Centre de documentation
scientifique

Preface: the 2020 edition of the XXIVth ISPRS congress / Clément Mallet in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2020 (August 2020)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-1-2020 (August 2020) . - pp 1 - 6 Titre : Preface: the 2020 edition of the XXIVth ISPRS congress Type de document : Article/Communication Auteurs : Clément Mallet , Auteur ; Florent Lafarge, Auteur ; Martyna Poreba , Auteur ; Ewelina Rupnik , Auteur ; Gaétan Bahl, Auteur ; Nicolas Girard, Auteur ; Anatol Garioud , Auteur ; Ian J. Dowman, Auteur ; Nicolas Paparoditis , Auteur Année de publication : 2020 Projets : 1-Pas de projet / Conférence : ISPRS 2020, Commission 1, virtual Congress, Imaging today foreseeing tomorrow 31/08/2020 02/09/2020 Nice (en ligne) France ISPRS OA Annals Commission 1 Article en page(s) : pp 1 - 6 Langues : Anglais (eng) Résumé : (auteur) We report key elements and figures related to the proceedings of the 2020 edition of the XXIVth ISPRS Congress. The COVID-19 pandemic causes global travel challenges and restrictions for the full year 2020. Consequently, the Congress planned in June 2020 in Nice (France) was postponed to July 2021. Papers were already submitted and the review process was almost complete. Thus, it has been decided to achieve the publication of the proceedings of these papers under the label ”2020 Edition”. The authors of published papers have the opportunity to present their work during a Virtual Event (31 August – 2 September 2020), while the papers of the 2021 edition will be presented during the (physical) Congress in July 2021. Numéro de notice : A2020-500 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-1-2020-1-2020 Date de publication en ligne : 03/08/2020 En ligne : https://doi.org/10.5194/isprs-annals-V-1-2020-1-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95641 [article]

Learning and geometric approaches for automatic extraction of objects from remote sensing images / Nicolas Girard (2020)  

Public Titre : Learning and geometric approaches for automatic extraction of objects from remote sensing images Type de document : Thèse/HDR Auteurs : Nicolas Girard, Auteur Editeur : Nice : Université Côte d'Azur Année de publication : 2020 Importance : 169 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat Présentée en vue de l’obtention du grade de docteur en Automatique, Traitement du Signal et des Images de l'Université Côte d’Azur Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] alignement [Termes IGN] appariement de données localisées [Termes IGN] apprentissage profond [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection du bâti [Termes IGN] erreur [Termes IGN] figure géométrique [Termes IGN] filtrage du bruit [Termes IGN] jeu de données [Termes IGN] polygonation [Termes IGN] réalité de terrain [Termes IGN] segmentation d'image [Termes IGN] vectorisation Index. décimale : THESE Thèses et HDR Résumé : (auteur) Creating a digital double of the Earth in the form of a map has many applications in e.g. autonomous driving, automated drone delivery, urban planning, telecommunications, and disaster management. Geographic Information Systems (GIS) are the frameworks used to integrate geolocalized data and represent maps. They represent shapes of objects in a vector representation so that it is as sparse as possible while representing shapes accurately, as well as making it easier to edit than raster data. With the increasing amount of satellite and aerial images being captured every day, automatic methods are being developed to transfer the information found in those remote sensing images into Geographic Information Systems. Deep learning methods for image segmentation are able to delineate the shapes of objects found in images, but they do so with a raster representation, in the form of a mask. Post-processing vectorization methods then convert that raster representation into a vector representation compatible with GIS. Another challenge in remote sensing is to deal with a certain type of noise in the data, which is the misalignment between different layers of geolocalized information (e.g. between images and building cadaster data). This type of noise is frequent due to various errors introduced during the processing of remote sensing data. This thesis develops combined learning and geometric approaches with the purpose to improve automatic GIS mapping from remote sensing images. We first propose a method for correcting misaligned maps over images, with the first motivation for them to match, but also with the motivation to create remote sensing datasets for image segmentation with alignment-corrected ground truth. Indeed training a model on misaligned ground truth would not lead to a nice segmentation, whereas aligned ground truth annotations will result in better segmentation models. During this work we also observed a denoising effect of our alignment model and use it to denoise a misaligned dataset in a self-supervised manner, meaning only the misaligned dataset was used for training. We then propose a simple approach to use a neural network to directly output shape information in the vector representation, in order to by-pass the post-processing vectorization step. Experimental results on a dataset of solar panels show that the proposed network succeeds in learning to regress polygon coordinates, yielding directly vectorial map outputs. Our simple method is limited to predicting polygons with a fixed number of vertices though. While more recent methods for learning directly in the vector representation are not limited to a fixed number of vertices, they still have other limitations in terms of the type of object shapes they can predict. More complex topological cases such as objects with holes or buildings touching each other (with a common wall which is very typical of European city centers) are not handled by these fully deep learning methods. We thus propose a hybrid approach alleviating those limitations by training a neural network to output a segmentation probability map as usual and also to output a frame field aligned with the contours of detected objects (buildings in our case). The frame field constitutes additional shape information learned by the network. We then propose our highly parallelizable polygonization method for leveraging that frame field information to vectorize the segmentation probability map efficiently. Because our polygonization method has access to additional information in the form of a frame field, it can be less complex than other advanced vectorization methods and is thus faster. Lastly, requiring an image segmentation network to also output a frame field only adds two convolutional layers and virtually does not increase inference time, making the use of a frame field only beneficial. Note de contenu : 1- Introduction 2- Building alignment 3- Building alignment from noisy ground truth 4- PolyCNN: learning polygons 5- Frame field learning 6- Polygonization by frame field 7- Conclusions and perspectives Numéro de notice : 28501 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Traitement du Signal et des Images : Côte d’Azur : 2020 Organisme de stage : Inria Sophia-Antipolis nature-HAL : Thèse DOI : sans En ligne : https://hal.inria.fr/tel-03111628/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96940