Centre de documentation
scientifique

Transferring deep learning models for cloud detection between Landsat-8 and Proba-V / Gonzalo Mateo-García in ISPRS Journal of photogrammetry and remote sensing, vol 160 (February 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 160 (February 2020) . - pp 1 - 17 Titre : Transferring deep learning models for cloud detection between Landsat-8 and Proba-V Type de document : Article/Communication Auteurs : Gonzalo Mateo-García, Auteur ; Valero Laparra, Auteur ; Dan López-Puigdollers, Auteur ; Luis Gómez-Chova, Auteur Année de publication : 2020 Article en page(s) : pp 1 - 17 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage par transformation [Termes IGN] apprentissage profond [Termes IGN] conversion de données [Termes IGN] détection des nuages [Termes IGN] échantillonnage de données [Termes IGN] image Landsat-8 [Termes IGN] image multibande [Termes IGN] image PROBA [Termes IGN] jeu de données [Termes IGN] masque [Termes IGN] réseau neuronal convolutif [Termes IGN] seuillage de points Résumé : (Auteur) Accurate cloud detection algorithms are mandatory to analyze the large streams of data coming from the different optical Earth observation satellites. Deep learning (DL) based cloud detection schemes provide very accurate cloud detection models. However, training these models for a given sensor requires large datasets of manually labeled samples, which are very costly or even impossible to create when the satellite has not been launched yet. In this work, we present an approach that exploits manually labeled datasets from one satellite to train deep learning models for cloud detection that can be applied (or transferred) to other satellites. We take into account the physical properties of the acquired signals and propose a simple transfer learning approach using Landsat-8 and Proba-V sensors, whose images have different but similar spatial and spectral characteristics. Three types of experiments are conducted to demonstrate that transfer learning can work in both directions: (a) from Landsat-8 to Proba-V, where we show that models trained only with Landsat-8 data produce cloud masks 5 points more accurate than the current operational Proba-V cloud masking method, (b) from Proba-V to Landsat-8, where models that use only Proba-V data for training have an accuracy similar to the operational FMask in the publicly available Biome dataset (87.79–89.77% vs 88.48%), and (c) jointly from Proba-V and Landsat-8 to Proba-V, where we demonstrate that using jointly both data sources the accuracy increases 1–10 points when few Proba-V labeled images are available. These results highlight that, taking advantage of existing publicly available cloud masking labeled datasets, we can create accurate deep learning based cloud detection models for new satellites, but without the burden of collecting and labeling a large dataset of images. Numéro de notice : A2020-043 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.11.024 Date de publication en ligne : 10/12/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.11.024 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94522 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020021	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2020023	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2020022	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Estimating forest species abundance through linear unmixing of CHRIS/PROBA imagery / S. Stagakis in ISPRS Journal of photogrammetry and remote sensing, vol 119 (September 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 119 (September 2016) . - pp 79 - 89 Titre : Estimating forest species abundance through linear unmixing of CHRIS/PROBA imagery Type de document : Article/Communication Auteurs : S. Stagakis, Auteur ; Theofilos Vanikiotis, Auteur ; Olga Sykioti, Auteur Année de publication : 2016 Article en page(s) : pp 79 - 89 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse des mélanges spectraux [Termes IGN] carte de la végétation [Termes IGN] classification bayesienne [Termes IGN] effet d'ombre [Termes IGN] espèce végétale [Termes IGN] Fagus sylvatica [Termes IGN] Grèce [Termes IGN] image hyperspectrale [Termes IGN] image Landsat-8 [Termes IGN] image PROBA-CHRIS [Termes IGN] orthoimage [Termes IGN] parc naturel national [Termes IGN] partition d'image [Termes IGN] Pinus nigra [Termes IGN] richesse floristique [Vedettes matières IGN] Inventaire forestier Résumé : (Auteur) The advancing technology of hyperspectral remote sensing offers the opportunity of accurate land cover characterization of complex natural environments. In this study, a linear spectral unmixing algorithm that incorporates a novel hierarchical Bayesian approach (BI-ICE) was applied on two spatially and temporally adjacent CHRIS/PROBA images over a forest in North Pindos National Park (Epirus, Greece). The scope is to investigate the potential of this algorithm to discriminate two different forest species (i.e. beech – Fagus sylvatica, pine – Pinus nigra) and produce accurate species-specific abundance maps. The unmixing results were evaluated in uniformly distributed plots across the test site using measured fractions of each species derived by very high resolution aerial orthophotos. Landsat-8 images were also used to produce a conventional discrete-type classification map of the test site. This map was used to define the exact borders of the test site and compare the thematic information of the two mapping approaches (discrete vs abundance mapping). The required ground truth information, regarding training and validation of the applied mapping methodologies, was collected during a field campaign across the study site. Abundance estimates reached very good overall accuracy (R2 = 0.98, RMSE = 0.06). The most significant source of error in our results was due to the shadowing effects that were very intense in some areas of the test site due to the low solar elevation during CHRIS acquisitions. It is also demonstrated that the two mapping approaches are in accordance across pure and dense forest areas, but the conventional classification map fails to describe the natural spatial gradients of each species and the actual species mixture across the test site. Overall, the BI-ICE algorithm presented increased potential to unmix challenging objects with high spectral similarity, such as different vegetation species, under real and not optimum acquisition conditions. Its full potential remains to be investigated in further and more complex study sites in view of the upcoming satellite hyperspectral missions. Numéro de notice : A2016-778 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2016.05.013 En ligne : https://doi.org/10.1016/j.isprsjprs.2016.05.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82473 [article]

