Descripteur
Documents disponibles dans cette catégorie (3546)
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
Learning and adapting robust features for satellite image segmentation on heterogeneous data sets / Sina Ghassemi in IEEE Transactions on geoscience and remote sensing, vol 57 n° 9 (September 2019)
[article]
Titre : Learning and adapting robust features for satellite image segmentation on heterogeneous data sets Type de document : Article/Communication Auteurs : Sina Ghassemi, Auteur ; Attilio Friandrotti, Auteur ; Gianluca Francini, Auteur ; Enrico Magli, Auteur Année de publication : 2019 Article en page(s) : pp 6517 - 6529 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] chaîne de traitement
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] coût
[Termes IGN] données hétérogènes
[Termes IGN] image binaire
[Termes IGN] image satellite
[Termes IGN] méthode robuste
[Termes IGN] réseau neuronal convolutif
[Termes IGN] segmentation binaire
[Termes IGN] segmentation d'image
[Termes IGN] test de performanceRésumé : (auteur) This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder–decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers’ statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. Numéro de notice : A2019-341 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2906689 Date de publication en ligne : 17/04/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2906689 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93379
in IEEE Transactions on geoscience and remote sensing > vol 57 n° 9 (September 2019) . - pp 6517 - 6529[article]Improving public data for building segmentation from Convolutional Neural Networks (CNNs) for fused airborne lidar and image data using active contours / David Griffiths in ISPRS Journal of photogrammetry and remote sensing, vol 154 (August 2019)
[article]
Titre : Improving public data for building segmentation from Convolutional Neural Networks (CNNs) for fused airborne lidar and image data using active contours Type de document : Article/Communication Auteurs : David Griffiths, Auteur ; Jan Böhm , Auteur Année de publication : 2019 Article en page(s) : pp 70 - 83 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] apprentissage profond
[Termes IGN] bati
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de contours
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] données publiques
[Termes IGN] fusion de données
[Termes IGN] image RVB
[Termes IGN] Royaume-Uni
[Termes IGN] scène urbaine
[Termes IGN] segmentation sémantique
[Termes IGN] semis de points
[Termes IGN] zone ruraleRésumé : (Auteur) Robust and reliable automatic building detection and segmentation from aerial images/point clouds has been a prominent field of research in remote sensing, computer vision and point cloud processing for a number of decades. One of the largest issues associated with deep learning methods is the high quantity of data required for training. To help address this we present a method to improve public GIS building footprint labels by using Morphological Geodesic Active Contours (MorphGACs). We demonstrate by improving the quality of building footprint labels for detection and semantic segmentation, more robust and reliable models can be obtained. We evaluate these methods over a large UK-based dataset of 24556 images containing 169835 building instances. This is achieved by training several Mask/Faster R-CNN and RetinaNet deep convolutional neural networks. Networks are supplied with both RGB and fused RGB-lidar data. We offer quantitative analysis on the benefits of the inclusion of depth data for building segmentation. By employing both methods we achieve a detection accuracy of 0.92 (mAP@0.5) and segmentation f1 scores of 0.94 over a 4911 test images ranging from urban to rural scenes. Numéro de notice : A2019-265 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.05.013 Date de publication en ligne : 06/06/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.05.013 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93079
in ISPRS Journal of photogrammetry and remote sensing > vol 154 (August 2019) . - pp 70 - 83[article]Réservation
Réserver ce documentExemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019081 RAB Revue Centre de documentation En réserve L003 Disponible 081-2019083 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2019082 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Integration of corner reflectors for the monitoring of mountain glacier areas with Sentinel-1 time series / Matthias Jauvin in Remote sensing, vol 11 n° 8 (August 2019)
[article]
Titre : Integration of corner reflectors for the monitoring of mountain glacier areas with Sentinel-1 time series Type de document : Article/Communication Auteurs : Matthias Jauvin, Auteur ; Yajing Yan, Auteur ; Emmanuel Trouvé, Auteur ; Bénédicte Fruneau , Auteur ; Michel Gay, Auteur ; Blaise Girard, Auteur Année de publication : 2019 Projets : 3-projet - voir note / Article en page(s) : n° 988 Note générale : bibliographie
