Camera Motion Parameter Estimation Technique Using 2D Homography and LM Method Based on Projective and Permutation Invariant Features

  • JeongHee Cha
  • GyeYoung Kim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3984)


Precise camera calibration is a core requirement of location system and augmented reality. In this paper, we propose a method to estimate camera motion parameter based on invariant point features. Typically, feature information of image has drawback, it is variable to camera viewpoint, and therefore information quantity increases after time. The LM (Levenberg-Marquardt) method using nonlinear minimum square evaluation also has a weak point, which has different iteration number for approaching the minimal point according to the initial values and convergence time increases if the process run into a local minimum. In order to complement these shortfalls, we, first propose constructing invariant features of geometry using similarity function and Graham search method. Secondly, we propose a two-stage camera parameter calculation method to improve accuracy and convergence by using 2D homography and LM method. In the experiment, we compare and analyze the proposed method with existing method to demonstrate the superiority of the proposed algorithms.


Convex Hull Feature Model Augmented Reality Corner Point Invariant Vector 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Drewniok, C., Rohr, K.: High-Precision Localization of Circular Landmarks in Aerial Images. In: Proc. 17. Dagm-Symposium, Musterkennung 1995, Bielefeld, Germany, September 13-15, pp. 594–601 (1995)Google Scholar
  2. 2.
    Hagan, M.T., Menhaj, M.B.: Training Feedback Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks 5(6) (November 1994)Google Scholar
  3. 3.
    Kanatani, K.: Computational Projective Geometry. In: CVGIP:Image Understanding Workshop, Washington, DC, pp. 745–753 (1993)Google Scholar
  4. 4.
    Lenz, R., Meer, P.: Point Configuration Invariants under Simultaneous Projective and Permutation Transformations. Pattern Recognition 27(11), 1523–1532 (1994)CrossRefGoogle Scholar
  5. 5.
    Birchfield, S.: KLT:An Implementation of the Kanade-Lucas-Tomasi Feature Tracker,
  6. 6.
    Trahanias, P.E., Velissaris, S., Garavelos, T.: Visual Landmark Extraction and Recognition for Autonomous Robot Navigation. In: Proc. IROS 1997, pp. 1036–1042 (1997)Google Scholar
  7. 7.
    Barnett, V.: The Ordering of Multivariate Data. Jornal of Royal Statistical Society A, Part 3 139, 318–343 (1976)MathSciNetGoogle Scholar
  8. 8.
    Vicente, M.A., Gil, P., Reinoso., T.F.: Object Recognition by Means of Projective Invariants Considering Corner-Points. In: Proc. SPIE, vol. 4570, pp. 105–112 (2002)Google Scholar
  9. 9.
    Mundy, J.L., Zisserman, A.: Geometric Invariance in Computer Vision. MIT Press, Cambridge (1992)Google Scholar
  10. 10.
    Fishler, M.A., Bolles, R.C.: Random Sample Consensus: A Paradigm for Model Fitting with Application to Image Analysis and Automated Cartography. Commumination ACM 24(6), 381–395 (1981)CrossRefGoogle Scholar
  11. 11.
    SeokWoo, J.: Shot Transition Detection by Compensating Camera Operations. Soongsil University Press (2000)Google Scholar
  12. 12.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • JeongHee Cha
    • 1
  • GyeYoung Kim
    • 1
  1. 1.School of ComputingSoongsil UniversitySeoulKorea

Personalised recommendations