ML Anthology

Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter

Jing Zhong, Stan Sclaroff
ICCV 2003 pp. 44-50
doi:10.1109/ICCV.2003.1238312 /iccv/2003/zhong2003iccv-segmenting/

Abstract

The algorithm presented in this paper aims to segment the foreground objects in video (e.g., people) given timevarying, textured backgrounds. Examples of time-varying backgrounds include waves on water, clouds moving, trees waving in the wind, automobile traffic, moving crowds, escalators, etc. We have developed a novel foregroundbackground segmentation algorithm that explicitly accounts for the non-stationary nature and clutter-like appearance of many dynamic textures. The dynamic texture is modeled by an Autoregressive Moving Average Model (ARMA). A robust Kalman filter algorithm iteratively estimates the intrinsic appearance of the dynamic texture, as well as the regions of the foreground objects. Preliminary experiments with this method have demonstrated promising results. 1

PDF ICCV Semantic Scholar

Cite

Text

Zhong and Sclaroff. "Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238312

Markdown

[Zhong and Sclaroff. "Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/zhong2003iccv-segmenting/) doi:10.1109/ICCV.2003.1238312

BibTeX

@inproceedings{zhong2003iccv-segmenting,
  title     = {{Segmenting Foreground Objects from a Dynamic Textured Background via a Robust Kalman Filter}},
  author    = {Zhong, Jing and Sclaroff, Stan},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {44-50},
  doi       = {10.1109/ICCV.2003.1238312},
  url       = {https://mlanthology.org/iccv/2003/zhong2003iccv-segmenting/}
}