Recognizing 3D Objects from 2D Images: An Error Analysis

Abstract

Object recognition systems that use a small number of pairings of data and model features to compute the 3D transformation from model to sensor coordinates are considered. The effects of 2D sensor uncertainty on such computations are examined. The uncertainty in transformation parameters is bounded, and the effect of this uncertainty on false positive recognition rates is analyzed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Grimson et al. "Recognizing 3D Objects from 2D Images: An Error Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223257

Markdown

[Grimson et al. "Recognizing 3D Objects from 2D Images: An Error Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/grimson1992cvpr-recognizing/) doi:10.1109/CVPR.1992.223257

BibTeX

@inproceedings{grimson1992cvpr-recognizing,
  title     = {{Recognizing 3D Objects from 2D Images: An Error Analysis}},
  author    = {Grimson, W. Eric L. and Huttenlocher, Daniel P. and Alter, Tao Daniel},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {316-321},
  doi       = {10.1109/CVPR.1992.223257},
  url       = {https://mlanthology.org/cvpr/1992/grimson1992cvpr-recognizing/}
}