Centre de documentation
scientifique

Marrying deep learning and data fusion for accurate semantic labeling of Sentinel-2 images / Guillemette Fonteix in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2021 (July 2021)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2021 (July 2021) . - pp 101 - 107 Titre : Marrying deep learning and data fusion for accurate semantic labeling of Sentinel-2 images Type de document : Article/Communication Auteurs : Guillemette Fonteix, Auteur ; M. Swaine, Auteur ; M. Leras, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 101 - 107 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] carte de confiance [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] fusion d'images [Termes IGN] image optique [Termes IGN] image Sentinel-MSI [Termes IGN] segmentation sémantique [Termes IGN] série temporelle Résumé : (auteur) The understanding of the Earth through global land monitoring from satellite images paves the way towards many applications including flight simulations, urban management and telecommunications. The twin satellites from the Sentinel-2 mission developed by the European Space Agency (ESA) provide 13 spectral bands with a high observation frequency worldwide. In this paper, we present a novel multi-temporal approach for land-cover classification of Sentinel-2 images whereby a time-series of images is classified using fully convolutional network U-Net models and then coupled by a developed probabilistic algorithm. The proposed pipeline further includes an automatic quality control and correction step whereby an external source can be introduced in order to validate and correct the deep learning classification. The final step consists of adjusting the combined predictions to the cloud-free mosaic built from Sentinel-2 L2A images in order for the classification to more closely match the reference mosaic image. Numéro de notice : A2021-492 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-3-2021-101-2021 Date de publication en ligne : 17/06/2021 En ligne : http://dx.doi.org/10.5194/isprs-annals-V-3-2021-101-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97957 [article]

Development of a Protocol to Convert and Manage Underground Infrastructure Maps into Geographic Information Systems (GIS) Format / Guillemette Fonteix (2018) 

Public Titre : Development of a Protocol to Convert and Manage Underground Infrastructure Maps into Geographic Information Systems (GIS) Format Type de document : Mémoire Auteurs : Guillemette Fonteix, Auteur Editeur : Champs-sur-Marne : Ecole nationale des sciences géographiques ENSG Année de publication : 2018 Importance : 32 p. Format : 21 x 30 cm Note générale : bibliographie Rapport de projet pluridisciplinaire, cycle Ingénieur 2e année Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] apprentissage automatique [Termes IGN] ArcGIS [Termes IGN] base de données localisées [Termes IGN] conception assistée par ordinateur [Termes IGN] conversion de données [Termes IGN] correction géométrique [Termes IGN] dessin assisté par ordinateur [Termes IGN] FME [Termes IGN] géocodage [Termes IGN] gestion urbaine [Termes IGN] protocole [Termes IGN] Python (langage de programmation) [Termes IGN] relation topologique 3D [Termes IGN] réseau technique souterrain [Termes IGN] réseau technique urbain [Termes IGN] système d'information urbain Index. décimale : PROJET Mémoires : Rapports de projet - stage des ingénieurs de 2e année Résumé : (auteur) In the cities, the underground networks system become more and more dense because of the occupation of many infrastructures for water, storm-water, sewer, electricity, gas, etc. Urban and ecological problems can be faced thanks to them. However, they are difficult to manage because of the impossibility of seeing them. The location of existing infrastructures is a necessity for controlling their development. Converting from CAD to GIS may improve the CAD drawings with spatial information and attributes and allows a better accessibility, accuracy and performance [Warner, 2013]. The Geographic Information System (GIS) implementation process for municipalities can be very complex, expensive, and time consuming, depending on the knowledge of municipalities. Maps of underground infrastructure systems are mainly stored in paper or CAD format and many cities and organizations around the world are putting significant efforts into converting those maps into GIS format. However, most of these efforts are uncoordinated and a formal protocol is missing to deal with GIS map update and version control. During this internship, it was asked to survey current practices in the world and develop a formal protocol to convert and manage GIS maps of underground infrastructure systems. The project required a technical expertise (to account for the potentials and limits of GIS) and specific knowledge about underground infrastructure systems. I had to survey current efforts in the world to convert and manage underground maps mainly thanks to a survey of municipalities and through online searches. Then developed a formal protocol illustrated by a general flowchart that should offer a streamlined strategy to ensure effective conversion from CAD to GIS and allows a better data management. The project resulted in a scientific publication. These works allowed me to develop GIS, Python, communication and writing skills in English. Note de contenu : Introduction 1- Challenges faced 2- Data management 3- Work carried out Conclusion Numéro de notice : 21810 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Mémoire de projet pluridisciplinaire Organisme de stage : Complex and Sustainable Urban Networks laboratory Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91298

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
21810-01	PROJET	Livre	Centre de documentation	Travaux d'élèves	Disponible

Documents numériques

peut être téléchargé Development of a Protocol... - pdf auteur Adobe Acrobat PDF