The authors would like to thank Antoine Rabatel (Univ. Grenoble Alpes, I.G.E.) for having provided DSM LiDAR-based, acquired as part of the project European Facility for Airborne Research Transnational Access (EUFAR TA, EU FP7 Integrating Activity)—project ISOTHERM (Ice, SnOw vegeTation HypERspectral Measurements) that he has led. The authors would also like to thank the French National Geographic Institute (IGN) for providing the DEM.Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] Alpes
[Termes IGN] chambre anéchoïque
[Termes IGN] coin réflecteur
[Termes IGN] erreur de phase
[Termes IGN] faille géologique
[Termes IGN] glacier d'Argentière
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-SAR
[Termes IGN] interféromètrie par radar à antenne synthétique
[Termes IGN] moraine
[Termes IGN] pente
[Termes IGN] prévention des risques
[Termes IGN] rétrodiffusion
[Termes IGN] surface équivalente radar
[Termes IGN] tectoniqueRésumé : (auteur) Glacier flow and slope instabilities in Alpine mountain areas represent a hazard issue. Sentinel-1 satellites provide regular Synthetic Aperture Radar (SAR) acquisitions that are potentially useful to monitor these areas, but they can be affected by temporal decorrelation due to rapid changes in the surface. The application of interferometric synthetic aperture radar (InSAR) therefore seems difficult due to loss of coherence. On the other hand, Corner Reflectors (CR) can be used as coherent targets in SAR images for accurate displacement measurement thanks to their strong backscattering property and temporal stability. The use of CRs in multi-temporal InSAR analysis in Alpine mountain areas can thus be beneficial. In this study, we present a comparison between triangular and rectangular CRs, based on Radar Cross Section (RCS) measurements in an anechoic chamber and on long-term experiments over the Argentière glacier and the surrounding slopes and moraine. The visibility in both summer and winter of 10 CRs installed on the test site was investigated. As this area is exposed to heavy precipitation including snow falls, two perforated CRs were tested. The amplitude stability and the phase error of each CR were estimated. A precise tracking of two CRs installed at the glacier surface was also able to measure the displacement of the Argentière glacier, giving results close to previous GPS measurements. Furthermore, a Persistent Scatterer Interferometry (PSI) study was conducted, using the most stable CR as reference point to estimate slope instabilities, which led to the identification of an area corresponding to a tectonic fault called “Faille de l’angle”. The precise absolute locations of the CRs were successfully estimated and PS heights were compared with a LiDAR-based (Light Detection And Ranging) digital elevation model (DEM) and GPS measurements. Numéro de notice : A2019-627 Affiliation des auteurs : UPEM-LASTIG+Ext (2016-2019) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs11080988 Date de publication en ligne : 25/04/2019 En ligne : https://doi.org/10.3390/rs11080988 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95363
in Remote sensing > vol 11 n° 8 (August 2019) . - n° 988[article]Landslide monitoring analysis of single-frequency BDS/GPS combined positioning with constraints on deformation characteristics / Dongwei Qiu in Survey review, vol 51 n° 367 (July 2019)
[article]
Titre : Landslide monitoring analysis of single-frequency BDS/GPS combined positioning with constraints on deformation characteristics Type de document : Article/Communication Auteurs : Dongwei Qiu, Auteur ; Laiyang Wang, Auteur ; Dean Luo, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 364 - 372 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] déformation de la croute terrestre
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] effondrement de terrain
[Termes IGN] modèle de simulation
[Termes IGN] positionnement par BeiDou
[Termes IGN] positionnement par GPS
[Termes IGN] précipitation
[Termes IGN] récepteur monofréquence
[Termes IGN] simulation numérique
