Empirically Convergent Adaptive Estimation of Grayvalue Structure Tensors

  title={Empirically Convergent Adaptive Estimation of Grayvalue Structure Tensors},
  author={Markus Middendorf and Hans-Hellmut Nagel},
An iterative adaptation process for the estimation of a Grayvalue Structure Tensor (GST) is studied experimentally: alternative adaptation rules, different parameterizations, and two convergence criteria are compared. The basic adaptation process converges for both synthetic and real image sequences in most cases towards essentially the same results even if different parameters are used. Only two identifiable local grayvalue configurations have been encountered so far where adaptation variants… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
12 Citations
20 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 12 extracted citations


Publications referenced by this paper.
Showing 1-10 of 20 references

Scharr : Accurate Optical Flow in Noisy Image Sequences

  • H. Spies, H.
  • Proc . 8 th International Conference on Computer…
  • 2001

Vehicle Tracking Using Adaptive Optical Flow Estimation

  • M. Middendorf, H.-H. Nagel
  • Proc. First Int. Workshop on Performance…
  • 2000
1 Excerpt

G̊arding : “ ShapeAdapted Smoothing in Estimation of 3 - D Depth Cues from Affine Distortions of Local 2 - D Brightness Structure ”

  • B. Neumann, J.
  • Proc . ECCV
  • 1998

Similar Papers

Loading similar papers…