ML Anthology

Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry

Xue Iuan Wong, Manoranjan Majji
CVPRW 2017 pp. 950-958
doi:10.1109/CVPRW.2017.131 /cvprw/2017/wong2017cvprw-uncertainty/

Abstract

An uncertainty quantification approach to estimate the errors incurred by the Kanade Lucas Tomasi (KLT) feature tracking algorithm is presented. The covariance analysis is based on the linearized sensitivity calculations of the KLT algorithm. Track uncertainty thus computed is utilized to quantify the errors associated with feature based relative pose estimation algorithms. This paper also show that the uncertainty analysis result can serve as a mean to measures reliability of feature correspondences. Proposed technique show that a large amount of outlier can be ejected effectively, and thus improve the efficiency of iterative method such as RANSAC.

CVPRW Semantic Scholar

Cite

Text

Wong and Majji. "Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.131

Markdown

[Wong and Majji. "Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/wong2017cvprw-uncertainty/) doi:10.1109/CVPRW.2017.131

BibTeX

@inproceedings{wong2017cvprw-uncertainty,
  title     = {{Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry}},
  author    = {Wong, Xue Iuan and Majji, Manoranjan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {950-958},
  doi       = {10.1109/CVPRW.2017.131},
  url       = {https://mlanthology.org/cvprw/2017/wong2017cvprw-uncertainty/}
}