Home
Uni-Logo
 

Video Segmentation with Just a Few Strokes

IEEE International Conference on Computer Vision (ICCV), 2015
Abstract: As the use of videos is becoming more popular in computer vision, the need for annotated video datasets increases. Such datasets are required either as training data or simply as ground truth for benchmark datasets. A particular challenge in video segmentation is due to disocclusions, which hamper frame-to-frame propagation, in conjunction with non-moving objects. We show that a combination of motion from point trajectories, as known from motion segmentation, along with minimal supervision can largely help solve this problem. Moreover, we integrate a new constraint that enforces consistency of the color distribution in successive frames. We quantify user interaction effort with respect to segmentation quality on challenging ego motion videos. We compare our approach to a diverse set of algorithms in terms of user effort and in terms of performance on common video segmentation benchmarks.
Downloads

Other associated files : ivideoseg_iccv15.pdf [3MB]   poster_landscape.pdf [12.1MB]  

Images and movies

 

See also

Link to data and code coming soon...


BibTex reference

@InProceedings{NSB15,
  author       = "N.S. Nagaraja and F.R. Schmidt and T. Brox",
  title        = "Video Segmentation with Just a Few Strokes",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  month        = " ",
  year         = "2015",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2015/NSB15"
}

Other publications in the database