Descripteur
Documents disponibles dans cette catégorie (927)
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 : Machine learning for image segmentation Titre original : Apprentissage artificiel pour la segmentation d'image Type de document : Thèse/HDR Auteurs : Kaiwen Chang, Auteur ; Jesus Angulo lopez, Directeur de thèse ; Jesus Angulo lopez, Directeur de thèse ; Bruno Figliuzzi, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2019 Importance : 155 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université PSL, Spécialité : Morphologie MathématiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] base de données d'images
[Termes IGN] graphe
[Termes IGN] morphologie mathématique
[Termes IGN] optique géométrique
[Termes IGN] rayonnement lumineux
[Termes IGN] segmentation d'image
[Termes IGN] segmentation par graphes d'adjacence de régions
[Termes IGN] superpixelIndex. décimale : THESE Thèses et HDR Résumé : (auteur) In this PhD thesis, our aim is to establish a general methodology for performing the segmentation of a dataset constituted of similar images with only a few annotated images as training examples. This methodology is directly intended to be applied to images gathered in Earth observation or materials science applications, for which there is not enough annotated examples to train state-of-the-art deep learning based segmentation algorithms. The proposed methodology starts from a superpixel partition of the image and gradually merges the initial regions until anactual segmentation is obtained. The two main contributions described in this PhD thesis are the development of a new superpixel algorithm which makes use of the Eikonal equation, and the development of a superpixel merging algorithm steaming from the adaption of the Eikonal equation to the setting of graphs. The superpixels merging approach makes use of a region adjacency graph computed from the superpixel partition. The edges are weighted by a dissimilarity measure learned by a machine learning algorithm from low-level cues computed on the superpixels. In terms of application, our approach to image segmentation is finally evaluated on the SWIMSEG dataset, a dataset which contains sky cloud images. On this dataset, using only a limited amount of images for training our algorithm, we were able to obtain segmentation results similar to the ones obtained with state-of-the-art algorithms. Note de contenu : 1- Introduction
2- Fast marching based superpixels
3- Hierarchical segmentation based on wavelet decomposition
4- Learning similarities between regions
5- Region merging
6- Application
Conclusion and perspectivesNuméro de notice : 25837 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Morphologie Mathématique : Paris Sciences et Lettres : 2019 Organisme de stage : Centre de Morphologie Mathématique (Mines ParisTech) nature-HAL : Thèse DOI : sans En ligne : https://hal.archives-ouvertes.fr/tel-02510662 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95191
Titre : Point cloud oversegmentation with graph-structured deep metric learning Type de document : Article/Communication Auteurs : Loïc Landrieu , Auteur ; Mohamed Boussaha , Auteur Editeur : Computer vision foundation CVF Année de publication : 2019 Projets : 1-Pas de projet / Conférence : CVPR 2019, IEEE Conference on Computer Vision and Pattern Recognition 16/06/2019 20/06/2019 Long Beach Californie - Etats-Unis Open Access Proceedings Importance : pp 7432 - 7441 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage profond
[Termes IGN] données localisées 3D
[Termes IGN] graphe
[Termes IGN] réseau neuronal artificiel
[Termes IGN] segmentation sémantique
[Termes IGN] semis de pointsRésumé : (auteur) We propose a new supervized learning framework foroversegmenting 3D point clouds into superpoints. We castthis problem as learning deep embeddings of the local ge-ometry and radiometry of 3D points, such that the border ofobjects presents high contrasts. The embeddings are com-puted using a lightweight neural network operating on thepoints’ local neighborhood. Finally, we formulate pointcloud oversegmentation as a graph partition problem withrespect to the learned embeddings.This new approach allows us to set a new state-of-the-artin point cloud oversegmentation by a significant margin, ona dense indoor dataset (S3DIS) and a sparse outdoor one(vKITTI). Our best solution requires over five times fewersuperpoints to reach similar performance than previouslypublished methods on S3DIS. Furthermore, we show thatour framework can be used to improve superpoint-basedsemantic segmentation algorithms, setting a new state-of-the-art for this task as well. Numéro de notice : C2019-017 Affiliation des auteurs : LASTIG MATIS (2012-2019) Autre URL associée : vers CVF Thématique : IMAGERIE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/CVPR.2019.00762 Date de publication en ligne : 09/01/2020 En ligne : https://doi.org/10.1109/CVPR.2019.00762 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93351 Spatial data management in apache spark: the GeoSpark perspective and beyond / Jia Yu in Geoinformatica, vol 23 n° 1 (January 2019)
[article]
