ML Anthology

Large-Scale Event Detection Using Semi-Hidden Markov Models

Somboon Hongeng, Ramakant Nevatia
ICCV 2003 pp. 1455-1462
doi:10.1109/ICCV.2003.1238661 /iccv/2003/hongeng2003iccv-large/

Abstract

We present a new approach to recognizing events in videos. We first detect and track moving objects in the scene. Based on the shape and motion properties of these objects, we infer probabilities of primitive events frame-by-frame by using Bayesian networks. Composite events, consisting of multiple primitive events, over extended periods of time are analyzed by using a hidden, semi-Markov finite state model. This results in more reliable event segmentation compared to the use of standard HMMs in noisy video sequences at the cost of some increase in computational complexity. We describe our approach to reducing this complexity. We demonstrate the effectiveness of our algorithm using both real-world and perturbed data.

ICCV Semantic Scholar

Cite

Text

Hongeng and Nevatia. "Large-Scale Event Detection Using Semi-Hidden Markov Models." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238661

Markdown

[Hongeng and Nevatia. "Large-Scale Event Detection Using Semi-Hidden Markov Models." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/hongeng2003iccv-large/) doi:10.1109/ICCV.2003.1238661

BibTeX

@inproceedings{hongeng2003iccv-large,
  title     = {{Large-Scale Event Detection Using Semi-Hidden Markov Models}},
  author    = {Hongeng, Somboon and Nevatia, Ramakant},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1455-1462},
  doi       = {10.1109/ICCV.2003.1238661},
  url       = {https://mlanthology.org/iccv/2003/hongeng2003iccv-large/}
}