Structure and Motion for Dynamic Scenes — The Case of Points Moving in Planes

  • Peter Sturm
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2351)


We consider dynamic scenes consisting of moving points whose motion is constrained to happen in one of a pencil of planes. This is for example the case when rigid objects move independently, but on a common ground plane (each point moves in one of a pencil of planes parallel to the ground plane). We consider stereo pairs of the dynamic scene, taken by a moving stereo system, that allow to obtain 3D reconstructions of the scene, for different time instants. We derive matching constraints for pairs of such 3D reconstructions, especially we introduce a simple tensor, that encapsulates parts of the motion of the stereo system and parts of the scene structure. This tensor allows to partially recover the dynamic structure of the scene. Complete recovery of structure and motion can be performed in a number of ways, e.g. using the information of static points or linear trajectories. We also develop a special self-calibration method for the considered scenario.


Motion Plane Stereo Pair Dynamic Scene Linear Trajectory Projective Reconstruction 
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.


  1. 1.
    Costeira, J., Kanade, T.: A Multi-Body Factorization Method for Motion Analysis. ICCV — International Conference on Computer Vision (1995) 1071–1076Google Scholar
  2. 2.
    Fitzgibbon, A.W., Zisserman, A.: Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects. ECCV — European Conference on Computer Vision (2000) 891–906Google Scholar
  3. 3.
    Han, M., Kanade, T.: Reconstruction of a Scene with Multiple Linearly Moving Objects. CVPR — International Conference on Computer Vision and Pattern Recognition, Vol. II (2000) 542–549Google Scholar
  4. 4.
    Han, M., Kanade, T.: Multiple Motion Scene Reconstruction from Uncalibrated Views. ICCV — International Conference on Computer Vision, Vol. I (2001) 163–170CrossRefGoogle Scholar
  5. 5.
    Hartley, R.I.: Estimation of Relative Camera Positions for Uncalibrated Cameras. ECCV — European Conference on Computer Vision (1992) 579–587Google Scholar
  6. 6.
    Hartley, R.: In Defence of the 8-Point Algorithm. ICCV — International Conference on Computer Vision (1995) 1064–1070Google Scholar
  7. 7.
    Newsam, G.N., Huynh, D.Q., Brooks, M.J., Pan, H.P.: Recovering Unknown Focal Lengths in Self-Calibration: An Essentially Linear Algorithm and Degenerate Configurations. XVIIIth ISPRS Congress, Part B3 (1996) 575–580Google Scholar
  8. 8.
    Semple, J.G., Kneebone, G.T.: Algebraic Projective Geometry. Oxford Science Publications (1952)Google Scholar
  9. 9.
    Shashua, A., Wolf, L.: Homography Tensors: On Algebraic Entities That Represent Three Views of Static or Moving Planar Points. ECCV — European Conference on Computer Vision (2000) 507–521Google Scholar
  10. 10.
    Triggs, B.: Matching Constraints and the Joint Image. ICCV — International Conference on Computer Vision (1995) 338–343Google Scholar
  11. 11.
    Wolf, L, Shashua, A., Wexler, Y.: Join Tensors: On 3D-to-3D Alignment of Dynamic Sets. ICPR — International Conference on Pattern Recognition (2000) 388–391Google Scholar
  12. 12.
    Wolf, L., Shashua, A.: On Projection Matrices P kP 2, k=3,..., 6, and their Applications in Computer Vision. ICCV — International Conference on Computer Vision, Vol. I (2001) 412–419CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Peter Sturm
    • 1
  1. 1.INRIA Rhône-AlpesMontbonnotFrance

Personalised recommendations