Centre de documentation
scientifique

Improving trajectory estimation using 3D city models and kinematic point clouds / Lucas Lucks in Transactions in GIS, Vol 25 n° 1 (February 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 1 (February 2021) . - pp 238 - 260 Titre : Improving trajectory estimation using 3D city models and kinematic point clouds Type de document : Article/Communication Auteurs : Lucas Lucks, Auteur ; Lasse Klingbeil, Auteur ; Lutz Plümer, Auteur ; Youness Dehbi, Auteur Année de publication : 2021 Article en page(s) : pp 238 - 260 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Navigation et positionnement [Termes IGN] algorithme ICP [Termes IGN] bruit (théorie du signal) [Termes IGN] centrale inertielle [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] interpolation [Termes IGN] milieu urbain [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] modèle sémantique de données [Termes IGN] navigation autonome [Termes IGN] semis de points Résumé : (Auteur) Accurate and robust positioning of vehicles in urban environments is of high importance for autonomous driving or mobile mapping. In mobile mapping systems, a simultaneous mapping of the environment using laser scanning and an accurate positioning using global navigation satellite systems are targeted. This requirement is often not guaranteed in shadowed cities where global navigation satellite system signals are usually disturbed, weak or even unavailable. We propose a novel approach which incorporates prior knowledge (i.e., a 3D city model of the environment) and improves the trajectory. The recorded point cloud is matched with the semantic city model using a point‐to‐plane iterative closest point method. A pre‐classification step enables an informed sampling of appropriate matching points. Random forest is used as classifier to discriminate between facade and remaining points. Local inconsistencies are tackled by a segmentwise partitioning of the point cloud where an interpolation guarantees a seamless transition between the segments. The general applicability of the method implemented is demonstrated on an inner‐city data set recorded with a mobile mapping system. Numéro de notice : A2021-188 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12719 Date de publication en ligne : 02/01/2021 En ligne : https://doi.org/10.1111/tgis.12719 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97157 [article]

Statistical Relational Learning of Grammar Rules for 3D Building Reconstruction / Youness Dehbi in Transactions in GIS, vol 21 n° 1 (February 2017)  

Public [article]  inTransactions in GIS > vol 21 n° 1 (February 2017) . - pp 134 – 150 Titre : Statistical Relational Learning of Grammar Rules for 3D Building Reconstruction Type de document : Article/Communication Auteurs : Youness Dehbi, Auteur ; Fabian Hadiji, Auteur ; Gerhard Gröger, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 134 – 150 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage dirigé [Termes IGN] arbre de décision [Termes IGN] modèle sémantique de données [Termes IGN] reconstruction 3D du bâti [Termes IGN] restitution lasergrammétrique [Termes IGN] semis de points [Termes IGN] traitement d'image Résumé : (auteur) The automatic interpretation of 3D point clouds for building reconstruction is a challenging task. The interpretation process requires highly structured models representing semantics. Formal grammars can describe structures as well as the parameters of buildings and their parts. We propose a novel approach for the automatic learning of weighted attributed context-free grammar rules for 3D building reconstruction, supporting the laborious manual design of rules. We separate structure from parameter learning. Specific Support Vector Machines (SVMs) are used to generate a weighted context-free grammar and predict structured outputs such as parse trees. The grammar is extended by parameters and constraints, which are learned based on a statistical relational learning method using Markov Logic Networks (MLNs). MLNs enforce the topological and geometric constraints. MLNs address uncertainty explicitly and provide probabilistic inference. They are able to deal with partial observations caused by occlusions. Uncertain projective geometry is used to deal with the uncertainty of the observations. Learning is based on a large building database covering different building styles and façade structures. In particular, a treebank that has been derived from the database is employed for structure learning. Numéro de notice : A2017-163 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12200 En ligne : http://dx.doi.org/10.1111/tgis.12200 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84693 [article]