Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > apprentissage profond
apprentissage profond |
Documents disponibles dans cette catégorie (712)
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
A new ZTD model based on permanent ground-based GNSS-ZTD data / M. Ding in Survey review, vol 48 n° 351 (October 2016)
[article]
Titre : A new ZTD model based on permanent ground-based GNSS-ZTD data Type de document : Article/Communication Auteurs : M. Ding, Auteur ; W. Hu, Auteur ; X. Jin, Auteur ; L. Yu, Auteur Année de publication : 2016 Article en page(s) : pp 385 - 391 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement
[Termes IGN] correction troposphérique
[Termes IGN] données GNSS
[Termes IGN] réseau neuronal artificiel
[Termes IGN] retard troposphérique zénithal
[Termes IGN] RussieRésumé : (Auteur) Tropospheric delay has a major effect on the accuracy of navigation and positioning when using the Global Navigation Satellite System (GNSS). Zenith tropospheric delay (ZTD) modelling has been used to weaken the influence of the atmosphere. The work reported here focused on ZTD modelling based on real-time surface meteorological parameters, traditionally represented by the Saastamoinen model. However, Saastamoinen accuracy only reaches scale of centimetres, even to scale of centimetres when the water vapour is active, whereas the scale of ground-based GNSS-ZTD data (i.e. ZTD derived from ground GNSS data) is on the millimetre scale and is considered to be the ‘true’ value. An important direction in GNSS studies is how to make good use of ground-based GNSS-ZTD data to improve the accuracy of the Saastamoinen model. Authors studied the residuals in the Saastamoinen model using high-precision GNSS-ZTD data provided by the International GNSS Service (IGS) product and then carried out modelling based on a back propagation neural network. A new ZTD model (ISAAS) based on real-time surface meteorological parameters is proposed based on this method. The ISAAS model has good accuracy: its BIAS and root mean square error (RMSE) at the test area in Russia were -4.4 and 20.4 mm, respectively, which are lower than the results obtained using the Saastamoinen model (-10.4 and 23.3 mm, respectively). The ISAAS model can improve the ZTD prediction accuracy by more than 12.4% and therefore has important implications for precision engineering measurements in Russia. Numéro de notice : A2016-821 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.1179/1752270615Y.0000000034 En ligne : https://doi.org/10.1179/1752270615Y.0000000034 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82636
in Survey review > vol 48 n° 351 (October 2016) . - pp 385 - 391[article]Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning / Xiaorui Ma in ISPRS Journal of photogrammetry and remote sensing, vol 120 (october 2016)
[article]
Titre : Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning Type de document : Article/Communication Auteurs : Xiaorui Ma, Auteur ; Hongyu Wang, Auteur ; Jie Wang, Auteur Année de publication : 2016 Article en page(s) : pp 99 - 107 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] classification par réseau neuronal
[Termes IGN] classification semi-dirigée
[Termes IGN] image hyperspectrale
[Termes IGN] pondérationRésumé : (Auteur) Semisupervised learning is widely used in hyperspectral image classification to deal with the limited training samples, however, some more information of hyperspectral image should be further explored. In this paper, a novel semisupervised classification based on multi-decision labeling and deep feature learning is presented to exploit and utilize as much information as possible to realize the classification task. First, the proposed method takes two decisions to pre-label each unlabeled sample: local decision based on weighted neighborhood information is made by the surrounding samples, and global decision based on deep learning is performed by the most similar training samples. Then, some unlabeled ones with high confidence are selected to extent the training set. Finally, self decision, which depends on the self features exploited by deep learning, is employed on the updated training set to extract spectral-spatial features and produce classification map. Experimental results with real data indicate that it is an effective and promising semisupervised classification method for hyperspectral image. Numéro de notice : A2016-797 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.09.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.09.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82532
in ISPRS Journal of photogrammetry and remote sensing > vol 120 (october 2016) . - pp 99 - 107[article]Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: a case study / Lei Wang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 8 (August 2016)
[article]
Titre : Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: a case study Type de document : Article/Communication Auteurs : Lei Wang, Auteur ; K. Andrea Scott, Auteur ; Linlin Xu, Auteur ; David A. Clausi, Auteur Année de publication : 2016 Article en page(s) : pp 4524 - 4533 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] classification par réseau neuronal
[Termes IGN] eau de fonte
[Termes IGN] glace de mer
[Termes IGN] iceberg
[Termes IGN] image Radarsat
[Termes IGN] navigation maritime
[Termes IGN] réseau neuronal convolutifRésumé : (Auteur) High-resolution ice concentration maps are of great interest for ship navigation and ice hazard forecasting. In this case study, a convolutional neural network (CNN) has been used to estimate ice concentration using synthetic aperture radar (SAR) scenes captured during the melt season. These dual-pol RADARSAT-2 satellite images are used as input, and the ice concentration is the direct output from the CNN. With no feature extraction or segmentation postprocessing, the absolute mean errors of the generated ice concentration maps are less than 10% on average when compared with manual interpretation of the ice state by ice experts. The CNN is demonstrated to produce ice concentration maps with more detail than produced operationally. Reasonable ice concentration estimations are made in melt regions and in regions of low ice concentration. Numéro de notice : A2016-886 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2543660 En ligne : https://doi.org/10.1109/TGRS.2016.2543660 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83066
