Fast, Robust, and Consistent Camera Motion Estimation

CVPR 1999 pp. 1164-1170

doi:10.1109/CVPR.1999.786934 /cvpr/1999/zhang1999cvpr-fast/

Abstract

Previous algorithms that recover camera motion from image velocities suffer from both bias and excessive variance in the results. We propose a robust estimator of camera motion that is statistically consistent when image noise is isotropic. Consistency means that the estimated motion converges in probability, to the true value as the number of image points increases. An algorithm based on reweighted Gauss-Newton iterations handles 100 velocity measurements in about 50 milliseconds on a workstation.

CVPR Semantic Scholar

Cite

Text

Zhang and Tomasi. "Fast, Robust, and Consistent Camera Motion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786934

Markdown

[Zhang and Tomasi. "Fast, Robust, and Consistent Camera Motion Estimation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/zhang1999cvpr-fast/) doi:10.1109/CVPR.1999.786934

BibTeX

@inproceedings{zhang1999cvpr-fast,
  title     = {{Fast, Robust, and Consistent Camera Motion Estimation}},
  author    = {Zhang, Tong and Tomasi, Carlo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {1164-1170},
  doi       = {10.1109/CVPR.1999.786934},
  url       = {https://mlanthology.org/cvpr/1999/zhang1999cvpr-fast/}
}