Descripteur
Documents disponibles dans cette catégorie (3072)
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
Graph convolutional networks by architecture search for PolSAR image classification / Hongying Liu in Remote sensing, vol 13 n° 7 (April-1 2021)
[article]
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 graphesRésumé : (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
in Remote sensing > vol 13 n° 7 (April-1 2021) . - n° 1404[article]Impact of the third frequency GNSS pseudorange and carrier phase observations on rapid PPP convergences / Jiang Guo in GPS solutions, vol 25 n° 2 (April 2021)
[article]
Titre : Impact of the third frequency GNSS pseudorange and carrier phase observations on rapid PPP convergences Type de document : Article/Communication Auteurs : Jiang Guo, Auteur ; Jianghui Geng, Auteur ; Chen Wang, Auteur Année de publication : 2021 Article en page(s) : 12 p. Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] bruit (théorie du signal)
[Termes IGN] fréquence multiple
[Termes IGN] ligne de base
[Termes IGN] mesurage de pseudo-distance
[Termes IGN] modèle fonctionnel
[Termes IGN] modèle stochastique
[Termes IGN] phase
[Termes IGN] positionnement ponctuel précis
[Termes IGN] résolution d'ambiguïté
[Termes IGN] signal BeiDou
[Termes IGN] signal Galileo
[Termes IGN] signal GNSS
[Termes IGN] temps de convergenceRésumé : (Auteur) New GNSS signals have significantly augmented positioning service and promoted algorithmic innovations such as rapid PPP convergence. With the emerging of multifrequency signals, it becomes essential to thoroughly explore the contribution of third frequency pseudorange and carrier phase toward PPP. In this study, we research the role of the third frequency observations on accelerating PPP convergence, commencing from both stochastic and functional models. We first constructed the stochastic model depending on the observation noise and then introduced two uncombined functional models with respect to different inter-frequency bias (IFB) estimation strategies. The double-differenced residuals based on a zero baseline were used to evaluate the signal noises, which were 0.09, 0.07, 0.11, 0.01 and 0.09 m for Galileo E1/E5a/E5b/E5/E6 pseudorange and 0.24, 0.31 and 0.05 m for BeiDou B1/B2/B3. Besides, carrier phase observations E5a/E5/E6/B1I/B3I shared a comparable signal noise of 0.002 m, while the signal noises of E1/E5b/B2I were 0.003 m. Both BeiDou-2/Galileo and Galileo-only float PPP were implemented based on the dataset collected from 25 stations, spanning 30 days. Triple-frequency Galileo PPP achieved convergence successfully in 19.9 min if observations were weighted according to observation precision, showing a comparable performance of dual-frequency PPP. Meanwhile, the convergence time of triple-frequency float PPP was further shortened to 19.2 min when satellite pair IFBs were eliminated by estimating a second satellite clock. While the improvement of triple-frequency float PPP was marginal, triple-frequency PPP-AR using signals E1/E5a/E6 shortened the initialization time of the dual-frequency counterpart by 38%. Moreover, the performance of triple-frequency PPP-AR kept almost unchanged after we excluded the third frequency pseudorange observations. We thus suggest that the contribution of the third frequency to PPP mainly rests on ambiguity resolution, favored by the additional carrier phase observations. Numéro de notice : A2021-090 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10291-020-01079-7 Date de publication en ligne : 10/01/2021 En ligne : https://doi.org/10.1007/s10291-020-01079-7 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96875
in GPS solutions > vol 25 n° 2 (April 2021) . - 12 p.[article]Multi-GNSS real-time precise clock estimation considering the correction of inter-satellite code biases / Liang Chen in GPS solutions, vol 25 n° 2 (April 2021)
[article]
Titre : Multi-GNSS real-time precise clock estimation considering the correction of inter-satellite code biases Type de document : Article/Communication Auteurs : Liang Chen, Auteur ; Min Li, Auteur ; Ying Zhao, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : 17 p. Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie spatiale
[Termes IGN] correction
[Termes IGN] décalage d'horloge
[Termes IGN] erreur systématique inter-systèmes
[Termes IGN] phase
[Termes IGN] positionnement par BeiDou
[Termes IGN] positionnement par Galileo
[Termes IGN] positionnement par GLONASS
[Termes IGN] positionnement par GNSS
[Termes IGN] positionnement par GPS
[Termes IGN] récepteur GNSS
