Advertisement

Motion — Stereo Integration for Depth Estimation

  • Christoph Strecha
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2351)

Abstract

Depth extraction with a mobile stereo system is described. The stereo setup is precalibrated, but the system extracts its own motion. Emphasis lies on the integration of the motion and stereo cues. It is guided by the relative confidence that the system has in these cues. This weighing is fine-grained in that it is determined for every pixel at every iteration. Reliable information spreads fast at the expense of less reliable data, both in terms of spatial communication and in terms of exchange between cues. The resulting system can handle large displacements, depth discontinuities and occlusions. Experimental results corroborate the viability of the approach.

Keywords

Depth Estimation Stereo Pair Epipolar Line Radial Distortion Depth Discontinuity 
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]
    F. Dornaika and R. Chung: Stereo correspondence from motion correspondence. CVPR, vol. 1, pp. 70–75, 1999.Google Scholar
  2. [2]
    P.K. Ho and R. Chung: Stereo-motion with stereo and motion in complement? PAMI, vol. 22, no. 2, pp. 215–220, 2000.Google Scholar
  3. [3]
    Z. Zhang, Q.T. Luong, and O. Faugeras: Motion of an uncalibrated stereo rig: Self-calibration and metric reconstruction. IEEE Trans. Robotics and Automation, vol. 12, no. 1, pp. 103–113, feb 1996.CrossRefGoogle Scholar
  4. [4]
    R. Mandelbaum, G. Salgian, and H. Sawhney: Correlationbased estimation of egomotion and structure from motion and stereo. ICCV, pp. 544–550, 1999.Google Scholar
  5. [5]
    G.P. Stein and A. Shashua: Direct estimation of motion and extended scene structure from a moving stereo rig. CVPR, pp. 211–218, 1998.Google Scholar
  6. [6]
    G. Sudhir, S. Banerjee, R. Bahl, and K. Biswas: A cooperative integration of stereopsis and optic flow computation. J. Opt. Soc. Am. A, vol. 12, pp. 2564, 1995.Google Scholar
  7. [7]
    M. Proesmans, L. Van Gool, E. Pauwels, and A. Oosterlinck: Determination of optical flow and its discontinuities using non-linear diffusion. ECCV, vol. 2, pp. 295–304, 1994.Google Scholar
  8. [8]
    A. Zisserman, P.A. Beardsley, and I.D. Reid: Metric calibration of a stereo rig. In Proc. IEEE Workshop on Representation of Visual Scenes, pp. 93–100, 1995.Google Scholar
  9. [9]
    G.P. Stein: Lens distortion calibration using point correspondences. CVPR, pp. 143–148, 1997.Google Scholar
  10. [10]
    J. Shah: A nonlinear diffusion model for discontinuous disparity and half-occlusions in stereo. CVPR, pp. 34–40, 1993.Google Scholar
  11. [11]
    M. Proesmans, E. Pauwels, and L. Van Gool: in Geometry-driven diffusion in computer vision, ed. Bart M. ter Haar Romeny Kluwer, 1994.Google Scholar
  12. [12]
    L. Alvarez, R. Deriche, J. Sanchez, and J. Weickert: Dense disparity map estimation respecting image discontinuities: pde and scalespace based approach. Tech. Rep. RR-3874, INRIA, 2000.Google Scholar
  13. [13]
    J. Weickert and C. Schnörr: Variational optic flow computation with a spatio-temporal smoothness constraint. Tech. Rep. 15, University of Mannheim, 2000.Google Scholar
  14. [14]
    J. Weickert, B.M. ter Haar Romeny, and M.A. Viergever: Efficent and reliable schemes for nonlinear diffusion filtering. IEEE Transactions on Image Processing, vol. 7, no. 3, pp. 398–410, 1998.CrossRefGoogle Scholar
  15. [15]
    D. Marr and T. Poggio: A theory of human steropsis. Proc. Royal Soc. B, vol. 204, pp. 301–328, 1979.CrossRefGoogle Scholar
  16. [16]
    D.J. Heeger and A.D. Jepson: Subspace methods for recovering rigid motion I:algorithm and implemenation. IJCV, vol. 7, no. 2, pp. 95–117, 1992.CrossRefGoogle Scholar
  17. [17]
    M. Irani: Multi-frame optical flow estimation using subspace constraints. ICCV, pp. 626–633, 1999.Google Scholar
  18. [18]
    G. Van Meerbergen, M. Vergauwen, M. Pollefeys, and L. Van Gool: A hierarchical stereo algorithm using dynamic programming. IEEE Workshop on Stereo and Multi-Baseline Vision, pp. 166–174, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Christoph Strecha
    • 1
  • Luc Van Gool
    • 1
  1. 1.KU Leuven ESAT/PSILeuvenBelgium

Personalised recommendations