KI - Künstliche Intelligenz

, Volume 24, Issue 3, pp 207–214 | Cite as

Real-time Image-based Localization for Hand-held 3D-modeling

  • Elmar Mair
  • Klaus H. Strobl
  • Tim Bodenmüller
  • Michael Suppa
  • Darius Burschka
Fachbeitrag

Abstract

We present a self-referencing hand-held scanning device for vision-based close-range 3D-modeling. Our approach replaces external global tracking devices with ego-motion estimation directly from the camera used for reconstruction. The system is capable of online estimation of the 6DoF pose on hand-held devices with high motion dynamics especially in rotational components. Inertial information supports directly the tracking process to allow for robust tracking and feature management in highly dynamic environments. We introduce a weighting function for landmarks that contribute to the pose estimation increasing the accuracy of the localization and filtering outliers in the tracking process. We validate our approach with experimental results showing the robustness and accuracy of the algorithm. We compare the results to external global referencing solutions used in current modeling systems.

Keywords

3D modeling Visual localization Hand-held scanning Inertia aided visual tracking 

References

  1. 1.
    Bodenmueller T, Hirzinger G (2004) Online surface reconstruction from unorganized 3d-points for the DLR hand-guided scanner system. In: Proc. of 2nd symposium on 3D data processing, visualization, transmission Google Scholar
  2. 2.
    Burschka D, Hager GD (2004) V-GPS(SLAM): vision-based inertial system for mobile robots. In: IEEE international conference on robotics and automation Google Scholar
  3. 3.
    Davison AJ, Reid ID, Molton ND, Stasse O (2007) Monoslam: real-time single camera slam. IEEE Trans Pattern Anal Mach Intell. doi:10.1109/TPAMI.2007.1049
  4. 4.
    Eade E, Drummond T (2006) Scalable monocular slam. IEEE conference on computer vision and pattern recognition Google Scholar
  5. 5.
    Hartley R, Zisserman A (2003) Multiple view geometry in computer vision. Cambridge University Press, Cambridge Google Scholar
  6. 6.
    Hebert P (2001) A self-referenced hand-held range sensor. In: Proceedings of the third international conference on 3-D digital imaging and modeling, 2001 Google Scholar
  7. 7.
    Klein G, Murray D (2007) Parallel tracking and mapping for small AR workspaces. In: Sixth IEEE and ACM international symposium on mixed and augmented reality (ISMAR’07) Google Scholar
  8. 8.
    Klein G, Murray D (2008) Improving the agility of keyframe-based SLAM. In: 10th European conference on computer vision (ECCV’08), pp 802–815 Google Scholar
  9. 9.
    Mair E, Strobl KH, Suppa M, Burschka D (2009) Efficient camera-based pose estimation for real-time applications. In: IEEE/RSJ international conference on intelligent robots and systems Google Scholar
  10. 10.
    Mouragnon E, Dekeyser F, Sayd P, Lhuillier M, Dhome M (2006) Real time localization and 3d reconstruction. In: IEEE conference on computer vision and pattern recognition Google Scholar
  11. 11.
    Mourikis AI, Roumeliotis SI (2008) A dual-layer estimator architecture for long-term localization. In: Workshop on visual localization for mobile platforms. IEEE computer society conference on computer vision and pattern recognition Google Scholar
  12. 12.
    Nister D (2004) An efficient solution to the five-point relative pose problem. IEEE Trans Pattern Anal Mach Intell. doi:10.1109/TPAMI.2004.17
  13. 13.
    Pollefeys M, Koch R, Vergauwen M, Gool LV (1999) Hand-held acquisition of 3D models with a video camera. In: IEEE 2nd international conference on 3D digital imaging and modeling Google Scholar
  14. 14.
    Shi J, Tomasi C (1994) Good features to track. In: IEEE conference on computer vision and pattern recognition Google Scholar
  15. 15.
    Strobl KH, Mair E, Bodenmüller T, Kielhöfer S, Sepp W, Suppa M, Burschka D, Hirzinger G (2009) The self-referenced DLR 3D-modeler. In: IEEE/RSJ international conference on intelligent robots and systems Google Scholar
  16. 16.
    Suppa M, Kielhöfer S, Langwald J, Hacker F, Strobl K, Hirzinger G (2007) The 3d-modeller: a multi-purpose vision platform. In: IEEE international conference on robotics and automation Google Scholar
  17. 17.
    Thanh TN, Sakaguchi Y, Nagahara H, Yachida M (2006) Stereo slam using two estimators. In: IEEE international conference on robotics and biomimetics Google Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  • Elmar Mair
    • 1
  • Klaus H. Strobl
    • 2
  • Tim Bodenmüller
    • 2
  • Michael Suppa
    • 2
  • Darius Burschka
    • 1
  1. 1.Institute of Robotics and Embedded SystemsTechnische Universität München (TUM)Garching bei MünchenGermany
  2. 2.Institute of Robotic and MechatronicsGerman Aerospace Center (DLR)WesslingGermany

Personalised recommendations