ML Anthology

Constraints for Recognizing and Locating Curved 3D Objects from Monocular Image Features

David J. Kriegman, B. Vijayakumar, Jean Ponce
ECCV 1992 pp. 829-833
doi:10.1007/3-540-55426-2_95 /eccv/1992/kriegman1992eccv-constraints/

Abstract

This paper presents viewpoint-dependent constraints that relate image features such as t-junctions and inflections to the pose of curved 3D objects. These constraints can be used to recognize and locate object instances in the imperfect line-drawing obtained by edge detection from a single image. For objects modelled by implicit algebraic equations, the constraints equations are polynomial, and methods for solving these systems of constraints are briefly discussed. An example of pose recovery is presented.

PDF ECCV Semantic Scholar

Cite

Text

Kriegman et al. "Constraints for Recognizing and Locating Curved 3D Objects from Monocular Image Features." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_95

Markdown

[Kriegman et al. "Constraints for Recognizing and Locating Curved 3D Objects from Monocular Image Features." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/kriegman1992eccv-constraints/) doi:10.1007/3-540-55426-2_95

BibTeX

@inproceedings{kriegman1992eccv-constraints,
  title     = {{Constraints for Recognizing and Locating Curved 3D Objects from Monocular Image Features}},
  author    = {Kriegman, David J. and Vijayakumar, B. and Ponce, Jean},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {829-833},
  doi       = {10.1007/3-540-55426-2_95},
  url       = {https://mlanthology.org/eccv/1992/kriegman1992eccv-constraints/}
}