A Comparison of Iterative 2D-3D Pose Estimation Methods for Real-Time Applications

  • Daniel Grest
  • Thomas Petersen
  • Volker Krüger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5575)


This work compares iterative 2D-3D Pose Estimation methods for use in real-time applications. The compared methods are available for public as C++ code. One method is part of the openCV library, namely POSIT. Because POSIT is not applicable for planar 3D-point configurations, we include the planar POSIT version. The second method optimizes the pose parameters directly by solving a Non-linear Least Squares problem which minimizes the reprojection error. For reference the Direct Linear Transform (DLT) for estimation of the projection matrix is inlcuded as well.


Point Cloud Initial Guess Augmented Reality Rotational Error Translation Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Araujo, H., Carceroni, R., Brown, C.: A Fully Projective Formulation to Improve the Accuracy of Lowe’s Pose Estimation Algorithm. Journal of Computer Vision and Image Understanding 70(2) (1998)Google Scholar
  2. 2.
    De Menthon, D.: (2008),
  3. 3.
    David, P., Dementhon, D., Duraiswami, R., Samet, H.: SoftPOSIT: Simultaneous Pose and Correspondence Determination. Int. J. Comput. Vision 59(3), 259–284 (2004)CrossRefzbMATHGoogle Scholar
  4. 4.
    DeMenthon, D.F., Davis, L.S.: Model-Based Object Pose in 25 Lines of Code. International Journal of Computer Vision 15, 335–343 (1995)CrossRefGoogle Scholar
  5. 5.
    Grest, D.: Marker-Free Human Motion Capture in Dynamic Cluttered Environments from a Single View-Point. PhD thesis, MIP, Uni. Kiel, Kiel, Germany (2007)Google Scholar
  6. 6.
    Intel. openCV: Open Source Computer Vision Library (2008),
  7. 7.
    Lepetit, V., Fua, P.: Monocular Model-Based 3D Tracking of Rigid Objects: A Survey. Foundations and Trends in Computer Graphics and Vision 1(1), 1–104 (2005)CrossRefGoogle Scholar
  8. 8.
    MIP Group Kiel. Basic Image AlgorithmS (BIAS) open-source-library, C++ (2008),
  9. 9.
    Moreno-Noguer, F., Lepitit, V., Fua, P.: Accurate Non-Iterative O(n) Solution to the PnP Problem. In: ICCV, Brazil (2007)Google Scholar
  10. 10.
    Oberkampf, D., DeMenthon, D.F., Davis, L.S.: Iterative pose estimation using coplanar feature points. CVIU 63(3), 495–511 (1996)Google Scholar
  11. 11.
    Williams, B., Klein, G., Reid, I.: Real-time SLAM Relocalisation. In: Proc. of Internatinal Conference on Computer Vision (ICCV), Brazil (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Daniel Grest
    • 1
  • Thomas Petersen
    • 1
  • Volker Krüger
    • 1
  1. 1.Computer Vision Intelligence LabAalborg University CopenhagenDenmark

Personalised recommendations