Centre dedocumentation
scientifique

Graph convolutional networks by architecture search for PolSAR image classification / Hongying Liu in Remote sensing, vol 13 n° 7 (April 2021)  

Public [article]  inRemote sensing > vol 13 n° 7 (April 2021) . - n° 1404 Titre : Graph convolutional networks by architecture search for PolSAR image classification Type de document : Article/Communication Auteurs : Hongying Liu, Auteur ; Derong Xu, Auteur ; Tianwen Zhu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 1404 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage profond [Termes IGN] bande L [Termes IGN] classification par nuées dynamiques [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification semi-dirigée [Termes IGN] échantillon [Termes IGN] graphe [Termes IGN] image AIRSAR [Termes IGN] image radar moirée [Termes IGN] noeud [Termes IGN] polarimétrie radar [Termes IGN] réseau neuronal de graphes Résumé : (auteur) Classification of polarimetric synthetic aperture radar (PolSAR) images has achieved good results due to the excellent fitting ability of neural networks with a large number of training samples. However, the performance of most convolutional neural networks (CNNs) degrades dramatically when only a few labeled training samples are available. As one well-known class of semi-supervised learning methods, graph convolutional networks (GCNs) have gained much attention recently to address the classification problem with only a few labeled samples. As the number of layers grows in the network, the parameters dramatically increase. It is challenging to determine an optimal architecture manually. In this paper, we propose a neural architecture search method based GCN (ASGCN) for the classification of PolSAR images. We construct a novel graph whose nodes combines both the physical features and spatial relations between pixels or samples to represent the image. Then we build a new searching space whose components are empirically selected from some graph neural networks for architecture search and develop the differentiable architecture search method to construction our ASGCN. Moreover, to address the training of large-scale images, we present a new weighted mini-batch algorithm to reduce the computing memory consumption and ensure the balance of sample distribution, and also analyze and compare with other similar training strategies. Experiments on several real-world PolSAR datasets show that our method has improved the overall accuracy as much as 3.76% than state-of-the-art methods. Numéro de notice : A2021-350 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs13071404 date de publication en ligne : 06/04/2021 En ligne : https://doi.org/10.3390/rs13071404 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97600 [article]

Variational learning of mixture wishart model for PolSAR image classification / Qian Wu in IEEE Transactions on geoscience and remote sensing, vol 57 n° 1 (January 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 1 (January 2019) . - pp 141 - 154 Titre : Variational learning of mixture wishart model for PolSAR image classification Type de document : Article/Communication Auteurs : Qian Wu, Auteur ; Biao Hou, Auteur ; Zaidao Wen, Auteur ; Licheng Jiao, Auteur Année de publication : 2019 Article en page(s) : pp 141 - 154 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] algorithme de Wishart [Termes IGN] classification [Termes IGN] image AIRSAR [Termes IGN] image radar moirée [Termes IGN] image Radarsat [Termes IGN] optimisation (mathématiques) [Termes IGN] polarimétrie radar Résumé : (Auteur) The phase difference, amplitude product, and amplitude ratio between two polarizations are important discriminators for terrain classification, which derives a significant statistical-distribution-based polarimetric synthetic aperture radar (PolSAR) image classification. Traditionally, statistical-distribution-based PolSAR image classification models pay attention to two aspects: searching for a suitable distribution to model certain PolSAR image and a satisfactory solution for the corresponding distribution model with samples in every terrain. Usually, the described distribution form is too complicated to build. Besides, inaccurate parameter estimation may lead to poor classification performance for PolSAR image. In order to refrain from this phenomenon, a variational thought is adopted for the statistical-distribution-based PolSAR classification method in this paper. First, a mixture Wishart model is built to model the PolSAR image to replace the complicated distribution for the PolSAR image. Second, a learning-based method is suggested instead of inaccurate point estimation of parameters to determine the distribution for every class in the mixture Wishart model. Finally, the proposed learning-based mixture Wishart model will be built as a variational form to realize a parametric model for PolSAR image classification. In the experiments, it will be proved that the class centers are easier to distinguish among different terrains learned from the proposed variational model. In addition, a classification performance on the PolSAR image is superior to the original point estimation Wishart model on both visual classification result and accuracy. Numéro de notice : A2019-104 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2852633 date de publication en ligne : 16/08/2018 En ligne : https://doi.org/10.1109/TGRS.2018.2852633 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92410 [article]

