Centre dedocumentation
scientifique

A typification method for linear building groups based on stroke simplification / Xiao Wang in Geocarto international, vol 36 n° 15 ([15/08/2021])  

Public [article]  inGeocarto international > vol 36 n° 15 [15/08/2021] . - pp 1732 - 1751 Titre : A typification method for linear building groups based on stroke simplification Type de document : Article/Communication Auteurs : Xiao Wang, Auteur ; Dirk Burghardt, Auteur Année de publication : 2021 Article en page(s) : pp 1732 - 1751 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] algorithme de Douglas-Peucker [Termes IGN] alignement [Termes IGN] bâtiment [Termes IGN] généralisation du bâti [Termes IGN] noeud [Termes IGN] objet géographique linéaire [Termes IGN] reconnaissance de formes [Termes IGN] simplification de contour [Termes IGN] triangulation de Delaunay [Vedettes matières IGN] Généralisation Résumé : (auteur) Linear building groups are common patterns and important local structures in large scale maps, which should be carefully generalized. This paper uses the idea of line simplification to typify linear building groups. Firstly, based on the stroke idea, the linear building groups are detected that each building group is related by only one stroke; the collinear and curvilinear patterns are distinguished by calculating the overlap rate between the defined auxiliary polygon and its oriented bounding box. Secondly, the stroke is simplified by removing one node in each iterative step; and the remained nodes are reallocated to the new positions, which serves as the centroids location of the newly typified buildings. Third, the representation (size, shape, elongation, and orientation) of the newly typified buildings are calculated by the geometry information of their corresponding parent buildings. The typification method can be carried out as a progressive process, which iterates over the three steps to derive continuous typification results. The method is tested on two building datasets, and the experimental results demonstrate that the proposed method can achieve good performance by well preserving the original linear patterns in the generalized building groups. Numéro de notice : A2021-569 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1669725 Date de publication en ligne : 26/09/2019 En ligne : https://doi.org/10.1080/10106049.2019.1669725 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98184 [article]

Automated registration of SfM‐MVS multitemporal datasets using terrestrial and oblique aerial images / Luigi Parente in Photogrammetric record, vol 36 n° 173 (March 2021)  

Public [article]  inPhotogrammetric record > vol 36 n° 173 (March 2021) . - pp 12 - 35 Titre : Automated registration of SfM‐MVS multitemporal datasets using terrestrial and oblique aerial images Type de document : Article/Communication Auteurs : Luigi Parente, Auteur ; Jim H. Chandler, Auteur ; Neil Dixon, Auteur Année de publication : 2021 Article en page(s) : pp 12 - 35 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] algorithme ICP [Termes IGN] alignement [Termes IGN] Angleterre [Termes IGN] détection de changement [Termes IGN] données multisources [Termes IGN] données multitemporelles [Termes IGN] géoréférencement direct [Termes IGN] image aérienne oblique [Termes IGN] image captée par drone [Termes IGN] image oblique [Termes IGN] image terrestre [Termes IGN] modèle stéréoscopique [Termes IGN] modélisation 3D [Termes IGN] point d'appui [Termes IGN] semis de points [Termes IGN] SIFT (algorithme) [Termes IGN] structure-from-motion Résumé : (auteur) Accurate alignment of 3D models is critical for valid change‐detection analysis from multitemporal photogrammetric datasets. This paper assesses an automated registration strategy which uses the scale‐invariant feature transform (SIFT) algorithm implemented in modern photogrammetric software. This registration solution, also known as “Time‐SIFT”, was tested at two study sites featuring vertical surfaces, including a sea cliff (~500 m2) and a quarry face (~50 000 m2). Tests demonstrated that the investigated registration strategy can achieve accurate alignments between multitemporal point clouds even when using multisource and multi‐perspective data, captured across widely varying spatial and temporal scales and under a range of weather and illumination conditions. The combination of the Time‐SIFT approach with an ICP algorithm produced moderate improvements in the alignment. Furthermore, the use of an innovative direct georeferencing technique, which used the tracking feature of a robotic total station, allowed for accurate georectification of 3D models. Numéro de notice : A2021-280 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1111/phor.12346 Date de publication en ligne : 06/01/2021 En ligne : https://doi.org/10.1111/phor.12346 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97377 [article]

Can graph convolution networks learn spatial relations? / Azelle Courtial (2021)  

