ML Anthology

Improving Foreground Segmentations with Probabilistic Superpixel Markov Random Fields

Alexander Schick, Martin Bäuml, Rainer Stiefelhagen
CVPRW 2012 pp. 27-31
doi:10.1109/CVPRW.2012.6238923 /cvprw/2012/schick2012cvprw-improving/

Abstract

We propose a novel post-processing framework to im-prove foreground segmentations with the use of Probabilis-tic Superpixel Markov Random Fields. First, we convert a given pixel-based segmentation into a probabilistic su-perpixel representation. Based on these probabilistic su-perpixels, a Markov random field exploits structural infor-mation and similarities to improve the segmentation. We evaluate our approach on all categories of the Change De-tection 2012 dataset. Our approach improves all perfor-mance measures simultaneously for eight different basis foreground segmentation algorithms. 1. Introduction and

PDF CVPRW Semantic Scholar

Cite

Text

Schick et al. "Improving Foreground Segmentations with Probabilistic Superpixel Markov Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6238923

Markdown

[Schick et al. "Improving Foreground Segmentations with Probabilistic Superpixel Markov Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/schick2012cvprw-improving/) doi:10.1109/CVPRW.2012.6238923

BibTeX

@inproceedings{schick2012cvprw-improving,
  title     = {{Improving Foreground Segmentations with Probabilistic Superpixel Markov Random Fields}},
  author    = {Schick, Alexander and Bäuml, Martin and Stiefelhagen, Rainer},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2012},
  pages     = {27-31},
  doi       = {10.1109/CVPRW.2012.6238923},
  url       = {https://mlanthology.org/cvprw/2012/schick2012cvprw-improving/}
}