Semi-local variational optical flow estimation

Denis Fortun, Charles Kervrann

Abstract

Global variational methods for optical flow estimation usually suffer from an over-smoothing effect. We propose a semi-local estimation framework designed to integrate and improve any variational method. The idea is to implicitly segment the minimization domain into coherently moving windows. In a first time, local variational estimations are performed in overlapping candidate square regions. Then, a global discrete optimization, non subject to the over-smoothing introduced by variational approaches, selects the optimal window for each pixel. Experimental results show an increasing of the sharpness of discontinuities and a significant improvement of global registration errors compared to the results of the baseline global variational method.
BibTeX
@inproceedings{fortun2012semi,
  author = {Denis Fortun and Charles Kervrann},
  title = {{Semi-local variational optical flow estimation}},
  booktitle = {ICIP},
  year = {2012},
  doi = {10.1109/icip.2012.6466799},
}

Loading related content...

Figure