ML Anthology

Structure from Small Baseline Motion with Central Panoramic Cameras

Omid Shakernia, René Vidal, Shankar Sastry
CVPRW 2003 pp. 83
doi:10.1109/CVPRW.2003.10077 /cvprw/2003/shakernia2003cvprw-structure/

Abstract

In applications of egomotion estimation, such as real-time vision-based navigation, one must deal with the double-edged sword of small relative motions between images. On one hand, tracking feature points is easier, while on the other, two-view structure-from-motion algorithms are poorly conditioned due to the low signal-to-noise ratio. In this paper, we derive a multi-frame structure from motion algorithm for calibrated central panoramic cameras. Our algorithm avoids the conditioning problem by explicitly incorporating the small baseline assumption in the algorithm's design. The proposed algorithm is linear, amenable to real-time implementation, and performs well in the small baseline domain for which it is designed.

CVPRW Semantic Scholar

Cite

Text

Shakernia et al. "Structure from Small Baseline Motion with Central Panoramic Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003. doi:10.1109/CVPRW.2003.10077

Markdown

[Shakernia et al. "Structure from Small Baseline Motion with Central Panoramic Cameras." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2003.](https://mlanthology.org/cvprw/2003/shakernia2003cvprw-structure/) doi:10.1109/CVPRW.2003.10077

BibTeX

@inproceedings{shakernia2003cvprw-structure,
  title     = {{Structure from Small Baseline Motion with Central Panoramic Cameras}},
  author    = {Shakernia, Omid and Vidal, René and Sastry, Shankar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2003},
  pages     = {83},
  doi       = {10.1109/CVPRW.2003.10077},
  url       = {https://mlanthology.org/cvprw/2003/shakernia2003cvprw-structure/}
}