Descripteur
Documents disponibles dans cette catégorie (1568)
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
Representing vector geographic information as a tensor for deep learning based map generalisation / Azelle Courtial (2022)
Titre : Representing vector geographic information as a tensor for deep learning based map generalisation Type de document : Article/Communication Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Editeur : AGILE Alliance Année de publication : 2022 Projets : 1-Pas de projet / Conférence : AGILE 2022, 25th international AGILE Conference on Geographic Information Science, Artificial intelligence in the service of geospatial technologies 14/06/2022 17/06/2022 Vilnius Lithuanie OA Proceedings Importance : 8 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] alignement des données
[Termes IGN] apprentissage profond
[Termes IGN] architecture de réseau
[Termes IGN] bati
[Termes IGN] carte topographique
[Termes IGN] couche
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] données vectorielles
[Termes IGN] information sémantique
[Termes IGN] milieu urbain
[Termes IGN] route
[Termes IGN] tenseur
[Vedettes matières IGN] GénéralisationRésumé : (auteur) Recently, many researchers tried to generate (generalised) maps using deep learning, and most of the proposed methods deal with deep neural network architecture choices. Deep learning learns to reproduce examples, so we think that improving the training examples, and especially the representation of the initial geographic information, is the key issue for this problem. Our article extracts some representation issues from a literature review and proposes different ways to represent vector geographic information as a tensor. We propose two kinds of contributions: 1) the representation of information by layers; 2) the representation of additional information. Then, we demonstrate the interest of some of our propositions with experiments that show a visual improvement for the generation of generalised topographic maps in urban areas. Numéro de notice : C2022-024 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/agile-giss-3-32-2022 En ligne : https://doi.org/10.5194/agile-giss-3-32-2022 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100921 Road traffic crashes and emergency response optimization: a geo-spatial analysis using closest facility and location-allocation methods / Sulaiman Yunus in Geomatics, Natural Hazards and Risk, vol 13 (2022)
[article]
Titre : Road traffic crashes and emergency response optimization: a geo-spatial analysis using closest facility and location-allocation methods Type de document : Article/Communication Auteurs : Sulaiman Yunus, Auteur ; Ishaq A. Abdulkarim, Auteur Année de publication : 2022 Article en page(s) : pp 1535 - 1555 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] accident de la route
[Termes IGN] allocation
[Termes IGN] chemin le plus court, algorithme du
[Termes IGN] distribution spatiale
[Termes IGN] données localisées
[Termes IGN] équipement sanitaire
[Termes IGN] itinéraire
[Termes IGN] Nigéria
[Termes IGN] optimisation (mathématiques)
[Termes IGN] réseau routier
[Termes IGN] secours d'urgenceRésumé : (auteur) Increased occurrence of road traffic crashes in Kano metropolis has resulted in a steady loss of lives, injuries, and increased people's risk exposure. This study looked into the emergency response to road traffic crashes in Kano, with a view to improving efficiency by developing linkages and synergy between Emergency Healthcare Facilities (EHCF), ambulances, and crash hotspots. The geographical location and attributes of the major EHCF, crash hotspots along highway intersections, and the two existent ambulances at the Kano State Fire Service (KSFS) and Federal Road Safety Corp head offices (FRSC) were obtained using GPS surveying. Road traffic network data (vector format) was digitized from satellite image, from which two major road classes (highways and minor roads) were identified, as well as their respective speed limits. The length and speed constraints were used to calculate time distances. Nearest Neighbor and Network (closest facility, shortest route, and location-allocation) analyses were carried out. Location-allocation analysis was to determine based on defined criteria the best locations to allocate EHCF or ambulance for optimum coverage. The results demonstrated that EHCF, ambulances, and crash places have different distribution patterns with almost no linkages. Closest ambulance facility analysis revealed the FRSC ambulance takes 9.41 minutes to arrive to crash spot 