ML Anthology

Refinement of Noisy Correspondence Using Feedback from 3D Motion

Yong C. Kim, Keith Price
CVPR 1992 pp. 836-838
doi:10.1109/CVPR.1992.223245 /cvpr/1992/kim1992cvpr-refinement/

Abstract

In automated feature-based motion analysis of multiple frames, correspondence data are usually noisy and fragmented. A technique that gradually refines the initial noisy correspondence data and links fragments of a single trajectory using feedback from 3D motion estimation is presented. First, 3D motion parameters are estimated using the initial correspondence data. Then, each noisy trajectory is partitioned into subsets of points, each of which conforms to the estimated motion. The best set is used as the input to the next motion estimation. This process is repeated, and the gaps in the refined correspondence data are filled by guidance from the predicted motion. Test results for a standard real image sequence are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Kim and Price. "Refinement of Noisy Correspondence Using Feedback from 3D Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223245

Markdown

[Kim and Price. "Refinement of Noisy Correspondence Using Feedback from 3D Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/kim1992cvpr-refinement/) doi:10.1109/CVPR.1992.223245

BibTeX

@inproceedings{kim1992cvpr-refinement,
  title     = {{Refinement of Noisy Correspondence Using Feedback from 3D Motion}},
  author    = {Kim, Yong C. and Price, Keith},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {836-838},
  doi       = {10.1109/CVPR.1992.223245},
  url       = {https://mlanthology.org/cvpr/1992/kim1992cvpr-refinement/}
}