Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos
Abstract
Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal movements into two sub-components: global body movement and local body posture. We model the dynamics and interaction of the coupled features in our novel Message-Passing Encoder-Decoder Recurrent Network. We observed that the decoupled features collaboratively interact in our spatio-temporal model to accurately identify human-related irregular events from surveillance video sequences. Compared to traditional appearance-based models, our method achieves superior outlier detection performance. Our model also offers "open-box" examination and decision explanation made possible by the semantically understandable features and a network architecture supporting interpretability.
Cite
Text
Morais et al. "Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01227Markdown
[Morais et al. "Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/morais2019cvpr-learning/) doi:10.1109/CVPR.2019.01227BibTeX
@inproceedings{morais2019cvpr-learning,
title = {{Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos}},
author = {Morais, Romero and Le, Vuong and Tran, Truyen and Saha, Budhaditya and Mansour, Moussa and Venkatesh, Svetha},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01227},
url = {https://mlanthology.org/cvpr/2019/morais2019cvpr-learning/}
}