Skip to main content

Parallax geometry of pairs of points for 3D scene analysis

Part of the Lecture Notes in Computer Science book series (LNCS,volume 1064)

Abstract

We present a geometric relationship between the image motion of pairs of points over multiple frames. This relationship is based on the parallax displacements of points with respect to an arbitrary planar surface, and does not involve epipolar geometry. A constraint is derived over two frames for any pair of points, relating their projective structure (with respect to the plane) based only on their image coordinates and their parallax displacements. Similarly, a 3D-rigidity constraint between pairs of points over multiple frames is derived. We show applications of these parallax-based constraints to solving three important problems in 3D scene analysis: (i) the recovery of 3D scene structure, (ii) the detection of moving objects in the presence of camera induced motion, and (iii) the synthesis of new camera views based on a given set of views. Moreover, we show that this approach can handle difficult situations for 3D scene analysis, e.g., where there is only a small set of parallax vectors, and in the presence of independently moving objects.

Keywords

  • Image Point
  • Camera View
  • Image Motion
  • Parallax Motion
  • Virtual View

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.

References

  1. J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani. Hierarchical model-based motion estimation. In ECCV, pages 237–252, Santa Margarita Ligure, May 1992.

    Google Scholar 

  2. J.R. Bergen, P.J. Burt, R. Hingorani, and S. Peleg. A three-frame algorithm for estimating two-component image motion. PAMI, 14:886–895, September 1992.

    Google Scholar 

  3. S. Carlsson. Duality of reconstruction and positioning from projective views. In Workshop on Representations of Visual Scenes, 1995.

    Google Scholar 

  4. O. Faugeras and L. Robert. What can two images tell us about a third one? In ECCV, pages 485–492, May 1994.

    Google Scholar 

  5. O.D. Faugeras. What can be seen in three dimensions with an uncalibrated stereo rig? In ECCV, pages 563–578, Santa Margarita Ligure, May 1992.

    Google Scholar 

  6. O.D. Faugeras and B. Mourrain. On the geometry and algebra of the point and line correspondences between n images. In ICCV, pages 951–956, June 1995.

    Google Scholar 

  7. M. Irani and P. Anandan. Parallax geometry of pairs of points for 3d scene analysis. Technical report, David Sarnoff Research Center, October 1995.

    Google Scholar 

  8. M. Irani, B. Rousso, and S. Peleg. Computing occluding and transparent motions. IJCV, 12(1):5–16, January 1994.

    Google Scholar 

  9. M. Irani, B. Rousso, and S. Peleg. Recovery of ego-motion using image stabilization. In CVPR, pages 454–460, Seattle, Wa., June 1994.

    Google Scholar 

  10. J.J. Koenderink and A.J. van Doorn. Representation of local geometry in the visual system. Biol. Cybern., 55:367–375, 1987.

    Google Scholar 

  11. R. Kumar, P. Anandan, and K. Hanna. Shape recovery from multiple views: a parallax based approach. In DARPA IU Workshop, November 1994.

    Google Scholar 

  12. J.M. Lawn and R. Cipolla. Robust egomotion estimation from affine motion parallax. In ECCV, pages 205–210, May 1994.

    Google Scholar 

  13. F. Meyer and P. Bouthemy. Region-based tracking in image sequences. In ECCV, pages 476–484, Santa Margarita Ligure, May 1992.

    Google Scholar 

  14. T. Chang R. Hartley, R. Gupta. Stereo from uncalibrated cameras. In CVPR-92.

    Google Scholar 

  15. Harpreet Sawhney. 3d geometry from planar parallax. In CVPR, June 1994.

    Google Scholar 

  16. A. Shashua. Algebraic functions for recognition. PAMI, 17:779–789, 1995.

    Google Scholar 

  17. A. Shashua and N. Navab. Relative affine structure: Theory and application to 3d reconstruction from perspective views. In CVPR, pages 483–489, 1994.

    Google Scholar 

  18. M. E. Spetsakis and J. Aloimonos. A unified theory of structure from motion. In DARPA IU Workshop, pages 271–283, 1990.

    Google Scholar 

  19. W.B. Thompson and T.C. Pong. Detecting moving objects. IJCV, 4:29–57, 1990.

    Google Scholar 

  20. P.H.S. Torr and D.W. Murray. Stochastic motion clustering. In ECCV, 1994.

    Google Scholar 

  21. P.H.S. Torr, A. Zisserman, and S.J. Maybank. Robust detection of degenerate configurations for the fundamental matrix. In ICCV, pages 1037–1042, 1995.

    Google Scholar 

  22. P.H.S. Torr, A. Zisserman, and D.W. Murray. Motion clustering using the trilinear constraint over three views. In Workshop on Geometric Modeling and Invariants for Computer Vision, 1995.

    Google Scholar 

  23. D. Weinshall, M.Werman, and A. Shashua. Shape descriptors: Bilinear, trilinear and quadlinear relations for multi-point geometry, and linear projective reconstruction algorithms. In Workshop on Representations of Visual Scenes, 1995.

    Google Scholar 

  24. Andrew Zisserman. A case against epipolar geometry. In Applications of Invariance in Computer Vision, pages 35–50, Ponta Delgada, Azores, October 1993.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Irani, M., Anandan, P. (1996). Parallax geometry of pairs of points for 3D scene analysis. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015520

Download citation

  • DOI: https://doi.org/10.1007/BFb0015520

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61122-6

  • Online ISBN: 978-3-540-49949-7

  • eBook Packages: Springer Book Archive