Centre dedocumentation
scientifique

Deep learning in denoising of micro-computed tomography images of rock samples / Mikhail Sidorenko in Computers & geosciences, vol 151 (June 2021)  

Public [article]  inComputers & geosciences > vol 151 (June 2021) . - n° 104716 Titre : Deep learning in denoising of micro-computed tomography images of rock samples Type de document : Article/Communication Auteurs : Mikhail Sidorenko, Auteur ; Denis Orlov, Auteur ; Mohammad Ebadi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 104716 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] accentuation d'image [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] filtrage du bruit [Termes descripteurs IGN] filtre passe-bande [Termes descripteurs IGN] roche [Termes descripteurs IGN] tomographie Résumé : (auteur) Nowadays, the advantages of Digital Rock Physics (DRP) are well known and widely applied in comprehensive core analysis. It is also known that the quality of the 3D pore scale model drastically influences the results of rock properties simulation, which makes the preprocessing stage of DRP very important. In this work, we consider the application of Deep Convolutional Neural Networks (CNNs) for the preprocessing of CT images, specifically for denoising, in two setups - conventional fully-supervised learning and the self-supervised learning, when the only available data is the noisy images. To train CNNs in a supervised setup, we use images processed by a combination of bilateral and bandpass filters. We trained CNNs of the same architecture with different loss functions to find out how the choice of a loss function influences the model's performance. Some of the obtained CNNs yielded the highest quality in terms of full-reference and no-reference metrics and significant histogram effect (bimodal intensity distribution). Images denoised with these models were qualitatively and quantitatively better than the reference “ground truth” images used for training. We use the Deep Image Prior algorithm to train denoising models in a self-supervised setup. The obtained models are much better than ones obtained in fully-supervised setup, but are too slow, as they are optimization-based rather than feed-forward. Such an algorithm can be used in the dataset generation for feed-forward meta-models. These results could help to develop an AI-based instrument to build high-quality 3D segmented models of rocks for DRP applications. Numéro de notice : A2021-389 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.cageo.2021.104716 date de publication en ligne : 02/03/2021 En ligne : https://doi.org/10.1016/j.cageo.2021.104716 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97672 [article]

An improved computerized ionospheric tomography model fusing 3-D multisource ionospheric data enabled quantifying the evolution of magnetic storm / Jian Kong in IEEE Transactions on geoscience and remote sensing, vol 59 n° 5 (May 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 5 (May 2021) . - pp 3725 - 3736 Titre : An improved computerized ionospheric tomography model fusing 3-D multisource ionospheric data enabled quantifying the evolution of magnetic storm Type de document : Article/Communication Auteurs : Jian Kong, Auteur ; Lulu Shan, Auteur ; Chen Zhou, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 3725 - 3736 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de géodésie spatiale [Termes descripteurs IGN] données GNSS [Termes descripteurs IGN] erreur absolue [Termes descripteurs IGN] filtre de Kalman [Termes descripteurs IGN] fusion de données multisource [Termes descripteurs IGN] modèle ionosphérique [Termes descripteurs IGN] modèle stochastique [Termes descripteurs IGN] perturbation ionosphérique [Termes descripteurs IGN] tempête magnétique [Termes descripteurs IGN] teneur totale en électrons [Termes descripteurs IGN] tomographie Résumé : (auteur) Global Navigation Satellite System (GNSS) ionospheric tomography is a typical ill-posed problem. Joint inversion with external observation data is one of the effective ways to mitigate the problem. In this article, by fusing 3-D multisource ionospheric data, and improving the stochastic model, an improved GNSS tomographic algorithm MFCIT [computerized ionospheric tomography (CIT) using mapping function] is presented. The accuracy of the algorithm is validated by selected data under different geomagnetic and solar conditions acquired in Europe. The results show that the estimated, statistically significant uncertainty for each of the layers is about 0.50–3.0TECU, with the largest absolute error within 6.0TECU. The advantage of the MFCIT is that it is based on the Kalman filter, which enables efficient near real-time 3-D monitoring of ionosphere. The temporal resolution can reach ~1 min level. Here, we apply the ionospheric tomography inversion to the magnetic storm on January 7, 2015, in the European region, and quantified the evolution of the storm. The results show that the difference of the core region between the MFCIT and CODE GIM is less than 1TECU. More importantly, during the initial phase of the storm, when the ionospheric disturbance is not evident in the single layer CODE GIM model, the MFCIT shows obvious positive disturbances in the upper ionosphere, although there is no disturbance in the F2 layer. The MFCIT further tracks the evolution of the magnetic storm that the ionospheric disturbance expands from the upper to the lower ionosphere layers, and at UT12:00, the disturbance continues to spread to the F2 layer. Numéro de notice : A2021-396 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3022949 date de publication en ligne : 24/09/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3022949 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97686 [article]

