Descripteur
Documents disponibles dans cette catégorie (1770)
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
Increasing the accuracy of crowdsourced information on land cover via a voting procedure weighted by information inferred from the contributed data / Giles M. Foody in ISPRS International journal of geo-information, vol 7 n° 3 (March 2018)
[article]
Titre : Increasing the accuracy of crowdsourced information on land cover via a voting procedure weighted by information inferred from the contributed data Type de document : Article/Communication Auteurs : Giles M. Foody, Auteur ; Linda M. See, Auteur ; Steffen Fritz, Auteur ; Inian Moorthy, Auteur ; Christoph Perger, Auteur ; Christian Schill, Auteur ; Doreen S. Boyd, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] cartographie collaborative
[Termes IGN] données localisées des bénévoles
[Termes IGN] modèle de classe latente
[Termes IGN] occupation du sol
[Termes IGN] pondération
[Termes IGN] précision de la classificationRésumé : (Auteur) Simple consensus methods are often used in crowdsourcing studies to label cases when data are provided by multiple contributors. A basic majority vote rule is often used. This approach weights the contributions from each contributor equally but the contributors may vary in the accuracy with which they can label cases. Here, the potential to increase the accuracy of crowdsourced data on land cover identified from satellite remote sensor images through the use of weighted voting strategies is explored. Critically, the information used to weight contributions based on the accuracy with which a contributor labels cases of a class and the relative abundance of class are inferred entirely from the contributed data only via a latent class analysis. The results show that consensus approaches do yield a classification that is more accurate than that achieved by any individual contributor. Here, the most accurate individual could classify the data with an accuracy of 73.91% while a basic consensus label derived from the data provided by all seven volunteers contributing data was 76.58%. More importantly, the results show that weighting contributions can lead to a statistically significant increase in the overall accuracy to 80.60% by ignoring the contributions from the volunteer adjudged to be the least accurate in labelling. Numéro de notice : A2018-093 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi7030080 Date de publication en ligne : 25/02/2018 En ligne : https://doi.org/10.3390/ijgi7030080 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89505
in ISPRS International journal of geo-information > vol 7 n° 3 (March 2018)[article]Systematic error reduction in geometric measurements based on altimetric enrichment of geographical features / Jean-François Girres in Cartographica, vol 53 n° 1 (Spring 2018)
[article]
Titre : Systematic error reduction in geometric measurements based on altimetric enrichment of geographical features Type de document : Article/Communication Auteurs : Jean-François Girres , Auteur Année de publication : 2018 Article en page(s) : pp 52 - 61 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG
[Termes IGN] données localisées 2D
[Termes IGN] données vectorielles
[Termes IGN] erreur systématique
[Termes IGN] mesure géométrique
[Termes IGN] modèle numérique de surface
[Termes IGN] objet géographique
[Termes IGN] Triangulated Irregular NetworkRésumé : (Auteur) In most GIS software, geometric measurements (length, area) computed from the geometry of vector objects are performed in two dimensions, which generates systematic underestimates. Several reasons can explain this critical situation: two of these include deficiencies in the geometric modelling of vector data and absence of correctly implemented methods for computing measurements using altitudes. To reduce the systematic error in geometric measurements caused by the omission of altitudes, methods are proposed to (1) enrich the geometry of geographical features using external altimetric data and (2) compute length and area using altitudes. These propositions are implemented in a model that allows any GIS user to take terrain into account in the computation of length and area and estimate the underestimation involved in two-dimensional measurements. Experiments are finally performed to illustrate the functioning of the model and test the impact of the quality of several altimetric data sources. Results demonstrate that freely available digital elevation models reduce measurement error. Based on comparisons with high-resolution databases, the results also show that omitting the terrain is not sufficient to assess the entire measurement error, which is also affected by other processes, such as digitizing error and cartographic projection. Numéro de notice : A2018-207 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3138/cart.53.1.2017-0006 Date de publication en ligne : 21/03/2018 En ligne : https://doi.org/10.3138/cart.53.1.2017-0006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89923
in Cartographica > vol 53 n° 1 (Spring 2018) . - pp 52 - 61[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 031-2018011 SL Revue Centre de documentation Revues en salle Disponible Comparing the performance of flat and hierarchical Habitat/Land-Cover classification models in a NATURA 2000 site / Yoni Gavish in ISPRS Journal of photogrammetry and remote sensing, vol 136 (February 2018)
[article]