Tracking seasonal changes of leaf and canopy light use efficiency in a Phlomis fruticosa Mediterranean ecosystem using field measurements and multi-angular satellite hyperspectral imagery / S. Stagakis in ISPRS Journal of photogrammetry and remote sensing, vol 97 (November 2014)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 97 (November 2014) . - pp 138 – 151 Titre : Tracking seasonal changes of leaf and canopy light use efficiency in a Phlomis fruticosa Mediterranean ecosystem using field measurements and multi-angular satellite hyperspectral imagery Type de document : Article/Communication Auteurs : S. Stagakis, Auteur ; Nikos Markos, Auteur ; Olga Sykioti, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp 138 – 151 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] climat méditerranéen [Termes IGN] flore locale [Termes IGN] Grèce [Termes IGN] image hyperspectrale [Termes IGN] image multiangulaire [Termes IGN] image PROBA-CHRIS Résumé : (Auteur) Numerous normalized difference spectral indices (NDSIs) derived from leaf measurements and CHRIS/PROBA hyperspectral and multi-angular satellite images were examined for their capacity to track seasonal variations of leaf (εleaf) and canopy (εcan) light use efficiency of a Mediterranean phryganic ecosystem. A series of seasonal field ecophysiological measurements, i.e. leaf area index (LAI), leaf photosynthesis and leaf reflectance, were conducted on the Phlomis fruticosa shrubs at the days of CHRIS acquisitions over the study site. Leaf scale analysis confirmed background theory on the relationship of the photochemical reflectance index (PRI) with εleaf and provided a detailed view of the wavelengths that can be used in PRI formulation for the specific species. In canopy scale analysis, PRI and some alternative formulations of this index based on CHRIS bands, presented the most significant relationships with εcan, indicating that this index preserves its efficiency in satellite observations for the specific ecosystem. Additionally, spectral indices related to chlorophyll and water content were found to present good relationships with εcan. Taking into account the functional relationship between εcan and chlorophyll content, a combination of the xanthophyll de-epoxidation band (531 nm) with 701 nm CHRIS band in a NDSI is suggested as an alternative to the original PRI formulation that could improve seasonal εcan estimations. The satellite observation geometry effects on the determination of εcan were not very intense for the studied ecosystem. However, the most effective viewing direction was proved to be the backward scattering, while zenith observations were the least efficient for the specific ecosystem, most probably due to increased background effects. Even though the sensitivity of the original PRI formulation to εcan was reduced in forward scattering viewing directions, when 531 nm xanthophyll de-epoxidation band was replaced with higher wavelength bands (540–550 nm), a strong PRI–εcan relationship reappeared. These findings indicate possible shift of xanthophyll de-epoxidation signal according to viewing direction. Numéro de notice : A2014-528 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2014.08.012 En ligne : https://doi.org/10.1016/j.isprsjprs.2014.08.012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74141 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2014111	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Improved capability in stone pine forest mapping and management in Lebanon using hyperspectral CHTIS-Proba data relative to Landsat ETM+ / Mohamad Awad in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 8 (August 2014)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 80 n° 8 (August 2014) . - pp. 725 - 731 Titre : Improved capability in stone pine forest mapping and management in Lebanon using hyperspectral CHTIS-Proba data relative to Landsat ETM+ Type de document : Article/Communication Auteurs : Mohamad Awad, Auteur ; Ihab Jomaa, Auteur ; Fatima Arab, Auteur Année de publication : 2014 Article en page(s) : pp. 725 - 731 Langues : Français (fre) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse diachronique [Termes IGN] carte topographique [Termes IGN] image hyperspectrale [Termes IGN] image Landsat-TM [Termes IGN] image PROBA-CHRIS [Termes IGN] Liban [Termes IGN] Pinus (genre) [Termes IGN] répartition géographique [Termes IGN] traitement automatique d'images Résumé : (Auteur)The Stone Pine (pinus pinea) is native to the Mediterranean region and has been used for their edible pine nuts since prehistoric times. They are widespread in horticultural cultivation as ornamental trees and planted in gardens and parks around the world. Economically speaking, the Stone Pine is very important for the agriculture sector, for tourism, and for the health sector. In this research, a pilot area located in Mount Lebanon is compared for changes in the Stone Pine cover between the years of 1962 and 2012. The comparison is based on processing a hyperspectral image provided by the European Space Agency (ESA) and a Landsat ETM+ image as well as topographic maps. Several issues related to the use of CHRiS-Proba hyperspectral images have been investigated and analyzed. The results established that hyperspectral data: (a) is 30 percent or more accurate and efficient when compared with multispectral data, and (b) helps determine precise extent of the Stone Pine cover. Numéro de notice : A2014-343 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.14358/PERS.80.8.725 En ligne : https://doi.org/10.14358/PERS.80.8.725 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=73713 [article]

