 35 n° 1 (January 2021) . - pp 84 - 115[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 079-2021011 SL Revue Centre de documentation Revues en salle Disponible
Titre : Smart cities : Their framework and applications Type de document : Monographie Auteurs : Anuar Mohamed Kassim, Éditeur scientifique ; Lufti Al-Sharif, Éditeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2021 Importance : 288 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-1-83962-296-0 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Urbanisme
[Termes IGN] bâtiment
[Termes IGN] croissance urbaine
[Termes IGN] données massives
[Termes IGN] handicap
[Termes IGN] intelligence artificielle
[Termes IGN] internet des objets
[Termes IGN] planification urbaine
[Termes IGN] réseau de capteurs
[Termes IGN] sécurité informatique
[Termes IGN] sécurité routière
[Termes IGN] transport public
[Termes IGN] urbanisation
[Termes IGN] ville durable
[Termes IGN] ville intelligenteRésumé : (éditeur) The development of smart cities is important and beneficial to a government and its citizens. With the advent of the smartphone, rapid and reliable communication between and among individuals and governments has become ubiquitous. Everything can be connected and accessed easily with the touch of a finger. Changes in mobile internet telecommunication systems allow for the advance of new urbanization using smart city development methods. The evolution of technology in Industry 4.0, such as the advancement of cutting-edge sensors utilizing the Internet of things (IoT) concept, has wide applications in developing various smart systems. This publication analyzes the interconnected cyber-physical systems inherent in smart cities, and the development methods and applications thereof. Note de contenu : 1. Application of advanced framework technology in smart cities to improve resource utilization
2. Orchestrating smart cities, new disruptive business models and informal enterprises
3. Does smart city development promote urbanization in India?
4. Smart buildings: A model approach for institutional buildings
5. Standard elevator information schema: Its origins, features and example applications
6. A universal methodology for generating elevator passenger origin-destination pairs for calculation and simulation
7. Data compression strategies for use in advanced metering infrastructure networks
8. Energy management and optimal power scheduling in a smart building under uncertainty
9. Cognitive dynamic system for AC state estimation and cyber-attack detection in smart grid
10. Architecture of a telemonitoring system for the mobility of the elderly in wheelchairs supported by Internet of things technologies as a component of a smart city
11. Smart growth and transit oriented development: Financing and execution challenges in India
12. Estimation of the efficiency indices for operating the vertical transportation systems
13. Passive safety of children carriages on busses
14. T-S fuzzy observers to design actuator fault-tolerant control for automotive vehicle lateral dynamicsNuméro de notice : 28693 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/SOCIETE NUMERIQUE/URBANISME Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.87707 En ligne : https://doi.org/10.5772/intechopen.87707 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100307
Titre : Spatial dataset search: Building a dedicated knowledge graph Type de document : Article/Communication Auteurs : Mehdi Zrhal , Auteur ; Bénédicte Bucher , Auteur ; Marie-Dominique Van Damme , Auteur ; Fayçal Hamdi , Auteur Editeur : AGILE Alliance Année de publication : 2021 Projets : 1-Pas de projet / Landrieu, Loïc Conférence : AGILE 2021, 24th AGILE Conference on Geographic Information Science 19/07/2021 22/07/2021 Aurora Colorado - Etats-Unis OA Proceedings Importance : 5 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Infrastructure de données
[Termes IGN] découverte de connaissances
[Termes IGN] données massives
[Termes IGN] données ouvertes
[Termes IGN] graphe
[Termes IGN] INSPIRE
[Termes IGN] jeu de données localisées
[Termes IGN] précision sémantique
[Termes IGN] recherche d'information géographique
[Termes IGN] requête spatiale
[Termes IGN] réseau sémantique
[Termes IGN] ressources web
[Termes IGN] service web géographique
[Termes IGN] terminologie
[Termes IGN] web des données
[Termes IGN] web sémantique géolocaliséRésumé : (auteur) A growing number of spatial datasets are published every year. These can usually be found in dedicated web portals with different structures and specificities. However, finding the dataset that fits user needs is a real challenge as prior knowledge of these portals is needed to retrieve it efficiently. In this article, we present the problem of spatial dataset search and how the use of a geographic Knowledge Graph could improve it. A proposed direction for future work, ex-tending these contributions, is then presented. Numéro de notice : C2021-008 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-2-43-2021 En ligne : https://doi.org/10.5194/agile-giss-2-43-2021 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97855 Spatial Linked Data in Europe: Report from Spatial Linked Data Session at Knowledge Graph in Action, October 6th, 2020, on-line conference / Bénédicte Bucher (February 2021)
