Descripteur



Etendre la recherche sur niveau(x) vers le bas
CNN-based dense image matching for aerial remote sensing images / Shunping Ji in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 6 (June 2019)
![]()
[article]
Titre : CNN-based dense image matching for aerial remote sensing images Type de document : Article/Communication Auteurs : Shunping Ji, Auteur ; Jin Liu, Auteur ; Meng Lu, Auteur Année de publication : 2019 Article en page(s) : pp 415 - 424 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] appariement d'images
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] Chine
[Termes descripteurs IGN] couple stéréoscopique
[Termes descripteurs IGN] image aérienne
[Termes descripteurs IGN] Munich
[Termes descripteurs IGN] réseau neuronal convolutif
[Termes descripteurs IGN] Stuttgart
[Termes descripteurs IGN] ville
[Termes descripteurs IGN] zone urbaineRésumé : (Auteur) Dense stereo matching plays a key role in 3D reconstruction. The capability of using deep learning in the stereo matching of remote sensing data is currently uncertain. This article investigated the application of deep learning–based stereo methods in aerial image series and proposed a deep learning–based multi-view dense matching framework. First, we applied three typical convolutional neural network models, MC-CNN, GC-Net, and DispNet, to aerial stereo pairs and compared the results with those of the SGM and a commercial software, SURE. Second, on different data sets, the generalization ability of each network is evaluated by using direct transfer learning with models pretrained on other data sets and by fine-tuning with a small number of target training data. Third, we present a deep learning–based multi-view dense matching framework where the multi-view geometry is introduced to further refine matching results. Three sets of aerial images as the main data sets and two open-source sets of street images as auxiliary data sets are used for testing. Experiments show that, first, the performance of deep learning–based stereo methods is slightly better than traditional methods. Second, both the GC-Net and the MC-CNN have demonstrated good generalization ability and can obtain satisfactory results on aerial images using a pretrained model on several available stereo benchmarks. Third, multi-view geometry constraints can further improve the performance of deep learning–based methods, which is better than that of the multi-view–based SGM and SURE. Numéro de notice : A2019-246 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.6.415 date de publication en ligne : 01/06/2019 En ligne : https://doi.org/10.14358/PERS.85.6.415 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93002
in Photogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 6 (June 2019) . - pp 415 - 424[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 105-2019061 SL Revue Centre de documentation Revues en salle Disponible Land cover mapping at very high resolution with rotation equivariant CNNs : Towards small yet accurate models / Diego Marcos in ISPRS Journal of photogrammetry and remote sensing, vol 145 - part A (November 2018)
![]()
[article]
Titre : Land cover mapping at very high resolution with rotation equivariant CNNs : Towards small yet accurate models Type de document : Article/Communication Auteurs : Diego Marcos, Auteur ; Michele Volpi, Auteur ; Benjamin Kellenberger, Auteur ; Devis Tuia, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] Bade-Wurtemberg (Allemagne)
[Termes descripteurs IGN] carte d'occupation du sol
[Termes descripteurs IGN] enrichissement sémantique
[Termes descripteurs IGN] étiquette
[Termes descripteurs IGN] filtrage numérique d'image
[Termes descripteurs IGN] image à ultra haute résolution
[Termes descripteurs IGN] modèle numérique de surface
[Termes descripteurs IGN] orthoimage
[Termes descripteurs IGN] réseau neuronal convolutifRésumé : (Auteur) In remote sensing images, the absolute orientation of objects is arbitrary. Depending on an object’s orientation and on a sensor’s flight path, objects of the same semantic class can be observed in different orientations in the same image. Equivariance to rotation, in this context understood as responding with a rotated semantic label map when subject to a rotation of the input image, is therefore a very desirable feature, in particular for high capacity models, such as Convolutional Neural Networks (CNNs). If rotation equivariance is encoded in the network, the model is confronted with a simpler task and does not need to learn specific (and redundant) weights to address rotated versions of the same object class. In this work we propose a CNN architecture called Rotation Equivariant Vector Field Network (RotEqNet) to encode rotation equivariance in the network itself. By using rotating convolutions as building blocks and passing only the values corresponding to the maximally activating orientation throughout the network in the form of orientation encoding vector fields, RotEqNet treats rotated versions of the same object with the same filter bank and therefore achieves state-of-the-art performances even when using very small architectures trained from scratch. We test RotEqNet in two challenging sub-decimeter resolution semantic labeling problems, and show that we can perform better than a standard CNN while requiring one order of magnitude less parameters. Numéro de notice : A2018-491 Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.01.021 date de publication en ligne : 19/02/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.01.021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91227