[Termes IGN] temps réelRésumé : (Auteur) For reasons mostly related to chip shape distortions, global navigation satellite system (GNSS) observations are corrupted by receiver-dependent biases. These are often stable in the long term, though numerically different depending on the signal frequency, satellite system and receiver manufacturer. Based on the mixed-differenced model combining undifferenced pseudorange with epoch-differenced carrier phase observations, we present a multi-GNSS real-time precise clock estimation model considering correction of inter-satellite code biases (ISCBs). Pre-estimated receiver-dependent ISCB corrections are introduced to correct the inter-receiver, inter-satellite and inter-system biases largely. Then the number of estimated parameters is reduced to a manageable level for real-time estimation. Comparisons with post-processed data show that compared to undifferenced, epoch-differenced and non-bias-corrected mixed-differenced models, the proposed bias-corrected model can greatly reduce the precise clock offset systematic biases, especially for GLONASS and BeiDou. The test results show the root mean square data reductions are improved by up to 96% for GLONASS, 78% for BeiDou and 40% for GPS and Galileo. Numéro de notice : A2021-092 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s10291-020-01065-z Date de publication en ligne : 15/01/2021 En ligne : https://doi.org/10.1007/s10291-020-01065-z Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96883
in GPS solutions > vol 25 n° 2 (April 2021) . - 17 p.[article]Temporal mosaicking approaches of Sentinel-2 images for extending topsoil organic carbon content mapping in croplands / Emmanuelle Vaudour in International journal of applied Earth observation and geoinformation, vol 96 (April 2021)
[article]
Titre : Temporal mosaicking approaches of Sentinel-2 images for extending topsoil organic carbon content mapping in croplands Type de document : Article/Communication Auteurs : Emmanuelle Vaudour, Auteur ; Cécile Gomez, Auteur ; Philippe Lagacherie, Auteur Année de publication : 2021 Article en page(s) : n° 102277 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] humidité du sol
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SAR
[Termes IGN] mosaïquage d'images
[Termes IGN] Normalized Difference Vegetation Index
[Termes IGN] puits de carbone
[Termes IGN] réflectance spectrale
[Termes IGN] série temporelle
[Termes IGN] sol nu
[Termes IGN] surface cultivée
[Termes IGN] teneur en carbone
[Termes IGN] terre arable
[Termes IGN] Yvelines (78)Résumé : (auteur) The spatial assessment of soil organic carbon (SOC) is a major environmental challenge, notably for evaluating soil carbon stocks. Recent works have shown the capability of Sentinel-2 to predict SOC content over temperate agroecosystems characterized with annual crops. However, because spectral models are only applicable on bare soils, the mapping of SOC is often obtained on limited areas. A possible improvement for increasing the number of pixels on which SOC can be retrieved by inverting bare soil reflectance spectra, consists of using optical images acquired at several dates. This study compares different approaches of Sentinel–2 images temporal mosaicking to produce a composite multi-date bare soil image for predicting SOC content over agricultural topsoils. A first approach for temporal mosaicking was based on a per-pixel selection and was driven by soil surface characteristics: bare soil or dry bare soil with/without removing dry vegetation. A second approach for creating composite images was based on a per-date selection and driven either by the models performance from single-date, or by average soil surface indicators of bare soil or dry bare soil. To characterize soil surface, Sentinel-1 (S1)-derived soil moisture and/or spectral indices such as normalized difference vegetation index (NDVI), Normalized Burn Ratio 2 (NBR2), bare soil index (BSI) and a soil surface moisture index (S2WI) were used either separately or in combination. This study highlighted the following results: i) none of the temporal mosaic images improved model performance for SOC prediction compared to the best single-date image; ii) of the per-pixel approaches, temporal mosaics driven by the S1-derived moisture content, and to a lesser extent, by NBR2 index, outperformed the mosaic driven by the BSI index but they did not increase the bare soil area predicted; iii) of the per-date approaches, the best trade-off between predicted area and model performance was achieved from the temporal mosaic driven by the S1-derived moisture content (R2 ~ 0.5, RPD ~ 1.4, RMSE ~ 3.7 g.kg-1) which enabled to more than double (*2.44) the predicted area. This study suggests that a number of bare soil mosaics based on several indicators (moisture, bare soil, roughness…), preferably in combination, might maintain acceptable accuracies for SOC prediction whilst extending over larger areas than single-date images. Numéro de notice : A2021-238 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.jag.2020.102277 Date de publication en ligne : 14/12/2020 En ligne : https://doi.org/10.1016/j.jag.2020.102277 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97258
