Toward automatic GIS–video initial registration

And application to buildings textures computation
  • Gaël Sourimant
  • Thomas Colleu
  • Vincent Jantet
  • Luce Morin
  • Kadi Bouatouch
Article

Abstract

In the context of registration between videos and geographic information system (GIS)-based 3D building models—for instance in augmented reality applications—we propose a solution to one of the most critical problems, namely the registration initialization. Successful automatic 2D/3D matching is achieved by combining two context-dependent improvements. On one hand, we associate semantic information to the low-level primitives we used to reduce the problem complexity. On the other hand, we avoid false initial registration solutions by analyzing the convergence of the iterative pose computation in a RANSAC framework. We require that videos are acquired together with global positioning system measures. We also present how such a registration can be exploited, once it has been performed for the whole video. Textures of visible buildings are extracted from the images. A new algorithm for façade texture fusion based on statistical analysis of the texels color is presented. It allows us to remove from the final textures all occluding objects in front of the viewed building façades.

Keywords

Data registration Urban modeling Texture synthesis GPS GIS Ransac 

References

  1. 1.
    Colleu T, Sourimant G, Morin L (2008) Automatic initialization for the registration of GIS and video data. In: 3DTV 2008. Istanbul, TurkeyGoogle Scholar
  2. 2.
    Comport A (2005) Robust real-time 3D tracking of rigid and articulated objects for augmented reality and robotics. PhD thesis, Université de Rennes 1, Mention informatiqueGoogle Scholar
  3. 3.
    David P, DeMenthon D, Duraiswami R, Samet H (2002) Softposit: simultaneous pose and correspondence determination. In: ECCV (3), pp 698–714Google Scholar
  4. 4.
    David P, Dementhon D, Duraiswami R, Samet H (2004) Softposit: simultaneous pose and correspondence determination. Int J Comput Vis 59(3):259–284CrossRefGoogle Scholar
  5. 5.
    Debevec PE, Taylor CJ, Malik J (1996) Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach. Comput Graph 30:11–20CrossRefGoogle Scholar
  6. 6.
    Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395MathSciNetCrossRefGoogle Scholar
  7. 7.
    Gomez JFV, Simon G, Berger MO (2005) Calibration errors in augmented reality: a practical study. In: Proceedings of the fourth IEEE and ACM international symposium on mixed and augmented reality (ISMAR)Google Scholar
  8. 8.
    Karner K, Bauer J, Klaus A, Schindler K (2002) Metropogis: a city information system. In: ICIP02, pp III:533–536Google Scholar
  9. 9.
    Korah T, Rasmussen C (2006) Improving spatiotemporal inpainting with layer appearance models. In: International symposium on visual computingGoogle Scholar
  10. 10.
    Liu L, Stamos I (2005) Automatic 3D to 2D registration for the photorealistic rendering of urban scenes. In: CVPR ’05, pp 137–143Google Scholar
  11. 11.
    Mayer H, Bornik A, Bauer J, Karner KF, Leberl F (2001) Multiresolution texture for photorealistic rendering. In: Spring conference on computer graphicsGoogle Scholar
  12. 12.
    Ortin D, Remondino F (2005) Occlusion-free image generation for realistic texture mapping. In: 3D-ARCH 2005: virtual reconstruction and visualization of complex architecturesGoogle Scholar
  13. 13.
    Poulin P, Ouimet M, Frasson MC (1998) Interactively modeling with photogrammetry. In: Proceedings of eurographics workshop on rendering, vol 98, pp 93–104Google Scholar
  14. 14.
    Rau J, Teo T, Chen L, Tsai F, Hsiao K, Hsu W (2006) Integration of gps, GIS and photogrammetry for texture mapping in photo-realistic city modeling. In: Pacific-Rim symposium on image and video technology, pp 1283–1292Google Scholar
  15. 15.
    Reitmayr G, Drummond T (2006) Going out: robust model-based tracking for outdoor augmented reality. In: ISMAR, pp 109–118Google Scholar
  16. 16.
    Shum HY, Han M, Szeliski R (1998) Interactive construction of 3D models from panoramic mosaics. In: Proc. of CVPR’98Google Scholar
  17. 17.
    Sourimant G, Morin L, Bouatouch K (2007) GPS, GIS and video registration for building reconstruction. In: ICIP 2007, 14th IEEE international conference on image processing. San Antonio, USAGoogle Scholar
  18. 18.
    Taillandier F (2000) Texture and relief estimation from multiple georeferenced images. Master’s thesis, Ecole PolytechniqueGoogle Scholar
  19. 19.
    Teller S, Antone M, Bodnar Z, Bosse M, Coorg S, Jethwa M, Master N (2003) Calibrated, registered images of an extended urban area. Int J Comput Vis 53(1):93–107CrossRefGoogle Scholar
  20. 20.
    Wang X, Totaro S, Taillandier F, Hanson A, Teller S (2002) Recovering facade texture and microstructure from real-world images. In: European conference on computer visionGoogle Scholar

Copyright information

© Institut Télécom and Springer-Verlag 2011

Authors and Affiliations

  • Gaël Sourimant
    • 1
  • Thomas Colleu
    • 1
  • Vincent Jantet
    • 1
  • Luce Morin
    • 2
  • Kadi Bouatouch
    • 3
  1. 1.INRIA Rennes Bretagne AtlantiqueRennes CedexFrance
  2. 2.IETR/INSA RennesRennesFrance
  3. 3.Université de Rennes 1Rennes CedexFrance

Personalised recommendations