Titre : Spatial Linked Data in Europe: Report from Spatial Linked Data Session at Knowledge Graph in Action, October 6th, 2020, on-line conference Type de document : Rapport Auteurs : Bénédicte Bucher , Auteur ; Erwin Folmer, Auteur ; Rob Brennan, Auteur ; Wouter Beek, Auteur ; Elio Hbeich, Auteur ; Falk Würriehausen, Auteur ; Lexi Rowland, Auteur ; Ricardo Alonso Maturana, Auteur ; Elena Alvarado, Auteur ; Raf Buyle, Auteur ; Pasquale Di Donato, Auteur Editeur : Dublin : European Spatial Data Research EuroSDR Année de publication : February 2021 Collection : EuroSDR official publication, ISSN 0257-0505 num. 73 Projets : 1-Pas de projet / Landrieu, Loïc Conférence : KiA 2020, Knowledge Graph in Action: DBpedia, Linked Geodata and Geo-information Integration 06/10/2020 06/10/2020 en ligne Colorado - Etats-Unis OA Proceedings Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes IGN] données localisées
[Termes IGN] réseau sémantique
[Termes IGN] SPARQL
[Termes IGN] web des donnéesRésumé : (éditeur) In 2020, the Knowledge Graph in Action (KGiA) online conference was organized as a joint event gathering three annual events with a common interest on producing, consolidating data, and supporting their joint reuse and different specific focuses within this common interest: the DBpedia day which more specifically focuses on advancing DBpedia, the EuroSDR Spatial Linked Data day which more specifically focuses on spatial linked data, and the EuroSDR VGI event which more specifically focuses on volunteered geographic information.
The event was organized around distinct parallel sessions dedicated to each event and joint plenary sessions. During plenary sessions, keynotes related to the modelling and the usage of spatial knowledge, in particular in the form of knowledge graphs, at the junction of these communities. Carsten Hoyer Click from the German Aerospace Center presented the design of a development of a distributed data infrastructure for energy systems analysis. Semantic Web techniques are used to interconnect data from different sources and prepare the integrated data layers needed for energy models. Peter Mooney from Maynooth University presented opportunities for more collaboration and geo-information integration between volunteered geographical information, the governmental agencies and the geospatial research communities. He insists on the complexity of data integration, which is always present even when flowcharts hide this complexity and on the semantics aspect being the more difficult to solve. Here the exploration of machine learning and artificial intelligence are the dominant trend. Marinos Kavouras from the National Technical University of Athens extended upon the need for our society to develop competences to interpret all the data available, in big quantities, to make sense of complex phenomena. He argues that space has been one of the strongest pivotal notions in semantically linking all kinds of data. Developing geospatial literacy skills is needed to empower people with a modern cartographic language, an indispensable communication and cognitive tool. Krzystof Janowicz from the University of California presented the application of knowledge graphs to address challenges at the interface between humans and their environment like for example crisis management. The information currently provided to end users is based on the integration of highly heterogeneous data from different fields of expertise and can lead to misinterpretation. Knowledge graphs and their technologies offer perspectives and lots of challenges still ahead to make data AIready at the level of individual statements instead of merely offering access to datasets, to provide additional contextual background information.
The rest of this report concerns presentations and exchanges that took place during the EuroSDR Spatial Linked Data sessions. EuroSDR is a not for profit association established since 1953 for the purpose of applied research and innovation in spatial data provision, distribution and usage in Europe. It gathers national mapping agencies, research institutes, universities and industries. Its activity on Linked data has two main objectives : 1) assessing the value of this technology in addressing current challenges in spatial data provision, distribution and exploitation, 2) identifying new needs for spatial data provision and distribution that have emerged with this technology. This activity started in 2015 and is grounded on big events -like the KGiA conference-, smaller working sessions, and since 2019 a technical group. EuroSDR LD group gathers participants with an interest in Spatial Linked Data (SLD). SLD can be characterized as a domain of applied research and innovation at the overlap between Linked Data and spatial data. Its finality is data production, sharing and reuse on the Web to support decisions with a geographical characteristic. Space is an important dimension to interconnect different information and achieve the Linked Data vision, for example to valorise linked data of different domains if any spatial footprints can be added to associate them with a geographical context or to detect possible connections between different data not connected otherwise. Vice versa, graph based models are promising approaches to address some unsolved issues in spatial data infrastructures.