18 (Maiduguri Road, following NNPC) and 7.52 minutes to arrive at AKTH, the nearest EHCF. Comparatively, getting to Court road incident scene (spot 16) and IRPH as the closest EHCF takes about 3 times the time it takes to get to spot 18 and 4 times the time it takes to get to AKTH. This means that practically almost all victims in the city suffocate before reaching to the hospital. This signifies that, in cases of demand for CPR at the incident scene, there are higher likelihood of dying as it is expected to be provided within the first four minutes after the crash. Based on a maximum of 4 minutes impedance cutoff from all directions towards the occurrences areas, location-allocation analysis found eight new locations to maximize coverage and improve efficiency. It is concluded that current road traffic crash emergency response system has been determined to be ineffective. As a result, more ambulances should be strategically placed to improve emergency response times. Numéro de notice : A2022-884 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/19475705.2022.2086829 Date de publication en ligne : 16/06/2022 En ligne : https://doi.org/10.1080/19475705.2022.2086829 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102209
in Geomatics, Natural Hazards and Risk > vol 13 (2022) . - pp 1535 - 1555[article]
Titre : Robustness of visual SLAM techniques to light changing conditions : Influence of contrasted local features, multi-planar representations and multimodal image analysis Type de document : Thèse/HDR Auteurs : Xi Wang, Auteur ; Eric Marchand, Directeur de thèse Editeur : Rennes : Université de Rennes 1 Année de publication : 2022 Importance : 153 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université de Rennes 1, Spécialité InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] cartographie et localisation simultanées
[Termes IGN] éclairage
[Termes IGN] estimation de pose
[Termes IGN] information sémantique
[Termes IGN] primitive géométrique
[Termes IGN] programmation linéaire
[Termes IGN] robotique
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) The SLAM (Simultaneous Localization And Mapping) technique concentrates on localizing and recovering the environment in a simultaneous way and is one of the core functionalities of many industrial products such as augmented reality, where the device poses should be tracked in real-time; autonomous driving, where one needs to localize the vehicle in a pre-generated map or unknown environment; and even modern filmmaking workflow, where the relative camera position and orientation are critical for post-processing or real-time prevising for directors and actors to visualise the visual effects on the stage. Multiple difficulties in different levels can influence the final performance of robot agents’s SLAM task, as the pipeline is long and complicated from the real world physics to the required information such as agent poses and 3-D map, which help us visualize colourful graphics scenes in AR devices or make hard decisions on the highway for autonomous driving. Many solutions are proposed for addressing each problem, respectively, with the means from classic statistic probability models to the modern data-driven deep neural network. However, the quest of improving the robot’s robustness under dynamic and complicated environments perisists and becomes more and more significant and active for nowadays robotics research. The need for improving the robustness of robot agents is imminent and regarded as one of most imperative factors for deploying robots ubiquitously in our daily life. Under this context, this thesis tries to address a small drop in the ocean of the problem of SLAM robustness, yet in a very systematic view: we try to break down the SLAM system into different and inter-influential modules. Then use the concept of "divide and conquer" for answering possible questions within each module and wishing to contribute to the community and help improve the robustness of SLAM systems under complicated conditions. With the above objectives, the contributions of the thesis are stated as follows for tackling the robustness problem from multiple angles: 1) From the image feature angle, we proposed a multiple layered image structure for improving the performance of traditional local image features under extreme conditions. Furthermore, an optimization method on linear searching and mutual information assisted convex optimization are designed for tuning the optimal parameters with the proposed structure; 2) From the geometric primitive angle, we proposed a relative pose estimation and SLAM framework under the multiple planar assumption, by keypoint feature-based and template tracker based methods, respectively. We tried to achieve better performance of mapping and tracking simultaneously with the help of a more general planar assumption. 