Descripteur
Termes IGN > imagerie > image radar > image radar moirée
image radar moiréeSynonyme(s)Interferogramme ;image SAR ;Image rso ;Image radar interférométrique Image par radar à antenne synthétiqueVoir aussi
|
Documents disponibles dans cette catégorie (449)
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
Deep supervised and contractive neural network for SAR image classification / Jie Geng in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)
[article]
Titre : Deep supervised and contractive neural network for SAR image classification Type de document : Article/Communication Auteurs : Jie Geng, Auteur ; Hongyu Wang, Auteur ; Jianchao Fan, Auteur ; Xiaorui Ma, Auteur Année de publication : 2017 Article en page(s) : pp 2442 - 2459 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] algorithme Graph-Cut
[Termes IGN] analyse discriminante
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] filtre de déchatoiement
[Termes IGN] filtre de Gabor
[Termes IGN] image radar moirée
[Termes IGN] matrice de co-occurrence
[Termes IGN] niveau de gris (image)Résumé : (Auteur) The classification of a synthetic aperture radar (SAR) image is a significant yet challenging task, due to the presence of speckle noises and the absence of effective feature representation. Inspired by deep learning technology, a novel deep supervised and contractive neural network (DSCNN) for SAR image classification is proposed to overcome these problems. In order to extract spatial features, a multiscale patch-based feature extraction model that consists of gray level-gradient co-occurrence matrix, Gabor, and histogram of oriented gradient descriptors is developed to obtain primitive features from the SAR image. Then, to get discriminative representation of initial features, the DSCNN network that comprises four layers of supervised and contractive autoencoders is proposed to optimize features for classification. The supervised penalty of the DSCNN can capture the relevant information between features and labels, and the contractive restriction aims to enhance the locally invariant and robustness of the encoding representation. Consequently, the DSCNN is able to produce effective representation of sample features and provide superb predictions of the class labels. Moreover, to restrain the influence of speckle noises, a graph-cut-based spatial regularization is adopted after classification to suppress misclassified pixels and smooth the results. Experiments on three SAR data sets demonstrate that the proposed method is able to yield superior classification performance compared with some related approaches. Numéro de notice : A2017-176 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2645226 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2645226 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84748
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2442 - 2459[article]Estimation of 3-D surface displacement based on InSAR and deformation modeling / Jun Hu in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)
[article]
Titre : Estimation of 3-D surface displacement based on InSAR and deformation modeling Type de document : Article/Communication Auteurs : Jun Hu, Auteur ; Xiao-Li Ding, Auteur ; Lei Zhang, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 2007 - 2016 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] déformation de surface
[Termes IGN] dynamique des fluides
[Termes IGN] élasticité
[Termes IGN] image radar moirée
[Termes IGN] interféromètrie par radar à antenne synthétique
[Termes IGN] modélisation 3D
[Termes IGN] test de performanceRésumé : (Auteur) A new approach is presented for mapping 3-D surface displacement caused by subsurface fluid volumetric change based on 1-D interferometric synthetic aperture radar (InSAR) line-of-sight measurements and surface deformation modeling. The relationship between surface deformation and source fluid volumetric change is modeled according to elastic half-space theory. A distinctive advantage of the proposed approach is that it effectively extends the capability of the sun-synchronous orbit side-looking synthetic aperture radar that has been essentially only able to measure 1-D displacements accurately or at most 2-D displacements when InSAR measurements from more than one orbit or platform are combined. Experimental studies are carried out with both simulated and real data sets to test the performance of the method. The results have demonstrated that the approach works very well. Numéro de notice : A2017-171 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2634087 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2634087 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84715
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2007 - 2016[article]Forest classification and impact of BIOMASS resolution on forest area and aboveground biomass estimation / Michael Schlund in International journal of applied Earth observation and geoinformation, vol 56 (April 2017)