SAR speckle removal using hybrid frequency modulations / Shuaiqi Liu in IEEE Transactions on geoscience and remote sensing, vol 59 n° 5 (May 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 5 (May 2021) . - pp 3956 - 3966 Titre : SAR speckle removal using hybrid frequency modulations Type de document : Article/Communication Auteurs : Shuaiqi Liu, Auteur ; Lele Gao, Auteur ; Yu Lei, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 3956 - 3966 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] artefact [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] filtrage du bruit [Termes descripteurs IGN] filtre de déchatoiement [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] modulation de fréquence Résumé : (auteur) Synthetic aperture radar (SAR) images often interfere with speckle artifacts that have a great impact on subsequent processing and analysis operations. To remove speckle artifacts, this article introduces a hybrid denoising approach by using a convolutional neural network (CNN) and consistent cycle spinning (CCS) in the nonsubsample shearlet transform (NSST) domain. First, we apply NSST to a noisy SAR image to gain low- and high-frequency coefficients. Second, we adopt a learned deep CNN model to eliminate the speckle noise in the low-frequency coefficients, which retains more contour information. Third, we employ CCS to enhance the high-frequency coefficients, which preserves more details of the original SAR image. Finally, we obtain the denoised image by using inverse NSST applied to the denoised coefficients. Compared with state-of-the-art algorithms, the results of the experiment indicate that our method not only achieves better speckle removal performance but also maintains more detailed information retention. Numéro de notice : A2021-397 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.3014130 date de publication en ligne : 18/08/2020 En ligne : https://doi.org/10.1109/TGRS.2020.3014130 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97688 [article]

Unsupervised multi-level feature extraction for improvement of hyperspectral classification / Qiaoqiao Sun in Remote sensing, vol 13 n° 8 (15 April 2021)  

Public [article]  inRemote sensing > vol 13 n° 8 (15 April 2021) . - n° 1602 Titre : Unsupervised multi-level feature extraction for improvement of hyperspectral classification Type de document : Article/Communication Auteurs : Qiaoqiao Sun, Auteur ; Xuefeng Liu, Auteur ; Salah Bourennane, Auteur Année de publication : 2021 Article en page(s) : n° 1602 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification non dirigée [Termes descripteurs IGN] codage [Termes descripteurs IGN] convolution (signal) [Termes descripteurs IGN] déconvolution [Termes descripteurs IGN] échantillonnage d'image [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] observation multiniveaux Résumé : (auteur) Deep learning models have strong abilities in learning features and they have been successfully applied in hyperspectral images (HSIs). However, the training of most deep learning models requires labeled samples and the collection of labeled samples are labor-consuming in HSI. In addition, single-level features from a single layer are usually considered, which may result in the loss of some important information. Using multiple networks to obtain multi-level features is a solution, but at the cost of longer training time and computational complexity. To solve these problems, a novel unsupervised multi-level feature extraction framework that is based on a three dimensional convolutional autoencoder (3D-CAE) is proposed in this paper. The designed 3D-CAE is stacked by fully 3D convolutional layers and 3D deconvolutional layers, which allows for the spectral-spatial information of targets to be mined simultaneously. Besides, the 3D-CAE can be trained in an unsupervised way without involving labeled samples. Moreover, the multi-level features are directly obtained from the encoded layers with different scales and resolutions, which is more efficient than using multiple networks to get them. The effectiveness of the proposed multi-level features is verified on two hyperspectral data sets. The results demonstrate that the proposed method has great promise in unsupervised feature learning and can help us to further improve the hyperspectral classification when compared with single-level features. Numéro de notice : A2021-380 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs13081602 date de publication en ligne : 20/04/2021 En ligne : https://doi.org/10.3390/rs13081602 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97628 [article]

Atmospheric correction of Sentinel-3/OLCI data for mapping of suspended particulate matter and chlorophyll-a concentration in Belgian turbid coastal waters / Quinten Vanhellemont in Remote sensing of environment, Vol 256 (April 2020)  