Titre : Comparing the performance of flat and hierarchical Habitat/Land-Cover classification models in a NATURA 2000 site Type de document : Article/Communication Auteurs : Yoni Gavish, Auteur ; Jerome O’Connell, Auteur ; Charles J. Marsh, Auteur ; Cristina Tarantino, Auteur ; Palma Blonda, Auteur ; Valeria Tomaselli, Auteur ; William E. Kunin, Auteur Année de publication : 2018 Article en page(s) : pp 1 - 12 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] analyse comparative
[Termes IGN] classification
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] habitat (nature)
[Termes IGN] occupation du sol
[Termes IGN] performance
[Termes IGN] site Natura 2000Résumé : (Auteur) The increasing need for high quality Habitat/Land-Cover (H/LC) maps has triggered considerable research into novel machine-learning based classification models. In many cases, H/LC classes follow pre‐defined hierarchical classification schemes (e.g., CORINE), in which fine H/LC categories are thematically nested within more general categories. However, none of the existing machine-learning algorithms account for this pre-defined hierarchical structure. Here we introduce a novel Random Forest (RF) based application of hierarchical classification, which fits a separate local classification model in every branching point of the thematic tree, and then integrates all the different local models to a single global prediction. We applied the hierarchal RF approach in a NATURA 2000 site in Italy, using two land-cover (CORINE, FAO-LCCS) and one habitat classification scheme (EUNIS) that differ from one another in the shape of the class hierarchy. For all 3 classification schemes, both the hierarchical model and a flat model alternative provided accurate predictions, with kappa values mostly above 0.9 (despite using only 2.2–3.2% of the study area as training cells). The flat approach slightly outperformed the hierarchical models when the hierarchy was relatively simple, while the hierarchical model worked better under more complex thematic hierarchies. Most misclassifications came from habitat pairs that are thematically distant yet spectrally similar. In 2 out of 3 classification schemes, the additional constraints of the hierarchical model resulted with fewer such serious misclassifications relative to the flat model. The hierarchical model also provided valuable information on variable importance which can shed light into “black-box” based machine learning algorithms like RF. We suggest various ways by which hierarchical classification models can increase the accuracy and interpretability of H/LC classification maps. Numéro de notice : A2018-071 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.12.002 Date de publication en ligne : 05/02/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.12.002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89430
in ISPRS Journal of photogrammetry and remote sensing > vol 136 (February 2018) . - pp 1 - 12[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2018021 RAB Revue Centre de documentation En réserve L003 Disponible 081-2018023 RAB Revue Centre de documentation En réserve L003 Disponible 081-2018022 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt Recognition of building group patterns in topographic maps based on graph partitioning and random forest / Xianjin He in ISPRS Journal of photogrammetry and remote sensing, vol 136 (February 2018)
[article]
Titre : Recognition of building group patterns in topographic maps based on graph partitioning and random forest Type de document : Article/Communication Auteurs : Xianjin He, Auteur ; Xinchang Zhang, Auteur ; Qinchuan Xin, Auteur Année de publication : 2018 Article en page(s) : pp 26 - 40 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage automatique
[Termes IGN] bati
[Termes IGN] graphe
[Termes IGN] Kouangtoung (Chine)
[Termes IGN] partitionnement
[Termes IGN] reconnaissance de formes
[Termes IGN] ville
[Vedettes matières IGN] GénéralisationRésumé : (Auteur) Recognition of building group patterns (i.e., the arrangement and form exhibited by a collection of buildings at a given mapping scale) is important to the understanding and modeling of geographic space and is hence essential to a wide range of downstream applications such as map generalization. Most of the existing methods develop rigid rules based on the topographic relationships between building pairs to identify building group patterns and thus their applications are often limited. This study proposes a method to identify a variety of building group patterns that allow for map generalization. The method first identifies building group patterns from potential building clusters based on a machine-learning algorithm and further partitions the building clusters with no recognized patterns based on the graph partitioning method. The proposed method is applied to the datasets of three cities that are representative of the complex urban environment in Southern China. Assessment of the results based on the reference data suggests that the proposed method is able to recognize both regular (e.g., the collinear, curvilinear, and rectangular patterns) and irregular (e.g., the L-shaped, H-shaped, and high-density patterns) building group patterns well, given that the correctness values are consistently nearly 90% and the completeness values are all above 91% for three study areas. The proposed method shows promises in automated recognition of building group patterns that allows for map generalization. Numéro de notice : A2018-073 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.12.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2017.12.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89433
