Advertisement

Direct Recovery of Planar-Parallax from Multiple Frames

  • Michal Irani
  • P. Anandan
  • Meir Cohen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1883)

Abstract

In this paper we present an algorithm that estimates dense planar-parallax motion from multiple uncalibrated views of a 3D scene. This generalizes the “plane + parallax” recovery methods to more than two frames. The parallax motion of pixels across multiple frames (relative to a planar surface) is related to the 3D scene structure and the camera epipoles. The parallax field, the epipoles, and the 3D scene structure are estimated directly from image brightness variations across multiple frames, without pre-computing correspondences.

Keywords

Reference Plane Shape Recovery Parallax Motion Epipolar Line Epipolar Geometry 
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.
    Bergen J. R., Anandan P., Hanna K. J., Hingorani R., Hierarchical Model-Based Motion Estimation, In European Conference on Computer Vision, pages 237–252, Santa Margarita Ligure, May 1992.Google Scholar
  2. 2.
    Criminisi C., Reid I., Zisserman Z., Duality, Rigidity, and Planar Parallax, In European Conference on Computer Vision, vol. II, 1998.Google Scholar
  3. 3.
    Hanna K.J., Direct Multi-Resolution Estimation of Ego-Motion and Structure From Motion, Workshop on Visual Motion, pp. 156–162, Princeton, NJ, Oct. 1991.Google Scholar
  4. 4.
    Hanna K. J. and Okamoto N. E., Combining Stereo and Motion for Direct Estimation of Scene Structure, International Conference on Computer Vision, 357–365, 1993.Google Scholar
  5. 5.
    Hartley R. I., In Defense of the Eight-Point Algorithm, In IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(6):580–593, June 1997.Google Scholar
  6. 6.
    Irani M., Rousso B., and Peleg S., Computing Occluding and Transparent Motions, In International Journal of Computer Vision 12(1):5–16, Jan. 1994. (also in ECCV-92).Google Scholar
  7. 7.
    Irani M. and Anandan P., Parallax Geometry of Pairs of Points for 3D Scene Analysis, In European Conference on Computer Vision, A, pages 17–30, Cambridge, UK, April 1996.Google Scholar
  8. 8.
    Irani M., Rousso B. and peleg P., Recovery of Ego-Motion Using Region Alignment, In IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(3), pp. 268–272, March 1997. (also in CVPR-94).Google Scholar
  9. 9.
    Irani M., Anandan P., Weinshall D., From Reference Frames to Reference Planes: Multi-View Parallax Geometry and Applications, In European Conference on Computer Vision, vol. II, pp. 829–845, 1998.Google Scholar
  10. 10.
    Irani M. and P. Anandan, A Unified Approach to Moving Object Detection in 2D and 3D Scenes, In IEEE Trans. on Pattern Analysis and Machine Intelligence, 20(6), pp. 577–589, June 1998.Google Scholar
  11. 11.
    Kumar R., Anandan P. and Hanna K., Direct Recovery of shape From Multiple Views: a Parallax Based Approach, International Conference on Pattern Recognition pp. 685–688, Oct. 1994.Google Scholar
  12. 12.
    Longuet-Higgins H.C., and Prazdny K., The Interpretation of a Moving Retinal Image, Proceedings of the Royal Society of London B, 208:385–397, 1980.CrossRefGoogle Scholar
  13. 13.
    Sawhney H. S., 3D Geometry From Planar Parallax, In IEEE Conference on Computer Vision and Pattern Recognition, pages 929–934, June 1994.Google Scholar
  14. 14.
    Shashua A. and Navab N., Relative affine Structure: Theory and Application to 3D Reconstruction From Perspective Views, In IEEE Conference on Computer Vision and Pattern Recognition, pages 483–489, 1994.Google Scholar
  15. 15.
    Stein G. P. and Shashua A., Model-based Brightness constraints: On Direct Estimation of Structure and Motion, In IEEE Conference on Computer Vision and Pattern Recognition, pages 400–406, 1997.Google Scholar
  16. 16.
    Szeliski R. and Kang S.B., Direct Methods for Visual Scene Reconstruction, In Workshop on Representations of Visual Scenes, 1995.Google Scholar
  17. 17.
    Torr P.H.S., Geometric motion segmentation and model selection, Proceedings of The Royal Society of London A, 356:1321–1340, 1998.zbMATHMathSciNetGoogle Scholar
  18. 18.
    Zhang Z., Determining the Epipolar Geometry and its Uncertainty: A Review, IJCV, 27(2):161–195, 1997.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Michal Irani
    • 1
  • P. Anandan
    • 2
  • Meir Cohen
    • 1
  1. 1.Dept. of Computer Science and Applied MathThe Weizmann Inst. of ScienceRehovotIsrael
  2. 2.Microsoft ResearchRedmondUSA

Personalised recommendations