Abstract

This note shows that the Riemann-space interpretation of motion vision developed by Barth and Watson is neither necessary for their results, nor sufficient to handle an intrinsic coordinate problem. Recasting the Barth-Watson framework as a classical velocity-solver (as in computer vision) solves these problems.

© Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |

  1. E. Barth, and A. B. Watson, "A geometric framework for nonlinear visual coding," Opt. Express 7, 155-165 (2000), http://www.opticsexpress.org/oearchive/source/23045.htm
    [CrossRef] [PubMed]
  2. C. Zetsche and E. Barth, "Direct detection of flow discontinuities by 3D-curvature operators," Pattern Recognition Lett. 12, 771-779 (1991).
    [CrossRef]
  3. C. Mota and E. Barth, "On the uniqueness of curvature features," Proc. Artificial Intell. (Dynamische Perzeption). K�ln: Infix Verlag, v. 9, pp. 175-178 (2000).

Other

E. Barth, and A. B. Watson, "A geometric framework for nonlinear visual coding," Opt. Express 7, 155-165 (2000), http://www.opticsexpress.org/oearchive/source/23045.htm
[CrossRef] [PubMed]

C. Zetsche and E. Barth, "Direct detection of flow discontinuities by 3D-curvature operators," Pattern Recognition Lett. 12, 771-779 (1991).
[CrossRef]

C. Mota and E. Barth, "On the uniqueness of curvature features," Proc. Artificial Intell. (Dynamische Perzeption). K�ln: Infix Verlag, v. 9, pp. 175-178 (2000).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Equations (6)

Equations on this page are rendered with MathJax. Learn more.

a f x + b f y + f t = 0 .
a f xx + b f xy = f xt
a f xy + b f yy = f yt
a f xt + b f yt = f tt
a = ( f xt f yy f yt f xy ) ( f xx f yy f xy f xy )
b = ( f xx f yt f xy f xt ) ( f xx f yy f xy f xy )

Metrics