Action Recognition Using Ballistic Dynamics
Abstract
We present a Bayesian framework for action recognition through ballistic dynamics. Psycho-kinesiological studies indicate that ballistic movements form the natural units for human movement planning. The framework leads to an efficient and robust algorithm for temporally segmenting videos into atomic movements. Individual movements are annotated with person-centric morphological labels called ballistic verbs. This is tested on a dataset of interactive movements, achieving high recognition rates. The approach is also applied on a gesture recognition task, improving a previously reported recognition rate from 84% to 92%. Consideration of ballistic dynamics enhances the performance of the popular Motion History Image feature. We also illustrate the approachpsilas general utility on real-world videos. Experiments indicate that the method is robust to view, style and appearance variations.
Cite
Text
Vitaladevuni et al. "Action Recognition Using Ballistic Dynamics." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587806Markdown
[Vitaladevuni et al. "Action Recognition Using Ballistic Dynamics." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/vitaladevuni2008cvpr-action/) doi:10.1109/CVPR.2008.4587806BibTeX
@inproceedings{vitaladevuni2008cvpr-action,
title = {{Action Recognition Using Ballistic Dynamics}},
author = {Vitaladevuni, Shiv Naga Prasad and Kellokumpu, Vili and Davis, Larry S.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2008},
doi = {10.1109/CVPR.2008.4587806},
url = {https://mlanthology.org/cvpr/2008/vitaladevuni2008cvpr-action/}
}