A Probabilistic Background Model for Tracking
Abstract
A new probabilistic background model based on a Hidden Markov Model is presented. The hidden states of the model enable discrimination between foreground, background and shadow. This model functions as a low level process for a car tracker. A particle filter is employed as a stochastic filter for the car tracker. The use of a particle filter allows the incorporation of the information from the low level process via importance sampling. A novel observation density for the particle filter which models the statistical dependence of neighboring pixels based on a Markov random field is presented. The effectiveness of both the low level process and the observation likelihood are demonstrated.
Cite
Text
Rittscher et al. "A Probabilistic Background Model for Tracking." European Conference on Computer Vision, 2000. doi:10.1007/3-540-45053-X_22Markdown
[Rittscher et al. "A Probabilistic Background Model for Tracking." European Conference on Computer Vision, 2000.](https://mlanthology.org/eccv/2000/rittscher2000eccv-probabilistic/) doi:10.1007/3-540-45053-X_22BibTeX
@inproceedings{rittscher2000eccv-probabilistic,
title = {{A Probabilistic Background Model for Tracking}},
author = {Rittscher, Jens and Kato, Jien and Joga, Sébastien and Blake, Andrew},
booktitle = {European Conference on Computer Vision},
year = {2000},
pages = {336-350},
doi = {10.1007/3-540-45053-X_22},
url = {https://mlanthology.org/eccv/2000/rittscher2000eccv-probabilistic/}
}