[Termes IGN] surveillance géologiqueRésumé : (Auteur) In order to optimise the selection of landslide monitoring points and save the cost of monitoring, a geological constitutive model was constructed by using 3D laser scanning and geological borehole data to simulate the relationship between rainfall and deformation. Thus, the main occurrence area and maximum deformation of the landslide were determined. Aiming at the deficiency of the single-epoch redundancy of the single-frequency GNSS receiver and the poor accuracy, this paper proposes a single-frequency BDS/GPS combined positioning and monitoring scheme with constraint of deformation features to restrict the search range of single-frequency ambiguity, obviously increase the ambiguity fixed success rate and then improve the BDS/GPS positioning accuracy. By contrast experiments, the landslide area obtained by numerical simulation basically matches with the on-site landslide area. The BDS/GPS combined positioning with constraint is consistent with the deep displacement changes, which can well reflect the displacement of the landslide body and make an early warning of disasters. Numéro de notice : A2019-364 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2018.1467075 Date de publication en ligne : 05/05/2018 En ligne : https://doi.org/10.1080/00396265.2018.1467075 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93449
in Survey review > vol 51 n° 367 (July 2019) . - pp 364 - 372[article]Monitoring of extreme land hydrology events in central Poland using GRACE, land surface models and absolute gravity data / Joanna Kuczynska-Siehien in Journal of applied geodesy, vol 13 n° 3 (July 2019)
[article]
Titre : Monitoring of extreme land hydrology events in central Poland using GRACE, land surface models and absolute gravity data Type de document : Article/Communication Auteurs : Joanna Kuczynska-Siehien, Auteur ; Dimitrios Piretzidis, Auteur ; Michael G. Sideris, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 229 – 243 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] analyse diachronique
[Termes IGN] analyse spectrale
[Termes IGN] données GLDAS
[Termes IGN] données GRACE
[Termes IGN] gravimètre absolu
[Termes IGN] inondation
[Termes IGN] levé gravimétrique
[Termes IGN] modèle numérique de surface
[Termes IGN] Pologne
[Termes IGN] risque naturel
[Termes IGN] sécheresse
[Termes IGN] surveillance hydrologique
[Termes IGN] variation temporelleRésumé : (auteur) This study deals with the analysis of temporal gravity variations in central Poland, deduced from multiple sources and covering the period from 2002–2016. The gravity data sets used comprise GRACE monthly solutions, GLDAS land surface models and absolute gravimeter measurements from the FG-5 gravimeter located in Józefosław, Poland. All data are corrected using standard processing methods in order to include the same gravity effects. After removing the annual and semi-annual components from all data using least-squares spectral analysis and seasonal-trend decomposition, the deseasoned time series are derived and examined for signatures of extreme hydrological events. The signatures of several severe drought and flood conditions affecting Poland and central Europe are identified. A complementary correlation analysis is performed to assess the level of agreement between different data sources. A higher correlation is shown when the analysis is restricted in the 2009–2012 period that includes the 2010 extreme flood and 2011 increased precipitation events, both affecting Poland. Numéro de notice : A2019-286 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1515/jag-2019-0003 Date de publication en ligne : 20/04/2019 En ligne : https://doi.org/10.1515/jag-2019-0003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93121
in Journal of applied geodesy > vol 13 n° 3 (July 2019) . - pp 229 – 243[article]Multi-GNSS real-time clock estimation using sequential least square adjustment with online quality control / Wenju Fu in Journal of geodesy, vol 93 n°7 (July 2019)PermalinkAnalyzing the recent dynamics of wildland fires in Quercus suber L. woodlands in Sardinia (Italy), Corsica (France) and Catalonia (Spain) / Michele Salis in European Journal of Forest Research, vol 138 n° 3 (June 2019)PermalinkAutomatisation du traitement de données "mobile mapping" : extraction d'éléments linéaires et ponctuels / Loïc Elsholz in XYZ, n° 159 (juin 2019)PermalinkA four‐dimensional agent‐based model: A case study of forest‐fire smoke propagation / Alex Smith in Transactions in GIS, vol 23 n° 3 (June 2019)PermalinkObservation et suivi de déformations de surface d'origine anthropique par interférométrie radar satellitaire / Daniel Raucoules in Revue Française de Photogrammétrie et de Télédétection, n° 219-220 (juin - octobre 2019)PermalinkReprésentation des éléments juridiques dans une maquette BIM / Bamba Ngom in Géomatique expert, n° 128 (juin - juillet 2019)PermalinkUsing Sentinel-1A DInSAR interferometry and Landsat 8 data for monitoring water level changes in two lakes in Crete, Greece / D.D. Alexakis in Geocarto international, vol 34 n° 7 ([01/06/2019])PermalinkAbility of GPS PPP in 2D deformation analysis with respect to GPS network solution / C. Aydin in Survey review, vol 51 n° 366 (May 2019)PermalinkIs there still a (land) surveying profession? / Brian J. Coutts in Survey review, vol 51 n° 366 (May 2019)PermalinkLa démarche GéoBIM : de la gestion du territoire à celle d’un bâtiment / Dimitri Sarafinof in Responsabilité et environnement, n° 94 (Avril 2019)Permalink