Descripteur
Documents disponibles dans cette catégorie (4708)
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
Unsupervised deep representation learning for real-time tracking / Ning Wang in International journal of computer vision, vol 129 n° 2 (February 2021)
[article]
Titre : Unsupervised deep representation learning for real-time tracking Type de document : Article/Communication Auteurs : Ning Wang, Auteur ; Wengang Zhou, Auteur ; Yibing Song, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 400 - 418 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement d'images
[Termes IGN] apprentissage profond
[Termes IGN] classification non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de cible
[Termes IGN] filtre
[Termes IGN] objet mobile
[Termes IGN] oculométrie
[Termes IGN] reconnaissance d'objets
[Termes IGN] réseau neuronal siamois
[Termes IGN] temps réel
[Termes IGN] traçage
[Termes IGN] trajectoire (véhicule non spatial)
[Termes IGN] vision par ordinateurRésumé : (auteur) The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotation and learn to track arbitrary objects, we propose an unsupervised learning method for visual tracking. The motivation of our unsupervised learning is that a robust tracker should be effective in bidirectional tracking. Specifically, the tracker is able to forward localize a target object in successive frames and backtrace to its initial position in the first frame. Based on such a motivation, in the training process, we measure the consistency between forward and backward trajectories to learn a robust tracker from scratch merely using unlabeled videos. We build our framework on a Siamese correlation filter network, and propose a multi-frame validation scheme and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed. Furthermore, our unsupervised framework exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy. Numéro de notice : A2021-353 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s11263-020-01357-4 Date de publication en ligne : 21/09/2020 En ligne : https://doi.org/10.1007/s11263-020-01357-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97604
in International journal of computer vision > vol 129 n° 2 (February 2021) . - pp 400 - 418[article]Web‐based real‐time visualization of large‐scale weather radar data using 3D tiles / Mingyue Lu in Transactions in GIS, Vol 25 n° 1 (February 2021)
[article]
Titre : Web‐based real‐time visualization of large‐scale weather radar data using 3D tiles Type de document : Article/Communication Auteurs : Mingyue Lu, Auteur ; Xinhao Wang, Auteur ; Xintao Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 25 - 43 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Chine
[Termes IGN] dalle
[Termes IGN] données météorologiques
[Termes IGN] données radar
[Termes IGN] géomatique web
[Termes IGN] grande échelle
[Termes IGN] temps réel
[Termes IGN] visualisation 3D
[Termes IGN] web des données
[Termes IGN] WebSIG
[Vedettes matières IGN] GéovisualisationRésumé : (Auteur) Weather radar data play an important role in meteorological analysis and forecasting. In particular, web‐based real‐time 3D visualization will enable and enhance various meteorological applications by avoiding the dissemination of a large amount of data over the internet. Despite that, most existing studies are either limited to 2D or small‐scale data analytics due to methodological limitations. This article proposes a new framework to enable web‐based real‐time 3D visualization of large‐scale weather radar data using 3D tiles and WebGIS technology. The 3D tiles technology is an open specification for online streaming massive heterogeneous 3D geospatial datasets, which is designed to improve rendering performance and reduce memory consumption. First, the weather radar data from multiple single‐radar sites across a large coverage area are organized into a spliced grid data (i.e., weather radar composing data, WRCD). Next, the WRCD is converted into a widely used 3D tile data structure in four steps: data preprocessing, data indexing, data transformation, and 3D tile generation. Last, to validate the feasibility of the proposed strategy, a prototype, namely Meteo3D at https://202.195.237.252:82, is implemented to accommodate the WRCD collected from all the weather radar sites over the whole of China. The results show that near real‐time and accurate visualization for the monitoring and early warning of strong convective weather can be achieved. Numéro de notice : A2021-185 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12638 Date de publication en ligne : 19/05/2020 En ligne : https://doi.org/10.1111/tgis.12638 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97147
