Bayesian Multimodal Fusion in Forensic Applications
Abstract
The public location of CCTV cameras and their connexion with public safety demand high robustness and reliability from surveillance systems. This paper focuses on the development of a multimodal fusion technique which exploits the benefits of a Bayesian inference scheme to enhance surveillance systems’ reliability. Additionally, an automatic object classifier is proposed based on the multimodal fusion technique, addressing semantic indexing and classification for forensic applications. The proposed Bayesian-based Multimodal Fusion technique, and particularly, the proposed object classifier are evaluated against two state-of-the-art automatic object classifiers on the i-LIDS surveillance dataset.
Cite
Text
Arguedas et al. "Bayesian Multimodal Fusion in Forensic Applications." European Conference on Computer Vision Workshops, 2012. doi:10.1007/978-3-642-33885-4_47Markdown
[Arguedas et al. "Bayesian Multimodal Fusion in Forensic Applications." European Conference on Computer Vision Workshops, 2012.](https://mlanthology.org/eccvw/2012/arguedas2012eccvw-bayesian/) doi:10.1007/978-3-642-33885-4_47BibTeX
@inproceedings{arguedas2012eccvw-bayesian,
title = {{Bayesian Multimodal Fusion in Forensic Applications}},
author = {Arguedas, Virginia Fernandez and Zhang, Qianni and Izquierdo, Ebroul},
booktitle = {European Conference on Computer Vision Workshops},
year = {2012},
pages = {466-475},
doi = {10.1007/978-3-642-33885-4_47},
url = {https://mlanthology.org/eccvw/2012/arguedas2012eccvw-bayesian/}
}