Robust Optical Flow Computation Based on Least-Median-of-Squares Regression

@article{Ong1999RobustOF,
  title={Robust Optical Flow Computation Based on Least-Median-of-Squares Regression},
  author={Ee Ping Ong and Michael Spann},
  journal={International Journal of Computer Vision},
  year={1999},
  volume={31},
  pages={51-82}
}
An optical flow estimation technique is presented which is based on the least-median-of-squares (LMedS) robust regression algorithm enabling more accurate flow estimates to be computed in the vicinity of motion discontinuities. The flow is computed in a blockwise fashion using an affine model. Through the use of overlapping blocks coupled with a block shifting strategy, redundancy is introduced into the computation of the flow. This eliminates blocking effects common in most other techniques… CONTINUE READING
Highly Cited
This paper has 75 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 51 extracted citations

75 Citations

051015'00'03'07'11'15
Citations per Year
Semantic Scholar estimates that this publication has 75 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 15 references

piecewise-smooth flow fields

  • M. J. Black, A. Rangarajan
  • Computer Vision and Image Understanding,
  • 1996
1 Excerpt

segmentation and motion estimation using a robust genetic partitioning algorithm

  • E. Dubois
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1992
1 Excerpt

Multimodal motion estimation and segmentation using markov random fields

  • F. Heitz, P. Bouthemy
  • Proceedings of 10th International Conference on…
  • 1990
1 Excerpt

Similar Papers

Loading similar papers…