in International journal of applied Earth observation and geoinformation > vol 96 (April 2021) . - n° 102277[article]Time-series snowmelt detection over the Antarctic using Sentinel-1 SAR images on Google Earth Engine / Dong Liang in Remote sensing of environment, Vol 256 (April 2020)
[article]
Titre : Time-series snowmelt detection over the Antarctic using Sentinel-1 SAR images on Google Earth Engine Type de document : Article/Communication Auteurs : Dong Liang, Auteur ; Huadong Guo, Auteur ; Lu Zhang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 112318 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] albedo
[Termes IGN] Antarctique
[Termes IGN] calotte glaciaire
[Termes IGN] changement climatique
[Termes IGN] coefficient de rétrodiffusion
[Termes IGN] distribution spatiale
[Termes IGN] fonte des glaces
[Termes IGN] Google Earth Engine
[Termes IGN] image radar moirée
[Termes IGN] image Sentinel-SAR
[Termes IGN] montée du niveau de la mer
[Termes IGN] série temporelleRésumé : (auteur) The Antarctic ice sheet is an important mass of glacier ice. It is particularly sensitive to climate change, and the flow of Antarctica's inland glaciers into the sea, accelerated by collapsing ice shelves, threatens global sea level rise. The amount of snowmelt on the surface of the ice sheet is an important metric for accurately assessing surface material loss and albedo change, which affect the stability of the ice sheet. This study proposes a framework for quickly extracting time-series freeze-thaw information at the continental scale and 40 m resolution by taking advantage of the huge amount of synthetic aperture radar (SAR) data acquired by Sentinel-1 satellites over the Antarctic, available for rapid processing on Google Earth Engine. Co-orbit normalization is used in the proposed framework to establish a unified standard of judgement by reducing the variations in the backscattering coefficient introduced by observation geometry, terrain fluctuations, and melt conditions between images acquired at different times. We implemented the framework to produce a massive dataset of both monthly freeze-thaw information over the Antarctic and higher temporal resolution freeze-thaw information for the Larsen C ice shelf from 2015 to 2019, with overall accuracies of 93% verified by a manual visual interpretation method and 84% evaluated from automatic weather station temperatures. Due to its effectiveness and robustness, the framework can be used to analyse the spatiotemporal distribution of snowmelt, the change in melt area, and anomalous melt events in Antarctica, especially those in Larsen C caused by foehn wind. Numéro de notice : A2021-477 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112318 Date de publication en ligne : 10/02/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112318 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97117
in Remote sensing of environment > Vol 256 (April 2020) . - n° 112318[article]Application of thermal imaging and hyperspectral remote sensing for crop water deficit stress monitoring / Gopal Krishna in Geocarto international, vol 36 n° 5 ([15/03/2021])PermalinkEarly detection of forest stress from European spruce bark beetle attack, and a new vegetation index: Normalized distance red & SWIR (NDRS) / Langning Huo in Remote sensing of environment, Vol 255 (March 2021)PermalinkA soil texture categorization mapping from empirical and semi-empirical modelling of target parameters of synthetic aperture radar / Shoba Periasamy in Geocarto international, vol 36 n° 5 ([15/03/2021])PermalinkCluster-based empirical tropospheric corrections applied to InSAR time series analysis / Kyle Dennis Murray in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)PermalinkON GLONASS pseudo-range inter-frequency bias solution with ionospheric delay modeling and the undifferenced uncombined PPP / Zheng Zhang in Journal of geodesy, vol 95 n° 3 (March 2021)PermalinkSaline-soil deformation extraction based on an improved time-series InSAR approach / Wei Xiang in ISPRS International journal of geo-information, vol 10 n° 3 (March 2021)PermalinkModelling potential density of natural regeneration of European oak species (Quercus robur L., Quercus petraea (Matt.) Liebl.) depending on the distance to the potential seed source: Methodological approach for modelling dispersal from inventory data at forest enterprise level / Maximilian Axer in Forest ecology and management, vol 482 ([15/02/2021])PermalinkCorrentropy-based spatial-spectral robust sparsity-regularized hyperspectral unmixing / Xiaorun Li in IEEE Transactions on geoscience and remote sensing, vol 59 n° 2 (February 2021)PermalinkForest height estimation using a single-pass airborne L-band polarimetric and interferometric SAR system and tomographic techniques / Yue Huang in Remote sensing, Vol 13 n° 3 (February 2021)PermalinkG-band radar for humidity and cloud remote sensing / Ken B. Cooper in IEEE Transactions on geoscience and remote sensing, vol 59 n° 2 (February 2021)Permalink