Curve Finder Combining Perceptual Grouping and a Kalman like Fitting

Abstract

We present an algorithm that extracts curves from a set of edgels within a specific class in a decreasing order of their "length". The algorithm inherits the perceptual grouping approaches. But, instead of using only local cues, a global constraint is imposed on each extracted subset of edgels, that the underlying curve belongs to a specific class. In order to reduce the complexity of the solution, we work with a linearly parameterized class of curves, a function of one image coordinate. This first allows one to use recursive Kalman based fitting and, second, to cast the problem as an optimal path search in a directed graph. Experiments on finding lane-markings on roads demonstrate that real-time processing is achievable.

Cite

Text

Guichard and Tarel. "Curve Finder Combining Perceptual Grouping and a Kalman like Fitting." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.790378

Markdown

[Guichard and Tarel. "Curve Finder Combining Perceptual Grouping and a Kalman like Fitting." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/guichard1999iccv-curve/) doi:10.1109/ICCV.1999.790378

BibTeX

@inproceedings{guichard1999iccv-curve,
  title     = {{Curve Finder Combining Perceptual Grouping and a Kalman like Fitting}},
  author    = {Guichard, Frédéric and Tarel, Jean-Philippe},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {1003-1008},
  doi       = {10.1109/ICCV.1999.790378},
  url       = {https://mlanthology.org/iccv/1999/guichard1999iccv-curve/}
}