The section “National presentations” reports on updates presented by different agencies or partners on latest developments, focusing on a given territory. These developments are either in a prototype stage or were presented as fully operational applications.
The remaining sections report on more technology oriented presentations.
The section entitled “Interfacing more users with data and related technologies” present results and approaches oriented on the appropriation of data by potential users, despite possible silos created by the complexity of data technologies, including linked data, was addressed in several presentations. The self-service GIS vision presented by the Kadaster is to support the querying and exploitation of complex data by more users beyond the limited Geomatics Community. The tools developed by Triply, in particular a wizard, focus on giving access to the potential of Linked data to users who are no LD specialists thanks to user oriented interfaces. Besides, a well known usage of Knowledge Graphs is to improve user access to resources -as on Amazon, AirBnB, Google and other platforms, based on the modelling in a knowledge graph of important knowledge related to the resources and also related to the usage. This can be applied in particular to specific resources: the data themselves. The discovery of “fitted for use” datasets, especially spatial datasets is a pending issue given the wide range of users on the one hand, and the difficulty to broker and compare datasets potentially relevant on the other hand. A new EuroSDR initiative targeting the design of an open European Knowledge Graph of geographical digital assets was presented. It consists of the collaborative creation of an open Knowledge Graph about digital assets in Europe, based on the EuroSDR LD Group sandbox and EuroSDR community as a whole.
The last section reported on GeoSPARQL focused presentations. A key technology associated with Linked Data and the Knowledge Graph is GeoSPARQL. One presentation focused on requirements from the domain of buildings and on the type of spatial queries that should be addressed to 3D linked data. Another presentation concerned the GeoSPARQL benchmark on the EuroSDR sandbox.Note de contenu : 1- Introduction
2- National presentations on spatial linked data activities
3- Interfacing more users with data and related technologies
4- GeoSPARQL focused presentations
5- Discussion and perspectivesNuméro de notice : 17014 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Rapport nature-HAL : DirectOuvrColl/Actes DOI : sans En ligne : http://www.eurosdr.net/sites/default/files/uploaded_files/eurosdr_publication_nd [...] Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98449 Spectral variability in hyperspectral unmixing : Multiscale, tensor, and neural network-based approaches / Ricardo Augusto Borsoi (2021)PermalinkStudy of an integrated pre-processing architecture for smart-imaging-systems, in the context of lowpower computer vision and embedded object detection / Luis Cubero Montealegre (2021)PermalinkSuivi de la rotation des cultures à partir de séries temporelles d’images satellite / Félix Quinton (2021)PermalinkSuivi des vignes par télédétection de proximité : le deep learning au service de l’agriculture de précision / Sami Beniaouf (2021)PermalinkSUMAC'21: Proceedings of the 3rd Workshop on Structuring and Understanding of Multimedia heritAge Contents / Valérie Gouet-Brunet (2021)PermalinkSuper-resolution of VIIRS-measured ocean color products using deep convolutional neural network / Xiaoming Liu in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)PermalinkSupplementary material for: Panoptic segmentation of satellite image time series with convolutional temporal attention networks / Vivien Sainte Fare Garnot (2021)PermalinkPermalinkThe challenge of robust trait estimates with deep learning on high resolution RGB images / Etienne David (2021)PermalinkThe use of deep machine learning for the automated selection of remote sensing data for the determination of areas of arable land degradation processes distribution / Dimitri I. Rukhovitch in Remote sensing, vol 13 n° 1 (January-1 2021)PermalinkPermalinkUnifying remote sensing image retrieval and classification with robust fine-tuning / Dimitri Gominski (2021)PermalinkPermalinkVectorization of historical maps using deep edge filtering and closed shape extraction / Yizi Chen (2021)PermalinkVegetation stratum occupancy prediction from airborne LiDAR 3D point clouds / Ekaterina Kalinicheva (2021)PermalinkVisual exploration of historical image collections: An interactive approach through space and time / Evelyn Paiz-Reyes (2021)PermalinkAutomatic building footprint extraction from UAV images using neural networks / Zoran Kokeza in Geodetski vestnik, vol 64 n° 4 (December 2020 - February 2021)PermalinkCartographic generalization / Monika Sester in Journal of Spatial Information