in ISPRS Journal of photogrammetry and remote sensing > vol 145 - part A (November 2018)[article]Réservation
Réserver ce documentExemplaires (3)
Code-barres Cote Support Localisation Section Disponibilité 081-2018111 SL Revue Centre de documentation Revues en salle Disponible 081-2018113 DEP-EXM Revue MATIS Dépôt en unité Exclu du prêt 081-2018112 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt Open land cover from OpenStreetMap and remote sensing / Michael Schultz in International journal of applied Earth observation and geoinformation, vol 63 (December 2017)
![]()
[article]
Titre : Open land cover from OpenStreetMap and remote sensing Type de document : Article/Communication Auteurs : Michael Schultz, Auteur ; Janek Voss, Auteur ; Michael Auer, Auteur ; Sarah Carter, Auteur ; Alexander Zipf, Auteur Année de publication : 2017 Article en page(s) : pp 206 - 213 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes descripteurs IGN] analyse diachronique
[Termes descripteurs IGN] classification par forêts aléatoires
[Termes descripteurs IGN] étiquette
[Termes descripteurs IGN] Heidelberg
[Termes descripteurs IGN] image Landsat-8
[Termes descripteurs IGN] occupation du sol
[Termes descripteurs IGN] OpenStreetMapRésumé : (auteur) OpenStreetMap (OSM) tags were used to produce a global Open Land Cover (OLC) product with fractional data gaps available at osmlanduse.org. Data gaps in the global OLC map were filled for a case study in Heidelberg, Germany using free remote sensing data, which resulted in a land cover (LC) prototype with complete coverage in this area. Sixty tags in the OSM were used to allocate a Corine Land Cover (CLC) level 2 land use classification to 91.8% of the study area, and the remaining gaps were filled with remote sensing data. For this case study, complete are coverage OLC overall accuracy was estimated 87%, which performed better than the CLC product (81% overall accuracy) of 2012. Spatial thematic overlap for the two products was 84%. OLC was in large parts found to be more detailed than CLC, particularly when LC patterns were heterogeneous, and outperformed CLC in the classification of 12 of the 14 classes. Our OLC product represented data created in different periods; 53% of the area was 2011–2016, and 46% of the area was representative of 2016–2017. Numéro de notice : A2017-638 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2017.07.014 En ligne : https://doi.org/10.1016/j.jag.2017.07.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86989
in International journal of applied Earth observation and geoinformation > vol 63 (December 2017) . - pp 206 - 213[article]Estimating the spatial distribution, extent and potential lignocellulosic biomass supply of Trees Outside Forests in Baden-Wuerttemberg using airborne LiDAR and OpenStreetMap data / Joachim Maack in International journal of applied Earth observation and geoinformation, vol 58 (June 2017)
![]()
[article]
Titre : Estimating the spatial distribution, extent and potential lignocellulosic biomass supply of Trees Outside Forests in Baden-Wuerttemberg using airborne LiDAR and OpenStreetMap data Type de document : Article/Communication Auteurs : Joachim Maack, Auteur ; Marcus Lingenfelder, Auteur ; Christina Eilers, Auteur ; Thomas Smaltschinski, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 118 - 125 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] arbre hors forêt
[Termes descripteurs IGN] Bade-Wurtemberg (Allemagne)
[Termes descripteurs IGN] biomasse
[Termes descripteurs IGN] classification
[Termes descripteurs IGN] détection d'objet
[Termes descripteurs IGN] distribution spatiale
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] données localisées 3D
[Termes descripteurs IGN] données localisées des bénévoles
[Termes descripteurs IGN] inventaire de la végétation
[Termes descripteurs IGN] lasergrammétrie
[Termes descripteurs IGN] OpenStreetMap
