Publications

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication


Year(s) from:  to 
Author:
Keywords (separated by spaces):

What’s going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes

Daniel Kuettel, Michael D. Breitenstein, Luc Van Gool, Vittorio Ferrari
IEEE Conference on Computer Vision and Pattern Recognition
June 2010

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.


Link to publisher's page
Download in pdf format
@InProceedings{eth_biwi_00723,
  author = {Daniel Kuettel and Michael D. Breitenstein and Luc Van Gool and Vittorio Ferrari},
  title = {What’s going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes},
  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
  year = {2010},
  month = {June},
  keywords = {}
}