Variational motion segmentation with level sets

Thomas Brox, A. Bruhn, J. Weickert
European Conference on Computer Vision (ECCV), Springer, LNCS, Vol.3951: 471-483, May 2006
Abstract: We suggest a variational method for the joint estimation of optic flow and the segmentation of the image into regions of similar motion. It makes use of the level set framework following the idea of motion competition, which is extended to non-parametric motion. Moreover, we automatically determine an appropriate initialization and the number of regions by means of recursive twophase splits with higher order region models. The method is further extended to the spatiotemporal setting and the use of additional cues like the gray value or color for the segmentation. It need not fear a quantitative comparison to pure optic flow estimation techniques: For the popular Yosemite sequence with clouds we obtain the currently most accurate result. We further uncover a mistake in the ground truth. Coarsely correcting this, we get an average angular error below 1 degree.

Other associated files : brox_eccv06_of.pdf [854KB]  

Images and movies


BibTex reference

  author       = "T. Brox and A. Bruhn and J. Weickert",
  title        = "Variational motion segmentation with level sets",
  booktitle    = "European Conference on Computer Vision (ECCV)",
  series       = "Lecture Notes in Computer Science",
  volume       = "3951",
  pages        = "471-483",
  month        = "May",
  year         = "2006",
  publisher    = "Springer",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2006/Bro06j"

Other publications in the database