in Transactions in GIS > Vol 25 n° 1 (February 2021) . - pp 25 - 43[article]GIS-based multicriteria evaluation for earthquake response: a case study of expert opinion in Vancouver, Canada / Blake Byron Walker in Natural Hazards, Vol 105 n° 2 (January 2021)
[article]
Titre : GIS-based multicriteria evaluation for earthquake response: a case study of expert opinion in Vancouver, Canada Type de document : Article/Communication Auteurs : Blake Byron Walker, Auteur ; Nadine Schuurman, Auteur ; David Swanlund, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2075 - 2091 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG
[Termes IGN] allocation
[Termes IGN] analyse multicritère
[Termes IGN] cartographie collaborative
[Termes IGN] cartographie d'urgence
[Termes IGN] planification urbaine
[Termes IGN] prévention des risques
[Termes IGN] secours d'urgence
[Termes IGN] séisme
[Termes IGN] Vancouver (Colombie britannique)
[Termes IGN] zone à risqueRésumé : (auteur) GIS-based multicriteria evaluation (MCE) provides a framework for analysing complex decision problems by quantifying variables of interest to score potential locations according to their suitability. In the context of earthquake preparedness and post-disaster response, MCE has relied mainly on uninformed or non-expert stakeholders to identify high-risk zones, prioritise areas for response, or highlight vulnerable populations. In this study, we compare uninformed, informed non-expert, and expert stakeholders’ responses in MCE modelling for earthquake response planning in Vancouver, Canada. Using medium- to low-complexity MCE models, we highlight similarities and differences in the importance of infrastructural and socioeconomic variables, emergency services, and liquefaction potential between a non-weighted MCE, a medium-complexity informed non-expert MCE, and a low-complexity MCE informed by 35 local earthquake planning and response experts from governmental and non-governmental organisations. Differences in the observed results underscore the importance of accessible, expert-informed approaches for prioritising locations for earthquake response planning and for the efficient and geographically precise allocation of resources. Numéro de notice : A2021-203 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11069-020-04390-1 Date de publication en ligne : 30/10/2020 En ligne : https://doi.org/10.1007/s11069-020-04390-1 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97164
in Natural Hazards > Vol 105 n° 2 (January 2021) . - pp 2075 - 2091[article]
Titre : L’Alpe d’Huez: A benchmark for topographic map generalisation Type de document : Article/Communication Auteurs : Guillaume Touya , Auteur Editeur : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2021 Conférence : ICA 2021, 24th ICA Workshop on Map Generalisation and Multiple Representation 13/12/2021 13/12/2021 Florence Italie OA Proceedings Importance : 2 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Français (fre) Descripteur : [Termes IGN] bâtiment
[Termes IGN] CartAGen (plateforme de généralisation)
[Termes IGN] carte topographique
[Termes IGN] généralisation cartographique
[Termes IGN] Institut national de l'information géographique et forestière (France)
[Termes IGN] test de performance
[Vedettes matières IGN] GénéralisationRésumé : (auteur) L’Alpe d’Huez is a ski resort in the French Alps, and it is also famous among cyclists for the number of bends in the road to the ski resort. It is a good location to evaluate the capabilities of map generalisation tools, as the surroundings contain urban, rural and mountainous areas, and it was chosen 15 years ago as one of the four datasets to benchmark map generalisation software (Stoter et al., 2009). The EuroSDR benchmark used data from IGN France, the French National Mapping Agency (NMA). At that time, open science policies were not popular in NMAs, but now they release their dataset with open licenses, so it is a good opportunity to create an open benchmark for topographic map generalisation. Numéro de notice : C2021-065 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComSansActesPubliés-Unpublished DOI : sans En ligne : https://hal.science/hal-03522475/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99524 An attempt to define perceptive and sensitive mapping through lived space experiments / Catherine Dominguès (2021)
