Spatiotemporally Adaptive Estimation and Segmenation of OF-Fields

Abstract

A grayvalue structure tensor provides knowledge about a local grayvalue variation. This knowledge can be used to devise a spatiotemporally adaptive optic flow estimation process. Such an adaptive estimation lowers the level at which the resulting optic flow (OF) field is disturbed by noise and estimation artefacts. This in turn substantially simplifies the analysis of remaining — often subtle — effects which easily jeopardize a ‘naive’ segmentation approach. Appropriate treatment of such effects eventually results in a basically simple, but nevertheless surprisingly robust segmentation approach. Various stages of this approach are illustrated by examples for the extraction of moving vehicle images from a digitized road intersection video-sequence.

Cite

Text

Nagel and Gehrke. "Spatiotemporally Adaptive Estimation and Segmenation of OF-Fields." European Conference on Computer Vision, 1998. doi:10.1007/BFB0054735

Markdown

[Nagel and Gehrke. "Spatiotemporally Adaptive Estimation and Segmenation of OF-Fields." European Conference on Computer Vision, 1998.](https://mlanthology.org/eccv/1998/nagel1998eccv-spatiotemporally/) doi:10.1007/BFB0054735

BibTeX

@inproceedings{nagel1998eccv-spatiotemporally,
  title     = {{Spatiotemporally Adaptive Estimation and Segmenation of OF-Fields}},
  author    = {Nagel, Hans-Hellmut and Gehrke, A.},
  booktitle = {European Conference on Computer Vision},
  year      = {1998},
  pages     = {86-102},
  doi       = {10.1007/BFB0054735},
  url       = {https://mlanthology.org/eccv/1998/nagel1998eccv-spatiotemporally/}
}