Centre dedocumentation
scientifique

Exploring the potential of deep learning segmentation for mountain roads generalisation / Azelle Courtial in ISPRS International journal of geo-information, vol 9 n° 5 (May 2020)  

Public [article]  inISPRS International journal of geo-information > vol 9 n° 5 (May 2020) . - 21 p. Titre : Exploring the potential of deep learning segmentation for mountain roads generalisation Type de document : Article/Communication Auteurs : Azelle Courtial, Auteur ; Achraf El Ayedi, Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Année de publication : 2020 Projets : 1-Pas de projet / Article en page(s) : 21 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] 1:25.000 [Termes descripteurs IGN] 1:250.000 [Termes descripteurs IGN] Alpes (France) [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données routières [Termes descripteurs IGN] données vectorielles [Termes descripteurs IGN] généralisation automatique de données [Termes descripteurs IGN] montagne [Termes descripteurs IGN] route [Termes descripteurs IGN] segmentation [Termes descripteurs IGN] symbole graphique [Termes descripteurs IGN] virage [Vedettes matières IGN] Généralisation Résumé : (auteur) Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potential on the popular mountain road generalisation problem, which requires smoothing the road, enlarging the bend summits, and schematising the bend series by removing some of the bends. We modelled the mountain road generalisation as a deep learning problem by generating an image from input vector road data, and tried to generate it as an output of the model a new image of the generalised roads. Similarly to previous studies on building generalisation, we used a U-Net architecture to generate the generalised image from the ungeneralised image. The deep learning model was trained and evaluated on a dataset composed of roads in the Alps extracted from IGN (the French national mapping agency) maps at 1:250,000 (output) and 1:25,000 (input) scale. The results are encouraging as the output image looks like a generalised version of the roads and the accuracy of pixel segmentation is around 65%. The model learns how to smooth the output roads, and that it needs to displace and enlarge symbols but does not always correctly achieve these operations. This article shows the ability of deep learning to understand and manage the geographic information for generalisation, but also highlights challenges to come. Numéro de notice : A2020-295 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9050338 date de publication en ligne : 25/05/2020 En ligne : https://doi.org/10.3390/ijgi9050338 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95131 [article]