Public [article]  inRemote sensing of environment > Vol 256 (April 2020) . - n° 112284 Titre : Atmospheric correction of Sentinel-3/OLCI data for mapping of suspended particulate matter and chlorophyll-a concentration in Belgian turbid coastal waters Type de document : Article/Communication Auteurs : Quinten Vanhellemont, Auteur ; Kevin Ruddick, Auteur Année de publication : 2021 Article en page(s) : n° 112284 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] Belgique [Termes descripteurs IGN] chlorophylle [Termes descripteurs IGN] correction atmosphérique [Termes descripteurs IGN] eaux côtières [Termes descripteurs IGN] image Sentinel-OLCI [Termes descripteurs IGN] particule [Termes descripteurs IGN] rayonnement infrarouge [Termes descripteurs IGN] réflectance [Termes descripteurs IGN] turbidité des eaux Résumé : (auteur) The performance of different atmospheric correction algorithms for the Ocean and Land Colour Instrument (OLCI) on board of Sentinel-3 (S3) is evaluated for retrieval of water-leaving radiance reflectance, and derived parameters chlorophyll-a concentration and turbidity in turbid coastal waters in the Belgian Coastal Zone (BCZ). This is performed using in situ measurements from an autonomous pan-and-tilt hyperspectral radiometer system (PANTHYR). The PANTHYR provides validation data for any satellite band between 400 and 900 nm, with the deployment in the BCZ of particular interest due to the wide range of observed Near-InfraRed (NIR) reflectance. The Dark Spectrum Fitting (DSF) atmospheric correction algorithm is adapted for S3/OLCI processing in ACOLITE, and its performance and that of 5 other processing algorithms (L2-WFR, POLYMER, C2RCC, SeaDAS, and SeaDAS-ALT) is compared to the in situ measured reflectances. Water turbidities across the matchups in the Belgian Coastal Zone are about 20–100 FNU, and the overall performance is best for ACOLITE and L2-WFR, with the former providing lowest relative (Mean Absolute Relative Difference, MARD 7–27%) and absolute errors (Mean Average Difference, MAD -0.002, Root Mean Squared Difference, RMSD 0.01–0.016) in the bands between 442 and 681 nm. L2-WFR provides the lowest errors at longer NIR wavelengths (754–885 nm). The algorithms that assume a water reflectance model, i.e. POLYMER and C2RCC, are at present not very suitable for processing imagery over the turbid Belgian coastal waters, with especially the latter introducing problems in the 665 and 709 nm bands, and hence the chlorophyll-a and turbidity retrievals. This may be caused by their internal model and/or training dataset not being well adapted to the waters encountered in the BCZ. The 1020 nm band is used most frequently by ACOLITE/DSF for the estimation of the atmospheric path reflectance (67% of matchups), indicating its usefulness for turbid water atmospheric correction. Turbidity retrieval using a single band algorithm showed good performance for L2-WFR and ACOLITE compared to PANTHYR for e.g. the 709 nm band (MARD 15 and 17%), where their reflectances were also very close to the in situ observations (MARD 11%). For the retrieval of chlorophyll-a, all methods except C2RCC gave similar performance, due to the RedEdge band-ratio algorithm being robust to typical spectrally flat atmospheric correction errors. C2RCC does not retain the spectral relationship in the Red and RedEdge bands, and hence its chlorophyll-a concentration retrieval is not at all reliable in Belgian coastal waters. L2-WFR and ACOLITE show similar performance compared to in situ radiometry, but due to the assumption of spatially consistent aerosols, ACOLITE provides less noisy products. With the superior performance of ACOLITE in the 490–681 nm wavelength range, and smoother output products, it can be recommended for processing of S3/OLCI data in turbid waters similar to those encountered in the BCZ. The ACOLITE processor for OLCI and the in situ matchup dataset used here are made available under an open source license. Numéro de notice : A2021-193 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112284 date de publication en ligne : 12/02/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112284 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97116 [article]

Automatic atmospheric correction for shortwave hyperspectral remote sensing data using a time-dependent deep neural network / Jian Sun in ISPRS Journal of photogrammetry and remote sensing, vol 174 (April 2021)  

Permalink

Detecting ground deformation in the built environment using sparse satellite InSAR data with a convolutional neural network / Nantheera Anantrasirichai in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Permalink

Hyperspectral image denoising via clustering-based latent variable in variational Bayesian framework / Peyman Azimpour in IEEE Transactions on geoscience and remote sensing, vol 59 n° 4 (April 2021)  

Permalink

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)  

Permalink

Early 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)  

Permalink

The Realization and evaluation of PPP ambiguity resolution with INS aiding in marine survey / Zhenqiang Du in Marine geodesy, vol 44 n° 2 (March 2021)  

Permalink

Cluster-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)  

Permalink

Denoising Sentinel-1 extra-wide mode cross-polarization images over sea ice / Yan Sun in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)  

Permalink

Enhanced trajectory estimation of mobile laser scanners using aerial images / Zille Hussnain in ISPRS Journal of photogrammetry and remote sensing, vol 173 (March 2021)  

Permalink

Impact of atmospheric correction on spatial heterogeneity relations between land surface temperature and biophysical compositions / Xin-Ming Zhu in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 3 (March 2021)  

Permalink