Parallel computation of optic flow

  • Shaogang Gong
  • Michael Brady
Optical Flow
Part of the Lecture Notes in Computer Science book series (LNCS, volume 427)


Both the tangential and normal components of the flow can be computed reliably where the image Hessian is well-conditioned. A fast algorithm to propagate flow along contours from such locations is proposed. Experimental results for an intrinsically parallel algorithm for computing the flow along zero-crossing contours are presented.


Flow Field Image Plane Diffusion Equation Optic Flow Normal Flow 
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. S.G. Gong, 1988 (September). Improved Local Flow. In Alvey Vision Conference, pages 129–134, University of Manchester, Manchester, England.Google Scholar
  2. S.G. Gong, 1989a (March). Curve Motion Constraint Equation and its Applications in the Parallel Visual Motion Estimation. In IEEE Workshop on Visual Motion, University of California, Irvine, California.Google Scholar
  3. S.G. Gong, 1989b (September). Parallel Computation of Visual Motion. PhD thesis, Department of Engineering Science, Oxford University.Google Scholar
  4. E.C. Hildreth, 1984. The Measurement of Visual Motion. MIT Press, Cambridge, Massachusetts.Google Scholar
  5. D.W. Murray and B.F. Buxton, 1989. Experiments in the Machine Interpretation of Visual Motion. MIT Press, Cambridge, Massachusetts.Google Scholar
  6. G.L Scott, 1986. Local and Global Interpretation of Moving Images. PhD thesis, Cognitive Studies Program, University of Sussex, England.Google Scholar
  7. G.L. Scott, S. Turner and A. Zisserman, 1988 (September). Using a Mixed Wave/Diffusion Process to Elicit the Symmetry Set. In Alvey Vision Conference, University of Manchester, Manchester, England.Google Scholar
  8. A. Yuille, 1988 (December). A Motion Coherence Theory. In IEEE International Conference on Computer Vision, Tampa, Florida.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Shaogang Gong
    • 1
  • Michael Brady
    • 2
  1. 1.Computer Science Department Queen Mary CollegeUniversity of LondonLondonUK
  2. 2.Department of Engineering ScienceOxford UniversityOxfordUK

Personalised recommendations