Public Titre : Can graph convolution networks learn spatial relations? Type de document : Article/Communication Auteurs : Azelle Courtial , Auteur ; Guillaume Touya , Auteur ; Xiang Zhang, Auteur Editeur : ... [Suède] : International Cartographic Association ICA - Association cartographique internationale ACI Année de publication : 2021 Collection : Abstracts of the ICA num. 3 Projets : 1-Pas de projet / Conférence : ICC 2021, 30th ICA international cartographic conference 14/12/2021 18/12/2021 Florence Italie Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] alignement [Termes IGN] bati [Termes IGN] objet géographique [Termes IGN] relation spatiale [Termes IGN] réseau neuronal convolutif [Termes IGN] réseau neuronal de graphes [Termes IGN] réseau routier [Vedettes matières IGN] Généralisation Résumé : (auteur) [introduction] Maps are composed of spatially related geographic objects. Spatial relations are key information for human as they support the description of relative locations: the house is to the east of the city centre, near the interchange, or at the end of the path. Consequently, preserving these spatial relations is important during map generalisation. For example, building typification is a generalisation operation that seeks to reduce the quantity of building while preserving relation between and within homogeneous buildings groups (Regnauld, 2001). Building or road patterns are remarkable distributions of elements in the map from which high-level concepts and semantics (e.g. landuse types and urban morphology) can be inferred. Such patterns can be characterized by spatial relations (e.g. proximity, similarity and continuity of these elements) and hence are visually easy to identify by a human. To identify these patterns automatically is important for automated map generalisation (Christophe and Ruas, 2002). However, it remains challenging to devise algorithms that can resemble the human level performance. The goal of this paper is to illustrate the potential of graph convolutional networks (GCN) for the identification of patterns and relations important for map generalisation with two use cases: building patterns detection, and road segment selection. Both tasks require some degree of understanding of the spatial relations between map objects. Hence, our experiments constitute a first step in exploring the capability of deep neural network for learning representations of spatial relations. Numéro de notice : C2021-045 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.5194/ica-abs-3-60-2021 Date de publication en ligne : 13/12/2021 En ligne : https://doi.org/10.5194/ica-abs-3-60-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99420

Automated conflation of digital elevation model with reference hydrographic lines / Timofey Samsonov 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) . - 40 p. Titre : Automated conflation of digital elevation model with reference hydrographic lines Type de document : Article/Communication Auteurs : Timofey Samsonov, Auteur Année de publication : 2020 Article en page(s) : 40 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] alignement [Termes IGN] cartographie hydrographique [Termes IGN] conflation [Termes IGN] données localisées [Termes IGN] données vectorielles [Termes IGN] modèle numérique de surface [Termes IGN] réseau de drainage [Termes IGN] Triangulated Irregular Network [Vedettes matières IGN] Généralisation Résumé : (auteur) Combining misaligned spatial data from different sources complicates spatial analysis and creation of maps. Conflation is a process that solves the misalignment problem through spatial adjustment or attribute transfer between similar features in two datasets. Even though a combination of digital elevation model (DEM) and vector hydrographic lines is a common practice in spatial analysis and mapping, no method for automated conflation between these spatial data types has been developed so far. The problem of DEM and hydrography misalignment arises not only in map compilation, but also during the production of generalized datasets. There is a lack of automated solutions which can ensure that the drainage network represented in the surface of generalized DEM is spatially adjusted with independently generalized vector hydrography. We propose a new method that performs the conflation of DEM with linear hydrographic data and is embeddable into DEM generalization process. Given a set of reference hydrographic lines, our method automatically recognizes the most similar paths on DEM surface called counterpart streams. The elevation data extracted from DEM is then rubbersheeted locally using the links between counterpart streams and reference lines, and the conflated DEM is reconstructed from the rubbersheeted elevation data. The algorithm developed for extraction of counterpart streams ensures that the resulting set of lines comprises the network similar to the network of ordered reference lines. We also show how our approach can be seamlessly integrated into a TIN-based structural DEM generalization process with spatial adjustment to pre-generalized hydrographic lines as additional requirement. The combination of the GEBCO_2019 DEM and the Natural Earth 10M vector dataset is used to illustrate the effectiveness of DEM conflation both in map compilation and map generalization workflows. Resulting maps are geographically correct and are aesthetically more pleasing in comparison to a straightforward combination of misaligned DEM and hydrographic lines without conflation. Numéro de notice : A2020-297 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9050334 Date de publication en ligne : 20/05/2020 En ligne : https://doi.org/10.3390/ijgi9050334 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95135 [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 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

Analyse du bilan d’erreur appliquée aux systèmes de levés hydrographiques de surface et sous-marin / Geraud Naankeu-Wati in XYZ, n° 152 (septembre - novembre 2017) 

Permalink

Tectonic and anthropogenic deformation at the Cerro Prieto geothermal step-over revealed by sentinel-1A InSAR / Xiaohua Xu in IEEE Transactions on geoscience and remote sensing, vol 55 n° 9 (September 2017)  

Permalink

New point matching algorithm using sparse representation of image patch feature for SAR image registration / Jianwei Fan in IEEE Transactions on geoscience and remote sensing, vol 55 n° 3 (March 2017)  

Permalink

Non-rigid registration of 3D point clouds under isometric deformation / Xuming Ge in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Permalink

Automatic geolocation correction of satellite imagery / Ozge C. Ozcanli in International journal of computer vision, vol 116 n° 3 (February 2016)  

Permalink

Characterisation of building alignments with new measures using C4.5 decision tree algorithm / Sinan Cetinkaya in Geodetski vestnik, vol 58 n° 3 ([01/09/2014])  

Permalink

Spacing and alignment rules for effective legend design / Zhilin Li in Cartography and Geographic Information Science, vol 41 n° 4 (September 2014)  

Permalink

Urban structure generalization in multi-agent process by use of reactional agents / Jérémy Renard in Transactions in GIS, vol 18 n° 2 (April 2014)    

Permalink

Building pattern recognition in topographic data: examples on collinear and curvilinear alignments / Xiang Zhang in Geoinformatica, vol 17 n° 1 (January 2013)  

Permalink

Multi-view scans alignment for 3D spherical mosaicing in large-scale unstructured environments / Daniela Craciun in Computer Vision and image understanding, vol 114 n° 11 (November 2010)  

Permalink