Statistical Foreground Modelling for Object Localisation

Abstract

A Bayesian approach to object localisation is feasible given suitable likelihood models for image observations. Such a likelihood involves statistical modelling - and learning - both of the object foreground and of the scene background. Statistical background models are already quite well understood. Here we propose a “conditioned likelihood” model for the foreground, conditioned on variations both in object appearance and illumination. Its effectiveness in localising a variety of objects is demonstrated.

Cite

Text

Sullivan et al. "Statistical Foreground Modelling for Object Localisation." European Conference on Computer Vision, 2000. doi:10.1007/3-540-45053-X_20

Markdown

[Sullivan et al. "Statistical Foreground Modelling for Object Localisation." European Conference on Computer Vision, 2000.](https://mlanthology.org/eccv/2000/sullivan2000eccv-statistical/) doi:10.1007/3-540-45053-X_20

BibTeX

@inproceedings{sullivan2000eccv-statistical,
  title     = {{Statistical Foreground Modelling for Object Localisation}},
  author    = {Sullivan, Josephine and Blake, Andrew and Rittscher, Jens},
  booktitle = {European Conference on Computer Vision},
  year      = {2000},
  pages     = {307-323},
  doi       = {10.1007/3-540-45053-X_20},
  url       = {https://mlanthology.org/eccv/2000/sullivan2000eccv-statistical/}
}