3) From the angle of relocalization of the SLAM system, the idea is to recover the already passed locations of the robot agent for lowering the overall estimation error or when the robot is in lost status. We proposed a binary graph structure for embedding spatial information and heterogeneous data formats such as depth image, semantic information etc. The proposed method enables robotics SLAM systems to relocalize themselves with a higher success rate even under different lighting, weather and seasonal conditions. Note de contenu : 1- Introduction
2- Résumé
3- Background on visual SLAM techniques
4- Related work
5- Organisation
6- Multiple layers image
7- Multi-planar relative pose estimation via superpixel
8- TT-SLAM
9- Binary graph descriptor for robust relocalization on heterogeneous data
ConclusionNuméro de notice : 24074 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Rennes 1 : 2022 Organisme de stage : IRISA DOI : sans En ligne : https://www.theses.fr/2022REN1S022 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102162 Spatial distribution of lead (Pb) in soil: a case study in a contaminated area of the Czech Republic / Nicolas Francos in Geomatics, Natural Hazards and Risk, vol 13 (2022)
[article]
Titre : Spatial distribution of lead (Pb) in soil: a case study in a contaminated area of the Czech Republic Type de document : Article/Communication Auteurs : Nicolas Francos, Auteur ; Asa Gholizadeh, Auteur ; Eyal Ben-Dor, Auteur Année de publication : 2022 Article en page(s) : pp 610 - 620 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] analyse de groupement
[Termes IGN] autocorrélation spatiale
[Termes IGN] contamination
[Termes IGN] distribution spatiale
[Termes IGN] image infrarouge
[Termes IGN] interpolation spatiale
[Termes IGN] krigeage
[Termes IGN] plomb
[Termes IGN] qualité du sol
[Termes IGN] République TchèqueRésumé : (auteur) For decades, the Příbram district in the Czech Republic has been affected by industrial and mining activities, which are the main sources of heavy metal pollutants and negatively affect soil quality. A recent study examined visible–near-infrared (VNIR), shortwave-infrared (SWIR), and X-ray fluorescence (XRF) spectroscopy to model soil lead (Pb) content in a selected area located in Příbram. Following that study, and using the data, we examined the spatial distribution of Pb content in the soil, with a combination of traditional techniques (Moran’s I, hotspot analysis, and Kriging). One of the novel points of this work is the use of the Getis–Ord hotspot analysis before the execution of Kriging interpolation to better emphasize clustering patterns. The results indicated that Pb was a spatially dependent soil property and through extensive in-situ sampling, it was possible to generate an accurate interpolation model. The high-Pb hotspots coincided with topographic obstacles that were modeled using topographic profiles extracted from Google Earth, indicating that Pb content does not always exhibit a direct relationship with topographic height as a result of runoff, due to the contribution of topographic steps. This observation provides a new perspective on the relationship between Pb content and topographic patterns. Numéro de notice : A2022-872 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/19475705.2022.2039786 Date de publication en ligne : 23/02/2022 En ligne : https://doi.org/10.1080/19475705.2022.2039786 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102166
in Geomatics, Natural Hazards and Risk > vol 13 (2022) . - pp 610 - 620[article]Studying informativeness of satellite image texture for sea ice state retrieval using deep learning methods / Clément Fougerouse (2022)
Titre : Studying informativeness of satellite image texture for sea ice state retrieval using deep learning methods Type de document : Mémoire Auteurs : Clément Fougerouse, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2022 Importance : 47 p. Format : 21 x 30 cm Note générale : Bibliographie
Rapport de projet pluridisciplinaire, cycle ING2Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] glace de mer
[Termes IGN] image Aqua-AMSR
[Termes IGN] image C-SAR
[Termes IGN] image radar moirée
[Termes IGN] inférence
[Termes IGN] optimisation (mathématiques)
[Termes IGN] réseau neuronal convolutif
