ML Anthology

Learning Dynamical Models Using Expectation-Maximisation

Ben North, Andrew Blake
ICCV 1998 pp. 384-389
doi:10.1109/ICCV.1998.710747 /iccv/1998/north1998iccv-learning/

Abstract

Tracking with deformable contours in a filtering framework requires a dynamical model for prediction. For any given application, tracking is improved by having an accurate model, learned from training data. We develop a method for learning dynamical models from training sequences, explicitly taking account of the fact that training data are noisy measurements and not true states. By introducing an 'augmented-state smoothing filter' we show how the technique of Expectation-Maximisation can be applied to this problem, and show that the resulting algorithm produces more robust and accurate tracking.

ICCV Semantic Scholar

Cite

Text

North and Blake. "Learning Dynamical Models Using Expectation-Maximisation." IEEE/CVF International Conference on Computer Vision, 1998. doi:10.1109/ICCV.1998.710747

Markdown

[North and Blake. "Learning Dynamical Models Using Expectation-Maximisation." IEEE/CVF International Conference on Computer Vision, 1998.](https://mlanthology.org/iccv/1998/north1998iccv-learning/) doi:10.1109/ICCV.1998.710747

BibTeX

@inproceedings{north1998iccv-learning,
  title     = {{Learning Dynamical Models Using Expectation-Maximisation}},
  author    = {North, Ben and Blake, Andrew},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1998},
  pages     = {384-389},
  doi       = {10.1109/ICCV.1998.710747},
  url       = {https://mlanthology.org/iccv/1998/north1998iccv-learning/}
}