[article]
Titre : Forest classification and impact of BIOMASS resolution on forest area and aboveground biomass estimation Type de document : Article/Communication Auteurs : Michael Schlund, Auteur ; Klaus Scipal, Auteur ; Malcolm W.J. Davidson, Auteur Année de publication : 2017 Article en page(s) : pp 65 - 76 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] bande P
[Termes IGN] base de données d'occupation du sol
[Termes IGN] biomasse aérienne
[Termes IGN] biomasse forestière
[Termes IGN] erreur systématique
[Termes IGN] estimation statistique
[Termes IGN] image radar moiréeRésumé : (auteur) The European Space Agency (ESA) is currently implementing the BIOMASS mission as 7th Earth Explorer satellite. BIOMASS will provide for the first time global forest aboveground biomass estimates based on P-band synthetic aperture radar (SAR) imagery. This paper addresses an often overlooked element of the data processing chain required to ensure reliable and accurate forest biomass estimates: accurate identification of forest areas ahead of the inversion of radar data into forest biomass estimates. The use of the P-band data from BIOMASS itself for the classification into forest and non-forest land cover types is assessed in this paper. For airborne data in tropical, hemi-boreal and boreal forests we demonstrate that classification accuracies from 90 up to 97% can be achieved using radar backscatter and phase information. However, spaceborne data will have a lower resolution and higher noise level compared to airborne data and a higher probability of mixed pixels containing multiple land cover types. Therefore, airborne data was reduced to 50 m, 100 m and 200 m resolution. The analysis revealed that about 50–60% of the area within the resolution level must be covered by forest to classify a pixel with higher probability as forest compared to non-forest. This results in forest omission and commission leading to similar forest area estimation over all resolutions. However, the forest omission resulted in a biased underestimated biomass, which was not equaled by the forest commission. The results underline the necessity of a highly accurate pre-classification of SAR data for an accurate unbiased aboveground biomass estimation. Numéro de notice : A2017-370 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.jag.2016.12.001 En ligne : https://doi.org/10.1016/j.jag.2016.12.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85789
in International journal of applied Earth observation and geoinformation > vol 56 (April 2017) . - pp 65 - 76[article]Surface soil moisture retrieval using the L-band synthetic aperture radar onboard the Soil Moisture Active–Passive Satellite and evaluation at core validation sites / Seung-Bum Kim in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)
[article]
Titre : Surface soil moisture retrieval using the L-band synthetic aperture radar onboard the Soil Moisture Active–Passive Satellite and evaluation at core validation sites Type de document : Article/Communication Auteurs : Seung-Bum Kim, Auteur ; Joel T. Johnson, Auteur ; Mahta Moghaddam, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 1897 - 1914 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] bande L
[Termes IGN] croissance végétale
[Termes IGN] données hétérogènes
[Termes IGN] humidité du sol
[Termes IGN] image radar moirée
[Termes IGN] mission SMAP
[Termes IGN] pente
[Termes IGN] polarisation
[Termes IGN] problème inverse
[Termes IGN] série temporelleRésumé : (Auteur) This paper evaluates the retrieval of soil moisture in the top 5-cm layer at 3-km spatial resolution using L-band dual-copolarized Soil Moisture Active-Passive (SMAP) synthetic aperture radar (SAR) data that mapped the globe every three days from mid-April to early July, 2015. Surface soil moisture retrievals using radar observations have been challenging in the past due to complicating factors of surface roughness and vegetation scattering. Here, physically based forward models of radar scattering for individual vegetation types are inverted using a time-series approach to retrieve soil moisture while correcting for the effects of static roughness and dynamic vegetation. Compared with the past studies in homogeneous field scales, this paper performs a stringent test with the satellite data in the presence of terrain slope, subpixel heterogeneity, and vegetation growth. The retrieval process also addresses any deficiencies in the forward model by removing any time-averaged bias between model and observations and by adjusting the strength of vegetation contributions. The retrievals are assessed at 14 core validation sites representing a wide range of global soil and vegetation conditions over grass, pasture, shrub, woody savanna, corn, wheat, and soybean fields. The predictions of the forward models used agree with SMAP measurements to within 0.5 dB unbiased-root-mean-square error (ubRMSE) and -0.05 dB (bias) for both copolarizations. Soil moisture retrievals have an accuracy of 0.052 m3/m3 ubRMSE, -0.015 m3/m3 bias, and a correlation of 0.50, compared to in situ measurements, thus meeting the accuracy target of 0.06 m3/m3 ubRMSE. The successful retrieval demonstrates the feasibility of a physically based time series retrieval with L-band SAR data for characterizing soil moisture over diverse conditions of soil moisture, surface roughness, and vegetation. Numéro de notice : A2017-169 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2631126 En ligne : http://dx.doi.org/10.1109/TGRS.2016.2631126 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84713
