Détail de l'auteur
Auteur Luc Van Gool |
Documents disponibles écrits par cet auteur (5)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Efficient edge-aware surface mesh reconstruction for urban scenes / András Bódis-Szomorú in Computer Vision and image understanding, vol 157 (April 2017)
[article]
Titre : Efficient edge-aware surface mesh reconstruction for urban scenes Type de document : Article/Communication Auteurs : András Bódis-Szomorú, Auteur ; Hayko Riemenschneider, Auteur ; Luc Van Gool, Auteur Année de publication : 2017 Article en page(s) : pp 3 - 24 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] carte de profondeur
[Termes IGN] données clairsemées
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] maillage par triangles
[Termes IGN] modèle 3D de l'espace urbain
[Termes IGN] modèle numérique de surface
[Termes IGN] reconstruction d'objet
[Termes IGN] scène urbaine
[Termes IGN] segmentation d'image
[Termes IGN] structure-from-motion
[Termes IGN] triangulation de DelaunayRésumé : (auteur) We propose an efficient approach for building compact, edge-preserving, view-centric triangle meshes from either dense or sparse depth data, with a focus on modeling architecture in large-scale urban scenes. Our method constructs a 2D base mesh from a preliminary view partitioning, then lifts the base mesh into 3D in a fast vertex depth optimization. Different view partitioning schemes are proposed for imagery and dense depth maps. They guarantee that mesh edges are aligned with crease edges and discontinuities. In particular, we introduce an effective plane merging procedure with a global error guarantee in order to maximally compact the resulting models. Moreover, different strategies for detecting and handling discontinuities are presented. We demonstrate that our approach provides an excellent trade-off between quality and compactness, and is eligible for fast production of polyhedral building models from large-scale urban height maps, as well as, for direct meshing of sparse street-side Structure-from-Motion (SfM) data. Numéro de notice : a2017-431 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.cviu.2016.06.002 En ligne : https://doi.org/10.1016/j.cviu.2016.06.002 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86332
in Computer Vision and image understanding > vol 157 (April 2017) . - pp 3 - 24[article]ATLAS: A three-layered approach to facade parsing / Markus Mathias in International journal of computer vision, vol 118 n° 1 (May 2016)
[article]
Titre : ATLAS: A three-layered approach to facade parsing Type de document : Article/Communication Auteurs : Markus Mathias, Auteur ; Anđelo Martinović, Auteur ; Luc Van Gool, Auteur Année de publication : 2016 Article en page(s) : pp 22 – 48 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] analyse d'image numérique
[Termes IGN] analyse syntaxique
[Termes IGN] appariement sémantique
[Termes IGN] classificateur paramétrique
[Termes IGN] couche
[Termes IGN] façade
[Termes IGN] intégration de données
[Termes IGN] méta connaissance
[Termes IGN] reconstruction 2D du bâti
[Termes IGN] test de performanceRésumé : (auteur) We propose a novel approach for semantic segmentation of building facades. Our system consists of three distinct layers, representing different levels of abstraction in facade images: segments, objects and architectural elements. In the first layer, the facade is segmented into regions, each of which is assigned a probability distribution over semantic classes. We evaluate different state-of-the-art segmentation and classification strategies to obtain the initial probabilistic semantic labeling. In the second layer, we investigate the performance of different object detectors and show the benefit of using such detectors to improve our initial labeling. The generic approaches of the first two layers are then specialized for the task of facade labeling in the third layer. There, we incorporate additional meta-knowledge in the form of weak architectural principles, which enforces architectural plausibility and consistency on the final reconstruction. Rigorous tests performed on two existing datasets of building facades demonstrate that we outperform the current state of the art, even when using outputs from lower layers of the pipeline. Finally, we demonstrate how the output of the highest layer can be used to create a procedural building reconstruction. Numéro de notice : A2016--150 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-015-0868-z En ligne : https://doi.org/10.1007/s11263-015-0868-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85918
in International journal of computer vision > vol 118 n° 1 (May 2016) . - pp 22 – 48[article]Automatic detection and tracking of pedestrians from a moving stereo rig / Konrad Schindler in ISPRS Journal of photogrammetry and remote sensing, vol 65 n° 6 (November - December 2010)
