Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos
Abstract
Mixture of Gaussians (MOG) is the most popular technique for background modeling and presents some limitations when dynamic changes occur in the scene like camera jitter and movement in the background. Furthermore, the MOG is initialized using a training sequence which may be noisy and/or insufficient to model correctly the background. All these critical situations generate false classification in the foreground detection mask due to the related uncertainty. In this context, we present a background modeling algorithm based on Type-2 Fuzzy Mixture of Gaussians which is particularly suitable for infrared videos. The use of the Type-2 Fuzzy Set Theory allows to take into account the uncertainty. The results using the OTCBVS benchmark/test dataset videos show the robustness of the proposed method in presence of dynamic backgrounds.
Cite
Text
El Baf et al. "Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009. doi:10.1109/CVPRW.2009.5204109Markdown
[El Baf et al. "Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2009.](https://mlanthology.org/cvprw/2009/baf2009cvprw-fuzzy/) doi:10.1109/CVPRW.2009.5204109BibTeX
@inproceedings{baf2009cvprw-fuzzy,
title = {{Fuzzy Statistical Modeling of Dynamic Backgrounds for Moving Object Detection in Infrared Videos}},
author = {El Baf, Fida and Bouwmans, Thierry and Vachon, Bertrand},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2009},
pages = {60-65},
doi = {10.1109/CVPRW.2009.5204109},
url = {https://mlanthology.org/cvprw/2009/baf2009cvprw-fuzzy/}
}