Titre : An attempt to define perceptive and sensitive mapping through lived space experiments Type de document : Article/Communication Auteurs : Catherine Dominguès , Auteur ; Laurence Jolivet , Auteur ; Eric Mermet , Auteur ; Sevil Seten, Auteur Editeur : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2021 Collection : Abstracts of the ICA num. 3 Projets : 1-Pas de projet / Conférence : ICC 2021, 30th ICA international cartographic conference 14/12/2021 18/12/2021 Florence Italie OA Proceedings Langues : Anglais (eng) Descripteur : [Termes IGN] analyse des besoins
[Termes IGN] cartographie sensible
[Termes IGN] expérience scientifique
[Termes IGN] utilisateur
[Vedettes matières IGN] CartologieRésumé : (auteur) [début] Maps are often used in the context of human and social sciences, including as a tool. For example, maps as graphic tools enable to locate survey fields and data. Especially, the synoptic property of maps makes it possible to investigate the spatial dimension of a phenomenon, the distribution of data, its changes over time, etc. In teaching activities and in support tasks for research at the EHESS in Paris, difficulties have arisen in showing research data and results in a manner which would be fruitful and acceptable to the students and researchers. The need for an adapted mapping has emerged, including the map-making process and the achieved map. Adapted mapping has been named by the phrase perceptive and sensitive mapping, in contrast with conventional mapping based on geographical databases, GIS tools and the theory of graphic semiology as taught by Jacques Bertin (Bertin, 1983). In response to this need, a training methodological seminar has been set up since 2016 in EHESS. It aims at providing an (organizational and material) framework for students in which they can experiment various protocols and be confronted with different data specifications. The procedures are designed in order to accentuate specific aspects that are not supposed to be fulfilled by conventional mapping. An analysis has been performed targeting the students' achievements and how they have been achieved. The analysis makes it possible to characterize the maps drawn in this context; to compare the students' difficulties and comments with the needs they initially expressed; to highlight in which cases conventional cartography may be inadequate for laying out some data. The result analysis enabled considering three questions: how may conventional mapping and perceptive and sensitive mapping be compared? How is perceptive and sensitive mapping a relevant tool? And thanks to the answers of the previous questions: What would be a definition of perceptive and sensitive mapping? To this end, the paper firstly details how the needs for maps were expressed and how the seminar tried to answer them by defining experiments. In the second section, the achievements are analyzed based on two items: the (displayed) graphical and cartographic features, and the protocols which enabled to make them. Lastly, the analysis enables to offer a definition of perceptive and sensitive mapping by means of a comparison with conventional mapping. Numéro de notice : C2021-044 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/ica-abs-3-70-2021 Date de publication en ligne : 13/12/2021 En ligne : https://doi.org/10.5194/ica-abs-3-70-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99394 Assessing the accuracy of remotely sensed fire datasets across the southwestern Mediterranean Basin / Luis Felipe Galizia in Natural Hazards and Earth System Sciences, vol 21 n° 1 (January 2021)PermalinkCalcul de la largeur à pleins bords de grands cours d’eau à partir de MNT LiDAR / Nicolas Fermen (2021)PermalinkPermalinkCartographie de gîsements de matières colorantes utilisées pendant la Préhistoire et configuration de l’application Input de relevés de terrain / Mathilde Waymel (2021)PermalinkCartographies en mouvement : parcours sensible, narration et participation, ch. 10. Conception de cartes en relief pour les personnes déficientes visuelles / Gauthier Fillières-Riveau (2021)PermalinkPermalinkDéveloppement d'un modèle de macro-dynamique forestière pour simuler la dynamique des forêts françaises dans un contexte non-stationnaire / Timothée Audinot (2021)PermalinkElevation models for reproducible evaluation of terrain representation / Patrick Kennelly in Cartography and Geographic Information Science, vol 48 n° 1 (January 2021)PermalinkEvaluating interactive comparison techniques in a multiclass density map for visual crime analytics / Lukas Svicarovic (2021)PermalinkFlood mapping from radar remote sensing using automated image classification techniques / Lisa Landuyt (2021)Permalink