Centre dedocumentation
scientifique

Deep SAR-Net: learning objects from signals / Zhongling Huang in ISPRS Journal of photogrammetry and remote sensing, vol 161 (March 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 161 (March 2020) . - pp 179 - 193 Titre : Deep SAR-Net: learning objects from signals Type de document : Article/Communication Auteurs : Zhongling Huang, Auteur ; Mihai Datcu, Auteur ; Zongxu Pan, Auteur ; Bin Lei, Auteur Année de publication : 2020 Article en page(s) : pp 179 - 193 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] image Terra [Termes descripteurs IGN] matrice de covariance [Termes descripteurs IGN] micro-onde [Termes descripteurs IGN] polarisation [Termes descripteurs IGN] temps-fréquence Résumé : (Auteur) This paper introduces a novel Synthetic Aperture Radar (SAR) specific deep learning framework for complex-valued SAR images. The conventional deep convolutional neural networks based methods usually take the amplitude information of single-polarization SAR images as the input to learn hierarchical spatial features automatically, which may have difficulties in discriminating objects with similar texture but discriminative scattering patterns. Our novel deep learning framework, Deep SAR-Net, takes complex-valued SAR images into consideration to learn both spatial texture information and backscattering patterns of objects on the ground. On the one hand, we transfer the detected SAR images pre-trained layers to extract spatial features from intensity images. On the other hand, we dig into the Fourier domain to learn physical properties of the objects by joint time-frequency analysis on complex-valued SAR images. We evaluate the effectiveness of Deep SAR-Net on three complex-valued SAR datasets from Sentinel-1 and TerraSAR-X satellite and demonstrate how it works better than conventional deep CNNs, especially on man-made objects classes. The proposed datasets and the trained Deep SAR-Net model with all codes are provided. Numéro de notice : A2020-065 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.01.016 date de publication en ligne : 23/01/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.01.016 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94583 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020031	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020033	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020032	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Polarization dependence of azimuth cutoff from quad-pol SAR images / Huimin Li in IEEE Transactions on geoscience and remote sensing, vol 57 n° 12 (December 2019)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 57 n° 12 (December 2019) . - pp 9878 - 9887 Titre : Polarization dependence of azimuth cutoff from quad-pol SAR images Type de document : Article/Communication Auteurs : Huimin Li, Auteur ; Alexis Mouche, Auteur ; He Wang, Auteur ; Justin E. Stopa, Auteur ; Bertrand Chapron, Auteur Année de publication : 2019 Article en page(s) : pp 9878 - 9887 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] angle d'incidence [Termes descripteurs IGN] azimut [Termes descripteurs IGN] données polarimétriques [Termes descripteurs IGN] image Gaofen [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Radarsat [Termes descripteurs IGN] polarisation [Termes descripteurs IGN] polarisation croisée [Termes descripteurs IGN] surface de la mer [Termes descripteurs IGN] transformation non linéaire [Termes descripteurs IGN] vague Résumé : (auteur) Although basic understanding of the synthetic aperture radar (SAR) imaging mechanism of ocean waves has been achieved, challenges still remain. In this paper, a large number of quad-polarized SAR images are analyzed to help assess how the standard SAR imaging transformation applies to all polarization channels. Foremost, the azimuth cutoff, a parameter essentially governed by the detected wave motions, is today solely related to radar configuration and the ocean wave spectrum but not to the polarization configuration. As obtained, the analyses based on quad-polarized Radarsat-2 and Gaofen-3 products document the distinct dependence of azimuth cutoff on polarization and incidence angle. Especially for cross-polarized VH measurements, azimuth cutoff estimates are generally larger than copolarized HH ones, the latter already being larger than values estimated under VV configuration. This trend increases with the incidence angle. The systematic comparisons between SAR measurements and simulations further demonstrate that the present SAR nonlinear transformation may not properly take into account the differing coherence time associated with the multi-polarized observation of ocean scenes. In particular, to reproduce the large azimuth cutoff parameters of cross-polarized images, a reduced coherence time shall be expected. This measurable sensitivity shall enhance the capabilities of polarized SAR systems to precisely derive more ocean surface properties, especially the influence of wave breakers, by combining both the copolarization and cross-polarization measurements. Numéro de notice : A2019-601 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2929835 date de publication en ligne : 14/08/2019 En ligne : http://doi.org/10.1109/TGRS.2019.2929835 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94602 [article]

