Catalogue en ligne IGN

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

IGN

Centre de documentation
scientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! fermeture automnale

Informations pratiques

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

IGN

Centre de documentationscientifique

Accueil

Sélection de la langue

Adresse

Se connecter

Actualité

L'actu ! fermeture automnale

Informations pratiques

IGN / ENSG

L'IGN a pour vocation

Accès directs

2014 -2024 IGN

Centre de documentation
scientifique