Constraint-Fusion for Interpretation of Articulated Objects

Abstract

This paper presents a method for interpretation of modeled objects that is general enough to cover articulated and other types of constrained models. The exibility between components of the model are expressed as spatial constraints which are fused into the pose estimation during the interpretation process. The constraint fusion assists in obtaining the correct interpretation and in reducing the search of possible correspondences. The proposed method can handle any constraint (including inequalities) between any number of di erent components of the model. The framework is based on Kalman ltering. 1

Cite

Text

Hel-Or and Werman. "Constraint-Fusion for Interpretation of Articulated Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323808

Markdown

[Hel-Or and Werman. "Constraint-Fusion for Interpretation of Articulated Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/helor1994cvpr-constraint/) doi:10.1109/CVPR.1994.323808

BibTeX

@inproceedings{helor1994cvpr-constraint,
  title     = {{Constraint-Fusion for Interpretation of Articulated Objects}},
  author    = {Hel-Or, Yacov and Werman, Michael},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {39-45},
  doi       = {10.1109/CVPR.1994.323808},
  url       = {https://mlanthology.org/cvpr/1994/helor1994cvpr-constraint/}
}