Representation and Optimal Recognition of Human Activities
Abstract
Towards the goal of realizing a generic automatic human activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation using three type of entities: image features, mobile object properties and scenarios. Taking image features of tracked moving regions from an image sequence as input, mobile object properties are first computed by specific methods while noise is suppressed by statistical methods. Scenarios are recognized from mobile object properties based on Bayesian analysis. Several scenarios are recognized by an algorithm using a probabilistic finite-state automaton (a variant of structured HMM). A demonstration of the optimality of this recognition method is discussed. Finally, the validity and the effectiveness of our approach is demonstrated on both real-world and perturbed data.
Cite
Text
Hongeng et al. "Representation and Optimal Recognition of Human Activities." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.855905Markdown
[Hongeng et al. "Representation and Optimal Recognition of Human Activities." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/hongeng2000cvpr-representation/) doi:10.1109/CVPR.2000.855905BibTeX
@inproceedings{hongeng2000cvpr-representation,
title = {{Representation and Optimal Recognition of Human Activities}},
author = {Hongeng, Somboon and Brémond, François and Nevatia, Ramakant},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2000},
pages = {1818-1825},
doi = {10.1109/CVPR.2000.855905},
url = {https://mlanthology.org/cvpr/2000/hongeng2000cvpr-representation/}
}