Combining machine learning and compact polarimetry for estimating soil moisture from C-Band SAR data / Emanuele Santi in Remote sensing, Vol 11 n° 20 (2 October 2019)  

Public [article]  inRemote sensing > Vol 11 n° 20 (2 October 2019) . - 18 p. Titre : Combining machine learning and compact polarimetry for estimating soil moisture from C-Band SAR data Type de document : Article/Communication Auteurs : Emanuele Santi, Auteur ; Mohammed Dabboor, Auteur ; Simone Pettinato, Auteur ; Simonetta Paloscia, Auteur Année de publication : 2019 Article en page(s) : 18 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] apprentissage automatique [Termes descripteurs IGN] bande C [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] humidité du sol [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Radarsat [Termes descripteurs IGN] Manitoba (Canada) [Termes descripteurs IGN] polarimétrie [Termes descripteurs IGN] polarisation [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] série temporelle [Termes descripteurs IGN] surface cultivée Résumé : (auteur) This research aimed at exploiting the joint use of machine learning and polarimetry for improving the retrieval of surface soil moisture content (SMC) from synthetic aperture radar (SAR) acquisitions at C-band. The study was conducted on two agricultural areas in Canada, for which a series of RADARSAT-2 (RS2) images were available along with direct measurements of SMC from in situ stations. The analysis confirmed the sensitivity of RS2 backscattering (O°) to SMC. The comparison of SMC with the compact polarimetry (CP) parameters, computed from the RS2 acquisitions by the CP data simulator, pointed out that some CP parameters had a sensitivity to SMC equal or better than O°, with correlation coe?cients up to R ' 0.4. Based on these results, the potential of machine learning (ML) for SMC retrieval was exploited by implementing and testing on the available data an artificial neural network (ANN) algorithm. The algorithm was implemented using several combinations of O° and CP parameters. Validation results of the algorithm with in situ observations confirmed the promising capabilities of the ML techniques for SMC monitoring. Furthermore, results pointed out the potential of CP in improving the SMC retrieval accuracy, especially when used in combination with linearly polarized O°. Depending on the considered input combination, the ANN algorithm was able to estimate SMC with Root Mean Square Error (RMSE) between 3% and 7% of SMC and R between 0.7 and 0.9. Numéro de notice : A2019-555 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs11202451 date de publication en ligne : 22/10/2019 En ligne : https://doi.org/10.3390/rs11202451 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94210 [article]

Comprehensive evaluation of soil moisture retrieval models under different crop cover types using C-band synthetic aperture radar data / P. Kumar in Geocarto international, vol 34 n° 9 ([15/06/2019])  

Public [article]  inGeocarto international > vol 34 n° 9 [15/06/2019] . - pp 1022-1041 Titre : Comprehensive evaluation of soil moisture retrieval models under different crop cover types using C-band synthetic aperture radar data Type de document : Article/Communication Auteurs : P. Kumar, Auteur ; A. Choudhary, Auteur ; D. K. Gupta, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 1022-1041 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] bande C [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] couvert végétal [Termes descripteurs IGN] échantillonnage d'image [Termes descripteurs IGN] humidité du sol [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Radarsat [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] modèle de régression [Termes descripteurs IGN] polarisation [Termes descripteurs IGN] réseau neuronal artificiel [Termes descripteurs IGN] séparateur à vaste marge [Termes descripteurs IGN] Uttar Pradesh (Inde ; état) Résumé : (auteur) In the present study, random forest regression (RFR), support vector regression (SVR) and artificial neural network regression (ANNR) models were evaluated for the retrieval of soil moisture covered by winter wheat, barley and corn crops. SVR with radial basis function kernel was provided the highest adj. R2 (0.95) value for soil moisture retrieval covered by the wheat crop at VV polarization. However, RFR provided the adj. R2 (0.94) value for soil moisture retrieval covered by barley crop at VV polarization using Sentinel-1A satellite data. The adj. R2 (0.94) values were found for the soil moisture covered by corn crop at VV polarization using RFR, SVR linear and radial basis function kernels. The least performance was reported using ANNR model for almost all the crops under investigation. The soil moisture retrieval outcomes were found better at VV polarization in comparison to VH polarization using three different models. Numéro de notice : A2019-517 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1464601 date de publication en ligne : 03/05/2018 En ligne : https://doi.org/10.1080/10106049.2018.1464601 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93876 [article]

