Preemptive RANSAC for Live Structure and Motion Estimation
Abstract
A system capable of performing robust live ego-motion estimation for perspective cameras is presented. The system is powered by random sample consensus with preemptive scoring of the motion hypotheses. A general statement of the problem of efficient preemptive scoring is given. Then a theoretical investigation of preemptive scoring under a simple inlier-outlier model is performed. A practical preemption scheme is proposed and it is shown that the preemption is powerful enough to enable robust live structure and motion estimation.
Cite
Text
Nistér. "Preemptive RANSAC for Live Structure and Motion Estimation." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238341Markdown
[Nistér. "Preemptive RANSAC for Live Structure and Motion Estimation." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/nister2003iccv-preemptive/) doi:10.1109/ICCV.2003.1238341BibTeX
@inproceedings{nister2003iccv-preemptive,
title = {{Preemptive RANSAC for Live Structure and Motion Estimation}},
author = {Nistér, David},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2003},
pages = {199-206},
doi = {10.1109/ICCV.2003.1238341},
url = {https://mlanthology.org/iccv/2003/nister2003iccv-preemptive/}
}