Science (JoSIS), n° 21 (2020)PermalinkA deep learning approach to improve the retrieval of temperature and humidity profiles from a ground-based microwave radiometer / Xing Yan in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkDeep learning for detecting and classifying ocean objects: application of YoloV3 for iceberg–ship discrimination / Frederik Hass in ISPRS International journal of geo-information, vol 9 n° 12 (December 2020)PermalinkExploring the inclusion of Sentinel-2 MSI texture metrics in above-ground biomass estimation in the community forest of Nepal / Santa Pandit in Geocarto international, vol 35 n° 16 ([01/12/2020])PermalinkLearning from urban form to predict building heights / Nikola Milojevic-Dupont in Plos one, vol 15 n° 12 (December 2020)PermalinkMapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks / Felix Schiefer in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)PermalinkMS-RRFSegNetMultiscale regional relation feature segmentation network for semantic segmentation of urban scene point clouds / Haifeng Luo in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkMultistrategy ensemble regression for mapping of built-up density and height with Sentinel-2 data / Christian Geiss in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)PermalinkNonlocal graph convolutional networks for hyperspectral image classification / Lichao Mou in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkA novel intelligent classification method for urban green space based on high-resolution remote sensing images / Zhiyu Xu in Remote sensing, vol 12 n° 22 (December-1 2020)PermalinkParsing very high resolution urban scene images by learning deep ConvNets with edge-aware loss / Xianwei Zheng in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)PermalinkSemantic‐based urban growth prediction / Marvin Mc Cutchan in Transactions in GIS, Vol 24 n° 6 (December 2020)PermalinkSemi-supervised PolSAR image classification based on improved tri-training with a minimum spanning tree / Shuang Wang in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkSTME: An effective method for discovering spatiotemporal multi‐type clusters containing events with different densities / Chao Wang in Transactions in GIS, Vol 24 n° 6 (December 2020)PermalinkUnderstanding the role of individual units in a deep neural network / David Bau in Proceedings of the National Academy of Sciences of the United States of America PNAS, vol 117 n° 48 (1 December 2020)PermalinkUnderstanding the synergies of deep learning and data fusion of multispectral and panchromatic high resolution commercial satellite imagery for automated ice-wedge polygon detection / Chandi Witharana in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)PermalinkUnsupervised deep joint segmentation of multitemporal high-resolution images / Sudipan Saha in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)PermalinkUsing multi-agent simulation to predict natural crossing points for pedestrians and choose locations for mid-block crosswalks / Egor Smirrnov in Geo-spatial Information Science, vol 23 n° 4 (December 2020)PermalinkForêt d'arbres aléatoires et classification d'images satellites : relation entre la précision du modèle d'entraînement et la précision globale de la classification / Aurélien N.G. Matsaguim in Revue Française de Photogrammétrie et de Télédétection, n° 222 (novembre 2020)PermalinkActive and incremental learning for semantic ALS point cloud segmentation / Yaping Lin in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)PermalinkBayesian-deep-learning estimation of earthquake location from single-station observations / S. Mostafa Mousavi in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)PermalinkBayesian transfer learning for object detection in optical remote sensing images / Changsheng Zhou in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)PermalinkA deep learning framework for matching of SAR and optical imagery / Lloyd Haydn Hughes in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)PermalinkEvaluating geo-tagged Twitter data to analyze tourist flows in Styria, Austria / Johannes Scholz in ISPRS International journal of geo-information, vol 9 n° 11 (November 2020)PermalinkHigh-resolution remote sensing image scene classification via key filter bank based on convolutional neural network / Fengpeng Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)PermalinkLandslide susceptibility mapping using Naïve Bayes and Bayesian network models in Umyeonsan, Korea / Sunmin Lee in Geocarto international, vol 35 n° 15 ([01/11/2020])PermalinkLearning-based hyperspectral imagery compression through generative neural networks / Chubo Deng in Remote sensing, vol 12 n° 21 (November 2020)PermalinkOptimizing local geoid undulation model using GPS/levelling measurements and heuristic regression approaches / Mosbeh R. Kaloop in Survey review, vol 52 n° 375 (November 2020)Permalink