Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection
Abstract
Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have shown to be a powerful instrument with excellent representational capacities, which can leverage the need for hand-crafted features. In this paper, we show that keeping track of the changes in the CNN feature across time can be used to effectively detect local anomalies. Specifically, we propose to measure local abnormality by combining semantic information (inherited from existing CNN models) with low-level optical-flow. One of the advantages of this method is that it can be used without the fine-tuning phase. The proposed method is validated on challenging abnormality detection datasets and the results show the superiority of our approach compared with the state-of-theart methods.
Cite
Text
Ravanbakhsh et al. "Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018. doi:10.1109/WACV.2018.00188Markdown
[Ravanbakhsh et al. "Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection." IEEE/CVF Winter Conference on Applications of Computer Vision, 2018.](https://mlanthology.org/wacv/2018/ravanbakhsh2018wacv-plug/) doi:10.1109/WACV.2018.00188BibTeX
@inproceedings{ravanbakhsh2018wacv-plug,
title = {{Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection}},
author = {Ravanbakhsh, Mahdyar and Nabi, Moin and Mousavi, Hossein and Sangineto, Enver and Sebe, Nicu},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2018},
pages = {1689-1698},
doi = {10.1109/WACV.2018.00188},
url = {https://mlanthology.org/wacv/2018/ravanbakhsh2018wacv-plug/}
}