Advertisement

Quantitative Depth Recovery from Time-Varying Optical Flow in a Kalman Filter Framework

  • John Barron
  • Wang Kay Jacky Ngai
  • Hagen Spies
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2616)

Abstract

We present a Kalman filter framework for recovering depth from the time-varying optical flow fields generated by a camera translating over a scene by a known amount. Synthetic data made from ray traced cubical, cylinderal and spherical primitives are used in the optical flow calculation and allow a quantitative error analysis of the recovered depth.

Keywords

Depth Map Depth from Optical Flow Kalman Filter 3D Camera Motion Quantitative Error Analysis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Barron J. L., Jepson A.D. and Tsotsos J.K. (1990), “The Feasibility of Motion and Structure From Noisy Time-Varying Image Velocity Information”, Int. Journal of Computer Vision, 5:3, pp. 239–269.CrossRefGoogle Scholar
  2. [2]
    Barron J. L. and Eagleson R. (1996), “Recursive Estimation of Time-Varying Motion and Structure Parameters”, Pattern Recognition, Vol. 29, No. 5, May, pp. 797–818.CrossRefGoogle Scholar
  3. [3]
    Barron J. L. and Khurana M. (1997), Determining optical flow for large motions Using Parametric Models in a Hierarchical Framework, Vision Interface, Kelowna, B. C., May, pp 47–56.Google Scholar
  4. [4]
    Black M. J. and Anandan P. (1996), “The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow fields”, Computer Vision and Image Understanding, 63:1, pp. 75–104.CrossRefGoogle Scholar
  5. [5]
    Faugeras O.D. and Lustman F. (1985), “Let Us Suppose that the World is Piecewise Planar”, 3 rd Intl. Symposium on Robotics, France, pp. 33–39Google Scholar
  6. [6]
    Gelb A. (1974), “Applied Optimal Estimation”, MIT Press.Google Scholar
  7. [7]
    Kalman, R. E. (1960), “A new approach to linear filtering and prediction problems”, Trans. of the ASME-Journal of Basic Engineering, pp 35–45.Google Scholar
  8. [8]
    Lucas, B. and Kanade, T. (1981), “An iterative image registration technique with an application to stereo vision”, Proc. DARPA IU Workshop, pp. 121–130.Google Scholar
  9. [9]
    Heel J. (1990), “Direct Dynamic Motion Vision”, Proc. IEEE Conf. Robotics and Automation, pp. 1142–1147.Google Scholar
  10. [10]
    Hung Y. S. and Ho H.T. (1999), “A Kalman Filter Approach to Direct Depth Estimation Incorporating Surface Structure”, IEEE PAMI, June, pp. 570–576.Google Scholar
  11. [11]
    Longuet-Higgins H.-C. and Prazdny K, (1980), “The Interpretation of a Moving Retinal Image”, Proc. R. Soc. Lond B 208, pp. 385–397.Google Scholar
  12. [12]
    Matthies L., Szeliski R. and Kanade T. (1989), “Kalman Filter-Based Algorithms for Estimating Depth from Image Sequences”, Int. J. Computer Vision 3:3, pp. 209–238.CrossRefGoogle Scholar
  13. [13]
    Simoncelli E.P. (1994), “Design of multi-dimensional derivative filters”, IEEE Int. Conf. Image Processing, Vol. 1, pp 790–793.Google Scholar
  14. [14]
    Press W.H., Flannery B.P., Teukolsky S.A., and Vetterling W.T. (1992), “Numerical Recipes in C (2nd edition)”, Cambridge University Press, pp 671–675.Google Scholar
  15. [15]
    Xiong Y. and Shafer S. (1995), “Dense Structure from a Dense Optical Flow Sequence”, Int. Symposium on Computer Vision, Coral Gables, Florida, pp 1–6.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • John Barron
    • 1
  • Wang Kay Jacky Ngai
    • 1
  • Hagen Spies
    • 2
  1. 1.Department of Computer ScienceUniversity of Western OntarioLondon, OntarioCanada
  2. 2.ICG-III: PhytosphereResearch Center JülichJülichGermany

Personalised recommendations