ML Anthology

Invariance-a New Framework for Vision

David A. Forsyth, Joseph L. Mundy, Andrew Zisserman, Christopher M. Brown
ICCV 1990 pp. 598-605
doi:10.1109/ICCV.1990.139604 /iccv/1990/forsyth1990iccv-invariance/

Abstract

It is shown that curved planar objects have shape descriptors that are unaffected by the position, orientation and intrinsic parameters of the camera. These shape descriptors can be used to index quickly and efficiently into a large model base of curved planar objects, because their value is independent of pose and unaffected by perspective. Thus, recognition can proceed independent of calculating pose. Object curves are represented using conics, attached with a fitting technique that commutes with projection. This means that the pose of an object can be determined by backprojecting known conics. The authors show examples of recognition and pose determination using real image data.< <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

Forsyth et al. "Invariance-a New Framework for Vision." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139604

Markdown

[Forsyth et al. "Invariance-a New Framework for Vision." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/forsyth1990iccv-invariance/) doi:10.1109/ICCV.1990.139604

BibTeX

@inproceedings{forsyth1990iccv-invariance,
  title     = {{Invariance-a New Framework for Vision}},
  author    = {Forsyth, David A. and Mundy, Joseph L. and Zisserman, Andrew and Brown, Christopher M.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {598-605},
  doi       = {10.1109/ICCV.1990.139604},
  url       = {https://mlanthology.org/iccv/1990/forsyth1990iccv-invariance/}
}