Géolocalisation en milieu urbain par appariement entre une collection d'images et un SIG 2D

Nous proposons un outil de geolocalisation combinant l’extraction d’information sur des images de facades et les requetes dans un Systeme d’Information Geographique 2D (SIG). Sur des photographies de scenes urbaines, nous calculons les angles et les rapports des lar- geurs entre les facades reconnues. Nous calculons aussi les incertitudes sur ces elements geo- metriques en fonction des erreurs de mesure dans l’image, puis nous les transformons en tole- rances dans des requetes dans un SIG. Un ensemble de poses est alors genere. Pour eliminer les poses incorrectes, nous verifions la coherence de chaque pose avec les couches route et bâ- timent du SIG, et nous combinons les informations issues de plusieurs images. L’utilisation de tolerances dans les requetes garantit que la pose correcte n’est jamais eliminee. Nous montrons sur des exemples reels qu’en utilisant un SIG a jour, on peut determiner la pose correcte.

[1]  Myriam Servières,et al.  Pose computation based on Correspondence between 2D GIS and Street Images , 2009 .

[2]  Michael Batty,et al.  3-D GIS: Virtual London and beyond , 2006 .

[3]  Myriam Servières,et al.  Outdoor Localization Approach Based on Image / GIS Correspondence Using a Simple 2D Building Layer , 2008 .

[4]  Ian D. Reid,et al.  A plane measuring device , 1999, Image Vis. Comput..

[5]  Roberto Cipolla,et al.  An Image-Based System for Urban Navigation , 2004, BMVC.

[6]  Norbert Haala,et al.  A multi-sensor system for positioning in urban environments , 2003 .

[7]  Luc Van Gool,et al.  Fast wide baseline matching for visual navigation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[8]  Michel Dhome,et al.  Architectural Reconstruction with Multiple Views and Geometric Constraints , 2003, BMVC.

[9]  Suya You,et al.  A robust hybrid tracking system for outdoor augmented reality , 2004, IEEE Virtual Reality 2004.

[10]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Suya You,et al.  Tracking with omni-directional vision for outdoor AR systems , 2002, Proceedings. International Symposium on Mixed and Augmented Reality.

[12]  Roberto Cipolla,et al.  A system for automatic pose-estimation from a single image in a city scene , 2002 .

[13]  Luce Morin,et al.  Gps, Gis and Video Fusion for Urban Modeling , 2007 .

[14]  Tom Drummond,et al.  Going out: robust model-based tracking for outdoor augmented reality , 2006, 2006 IEEE/ACM International Symposium on Mixed and Augmented Reality.

[15]  Hugh F. Durrant-Whyte,et al.  Simultaneous Localization, Mapping and Moving Object Tracking , 2007, Int. J. Robotics Res..

[16]  Reinhard Koch,et al.  Extraction of 3D freeform surfaces as visual landmarks for real-time tracking , 2007, Journal of Real-Time Image Processing.

[17]  Konrad Schindler,et al.  Towards Feature-Based Building Reconstruction from Images , 2003, WSCG.

[18]  Franck Jung,et al.  Détection automatique des points de fuite et calcul de leur incertitude à l'aide de la géomét rie projective Automatic detection of vanishing points and their uncertainty based on projective geometry , 2008 .

[19]  Florent Lafarge,et al.  Modèles stochastiques pour la reconstruction tridimensionnelle d'environnements urbains. (Stochastic approaches for 3D building reconstruction) , 2007 .

[20]  Thomas Leduc,et al.  GDMS-R: A mixed SQL to manage raster and vector data , 2009 .

[21]  Lucas Paletta,et al.  Urban Object Recognition from Informative Local Features , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[22]  Luc Van Gool,et al.  Image-based procedural modeling of facades , 2007, SIGGRAPH 2007.

[23]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[24]  Wei Zhang,et al.  Video Compass , 2002, ECCV.

[25]  Harald Ganster,et al.  Hybrid Tracking for Outdoor Augmented Reality Applications , 2002, IEEE Computer Graphics and Applications.

[26]  Roberto Cipolla,et al.  Building Architectural Models from Many Views Using Map Constraints , 2002, ECCV.

[27]  Philip David,et al.  SoftPOSIT: Simultaneous Pose and Correspondence Determination , 2002, ECCV.

[28]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[29]  Venkataraman Sundareswaran,et al.  Model-based visual tracking for outdoor augmented reality applications , 2002, Proceedings. International Symposium on Mixed and Augmented Reality.