Separating the influence of vegetation changes in polarimetric differential SAR interferometry / Virginia Brancato in IEEE Transactions on geoscience and remote sensing, vol 56 n° 12 (December 2018)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 56 n° 12 (December 2018) . - pp 6871 - 6883 Titre : Separating the influence of vegetation changes in polarimetric differential SAR interferometry Type de document : Article/Communication Auteurs : Virginia Brancato, Auteur ; Irena Hajnsek, Auteur Année de publication : 2018 Article en page(s) : pp 6871 - 6883 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] bande L [Termes IGN] biomasse [Termes IGN] carte de la végétation [Termes IGN] détection de changement [Termes IGN] données polarimétriques [Termes IGN] humidité du sol [Termes IGN] image AIRSAR [Termes IGN] interferométrie différentielle [Termes IGN] interféromètrie par radar à antenne synthétique [Termes IGN] polarimétrie radar [Termes IGN] surface cultivée [Termes IGN] télédétection en hyperfréquence Résumé : (auteur) Soil moisture and wet biomass changes between two noninstantaneous SAR observations markedly affect the displacement estimates obtainable with Differential Interferometric Synthetic Aperture Radar (DInSAR). The separation, the modeling of these influences besides their uncoupling from the displacement signal, and the atmospheric disturbances are still unsolved issues for several repeat-pass interferometric applications. This paper focuses on the separation of vegetation changes from the other phase contributions affecting repeat-pass measurements over vegetated areas. These phase terms mainly relate to changes in soil moisture, atmospheric delays, and surface deformation. The separation is achieved with a first-order scattering solution decomposing the observed HH and VV DInSAR phases in the sum of several phase terms. The latter mainly consider the changes in soil surface scattering and in the two-way propagation through a vertically oriented vegetation canopy. No assumption is made on the spatiotemporal evolution of the displacement and atmosphere. The overall approach is tested on a L-band data set acquired over an agricultural area. Upon calibration, the model allows for estimating changes in wet biomass based on the nonzero HH–VV DInSAR phase difference observed over several birefringent agricultural fields. The obtained biomass estimates provide then a correction for the effect of vegetation changes on the observed HH and VV DInSAR phases. Deprived of the vegetation contribution, the remainder phase terms can be more easily explored for further analyses, e.g., the estimation of soil moisture changes and/or surface movements in vertically oriented vegetated areas. Numéro de notice : A2018-551 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2018.2845368 date de publication en ligne : 14/08/2018 En ligne : http://dx.doi.org/10.1109/TGRS.2018.2845368 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91639 [article]

Classification of fully polarimetric SAR data for land use cartography / Cédric Lardeux in Revue Française de Photogrammétrie et de Télédétection, n° 182 (Juin 2006) 

Public [article]  contenu dans ISPRS Commission 1 Symposium 2006, Paris, Marne-la-Vallée, 3-6 Juillet 2006: Des capteurs à l'imagerie, 1. Tome 1 / Alain Baudoin (2006)   inRevue Française de Photogrammétrie et de Télédétection > n° 182 (Juin 2006) . - pp 23 - 27 Titre : Classification of fully polarimetric SAR data for land use cartography Type de document : Article/Communication Auteurs : Cédric Lardeux, Auteur ; Pierre-Louis Frison , Auteur ; Jean-Paul Rudant , Auteur ; et al., Auteur Congrès : Congrès: ISPRS 2006 - Commission 1 Symposium Des capteurs à l'imagerie = From sensors to imagery (3 - 6 juillet 2006; Champs-sur-Marne in Marne-la-Vallée, France), Commanditaire Année de publication : 2006 Article en page(s) : pp 23 - 27 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] bande L [Termes IGN] bande P [Termes IGN] carte d'occupation du sol [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] données polarimétriques [Termes IGN] image AIRSAR [Termes IGN] polarimétrie radar [Termes IGN] Polynésie française Résumé : (Auteur) French Polynesia islands are located at the middle of the South Pacific Ocean. They are thus subject to a strong environmental planning leading to landscape changes as well as to the introduction of invasive species. This study comes within the framework of the global cartography and inventory of the Polynesian landscape. An AIRSAR airborne mission took place in August 2000 over the main Polynesian islands. Polarimetric SAR data are particularly adapted to the cloudy conditions generally encountered over the South Pacific Islands. Fully polarimetric data allows the analysis of a geometrical and physical point of view. Different decompositions, such as H/A/a or based on the Pauli formalism have shown their potential for such applications. In order to apply these indicators and to produce a semi-automatic cartography of the Tubuai Island, we choose to use the SVM (Support Vector Machine) as supervised classifier. These results are also compared with the Wishart classifier based on the analysis of the polarimetric coherency matrix only. As our full polarimetric data are also available in P and L bands, this study evaluates the contribution of the different wavelength. This study shown that the combination of SVM and full polarimetric data, associates with different wavelength, gives promising results. Copyright SFPT Numéro de notice : A2006-619 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28342 [article]

