Advertisement

Global Pose Estimation of Multiple Cameras with Particle Filters

  • Ryuichi Ueda
  • Stefanos Nikolaidis
  • Akinobu Hayashi
  • Tamio Arai

Abstract

Though image processing algorithms are sophisticated and provided as software libraries, it is still difficult to assure that complicated programs can work in various situations. In this paper, we propose a novel global pose estimation method for network cameras to actualize auto-calibration. This method uses native information from images. The sets of partial information are integrated with particle filters. Though some kinds of limitation still exist in the method, we can verify that the particle filters can deal with the nonlinearity of estimation with the experiment.

Keywords

Particle Filter Translation Vector Image Processing Algorithm Multiple Camera Rotational 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bradski, G., Kaehler, A. (eds.): Learning OpenCV: Computer Vision With the Opencv Library. SOreilly (2008)Google Scholar
  2. 2.
    Tsai, R.: A versatile camera calibration technique for high accuracy 3D machine vision metrology using off-the-shelf TV camera and lenses. IEEE Journal of Robotics and Automation 3(4), 323–344 (1987)CrossRefGoogle Scholar
  3. 3.
    Horn, B.K.P.: Closed-form solution of absolute orientation using unit quaternions. Optical Society of America A 4(4), 629–642 (1987)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Thrun, S., Burgard, W., Fox, D.: Probabilistic ROBOTICS. MIT Press, Cambridge (2005)zbMATHGoogle Scholar
  5. 5.
    Ueda, R., et al.: Expansion Resetting for Recovery from Fatal Error in Monte Carlo Localization – Comparison with Sensor Resetting Methods. In: Proc. of IROS, pp. 2481–2486 (2004)Google Scholar
  6. 6.
    Lenser, S., Veloso, M.: Sensor resetting localization for poorly modelled robots. In: Proc. of IEEE ICRA, pp. 1225–1232 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ryuichi Ueda
    • 1
  • Stefanos Nikolaidis
    • 1
  • Akinobu Hayashi
    • 1
  • Tamio Arai
    • 1
  1. 1.Dept. of Precision EngineeringUniv. of TokyoTokyo 

Personalised recommendations