in ISPRS Journal of photogrammetry and remote sensing > vol 136 (February 2018) . - pp 26 - 40[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2018021 RAB Revue Centre de documentation En réserve L003 Disponible 081-2018023 RAB Revue Centre de documentation En réserve L003 Disponible 081-2018022 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt
Titre : Classification of land use from high resolution satellite imagery Type de document : Mémoire Auteurs : Yasser Kotrsi, Auteur ; Arnaud Le Bris , Encadrant ; Nesrine Chehata , Encadrant ; Anne Puissant, Encadrant ; Tristan Postadjian , Encadrant Editeur : Tunis [Tunisie] : Ecole nationale d'ingénieurs de Carthage Année de publication : 2018 Importance : 112 p. Note générale : bibliographie
End Of Studies Project Report, in fulfillment of the requirements for the degree of National engineering diploma in software engineeringLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] bibliothèque logicielle
[Termes IGN] classification barycentrique
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] Finistère (29)
[Termes IGN] fusion d'images
[Termes IGN] image Sentinel-MSI
[Termes IGN] image SPOT 6
[Termes IGN] milieu urbain
[Termes IGN] occupation du sol
[Termes IGN] OpenCV
[Termes IGN] Python (langage de programmation)
[Termes IGN] semis de pointsRésumé : (auteur) The MATIS team of the LaSTIG Laboratory of the french mapping agency (IGN) has for several years conducted research activities in the field of classification of remote sensing data (aerial or satellite optical images and point clouds 3D lidar) for land use (OCS), in urban and rural areas. With the arrival of the new Sentinel S1 (radar) and S2 (optical) sensors, time series of images are now available free of charge with a high temporal resolution (between 10 and 15 days) and a high spectral resolution for optical images. In addition, the national territory is covered annually by acquisition of SPOT 6-7 images. The CES Artificialisation-urbanization pole Theia aims at the production of a map of land use in urban environment, with a resolution of 10m. Early work based on the fusion of Sentinel 2 time series with very high resolution data (THR) SPOT 6-7, Pleiades led to the detection of artifical spots, as well as well shaped urban objects. It is now a question of better characterizing this urban space by investigating about the relations between those image regions as well as each one’s spatial properties in order to produce a detailed cartography classified into different types of urban fabrics (residential, dense urban, non-dense, industrial, ...). In this study we dive deep through the problematic of the land use classification, its aspects as well the different approaches to characterize the extracted information about it in order to obtain an accurate classification that corresponds well to the expected results. This study therefore focuses on the continuation of previous work and consists in obtaining a detailed cartography in different types of urban fabrics (residential, dense urban, non-dense, industrial, ..). For that, several scientific locks are raised: • Test the data fusion methods previously used for fine mapping of the urban environment. • Develop different multiscale spatial indicators (size of objects, distance between objects, density of objects, presence of vegetation, ...) to describe the city. • Exploit these indicators in order to find different types of neighborhoods and to characterize land use. The calculation of indicators is based in part on SPOT image classifications 6-7 obtained during previous work. Also the Urban Atlas database, which also details urban spaces in urban classes, is used in the learning stage as well as the Corine Land Cover database. Note de contenu : Introduction
1- Project introduction
2- State of the art and background material
3- Available data and study areas
4- Methodology
5- Results and discussions
Conclusion and perspectivesNuméro de notice : 17187 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Mémoire ingénieur Organisme de stage : LaSTIG (IGN) DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98348 Documents numériques
peut être téléchargé
Classification of land use ... - pdf auteurAdobe Acrobat PDF Classification à très haute résolution (THR) spatiale et fusion d'occupation des sols (OCS) / Tristan Postadjian (2018)PermalinkDomain adaptation for large scale classification of very high resolution satellite images with deep convolutional neural networks / Tristan Postadjian (2018)PermalinkExploring the impact of seasonality on urban land-cover mapping using multi-season sentinel-1A and GF-1 WFV images in a subtropical monsoon-climate region / Tao Zhou in ISPRS International journal of geo-information, vol 7 n° 1 (January 2018)PermalinkFusion tardive d’images SPOT-6/7 et de données multitemporelles Sentinel-2 pour la détection de la tache urbaine / Cyril Wendl (2018)PermalinkLocalisation par l'image en milieu urbain : application à la réalité augmentée / Antoine Fond (2018)PermalinkMise en place d’un outil de classification et d’utilisation des données LiDAR pour l’étude du couvert arboré à Florence / Florian Thill (2018)PermalinkModélisation spatio-temporelle multi-niveau à base d'ontologies pour le suivi de la dynamique en imagerie satellitaire / Fethi Ghazouani (2018)PermalinkObject-based superresolution land-cover mapping from remotely sensed imagery / Yuehong Chen in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)PermalinkL'occupation et l'usage des sols par télédétection, où en sommes-nous aujourd'hui ? [Introduction] / Clément Mallet (2018)PermalinkPermalink