Titre : Spatial data management in apache spark: the GeoSpark perspective and beyond Type de document : Article/Communication Auteurs : Jia Yu, Auteur ; Zongsi Zhang, Auteur ; Mohamed Sarwat, Auteur Année de publication : 2019 Article en page(s) : pp 37 - 78 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] analyse comparative
[Termes IGN] Apache (serveur)
[Termes IGN] arbre k-d
[Termes IGN] arbre quadratique
[Termes IGN] arbre-R
[Termes IGN] données massives
[Termes IGN] Hadoop
[Termes IGN] index spatial
[Termes IGN] performance
[Termes IGN] Spark
[Termes IGN] traitement répartiRésumé : (auteur) The paper presents the details of designing and developing GeoSpark, which extends the core engine of Apache Spark and SparkSQL to support spatial data types, indexes, and geometrical operations at scale. The paper also gives a detailed analysis of the technical challenges and opportunities of extending Apache Spark to support state-of-the-art spatial data partitioning techniques: uniform grid, R-tree, Quad-Tree, and KDB-Tree. The paper also shows how building local spatial indexes, e.g., R-Tree or Quad-Tree, on each Spark data partition can speed up the local computation and hence decrease the overall runtime of the spatial analytics program. Furthermore, the paper introduces a comprehensive experiment analysis that surveys and experimentally evaluates the performance of running de-facto spatial operations like spatial range, spatial K-Nearest Neighbors (KNN), and spatial join queries in the Apache Spark ecosystem. Extensive experiments on real spatial datasets show that GeoSpark achieves up to two orders of magnitude faster run time performance than existing Hadoop-based systems and up to an order of magnitude faster performance than Spark-based systems. Numéro de notice : A2019-225 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10707-018-0330-9 Date de publication en ligne : 22/10/2018 En ligne : http://dx.doi.org/10.1007/s10707-018-0330-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92621
in Geoinformatica > vol 23 n° 1 (January 2019) . - pp 37 - 78[article]
Titre : Supervized segmentation with graph-structured deep metric learning Type de document : Article/Communication Auteurs : Loïc Landrieu , Auteur ; Mohamed Boussaha , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2019 Projets : 1-Pas de projet / Conférence : ICML 2019, Workshop on Learning and Reasoning with Graph-Structured Representations in International Conference on Machine Learning 15/06/2019 15/06/2019 Long Beach Californie - Etats-Unis Open Access Proceedings Importance : 15 p. Langues : Français (fre) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] graphe
[Termes IGN] segmentation
[Termes IGN] semis de pointsRésumé : (auteur) We present a fully-supervized method for learning to segment data structured by an adjacency graph. We introduce the graph-structured contrastive loss, a loss function structured by a ground truth segmentation. It promotes learning vertex embeddings which are homogeneous within desired segments, and have high contrast at their interface. Thus, computing a piecewise-constant approximation of such embeddings produces a graph-partition close to the objective segmentation. This loss is fully backpropagable, which allows us to learn vertex embeddings with deep learning algorithms. We evaluate our methods on a 3D point cloud oversegmentation task, defining a new state-of-the-art by a large margin. These results are based on the published work of Landrieu and Boussaha 2019. Numéro de notice : C2019-050 Affiliation des auteurs : LASTIG MATIS (2012-2019) Autre URL associée : vers ArXiv Nature : Poster nature-HAL : Poster-avec-CL DOI : 10.48550/arXiv.1905.04014 Date de publication en ligne : 19/05/2019 En ligne : https://graphreason.github.io/papers/4.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92819
Titre : Sustainable development goals connectivity dilemma : Land and geospatial information for urban and rural resilience Type de document : Monographie Auteurs : Abbas Rajabifard, Éditeur scientifique Editeur : Boca Raton, New York, ... : CRC Press Année de publication : 2019 Importance : 376 p. Format : 16 x 24 cm ISBN/ISSN/EAN : 978-0-367-25935-8 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Infrastructure de données
[Termes IGN] approche holistique
[Termes IGN] connexité (graphes)
[Termes IGN] développement durable
[Termes IGN] données localisées
[Termes IGN] infrastructure mondiale des données localisées
[Termes IGN] migration humaine
[Termes IGN] résilience écologique
[Termes IGN] système d'information géographique
[Termes IGN] ville intelligente
[Termes IGN] zone rurale
