Event Modeling and Recognition Using Markov Logic Networks
Abstract
We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited to overcome them. The knowledge is represented as first-order logic production rules with associated weights to indicate their confidence. These rules are used in combination with a relaxed deduction algorithm to construct a network of grounded atoms, the Markov Logic Network. The network is used to perform probabilistic inference for input queries about events of interest. The system’s performance is demonstrated on a number of videos from a parking lot domain that contains complex interactions of people and vehicles.
Cite
Text
Tran and Davis. "Event Modeling and Recognition Using Markov Logic Networks." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88688-4_45Markdown
[Tran and Davis. "Event Modeling and Recognition Using Markov Logic Networks." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/tran2008eccv-event/) doi:10.1007/978-3-540-88688-4_45BibTeX
@inproceedings{tran2008eccv-event,
title = {{Event Modeling and Recognition Using Markov Logic Networks}},
author = {Tran, Son Dinh and Davis, Larry S.},
booktitle = {European Conference on Computer Vision},
year = {2008},
pages = {610-623},
doi = {10.1007/978-3-540-88688-4_45},
url = {https://mlanthology.org/eccv/2008/tran2008eccv-event/}
}