Advertisement

Dramatic Improvements to Feature Based Stereo

  • V. N. Smelyansky
  • R. D. Morris
  • F. O. Kuehnel
  • D. A. Maluf
  • P. Cheeseman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2351)

Abstract

The camera registration extracted from feature based stereo is usually considered sufficient to accurately localize the 3D points. However, for natural scenes the feature localization is not as precise as in man-made environments. This results in small camera registration errors. We show that even very small registration errors result in large errors in dense surface reconstruction.

We describe a method for registering entire images to the inaccurate surface model. This gives small, but crucially important improvements to the camera parameters. The new registration gives dramatically better dense surface reconstruction.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. Foley, A. van Dam, S. Finer, and J. Hughes. Computer Graphics, principles and practice. Addison-Wesley, 2nd ed. edition, 1990.Google Scholar
  2. 2.
    A.L. Yuille, D. Snow, R. Epstein and P.N. Belhumeur Determining Generative Models of Objects Under Varying Illumination: Shape and Albedo from Multiple Images Using SVD and Integrability. International Journal of Computer Vision, 35(3), 203–222, 1999.CrossRefGoogle Scholar
  3. 3.
    P. Fua and Y.G. Leclerc Object-Centered Surface Reconstruction: Combining Multi-Image Stereo and Shading. International Journal of Computer Vision. September 1995.Google Scholar
  4. 4.
    P. Fua and Y.G. Leclerc Registration Without Correspondences. International Conference on Computer Vision and Pattern Recognition, Seattle, WA, pp. 121–128, Jun 1994.Google Scholar
  5. 5.
    V.N. Smelyanskiy, P. Cheeseman, D.A. Maluf and R.D. Morris Bayesian Super-Resolved Surface Reconstruction from Images. Proceedings of International Conference on Computer Vision and Pattern Recognition, June 2000Google Scholar
  6. 6.
    J. Bernardo and A. Smith. Bayesian Theory. Wiley, Chichester, New York, 1994.zbMATHGoogle Scholar
  7. 7.
    K. Weiler and P. Atherton. Hidden Surface Removal Using Polygon Area Sorting Proceedings of SIGGRAPH, pp 214–222, 1977.Google Scholar
  8. 8.
    E. Catmull A Hidden-Surface Algorithm, with Anti-Aliasing Proceedings of SIGGRAPH, pp 6–11, 1978.Google Scholar
  9. 9.
    O. Faugeras. Three-Dimensional Computer Vision. MIT Press, 1993.Google Scholar
  10. 10.
    Z. Zhang. A Flexible New Technique for Camera Calibration. Technical Report MSR-TR-98-71, Microsoft Research, Redmond, Washington.Google Scholar
  11. 11.
    C. Harris. A Combined Corner and Edge Detector. Proceedings of the Alvey Vision Conference, pp 189–192, 1987.Google Scholar
  12. 12.
    Z. Zhang, R. Deriche, O. Faugeras, and Q.T. Luong. A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry. AI Journal, vol. 78, pp 87–119, 1994.Google Scholar
  13. 13.
    V.N. Smelyanskiy, R.D. Morris, D.A. Maluf and P. Cheeseman, (Almost) Featureless Stereo-Calibration and Dense 3D Reconstruction Using Whole Image Operations. Technical Report TR01-26, 2001, RIACS. http://www.riacs.edu

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • V. N. Smelyansky
    • 1
  • R. D. Morris
    • 1
  • F. O. Kuehnel
    • 1
  • D. A. Maluf
    • 1
  • P. Cheeseman
    • 1
  1. 1.NASA Ames Research CenterMoffett FieldUSA

Personalised recommendations