What's Going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes
Abstract
We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the right of way between different lanes or typical traffic light sequences. To extract them, sequences of activities need to be learned. While the first method extracts rules based on a learned topic model, the second model called DDP-HMM jointly learns co-occurring activities and their time dependencies. To this end we employ Dependent Dirichlet Processes to learn an arbitrary number of infinite Hidden Markov Models. In contrast to previous work, we build on state-of-the-art topic models that allow to automatically infer all parameters such as the optimal number of HMMs necessary to explain the rules governing a scene. The models are trained offline by Gibbs Sampling using unlabeled training data. ©2010 IEEE.
Cite
Text
Küttel et al. "What's Going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539869Markdown
[Küttel et al. "What's Going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/kuttel2010cvpr-going/) doi:10.1109/CVPR.2010.5539869BibTeX
@inproceedings{kuttel2010cvpr-going,
title = {{What's Going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes}},
author = {Küttel, Daniel and Breitenstein, Michael D. and Van Gool, Luc and Ferrari, Vittorio},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {1951-1958},
doi = {10.1109/CVPR.2010.5539869},
url = {https://mlanthology.org/cvpr/2010/kuttel2010cvpr-going/}
}