Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

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

P. Ochs and T. Brox

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.
pdf Bibtex Publisher's link Code
Citation:
P. Ochs, T. Brox:
Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions. [pdf]
IEEE International Conference on Computer Vision (ICCV), 2011.
Bibtex:
@inproceedings{OB11,
  title        = {Object segmentation in video: a hierarchical variational approach for turning point trajectories into dense regions},
  author       = {P. Ochs and T. Brox},
  year         = {2011},
  booktitle    = {IEEE International Conference on Computer Vision (ICCV)},
}


MOP Group
©2017-2024
The author is not
responsible for
the content of
external pages.