Figure/ground video segmentation using greedy transductive cosegmentation

Zhihui Fu, Hongkai Xiong

Abstract

Cosegmentation has achieved great success in exploiting inter-image segmentation consistency to segment a group of images simultaneously. To enforces non-local temporal coherence across all the frames by high-order object-level appearance/semantic correspondence with a compensation to the short-time window motion coherence cue, this paper cosegments the video frames together with a novel interframe segmentation consistency term. A direct application of existing cosegmentation algorithms to video frames encounters the following challenges: the high correlation of adjacent frames which makes the segmentation ambiguous and a large number of video frames which makes the computation expensive. To tackle them, we formulate the cosegmentation in a transductive learning framework to iteratively learn the inter-frame consistency term from all the video frames. The proposed algorithm is evaluated on the standard SegTrack dataset and promising results are obtained.
BibTeX
@inproceedings{fu2014figure,
  author = {Zhihui Fu and Hongkai Xiong},
  title = {{Figure/ground video segmentation using greedy transductive cosegmentation}},
  booktitle = {ICIP},
  year = {2014},
  doi = {10.1109/icip.2014.7025665},
}

Loading related content...

Figure