[Termes IGN] zone urbaineRésumé : (éditeur) Large-scale migration from rural to urban areas, and between countries, affects sustainable development at local, national, and regional levels. To strengthen urban and rural resilience to global challenges, Sustainable Development Goals Connectivity Dilemma: Land and Geospatial Information for Urban and Rural Resilience, brings together leading international geospatial experts to analyze the role of land and geospatial data infrastructures and services for achieving the United Nations' Sustainable Development Goals (SDGs). While the goals outlined in the 2030 Agenda have been longstanding aspirations worldwide, the complexity and connectivity between social, economic, environmental, and governance challenges are changing with large-scale urbanization and population growth. Structured in 5 parts, the themes and objectives of the book are in line with the critical challenges, gaps, and opportunities raised at all UN-GGIM events and UN-GGIM Academic Network forums. Through the different perspectives of scholars, industry actors, and policy-makers, this book provides interdisciplinary analysis and multisectoral expertise on the interconnection between the SDGs, geospatial information, and urban and rural resilience. Sustainable Development Goals Connectivity Dilemma: Land and Geospatial Information for Urban and Rural Resilience is an essential reference for researchers, industry professionals, and postgraduate students in fields such as geomatics, land administration, urban planning, GIS, and sustainable development. It will also prove a vital resource for environmental protection specialists, government practitioners, UN-GGIM delegates, and geospatial and land administration agencies. Note de contenu : Part I- Setting the Scene
Part II- Enhancing SDGs Connectivity and Disaster Resilience
Part III- Supporting SDGs: Legal, Policies and Institutional Components and Capacity Building
Part IV- Enabling Tools and Technical Components
Part V- SDGs Perspectives: Current Practices and Case StudiesNuméro de notice : 25852 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/URBANISME Nature : Monographie DOI : sans En ligne : https://www.taylorfrancis.com/books/e/9780429290626 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95443 PermalinkVectorisation du cadastre ancien : restructuration de la chaîne de traitement, implémentation d’une nouvelle méthode de détection et utilisation de la théorie des graphes / Antony Chalais (2019)PermalinkUn algorithme pour battre le record du SwissTrainChallenge : poser le pied dans chacun des 26 cantons le plus rapidement possible en utilisant uniquement des transports publics / Emmanuel Clédat in XYZ, n° 157 (décembre 2018 - février 2019)PermalinkDEM refinement by low vegetation removal based on the combination of full waveform data and progressive TIN densification / Hongchao Ma in ISPRS Journal of photogrammetry and remote sensing, vol 146 (December 2018)PermalinkRoad safety evaluation through automatic extraction of road horizontal alignments from Mobile LiDAR System and inductive reasoning based on a decision tree / José Antonio Martin-Jimenez in ISPRS Journal of photogrammetry and remote sensing, vol 146 (December 2018)PermalinkAn algorithm for on-the-fly K shortest paths finding in multi-storey buildings using a hierarchical topology model / Rosen Ivanov in International journal of geographical information science IJGIS, vol 32 n° 11-12 (November - December 2018)PermalinkCompactly representing massive terrain models as TINs in CityGML / Kavisha Kumar in Transactions in GIS, vol 22 n° 5 (October 2018)PermalinkA context-based geoprocessing framework for optimizing meetup location of multiple moving objects along road networks / Shaohua Wang in International journal of geographical information science IJGIS, vol 32 n° 7-8 (July - August 2018)PermalinkFrom hierarchy to networking: the evolution of the “twenty-first-century Maritime Silk Road” container shipping system / Liehui Wang in Transport reviews, vol 38 n° 4 ([01/07/2018])PermalinkL’opérateur de collage : Gestion de plusieurs points de vue dans un contexte spatial / Géraldine Del Mondo in Revue internationale de géomatique, vol 28 n° 3 (juillet - septembre 2018)PermalinkVoronoi tessellation on the ellipsoidal earth for vector data / Christos Kastrisios in International journal of geographical information science IJGIS, vol 32 n° 7-8 (July - August 2018)PermalinkPré-estimation et analyse de la précision pour la cartographie par drone / Laurent Valentin Jospin in XYZ, n° 155 (juin - août 2018)PermalinkA voxel- and graph-based strategy for segmenting man-made infrastructures using perceptual grouping laws: comparison and evaluation / Yusheng Xu in Photogrammetric Engineering & Remote Sensing, PERS, vol 84 n° 6 (juin 2018)PermalinkWeighted simplicial complex reconstruction from mobile laser scanning using sensor topology / Stéphane Guinard in Revue Française de Photogrammétrie et de Télédétection, n° 217-218 (juin - septembre 2018)PermalinkComparison of the performances of ground filtering algorithms and DTM generation from a UAV-based point cloud / Cigdem Serifoglu Yilmaz in Geocarto international, vol 33 n° 5 (May 2018)PermalinkA novel orthoimage mosaic method using a weighted A∗ algorithm : Implementation and evaluation / Maoteng Zheng in ISPRS Journal of photogrammetry and remote sensing, vol 138 (April 2018)PermalinkOptimization of deformation monitoring networks using finite element strain analysis / M. Amin Alizadeh-Khameneh in Journal of applied geodesy, vol 12 n° 2 (April 2018)PermalinkSpace-time tree ensemble for action recognition and localization / Shugao Ma in International journal of computer vision, vol 126 n° 2-4 (April 2018)PermalinkA spatio-temporal index for aerial full waveform laser scanning data / Debra F. Laefer in ISPRS Journal of photogrammetry and remote sensing, vol 138 (April 2018)PermalinkGenerative street addresses from satellite imagery / İlke Demir in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)Permalink