Centre de documentation
scientifique

Classification of land use from high resolution satellite imagery / Yasser Kotrsi (2018) 

Public Titre : Classification of land use from high resolution satellite imagery Type de document : Mémoire Auteurs : Yasser Kotrsi, Auteur ; Arnaud Le Bris , Encadrant ; Nesrine Chehata , Encadrant ; Anne Puissant, Encadrant ; Tristan Postadjian , Encadrant Editeur : Tunis [Tunisie] : Ecole nationale d'ingénieurs de Carthage Année de publication : 2018 Importance : 112 p. Note générale : bibliographie End Of Studies Project Report, in fulfillment of the requirements for the degree of National engineering diploma in software engineering Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] bibliothèque logicielle [Termes IGN] classification barycentrique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] Finistère (29) [Termes IGN] fusion d'images [Termes IGN] image Sentinel-MSI [Termes IGN] image SPOT 6 [Termes IGN] milieu urbain [Termes IGN] occupation du sol [Termes IGN] OpenCV [Termes IGN] Python (langage de programmation) [Termes IGN] semis de points Résumé : (auteur) The MATIS team of the LaSTIG Laboratory of the french mapping agency (IGN) has for several years conducted research activities in the field of classification of remote sensing data (aerial or satellite optical images and point clouds 3D lidar) for land use (OCS), in urban and rural areas. With the arrival of the new Sentinel S1 (radar) and S2 (optical) sensors, time series of images are now available free of charge with a high temporal resolution (between 10 and 15 days) and a high spectral resolution for optical images. In addition, the national territory is covered annually by acquisition of SPOT 6-7 images. The CES Artificialisation-urbanization pole Theia aims at the production of a map of land use in urban environment, with a resolution of 10m. Early work based on the fusion of Sentinel 2 time series with very high resolution data (THR) SPOT 6-7, Pleiades led to the detection of artifical spots, as well as well shaped urban objects. It is now a question of better characterizing this urban space by investigating about the relations between those image regions as well as each one’s spatial properties in order to produce a detailed cartography classified into different types of urban fabrics (residential, dense urban, non-dense, industrial, ...). In this study we dive deep through the problematic of the land use classification, its aspects as well the different approaches to characterize the extracted information about it in order to obtain an accurate classification that corresponds well to the expected results. This study therefore focuses on the continuation of previous work and consists in obtaining a detailed cartography in different types of urban fabrics (residential, dense urban, non-dense, industrial, ..). For that, several scientific locks are raised: • Test the data fusion methods previously used for fine mapping of the urban environment. • Develop different multiscale spatial indicators (size of objects, distance between objects, density of objects, presence of vegetation, ...) to describe the city. • Exploit these indicators in order to find different types of neighborhoods and to characterize land use. The calculation of indicators is based in part on SPOT image classifications 6-7 obtained during previous work. Also the Urban Atlas database, which also details urban spaces in urban classes, is used in the learning stage as well as the Corine Land Cover database. Note de contenu : Introduction 1- Project introduction 2- State of the art and background material 3- Available data and study areas 4- Methodology 5- Results and discussions Conclusion and perspectives Numéro de notice : 17187 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Mémoire ingénieur Organisme de stage : LaSTIG (IGN) DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98348

Documents numériques

peut être téléchargé Classification of land use ... - pdf auteur Adobe Acrobat PDF