Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions

CVPR 2001 pp. II:358-365

doi:10.1109/CVPR.2001.990983 /cvpr/2001/nestares2001cvpr-probabilistic/

Abstract

We describe a probabilistic framework for detecting and tracking motion boundaries. It builds on previous work (M.J. Black and D.J. Fleet, 2000) that used a particle filter to compute a posterior distribution over multiple, local motion models, one of which was specific for motion boundaries. We extend that framework in two ways: 1) with an enhanced likelihood that combines motion and edge support, 2) with a spatiotemporal model that propagates beliefs between adjoining image neighborhoods to encourage boundary continuity and provide better temporal predictions for motion boundaries. Approximate inference is achieved with a combination of tools: sampled representations allow us to represent multimodal non-Gaussian distributions and to apply nonlinear dynamics, while mixture models are used to simplify the computation of joint prediction distributions.

PDF CVPR Semantic Scholar

Cite

Text

Nestares and Fleet. "Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001. doi:10.1109/CVPR.2001.990983

Markdown

[Nestares and Fleet. "Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2001.](https://mlanthology.org/cvpr/2001/nestares2001cvpr-probabilistic/) doi:10.1109/CVPR.2001.990983

BibTeX

@inproceedings{nestares2001cvpr-probabilistic,
  title     = {{Probabilistic Tracking of Motion Boundaries with Spatiotemporal Predictions}},
  author    = {Nestares, Oscar and Fleet, David J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2001},
  pages     = {II:358-365},
  doi       = {10.1109/CVPR.2001.990983},
  url       = {https://mlanthology.org/cvpr/2001/nestares2001cvpr-probabilistic/}
}