ML Anthology

Robustness of Correspondence-Based Structure from Motion

Rabindranath Dutta, Mark A. Snyder
ICCV 1990 pp. 106-110
doi:10.1109/ICCV.1990.139504 /iccv/1990/dutta1990iccv-robustness/

Abstract

An examination is made of the robustness of correspondence-based approaches to structure from motion. It is proven in an algorithm-independent way, that small absolute errors in image displacements cause absolute errors in rotational motion parameters significant enough to lead to large relative errors in the determination of environmental depth. Even if the exact motion parameters are known a priori small errors in image displacements still lead to large errors in depth for environmental points whose distance from the camera is greater than a few multiples of the total translation in depth of the camera. In order to clarify the many robustness issues that are raised, a depth determination algorithm is developed and applied to dynamic image sequences of natural outdoor scenes.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

ICCV Semantic Scholar

Cite

Text

Dutta and Snyder. "Robustness of Correspondence-Based Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139504

Markdown

[Dutta and Snyder. "Robustness of Correspondence-Based Structure from Motion." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/dutta1990iccv-robustness/) doi:10.1109/ICCV.1990.139504

BibTeX

@inproceedings{dutta1990iccv-robustness,
  title     = {{Robustness of Correspondence-Based Structure from Motion}},
  author    = {Dutta, Rabindranath and Snyder, Mark A.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {106-110},
  doi       = {10.1109/ICCV.1990.139504},
  url       = {https://mlanthology.org/iccv/1990/dutta1990iccv-robustness/}
}