Optimal Filters for Gradient-based Motion Estimation

  title={Optimal Filters for Gradient-based Motion Estimation},
  author={Michael Elad and Patrick C. Teo and Yacov Hel-Or},
Gradient based approaches for motion estimation Optical Flow estimate the motion of an image sequence based on local changes in the image intensities In order to best evaluate local changes in the intensities speci c lters are applied to the image sequence These lters are typically composed of spatio temporal deriva tives The design of these lters plays an important role in the estimation accuracy This paper proposes a method for the design of these lters in an optimal manner Unlike previous… CONTINUE READING
Highly Cited
This paper has 48 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.
29 Citations
11 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 11 references

Digital Image Processing - Con- cepts, Algorithms, and Scienti c Applications

  • B. Jahne
  • 1995
Highly Influential
5 Excerpts

Optimal lters for gradient-based motion estimation

  • M. Elad, P. Teo, Y. Hel-Or
  • Technical Report TR-97-111, HP Lab,
  • 1997
2 Excerpts

Recursive optical ow es- timation - adaptive ltering approach

  • M. Elad, A. Feuer
  • Submitted to the Journal of Visual Comm. and…
  • 1996
1 Excerpt

Similar Papers

Loading similar papers…