[Termes IGN] restauration d'imageIndex. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (Auteur) De nos jours, la détermination des glaces de mers se fait manuellement et est réalisée par des experts, les cartes obtenues ne sont donc pas bien précises et peuvent comporter des erreurs. L’objectif de l’étude est de pouvoir automatiser la classification des différents types de glaces de mer à partir d’images satellitaires SAR et AMSR2, en utilisant des réseaux de neurones convolutifs et d’améliorer la précision des réseaux déjà existants. Pour cela, nous partons des réseaux existants et nous rajoutons de nouvelles données d’apprentissages et nous modifions la structure du réseau de neurones convolutif. Puis nous étudions la texture des images pour pouvoir prendre en compte les formes des glaces et ainsi de créer plusieurs classes pour les glaces de mers. Que ce soit avec l’ajout de nouvelles données ou la modification de la structure du réseau, la précision des prédictions du réseau de neurones a grandement été amélioré. Nous passons d’une précision de 74% en moyenne sur les quatre classes utilisées à une moyenne de 95% après toutes les améliorations réalisées. Notons également, que la détection de la présence ou non de glace est très précise 98%. Quant à l’ajout des nouvelles classes et à la prise en compte de la texture des images satellitaires, nous obtenons des résultats très intéressants : le classificateur permet de distinguer certaines combinaisons, mais a du mal pour d’autres, notamment pour les glaces qui ont des petites formes. Ainsi, cette étude a permis d’améliorer considérablement la précision des réseaux existants pour classer la glace dans les quatre types habituels bien qu'ils restent moins performants pour classer en prenant en compte la forme des glaces. L’étude du caractère informatif a permis de connaitre les combinaisons détectées par la texture des images SAR. Note de contenu : 1. Introduction
2. Data used for training the CNN
2.1 NetCDF files
2.2 SAR data
2.3 AMSR2 data
2.4 Ice Chart
3. Processing
3.1 Overview
3.2 Statistical analysis
3.3 Preprocessing
3.3 Training
3.4 Inference
3.4 Baseline binary CNN
3.5 Baseline continuous CNN
3.6 Adding the larger area SAR data
3.7 Adding the AMSR2 data
3.8 Optimization
3.9 Experiments with informativeness
4. Results
4.1 Statistics
4.2 Baseline Binary
4.3 Hugo continuous
4.4 Extended SAR sub-image
4.5 AMSR2
4.6 Optimization
4.7 Informativeness tests
5. Conclusion and discussionNuméro de notice : 26868 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Mémoire de projet pluridisciplinaire Organisme de stage : Nansen Environmental and Remote Sensing Center NERSC Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101688 Documents numériques
en open access
Studying informativeness of satellite image texture for sea ice state retrieval using deep learning methods - pdf auteurAdobe Acrobat PDF PermalinkComparative analysis for methods of building digital elevation models from topographic maps using geoinformation technologies / Vadim Belenok in Geodesy and cartography, vol 47 n° 4 (December 2021)PermalinkUn désordre complexe à modéliser / Laurent Polidori in Géomètre, n° 2197 (décembre 2021)PermalinkFast estimation for robust supervised classification with mixture models / Erwan Giry Fouquet in Pattern recognition letters, vol 152 (December 2021)PermalinkImproving soil moisture retrieval from GNSS-interferometric reflectometry: parameters optimization and data fusion via neural network / Yajie Shi in International Journal of Remote Sensing IJRS, vol 42 n° 23 (1-10 December 2021)PermalinkMSegnet, a practical network for building detection from high spatial resolution images / Bo Yu in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 12 (December 2021)PermalinkParticle swarm optimization based water index (PSOWI) for mapping the water extents from satellite images / Mohammad Hossein Gamshadzaei in Geocarto international, vol 36 n° 20 ([01/12/2021])PermalinkThe method of detection and localization of configuration defects in geodetic networks by means of Tikhonov regularization / Roman Kadaj in Reports on geodesy and geoinformatics, vol 112 n° 1 (December 2021)PermalinkA topology-based graph data model for indoor spatial-social networking / Mahdi Rahimi in International journal of geographical information science IJGIS, vol 35 n° 12 (December 2021)PermalinkIdentifying surface urban heat island drivers and their spatial heterogeneity in China’s 281 cities: An empirical study based on multiscale geographically weighted regression / Lu Niu in Remote sensing, vol 13 n° 21 (November-1 2021)Permalink