ML Anthology

Learning Pedestrian Dynamics from the Real World

Paul Scovanner, Marshall F. Tappen
ICCV 2009 pp. 381-388
doi:10.1109/ICCV.2009.5459224 /iccv/2009/scovanner2009iccv-learning/

Abstract

In this paper we describe a method to learn parameters which govern pedestrian motion by observing video data. Our learning framework is based on variational mode learning and allows us to efficiently optimize a continuous pedestrian cost model. We show that this model can be trained on automatic tracking results, and provides realistic and accurate pedestrian motions.

PDF ICCV Semantic Scholar

Cite

Text

Scovanner and Tappen. "Learning Pedestrian Dynamics from the Real World." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459224

Markdown

[Scovanner and Tappen. "Learning Pedestrian Dynamics from the Real World." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/scovanner2009iccv-learning/) doi:10.1109/ICCV.2009.5459224

BibTeX

@inproceedings{scovanner2009iccv-learning,
  title     = {{Learning Pedestrian Dynamics from the Real World}},
  author    = {Scovanner, Paul and Tappen, Marshall F.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {381-388},
  doi       = {10.1109/ICCV.2009.5459224},
  url       = {https://mlanthology.org/iccv/2009/scovanner2009iccv-learning/}
}