Lines as the Fundamental Unit of Vision

  • Patrick Baker
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2616)


We explore the consequences of using only lines as our object in computer vision. We show a new constraint, which we call the prismatic line constraint. This constraint is based on the reconstruction of local shape using line measurements and rotation only, which is a new reconstruction in computer vision. We show that the point trilinear constraint can be broken down into the epipolar constraint and constraints on lines, which are thus the only constraints which need to be considered in computer vision.


Computer Vision Parallel Line Image Point World Line Local Shape 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    J. Aloimonos. Shape from texture. Biological Cybernetics, 58:345–360, 1988.zbMATHCrossRefGoogle Scholar
  2. [2]
    O. Bottema and B. Roth. Theoretical Kinematics. Dover, 1990.Google Scholar
  3. [3]
    O. D. Faugeras and B. Mourrain. On the geometry and algebra of the point and line correspondences between n images. In Proc. 5th International Conference on Computer Vision, pages 951–956, Cambridge, MA, 1995.Google Scholar
  4. [4]
    A. Heyden. A common framework for multiple view tensors. In ECCV98, pages 3–19, 1998.Google Scholar
  5. [5]
    Y. Liu and T. S. Huang. Estimation of rigid body motion using straight line correspondences. Computer Vision, Graphics, and Image Processing, 43:37–52, 1988.CrossRefGoogle Scholar
  6. [6]
    H. C. Longuet-Higgins. A computer algorithm for reconstructing a scene from two projections. Nature, 293:133–135, 1981.CrossRefGoogle Scholar
  7. [7]
    A. Shashua. Algebraic functions for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8):779–789, 1995.CrossRefGoogle Scholar
  8. [8]
    M. E. Spetsakis and J. Aloimonos. Structure from motion using line correspondences. International Journal of Computer Vision, 4:171–183, 1990.CrossRefGoogle Scholar
  9. [9]
    M. E. Spetsakis and J. Aloimonos. A multi-frame approach to visual motion perception. International Journal of Computer Vision, 6:245–255, 1991.CrossRefGoogle Scholar
  10. [10]
    A. P. Witkin. Recovering surface shape and orientation from texture. Artificial Intelligence, 17:17–45, 1981.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Patrick Baker
    • 1
  1. 1.University of MarylandCollege ParkUSA

Personalised recommendations