Multi-Agent Event Recognition
Abstract
This paper presents a new approach to recognizing multiagent events observed by a static camera. To track objects robustly, knowledge about the ground plane and the events is used. An event is considered as composed of action threads, each thread being executed by a single actor. A single thread of action is recognized from the characteristics of the trajectory and moving blob of the actor using Bayesian methods. A multi-agent event is represented by a number of action threads related by temporal constraints. Multi-agent events are recognized by propagating the constraints and likelihoods of event threads in a temporal logic network.
Cite
Text
Hongeng and Nevatia. "Multi-Agent Event Recognition." IEEE/CVF International Conference on Computer Vision, 2001. doi:10.1109/ICCV.2001.937608Markdown
[Hongeng and Nevatia. "Multi-Agent Event Recognition." IEEE/CVF International Conference on Computer Vision, 2001.](https://mlanthology.org/iccv/2001/hongeng2001iccv-multi/) doi:10.1109/ICCV.2001.937608BibTeX
@inproceedings{hongeng2001iccv-multi,
title = {{Multi-Agent Event Recognition}},
author = {Hongeng, Somboon and Nevatia, Ramakant},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2001},
pages = {84-93},
doi = {10.1109/ICCV.2001.937608},
url = {https://mlanthology.org/iccv/2001/hongeng2001iccv-multi/}
}