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 1897 - 1914[article]Trace coherence : a new operator for polarimetric and interferometric SAR images / Armando Marino in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)
[article]
Titre : Trace coherence : a new operator for polarimetric and interferometric SAR images Type de document : Article/Communication Auteurs : Armando Marino, Auteur Année de publication : 2017 Article en page(s) : pp 2326 - 2339 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications
[Termes IGN] classification
[Termes IGN] cohérence des données
[Termes IGN] détection de changement
[Termes IGN] image radar moirée
[Termes IGN] Pol-INSAR
[Termes IGN] polarimétrie radarRésumé : (Auteur) Quadratic forms play an important role in the development of several polarimetric and interferometric synthetic aperture radar (Pol-InSAR) methodologies, which are very powerful tools for earth observation. This paper investigates integrals of Pol-InSAR operators based on quadratic forms, with special interest on the Pol-InSAR coherence. A new operator, namely Trace Coherence, is introduced, which provides an approximation for the center of mass of the coherence region (CoRe). The latter is the locus of points on the polar plot containing all the possible coherence values. Such center of mass can be calculated as the integral of Pol-InSAR coherences over the scattering mechanisms (SMs). The trace coherence provides synthetic information regarding the partial target as one single entity. Therefore, it provides a representation, which is not dependent on the selection of one specific polarization channel. It may find application in change detection (e.g., coherent change detection and differential DEM), classification (e.g., building structure parameters), and modeling (e.g., for the retrieval of forest height). In calculating the integral of the Pol-InSAR coherences, an approximate trace coherence expression is derived and shown to improve the calculation speed by several orders of magnitude. The trace coherence approximation is investigated using Monte Carlo simulations and validated ESA (DLR) L-band quad-polarimetric data acquired during the AGRISAR 2006 campaign. The result of the analysis using simulated and real data is that the average error in approximating the integral of the coherence region is 0.025 in magnitude and 3° in phase (in scenarios with sufficiently high coherence). Numéro de notice : A2017-175 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2641742 En ligne : https://doi.org/10.1109/TGRS.2016.2641742 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84747
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2326 - 2339[article]Active interseismic shallow deformation of the Pingting terraces (Longitudinal Valley – Eastern Taiwan) from UAV high-resolution topographic data combined with InSAR time series / Benoit Deffontaines in Geomatics, Natural Hazards and Risk, vol 8 (2017)PermalinkGeometric accuracy evaluation of YG-18 satellite imagery based on RFM / Ruishan Zhao in Photogrammetric record, vol 32 n° 157 (March - May 2017)PermalinkHyperspectral SAR / Matthew Ferrara in IEEE Transactions on geoscience and remote sensing, vol 55 n° 3 (March 2017)PermalinkImage-based target detection and radial velocity estimation methods for multichannel SAR-GMTI / Kei Suwa in IEEE Transactions on geoscience and remote sensing, vol 55 n° 3 (March 2017)PermalinkNew point matching algorithm using sparse representation of image patch feature for SAR image registration / Jianwei Fan in IEEE Transactions on geoscience and remote sensing, vol 55 n° 3 (March 2017)PermalinkSatellite-based probabilistic assessment of soil moisture using C-band quad-polarized RISAT1 data / Manali Pal in IEEE Transactions on geoscience and remote sensing, vol 55 n° 3 (March 2017)PermalinkA network-based enhanced spectral diversity approach for TOPS time-series analysis / Heresh Fattahi in IEEE Transactions on geoscience and remote sensing, vol 55 n° 2 (February 2017)PermalinkPermalinkFusing meter-resolution 4-D InSAR point clouds and optical images for semantic urban infrastructure monitoring / Yuanyuan Wang in IEEE Transactions on geoscience and remote sensing, vol 55 n° 1 (January 2017)PermalinkPermalink