Performance of Optical Flow Techniques

Barron, John L.; Fleet, David J.; Beauchemin, Steven S.; Burkitt, T. A.

doi:10.1109/CVPR.1992.223269

Performance of Optical Flow Techniques

John L. Barron, David J. Fleet, Steven S. Beauchemin, T. A. Burkitt

CVPR 1992 pp. 236-242

doi:10.1109/CVPR.1992.223269 /cvpr/1992/barron1992cvpr-performance/

Abstract

The performance of six optical flow techniques is compared, emphasizing measurement accuracy. The most accurate methods are found to be the local differential approaches, where nu is computed explicitly in terms of a locally constant or linear model. Techniques using global smoothness constraints appear to produce visually attractive flow fields, but in general seem to be accurate enough for qualitative use only and insufficient as precursors to the computations of egomotion and 3D structures. It is found that some form of confidence measure/threshold is crucial for all techniques in order to separate the inaccurate from the accurate. Drawbacks of the six techniques are discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

CVPR Semantic Scholar

Cite

Text

Barron et al. "Performance of Optical Flow Techniques." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223269

Markdown

[Barron et al. "Performance of Optical Flow Techniques." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/barron1992cvpr-performance/) doi:10.1109/CVPR.1992.223269

BibTeX

@inproceedings{barron1992cvpr-performance,
  title     = {{Performance of Optical Flow Techniques}},
  author    = {Barron, John L. and Fleet, David J. and Beauchemin, Steven S. and Burkitt, T. A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {236-242},
  doi       = {10.1109/CVPR.1992.223269},
  url       = {https://mlanthology.org/cvpr/1992/barron1992cvpr-performance/}
}