[article]
Titre : Automatic detection and tracking of pedestrians from a moving stereo rig Type de document : Article/Communication Auteurs : Konrad Schindler, Auteur ; A. Ess, Auteur ; B. Liebe, Auteur ; Luc Van Gool, Auteur Année de publication : 2010 Article en page(s) : pp 523 - 537 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] détection automatique
[Termes IGN] détection de piéton
[Termes IGN] données localisées
[Termes IGN] itinéraire
[Termes IGN] milieu urbain
[Termes IGN] modèle 3D de l'espace urbain
[Termes IGN] piéton
[Termes IGN] reconstruction 3D
[Termes IGN] séquence d'images
[Termes IGN] trajet (mobilité)
[Termes IGN] vidéo numériqueRésumé : (Auteur) We report on a stereo system for 3D detection and tracking of pedestrians in urban traffic scenes. The system is built around a probabilistic environment model which fuses evidence from dense 3D reconstruction and image-based pedestrian detection into a consistent interpretation of the observed scene, and a multi-hypothesis tracker to reconstruct the pedestrians’ trajectories in 3D coordinates over time. Experiments on real stereo sequences recorded in busy inner-city scenarios are presented, in which the system achieves promising results. Numéro de notice : A2010-485 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2010.06.006 En ligne : https://doi.org/10.1016/j.isprsjprs.2010.06.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30678
in ISPRS Journal of photogrammetry and remote sensing > vol 65 n° 6 (November - December 2010) . - pp 523 - 537[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 081-2010061 SL Revue Centre de documentation Revues en salle Disponible
Titre : Generalised linear pose estimation Type de document : Article/Communication Auteurs : A. Ess, Auteur ; Alexander Neubeck, Auteur ; Luc Van Gool, Auteur Editeur : The British Machine Vision Association Press (BMVA) Année de publication : 2007 Conférence : BMVC 2007, British Machine Vision Conference 10/09/2007 13/09/2007 Coventry Royaume-Uni OA Proceedings Importance : pp 361 - 370 ISBN/ISSN/EAN : 978-0-902683-81-5 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] estimation de pose
[Termes IGN] vision par ordinateurRésumé : (auteur) This paper investigates several aspects of 3D-2D camera pose estimation, aimed at robot navigation in poorly-textured scenes. The major contribution is a fast, linear algorithm for the general case with six or more points. We show how to specialise this to work with only four or five points, which is of utmost importance in a test and hypothesis framework. Our formulation allows for an easy inclusion of lines, as well as the handling of other camera geometries, such as stereo rigs. We also treat the special case of planar motion, a valid restriction for most indoor environments. We conclude the paper with extensive simulated tests and a real test case, which substantiate the algorithm’s usability for our application domain. Note de contenu : 1- Tracking
2- Surveillance - Registration
3- Biometrics
4- SegmentationNuméro de notice : C2007-048 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Communication DOI : sans En ligne : http://www.bmva.org/bmvc/2007/papers/paper-89.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93134 Virtualising the 3D real world: automatic method for the acquisition of detailed 3D models from image sequences / Marc Pollefeys in GIM international, vol 14 n° 4 (April 2000)
[article]
Titre : Virtualising the 3D real world: automatic method for the acquisition of detailed 3D models from image sequences Type de document : Article/Communication Auteurs : Marc Pollefeys, Auteur ; Luc Van Gool, Auteur Année de publication : 2000 Article en page(s) : 3 p. ; pp 12 - 15 Note générale : Bibliographie 3 ref Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] étalonnage d'instrument
[Termes IGN] langage de modélisation
[Termes IGN] modélisation 3D
[Termes IGN] photogrammétrie numérique
[Termes IGN] visualisation 3DRésumé : (Auteur) The author propose an approach to automatic recovery of a realistic 3D surface from photos or videos. There is no need whatsoever for measurements in the scene or calibration procedures. It is just as easy to model a small object (using a macro lens), as to model a complete building or even a whole landscape. The method thus offers a previously unknown flexilbility in 3D model acquisition, accompanied by a decrease in cost. This flexibility opens the way to many new applications. Copyright GITC Numéro de notice : A2000-053 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21473
in GIM international > vol 14 n° 4 (April 2000) . - 3 p. ; pp 12 - 15[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 061-00041 RAB Revue Centre de documentation En réserve L003 Disponible