Analyzing Articulated Motion Using Expectation-Maximization

CVPR 1997 pp. 935-941

doi:10.1109/CVPR.1997.609440 /cvpr/1997/rowley1997cvpr-analyzing/

Abstract

We present a novel application of the Expectation-Maximization algorithm to the global analysis of articulated motion. The approach utilizes a kinematic model to constrain the motion estimates, producing a segmentation of the flow field into parts with different articulated motions. Experiments with synthetic and real images are described.

CVPR Semantic Scholar

Cite

Text

Rowley and Rehg. "Analyzing Articulated Motion Using Expectation-Maximization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609440

Markdown

[Rowley and Rehg. "Analyzing Articulated Motion Using Expectation-Maximization." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/rowley1997cvpr-analyzing/) doi:10.1109/CVPR.1997.609440

BibTeX

@inproceedings{rowley1997cvpr-analyzing,
  title     = {{Analyzing Articulated Motion Using Expectation-Maximization}},
  author    = {Rowley, Henry A. and Rehg, James M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {935-941},
  doi       = {10.1109/CVPR.1997.609440},
  url       = {https://mlanthology.org/cvpr/1997/rowley1997cvpr-analyzing/}
}