Intertidal topography mapping using the waterline method from Sentinel-1 & -2 images: The examples of Arcachon and Veys Bays in France / Edward Salameh in ISPRS Journal of photogrammetry and remote sensing, vol 163 (May 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 163 (May 2020) . - pp 98 - 120 Titre : Intertidal topography mapping using the waterline method from Sentinel-1 & -2 images: The examples of Arcachon and Veys Bays in France Type de document : Article/Communication Auteurs : Edward Salameh, Auteur ; Frédéric Frappart, Auteur ; Imen Turki, Auteur ; Benoit Laignel, Auteur Année de publication : 2020 Article en page(s) : pp 98 - 120 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] aménagement du littoral [Termes descripteurs IGN] Arcachon (bassin d') [Termes descripteurs IGN] carte topographique [Termes descripteurs IGN] Cotentin [Termes descripteurs IGN] estran [Termes descripteurs IGN] France (administrative) [Termes descripteurs IGN] hydrodynamique [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] niveau de l'eau [Termes descripteurs IGN] sédiment [Termes descripteurs IGN] télédétection spatiale [Termes descripteurs IGN] trait de côte [Termes descripteurs IGN] zone tampon Résumé : (auteur) Intertidal flats lying as a buffer zone between land and sea provide critical services including protection against storm surges and coastal flooding. These environments are characterized by a continuous redistribution of sediment and changes in topography. Sea level rise, anthropogenic pressures, and their related stressors have a considerable impact on these areas and are expected to put them under more stress; hence the increased need for frequent and updated topography maps. Comparing to traditional surveying approaches, spaceborne remote sensing is able to provide topography maps more frequently with a lower cost and a higher coverage. The latter is currently considered as an established tool for measuring intertidal topography. In this study, an improved approach of the waterline method was developed to derive intertidal Digital Elevation Models (DEMs). The changes include a faster, more efficient and quasi-automatic detection and post-processing of waterlines. The edge detection technique consists in combining a k-means based segmentation and an active contouring procedure. This method was designed to generate closed contours in order to enable an automatization of the post-processing of the extracted waterlines. The waterlines were extracted from Sentinel-1 and Sentinel-2 images for two bays located on the French Coast: the Arcachon lagoon and the Bay of Veys. DEMs were generated for the Arcachon Bay between 2015 and 2018, and for the Bay of Veys between 2016 and 2018 using satellite acquisitions made during summer (low storm activity period). The comparison of the generated DEMs with lidar observations showed an error of about 19–25 cm. This study also demonstrated that the waterline method applied to Sentinel images is suitable for monitoring the morpho-sedimentary evolution in intertidal areas. By comparing the DEMs generated between 2016 and 2018, the Arcachon Bay and the Bay of Veys experienced net volume losses of 1.12 × 106 m3 and 0.70 × 106 m3 respectively. The generated DEMs provide useful and needed information for several scientific applications (e.g., sediment balance, hydrodynamic modelling), but also for authorities and stakeholders for coastal management and implementation of ecosystem protection policies. Numéro de notice : A2020-138 Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.03.003 date de publication en ligne : 13/03/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.03.003 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94756 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020051	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020053	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020052	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Tephra mass eruption rate from ground-based X-band and L-band microwave radars during the November 23, 2013, Etna Paroxysm / Frank S. Marzano in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 5 (May 2020) . - pp 3314 - 3327 Titre : Tephra mass eruption rate from ground-based X-band and L-band microwave radars during the November 23, 2013, Etna Paroxysm Type de document : Article/Communication Auteurs : Frank S. Marzano, Auteur ; Luigi Mereu, Auteur ; Simona Scollo, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 3314 - 3327 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Télédétection [Termes descripteurs IGN] bande L [Termes descripteurs IGN] bande X [Termes descripteurs IGN] capteur terrestre [Termes descripteurs IGN] éruption volcanique [Termes descripteurs IGN] Etna (volcan) [Termes descripteurs IGN] lave [Termes descripteurs IGN] masse [Termes descripteurs IGN] micro-onde [Termes descripteurs IGN] radar à antenne synthétique [Termes descripteurs IGN] rayonnement infrarouge thermique [Termes descripteurs IGN] surveillance géologique [Termes descripteurs IGN] volcanologie Résumé : (auteur) The morning of November 23, 2013, a lava fountain formed from the New South-East Crater (NSEC) of Mt. Etna (Italy), one of the most active volcanoes in Europe. The explosive activity was observed from two ground-based radars, the X-band polarimetric scanning and the L-band Doppler fixed-pointing, as well as from a thermal-infrared camera. Taking advantage of the capability of the microwave radars to probe the volcanic plume and extending the volcanic ash radar retrieval (VARR) methodology, we estimate the mass eruption rate (MER) using three main techniques, namely surface-flux approach (SFA), mass continuity-based approach (MCA), and top-plume approach (TPA), as well as provide a quantitative evaluation of their uncertainty. Estimated exit velocities are between 160 and 230 m/s in the paroxysmal phase. The intercomparison between the SFA, MCA, and TPA methods, in terms of retrieved MER, shows a fairly good consistency with values up to $2.4\times 10^{6}$ kg/s. The estimated total erupted mass (TEM) is $3.8\times 10^{9}$ , $3.9\times 10^{9}$ , and $4.7\times 10^{9}$ kg for SFA with L-band, X-band, and thermal-infrared camera, respectively. Estimated TEM is between $1.7\times 10^{9}$ kg and $4.3\times 10^{9}$ for TPA methods and $3.9\times 10^{9}$ kg for the MCA technique. The SFA, MCA, and TPA results for TEM are in fairly good agreement with independent evaluations derived from ground collection of tephra deposit and estimated to be between $1.3\,\,\pm \,\,1.1\times 10^{9}$ and $5.7\times 10^{9}$ kg. This article shows that complementary strategies of ground-based remote sensing systems can provide an accurate real-time monitoring of a volcanic explosive activity. Numéro de notice : A2020-236 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2953167 date de publication en ligne : 23/12/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2953167 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94982 [article]

Impact of GPS processing on the estimation of snow water equivalent using refracted GPS signals / Ladina Steiner in IEEE Transactions on geoscience and remote sensing, vol 58 n° 1 (January 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 1 (January 2020) . - pp 123 - 135 Titre : Impact of GPS processing on the estimation of snow water equivalent using refracted GPS signals Type de document : Article/Communication Auteurs : Ladina Steiner, Auteur ; Michael Meindl, Auteur ; Christoph Marty, Auteur ; Alain Geiger, Auteur Année de publication : 2020 Article en page(s) : pp 123 - 135 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes descripteurs IGN] Alpes [Termes descripteurs IGN] altitude [Termes descripteurs IGN] antenne GPS [Termes descripteurs IGN] eau de fonte [Termes descripteurs IGN] étalonnage des données [Termes descripteurs IGN] manteau neigeux [Termes descripteurs IGN] modèle hydrographique [Termes descripteurs IGN] neige [Termes descripteurs IGN] phase GPS [Termes descripteurs IGN] pondération [Termes descripteurs IGN] réfraction [Termes descripteurs IGN] signal GPS [Termes descripteurs IGN] Suisse Résumé : (auteur) Global navigation satellite system (GNSS) antennas buried underneath a snowpack have a high potential for in situ snow water equivalent (SWE) estimation. Automated and continuous SWE quantification independent of weather conditions could enhance snow hydrological monitoring and modeling. Accurate and reliable in situ data are needed for the calibration and validation of remote sensing data and snowpack modeling. A relative bias of less than 5% is achieved using sub-snow global positioning system (GPS) antennas (GPS refractometry) during a three full seasons time period in the Swiss Alps. A systematic overview regarding the temporal reliability of the sub-snow GPS derived results is, however, missing for this emerging technique. Moreover, GPS processing impacts the results significantly. Different GPS processing parameters are therefore selected and their influence on the SWE estimation is investigated. The impact of elevation-dependent weighting, the elevation cutoff angles, and the time intervals for SWE estimation are systematically assessed. The best results are achieved using all observations with an elevation-dependent weighting scheme. Moreover, the SWE estimation performance is equally accurate for hourly SWE estimation as for lower temporal resolutions up to daily estimates. The impact of snow on the coordinate solution is furthermore evaluated. While the east and north components are not systematically influenced by the overlying snowpack, the vertical component exhibits a significant variation and strongly depends on the SWE. The biased vertical component therefore provides an additional possibility to estimate SWE. Numéro de notice : A2020-074 Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2934016 date de publication en ligne : 06/09/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2934016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94605 [article]