Improvement and application of the conifer forest multiangular hybrid GORT model MGeoSAIL / Qiang Wang in IEEE Transactions on geoscience and remote sensing, vol 51 n° 10 (October 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 10 (October 2013) . - pp 5047 - 5059 Titre : Improvement and application of the conifer forest multiangular hybrid GORT model MGeoSAIL Type de document : Article/Communication Auteurs : Qiang Wang, Auteur ; Yong Pang, Auteur ; Zengyuan Li, Auteur ; et al., Auteur Année de publication : 2013 Article en page(s) : pp 5047 - 5059 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Chine [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] forêt [Termes IGN] houppier [Termes IGN] image PROBA-CHRIS [Termes IGN] Leaf Area Index [Termes IGN] modèle de transfert radiatif [Termes IGN] Pinophyta Résumé : (Auteur) Compared with traditional remote sensing, multiangular observation provides 3-D structural information of a forest through different directional observations. The MGeoSAIL model, suitable for multiangular observations, was developed based on the single-angle model GeoSAIL. The MGeoSAIL model combines the geometric-optic model with the radiation transfer model and has the advantages of both models. Thus, it is more accurate and feasible. The geometric-optic model calculates the amount of shadowed and illuminated components within a forest scene, while the radiation transfer model [Scattering by Arbitrarily Inclined Leaves (SAIL)] calculates the reflectance and transmittance of tree crowns. The uniform index is introduced to characterize the relationship quantitatively between tree distribution pattern and the bidirectional reflectance distribution function (BRDF). The simulation results show that the MGeoSAIL model could simulate the “hot” spot in red and near-infrared bands, as well as the “bowl” shape in the near-infrared band. The relationship between the uniform index and BRDF is negatively exponential. Finally, the look-up table was calculated using the MGeoSAIL model, and leaf area index (LAI) was inversed from compact high-resolution imaging spectrometry data. The results compared well with the measured LAI in Changbai Mountain area, China. Numéro de notice : A2013-603 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2234466 En ligne : https://doi.org/10.1109/TGRS.2012.2234466 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32739 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013101	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Multiple endmember unmixing of CHRIS/Proba imagery for mapping impervious surfaces in urban and suburban environments / Luca Demarchi in IEEE Transactions on geoscience and remote sensing, vol 50 n° 9 (October 2012)  

Permalink

Mapping impervious surfaces from superresolution enhanced CHRIS/Proba imagery using multiple endmember unmixing / Luca Demarchi in ISPRS Journal of photogrammetry and remote sensing, vol 72 (August 2012)  

Permalink

Pixel unmixing in hyperspectral data by means of neural networks / Giorgio Licciardi in IEEE Transactions on geoscience and remote sensing, vol 49 n° 11 Tome 1 (November 2011)  

Permalink

Superresolution enhancement of hyperspectral CHRIS/Proba images with a thin-plate spline nonrigid transform model / J. Chan in IEEE Transactions on geoscience and remote sensing, vol 48 n° 6 (June 2010)  

Permalink

Potential accuracy of image orientation of small satellites: a case study of CHRIS/Proba data / Ahmed Shaker in Photogrammetric record, vol 23 n° 123 (September - November 2008)  

Permalink

PROBA proves the technology: PROBA-1 passes 5 years in orbit / F. Teston in ESA bulletin, n° 129 (February 2007)  

Permalink

A method for the surface reflectance retrieval from PROBA/CHRIS data over land: application to ESA SPARC campaigns / L. Guanter in IEEE Transactions on geoscience and remote sensing, vol 43 n° 12 (December 2005)  

Permalink