Home
Uni-Logo
 

Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions

IEEE International Conference on Computer Vision (ICCV), 2011
Abstract: Point trajectories have emerged as a powerful means to obtain high quality and fully unsupervised segmentation of objects in video shots. They can exploit the long term motion difference between objects, but they tend to be sparse due to computational reasons and the difficulty in estimating motion in homogeneous areas. In this paper we introduce a variational method to obtain dense segmentations from such sparse trajectory clusters. Information is propagated with a hierarchical, nonlinear diffusion process that runs in the continuous domain but takes superpixels into account. We show that this process raises the density from 3% to 100% and even increases the average precision of labels.
Downloads

Other associated files : ochs_iccv2011.pdf [4.6MB]  

Images and movies

 

BibTex reference

@InProceedings{OB11,
  author       = "P.Ochs and T.Brox",
  title        = "Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  year         = "2011",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2011/OB11"
}

Other publications in the database