Tracking Objects Using Density Matching and Shape Priors

Abstract

We present a novel method for tracking objects by combining density matching with shape priors. Density matching is a tracking method which operates by maximizing the Bhattacharyya similarity measure between the photometric distribution from an estimated image region and a model photometric distribution. Such trackers can be expressed as PDE-based curve evolutions, which can be implemented using level sets. Shape priors can be combined with this levelset implementation of density matching by representing the shape priors as a series of level sets; a variational approach allows for a natural, parametrization-independent shape term to be derived. Experimental results on real image sequences are shown.

Cite

Text

Zhang and Freedman. "Tracking Objects Using Density Matching and Shape Priors." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238466

Markdown

[Zhang and Freedman. "Tracking Objects Using Density Matching and Shape Priors." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/zhang2003iccv-tracking/) doi:10.1109/ICCV.2003.1238466

BibTeX

@inproceedings{zhang2003iccv-tracking,
  title     = {{Tracking Objects Using Density Matching and Shape Priors}},
  author    = {Zhang, Tao and Freedman, Daniel},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1056-1062},
  doi       = {10.1109/ICCV.2003.1238466},
  url       = {https://mlanthology.org/iccv/2003/zhang2003iccv-tracking/}
}