[Vedettes matières IGN] Inventaire forestierRésumé : (auteur) Trees Outside Forests (TOF) represent a source of lignocellulosic biomass that has received increasing attention in the recent years. While some studies have already investigated the potential of TOF in Germany, a spatial explicit analysis, specifically for Baden-Wuerttemberg, is still lacking. We used a unique wall-to-wall airborne Light Detection and Ranging (LiDAR) dataset combined with OpenStreetMap (OSM) data to map and classify TOF of the federal state of Baden-Wuerttemberg (∼35.000 km2) in south-western Germany. Furthermore, from annual biomass potentials of TOF areas collected from available literature, we calculated the mean annual biomass supply for all TOF areas in Baden-Wuerttemberg. This combination of remote sensing-based classification and available literature resulted in a mean annual biomass supply between ∼490,000–730,000 t from TOF in Baden-Wuerttemberg. The classification congruence on three reference sites was very high (∼99%) using a simple filter technique applied to the LiDAR data and masking man-made objects using OSM data. In contrast, the available literature revealed a high variability of biomass potentials, supporting the demand for an inventory system. Still, the results demonstrate the applicability of LiDAR based vegetation mapping and the value of OSM data in Baden-Wuerttemberg to detect man-made objects. Numéro de notice : A2017-367 Thématique : FORET/GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : https://doi.org/10.1016/j.jag.2017.02.002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85795
in International journal of applied Earth observation and geoinformation > vol 58 (June 2017) . - pp 118 - 125[article]An exploration of future patterns of the contributions to OpenStreetMap and development of a contribution index / Jamal Jokar Arsanjani in Transactions in GIS, vol 19 n° 6 (December 2015)
![]()
[article]
Titre : An exploration of future patterns of the contributions to OpenStreetMap and development of a contribution index Type de document : Article/Communication Auteurs : Jamal Jokar Arsanjani, Auteur ; Peter Mooney, Auteur ; Marco Helbich, Auteur ; Alexander Zipf, Auteur Année de publication : 2015 Article en page(s) : pp 896 – 914 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes descripteurs IGN] Allemagne
[Termes descripteurs IGN] approche participative
[Termes descripteurs IGN] automate cellulaire
[Termes descripteurs IGN] base de données spatiotemporelles
[Termes descripteurs IGN] cartographie collaborative
[Termes descripteurs IGN] données localisées des bénévoles
[Termes descripteurs IGN] indexation sémantique
[Termes descripteurs IGN] OpenStreetMap
[Termes descripteurs IGN] StuttgartRésumé : (auteur) OpenStreetMap (OSM) represents one of the most well-known examples of a collaborative mapping project. Major research efforts have so far dealt with data quality analysis but the modality of OSM's evolution across space and time has barely been noted. This study aims to analyze spatio-temporal patterns of contributions in OSM by proposing a contribution index (CI) in order to investigate the dynamism of OSM. The CI is based on a per cell analysis of the node quantity, interactivity, semantics, and attractivity (the ability to attract contributors). Additionally this research explores whether OSM has been constantly attracting new users and contributions or if OSM has experienced a decline in its ability to attract continued contributions. Using the Stuttgart region of Germany as a case study the empirical findings of the CI over time confirm that since 2007, OSM has been constantly attracting new users, who create new features, edit the existing spatial objects, and enrich them with attributes. This rate has been dramatically growing since 2011. The utilization of a Cellular Automata-Markov (CA-Markov) model provides evidence that by the end of 2016 and 2020, the rise of CI will spread out over the study area and only a few cells without OSM features will remain. Numéro de notice : A2016-437 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1111/tgis.12139 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81347
in Transactions in GIS > vol 19 n° 6 (December 2015) . - pp 896 – 914[article]PermalinkLe suivi de l'occupation du sol à travers le monde / Romain Pfältzer in Cahiers de l'Institut d'aménagement et d'urbanisme de la région Île-de-France, n° 168 (décembre 2013)
PermalinkLiDAR surveys in the upper Rhine Valley: New insights for archeological and landscape applications / F. Basoge in Revue Française de Photogrammétrie et de Télédétection, n° 193 (Janvier 2011)
PermalinkDes preuves venues de l'espace : Traduction de l'original paru en décembre 2009 dans la revue allemande "Der Eisenbahningenieur" / K. Herrmann in XYZ, n° 125 (décembre 2010 - février 2011)
PermalinkPermalinkPremières applications de la technique du lidar appliquée à l'étude des sites patrimoniaux, les exemples allemands et alsaciens / B. Sittler in Revue Française de Photogrammétrie et de Télédétection, n° 186 (Juin 2007)
PermalinkFiltering airborne Laser scanner data: a wavelet-based clustering method / T. Thuy in Photogrammetric Engineering & Remote Sensing, PERS, vol 70 n° 11 (November 2004)
PermalinkAnalyse de données acquises par laser aéroporté pour la reconstruction 3D de scènes urbaines / R. Elkharroubi (2002)
PermalinkPermalink[Ville de Karlsruhe, Allemagne] = Rapport de stage de troisième année d'ingénieur des travaux, ESSEC, stage effectué au département développement et statistiques de la ville de Karlsruhe (Allemagne) du 26 juin au 31 aout 2000 / G. Kermarrec (2000)
Permalink