Exemplaires (2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
018-06021	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
018-06022	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

Documents numériques

en open access Classification of fully polarimetric... - pdf editeur ISPRS Adobe Acrobat PDF

High-resolution change estimation of soil moisture using L-band radiometer and Radar observations made during the SMEX02 experiments / U. Narayan in IEEE Transactions on geoscience and remote sensing, vol 44 n° 6 (June 2006)

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 44 n° 6 (June 2006) . - pp 1545 - 1554 Titre : High-resolution change estimation of soil moisture using L-band radiometer and Radar observations made during the SMEX02 experiments Type de document : Article/Communication Auteurs : U. Narayan, Auteur ; V. Lakshmi, Auteur ; Thomas J. Jackson, Auteur Année de publication : 2006 Article en page(s) : pp 1545 - 1554 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] bande L [Termes IGN] coefficient de rétrodiffusion [Termes IGN] détection de changement [Termes IGN] humidité du sol [Termes IGN] image AIRSAR [Termes IGN] image ALOS [Termes IGN] Iowa (Etats-Unis) [Termes IGN] limite de résolution radiométrique [Termes IGN] radiomètre à hyperfréquence [Termes IGN] rugosité du sol [Termes IGN] simulation numérique [Termes IGN] SOIL MOISTURE EXPERIMENT [Termes IGN] température de luminance Résumé : (Auteur) The soil moisture experiments held during June-July 2002 (SMEX02) at lowa demonstrated the potential of the L-band radiometer (PALS) in estimation of near surface soil moisture under dense vegetation canopy conditions. The L-band radar was also shown to be sensitive to near surface soil moisture. However, the spatial resolution of a typical satellite L-band radiometer is of the order of tens of kilometers, which is not sufficient to serve the full range of science needs for land surface hydrology and weather modeling applications. Disaggregation schemes for deriving subpixel estimates of soil moisture from radiometer data using higher resolution radar observations may provide the means for making available global soil moisture observations at a much finer scale. This paper presents a simple approach for estimation of change in soil moisture at a higher (radar) spatial resolution by combining L-band copolarized radar backscattering coefficients and L-band radiometric brightness temperatures. Sensitivity of AIRSAR L-band copolarized channels has been demonstrated by comparison with in situ soil moisture measurements as well as PALS brightness temperatures. The change estimation algorithm has been applied to coincident PALS and AIRSAR datasets acquired during the SMEX02 campaign. Using AIRSAR data aggregated to a 100-m resolution, PALS radiometer estimates of soil moisture change at a 400-m resolution have been disaggregated to 100-m resolution. The effect of surface roughness variability on the change estimation algorithm has been explained using integral equation model (IEM) simulations. A simulation experiment using synthetic data has been performed to analyze the performance of the algorithm over a region undergoing gradual wetting and dry down. Copyright IEEE Numéro de notice : A2006-260 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=27987 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-06061	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

Elaboration de MNT par extraction de pentes topographiques de données polarimétriques / Yohann Ly (2006)

Permalink

Apport de la polarimétrie radar pour la cartographie thématique en Polynésie française / Cédric Lardeux (2005)

Permalink

A phase signature for detecting wet subsurface structures using polarimetric L-band SAR / Y. Lasne in IEEE Transactions on geoscience and remote sensing, vol 42 n° 8 (August 2004)

Permalink

Event-driven SAR data acquisition in urban areas using GIS / Uwe Sörgel in GIS Geo-Informations-Systeme, vol 2003 n° 12 (Dezember 2003)

Permalink

The use of fully polarimetric information for the fuzzy neural classification of SAR images / C.T. Chen in IEEE Transactions on geoscience and remote sensing, vol 41 n° 9 (September 2003)

Permalink

Development of models for monitoring the urban environment using radar remote sensing / Catherine Ticehurst (1998)

Permalink