in IEEE Transactions on geoscience and remote sensing > vol 54 n° 8 (August 2016) . - pp 4524 - 4533[article]Modeling of ionosphere time series using wavelet neural networks (case study: N-W of Iran) / Mir Reza Ghaffari Razin in Advances in space research, vol 58 n° 1 (July 2016)
[article]
Titre : Modeling of ionosphere time series using wavelet neural networks (case study: N-W of Iran) Type de document : Article/Communication Auteurs : Mir Reza Ghaffari Razin, Auteur ; Behzad Voosoghi, Auteur Année de publication : 2016 Article en page(s) : pp 74 - 83 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale
[Termes IGN] International Reference Ionosphere
[Termes IGN] Iran
[Termes IGN] modèle numérique
[Termes IGN] ondelette
[Termes IGN] réseau neuronal artificiel
[Termes IGN] série temporelle
[Termes IGN] teneur totale en électronsRésumé : (auteur) Wavelet neural networks (WNNs) are important tools for analyzing time series especially when it is non-linear and non-stationary. It takes advantage of high resolution of wavelets and feed forward nature of neural networks (NNs). Therefore, in this paper, WNNs is used for modeling of ionosphere time series in Iran. To apply the method, observations collected at 22 GPS stations in 12 successive days of 2012 (DOY# 219–230) from Azerbaijan local GPS network are used. For training of WNN, back-propagation (BP) algorithm is used. The results of WNN compared with results of international reference ionosphere 2012 (IRI-2012) and international GNSS service (IGS) products. To assess the error of WNN, statistical indicators, relative and absolute errors are used. Minimum relative error for WNN compared with GPS TEC is 6.37% and maximum relative error is 12.94%. Also the maximum and minimum absolute error computed 6.32 and 0.13 TECU, respectively. Comparison of diurnal predicted TEC values from the WNN model and the IRI-2012 with GPS TEC revealed that the WNN provides more accurate predictions than the IRI-2012 model and IGS products in the test area. Numéro de notice : A2016-562 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.asr.2016.04.006 En ligne : http://dx.doi.org/10.1016/j.asr.2016.04.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81742
in Advances in space research > vol 58 n° 1 (July 2016) . - pp 74 - 83[article]Deep filter banks for texture recognition, description, and segmentation / Mircea Cimpoi in International journal of computer vision, vol 118 n° 1 (May 2016)
[article]
Titre : Deep filter banks for texture recognition, description, and segmentation Type de document : Article/Communication Auteurs : Mircea Cimpoi, Auteur ; Subhransu Maji, Auteur ; Iasonas Kokkinos, Auteur ; Andrea Vedaldi, Auteur Année de publication : 2016 Article en page(s) : pp 65 – 94 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] accès aux données
[Termes IGN] apprentissage profond
[Termes IGN] attribut sémantique
[Termes IGN] filtrage numérique d'image
[Termes IGN] jeu de données
[Termes IGN] segmentation d'image
[Termes IGN] texture d'imageRésumé : (auteur) Visual textures have played a key role in image understanding because they convey important semantics of images, and because texture representations that pool local image descriptors in an orderless manner have had a tremendous impact in diverse applications. In this paper, we make several contributions to texture understanding. First, instead of focusing on texture instance and material category recognition, we propose a human-interpretable vocabulary of texture attributes to describe common texture patterns, complemented by a new describable texture dataset for benchmarking. Second, we look at the problem of recognizing materials and texture attributes in realistic imaging conditions, including when textures appear in clutter, developing corresponding benchmarks on top of the recently proposed OpenSurfaces dataset. Third, we revisit classic texture representations, including bag-of-visual-words and the Fisher vectors, in the context of deep learning and show that these have excellent efficiency and generalization properties if the convolutional layers of a deep model are used as filter banks. We obtain in this manner state-of-the-art performance in numerous datasets well beyond textures, an efficient method to apply deep features to image regions, as well as benefit in transferring features from one domain to another. Numéro de notice : A2016--151 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-015-0872-3 En ligne : https://doi.org/10.1007/s11263-015-0872-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85919
in International journal of computer vision > vol 118 n° 1 (May 2016) . - pp 65 – 94[article]PermalinkEstimation of forest biomass using multivariate relevance vector regression / Alireza Sharifi in Photogrammetric Engineering & Remote Sensing, PERS, vol 82 n° 1 (January 2016)PermalinkA back-propagation neural network-based approach for multi-represented feature matching in update propagation / Yanxia Wang in Transactions in GIS, vol 19 n° 6 (December 2015)PermalinkA semiautomated probabilistic framework for tree-cover delineation from 1-m NAIP imagery using a high-performance computing architecture / S. Basu in IEEE Transactions on geoscience and remote sensing, vol 53 n° 10 (October 2015)PermalinkPrediction of traffic counts using statistical and neural network models / Abul Kalam Azad in Geomatica, vol 69 n° 3 (september 2015)PermalinkMulticlass feature learning for hyperspectral image classification: Sparse and hierarchical solutions / Devis Tuia in ISPRS Journal of photogrammetry and remote sensing, vol 105 (July 2015)PermalinkPerformance analysis of radial basis function networks and multi-layer perceptron networks in modeling urban change: a case study / Hossein Shafizadeh-Moghadam in International journal of geographical information science IJGIS, vol 29 n° 4 (April 2015)PermalinkPermalinkLand cover and soil type mapping from spaceborne PolSAR Data at L-Band with probabilistic neural network / Oleg Antropov in IEEE Transactions on geoscience and remote sensing, vol 52 n° 9 Tome 1 (September 2014)PermalinkModel generalization of two different drainage patterns by self-organizing maps / Alper Sen in Cartography and Geographic Information Science, vol 41 n° 2 (March 2014)Permalink