Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · 1996

Viewpoint variation in the noise sensitivity of pose estimation

Claus Madsen

Cited by 4Abstract and details only

Abstract

The paper presents an analysis of the stability of pose estimation. The investigated pose estimation technique is based on orientations of three edge segments and provides the rotation part of object pose. The specific emphasis of the analysis is on determining how the stability varies with view point relative to an object. The stability investigation propagates the uncertainty in edge segment orientations to the resulting effect on the pose parameters. It is shown that there is a very strong variation in noise sensitivity over the range of viewpoints and that exactly what viewpoints offer highest robustness towards noise can be determined in advance. Experiments on real images verify the theoretical results and show that, dependent on viewpoint, pose parameter variance varies from 0.05 to 20 (degrees squared).

Cite this paper

APA 7

Madsen, C. (1996). Viewpoint variation in the noise sensitivity of pose estimation. https://doi.org/10.1109/cvpr.1996.517051

MLA 9

Madsen, Claus. “Viewpoint variation in the noise sensitivity of pose estimation.” vol. 16, 1996, pp. 41–46, https://doi.org/10.1109/cvpr.1996.517051.

Chicago

Madsen, Claus. 1996. “Viewpoint variation in the noise sensitivity of pose estimation.” https://doi.org/10.1109/cvpr.1996.517051.

Harvard

Madsen, C. (1996) ‘Viewpoint variation in the noise sensitivity of pose estimation’. Available at: https://doi.org/10.1109/cvpr.1996.517051.

BibTeX
@article{madsen1996viewpoint,
  title = {{Viewpoint variation in the noise sensitivity of pose estimation}},
  author = {Madsen, Claus},
  volume = {16},
  pages = {41--46},
  year = {1996},
  doi = {10.1109/cvpr.1996.517051}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.

Related papers