Estimation of the forest stand mean height and aboveground biomass in Northeast China using SAR Sentinel-1B, multispectral Sentinel-2A, and DEM imagery / Yanan Liu in ISPRS Journal of photogrammetry and remote sensing, vol 151 (May 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 151 (May 2019) . - pp 277 - 289 Titre : Estimation of the forest stand mean height and aboveground biomass in Northeast China using SAR Sentinel-1B, multispectral Sentinel-2A, and DEM imagery Type de document : Article/Communication Auteurs : Yanan Liu, Auteur ; Weishu Gong, Auteur ; Yanqiu Xing, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 277 - 289 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] biomasse forestière [Termes descripteurs IGN] carbone [Termes descripteurs IGN] Chine [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] hauteur des arbres [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] polarisation Résumé : (Auteur) Accurate mapping the forest stand mean height (FSMH) and aboveground biomass (AGB) with a high spatial resolution are important for monitoring carbon stocks on Earth and the variability and trends of terrestrial carbon fluxes. The recently launched Sentinel-1 (SAR) and Sentinel-2 (multispectral) missions offers a new opportunity to map FSMH and AGB. Here we present a methodological framework to map the FSMH and AGB at a resolution of 10 m in Yichun, Northeast China, by integrating field plots, Sentinel imagery, topographic data, and national geographical conditions monitoring data. First, a spatial continuous FSMH product was retrieved using an empirical model, which adopts the backscattering of SAR Sentinel-1B and the fraction of vegetation cover (FVC) variable from multispectral Sentinel-2A imagery. Subsequently, three AGB estimation models were developed for different forest types to link the field measurements to the FSMH, biophysical variables, spectral vegetation index, and topographic variables using the random forest algorithm. The mapping results show that the FSMH estimated using SAR backscatter values from VH polarization is more robust and accurate than that based on VV polarization. Furthermore, the three AGB estimation models based on three different forest types perform better than the model built by grouping all forest types together. The determination coefficient (R2) and root-mean-squared error (RMSE) range from 0.69 to 0.74 and 23.38 Mg/ha to 24.21 Mg/ha, respectively. Overall, our study demonstrates that the proposed methodological framework can be used to map the FSMH and AGB products at a high spatial resolution utilizing freely accessible Sentinel-1 SAR and Sentinel-2 multispectral imagery. Numéro de notice : A2019-211 Thématique : BIODIVERSITE/FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.03.016 date de publication en ligne : 30/03/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.03.016 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92677 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019053	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Détection de changement par imagerie radar sur les zones naturelles et agricoles en milieu tropical / Jérôme Lebreton (2018) 

Permalink

A wavelet decomposition and polynomial fitting-based method for the estimation of time-varying residual motion error in airborne interferometric SAR / Hai Qiang Fu in IEEE Transactions on geoscience and remote sensing, vol 56 n° 1 (January 2018)  

Permalink

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)  

Permalink

Satellite-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)  

Permalink

Double take : mitigating interference with a dual-polarized antenna array in a real environment / Matteo Sgammini in GPS world, vol 28 n° 2 (February 2017)

Permalink

Airborne DLSLA 3-D SAR image reconstruction by combination of polar formatting and L_1 regularization / Xueming Peng in IEEE Transactions on geoscience and remote sensing, vol 54 n° 1 (January 2016)  

Permalink

Forcing scale invariance in multipolarization SAR change detection / Vincenzo Carotenuto in IEEE Transactions on geoscience and remote sensing, vol 54 n° 1 (January 2016)    

Permalink

Invariant rules for multipolarization SAR change detection / Vincenzo Carotenuto in IEEE Transactions on geoscience and remote sensing, vol 53 n° 6 (June 2015)  

Permalink

Assessment of the relevance of information derived from the unmixing of polarimetric radar images / Sébastien Giordano (2015)  

Permalink

Ground-based array for tomographic imaging of the tropical forest in P-band / Ho Tong Minh Dinh in IEEE Transactions on geoscience and remote sensing, vol 51 n° 8 (August 2013)  

Permalink