La succession végétale dans les Landes de Gascogne et la position de l’Avoine de Thore (Pseudarrhenatherum longifolium) / Pierre Lafon in Evaxiana, n° 6 (2019)

Public [article]  inEvaxiana > n° 6 (2019) . - pp 131 - 150 Titre : La succession végétale dans les Landes de Gascogne et la position de l’Avoine de Thore (Pseudarrhenatherum longifolium) Type de document : Article/Communication Auteurs : Pierre Lafon, Auteur Année de publication : 2019 Article en page(s) : pp 131 - 150 Note générale : bibliographie, tableaux phytosociologiques Langues : Français (fre) Descripteur : [Termes descripteurs IGN] Landes de Gascogne [Termes descripteurs IGN] phytosociologie [Termes descripteurs IGN] Pinus pinaster [Termes descripteurs IGN] quercus pedunculata [Termes descripteurs IGN] unité phytosociologique [Vedettes matières IGN] Ecologie forestière Résumé : (auteur) Cet article est une contribution à l’amélioration des connaissances des végétations du sud-ouest de la France (Nouvelle-Aquitaine). Nous proposons ici une nouvelle association d’ourlet acidiphile thermo-atlantique, l’Arenario montanae–Pseudarrhenatheretum longifolii ass. nov. que nous positionnons dans le contexte de la succession végétale des Landes de Gascogne. Nous présentons également les différentes végétations qui s’insèrent dans cette succession en contexte naturel, c’est-à-dire évoluant vers une forêt de feuillus et en contexte de sylviculture intensive de Pinus pinaster. Numéro de notice : A2019-421 Thématique : FORET Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93645 [article]

Increasing precision for French forest inventory estimates using the k-NN technique with optical and photogrammetric data and model-assisted estimators / Dinesh Babu Irulappa Pillai Vijayakumar in Remote sensing, vol 11 n° 8 (August 2019)  

Permalink

Integration of corner reflectors for the monitoring of mountain glacier areas with Sentinel-1 time series / Matthias Jauvin in Remote sensing, vol 11 n° 8 (August 2019)  

Permalink

Occlusion probability in operational forest inventory field sampling with ForeStereo / Fernando Montes in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 7 (July 2019)  

Permalink

Genetic diversity and structure of Silver fir (Abies alba Mill.) at the south-eastern limit of its distribution range / Maria Teodosiu in Annals of forest research, vol 62 n° 2 (June - December 2019)  

Permalink

High-resolution models of tropospheric delays and refractivity based on GNSS and numerical weather prediction data for alpine regions in Switzerland / Karina Wilgan in Journal of geodesy, vol 93 n°6 (June 2019)  

Permalink

Couplings in cell differentiation kinetics mitigate air temperature influence on conifer wood anatomy / Henri Cuny in Plant, cell & environment, vol 42 n° 4 (April 2019)  

Permalink

Patterns of tree diameter distributions in managed and unmanaged Abies alba Mill. and Fagus sylvatica L. forest patches / Rafał Podlaski in Forest ecology and management, vol 435 (1 March 2019)  

Permalink

Effect of forest structure on stand productivity in Central European forests depends on developmental stage and tree species diversity / Laura Zeller in Forest ecology and management, vol 434 (28 February 2019)  

Permalink

How do tree mortality models from combined tree-ring and inventory data affect projections of forest succession? / Marco Vanoni in Forest ecology and management, vol 433 (15 February 2019)  

Permalink

Apport des mesures du radar à synthèse d'ouverture de Sentinel-1 pour l'étude des propriétés du manteau neigeux / Gaëlle Veyssière (2019)  

Permalink