ML Anthology

Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking

John MacCormick, Michael Isard
ECCV 2000 pp. 3-19
doi:10.1007/3-540-45053-X_1 /eccv/2000/maccormick2000eccv-partitioned/

Abstract

Partitioned sampling is a technique which was introduced in [ I7 ] for avoiding the high cost of particle filters when tracking more than one object. In fact this technique can reduce the curse of dimensionality in other situations too. This paper describes how to use partitioned sampling on articulated objects, obtaining results that would be impossible with standard sampling methods. Because partitioned sampling is the statistical analogue of a hierarchical search, it makes sense to use it on articulated objects, since links at the base of the object can be localised before moving on to search for subsequent links.

PDF ECCV Semantic Scholar

Cite

Text

MacCormick and Isard. "Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking." European Conference on Computer Vision, 2000. doi:10.1007/3-540-45053-X_1

Markdown

[MacCormick and Isard. "Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking." European Conference on Computer Vision, 2000.](https://mlanthology.org/eccv/2000/maccormick2000eccv-partitioned/) doi:10.1007/3-540-45053-X_1

BibTeX

@inproceedings{maccormick2000eccv-partitioned,
  title     = {{Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking}},
  author    = {MacCormick, John and Isard, Michael},
  booktitle = {European Conference on Computer Vision},
  year      = {2000},
  pages     = {3-19},
  doi       = {10.1007/3-540-45053-X_1},
  url       = {https://mlanthology.org/eccv/2000/maccormick2000eccv-partitioned/}
}