ML Anthology

Automatic Singularity Test for Motion Analysis by an Information Criterion

Ken-ichi Kanatani
ECCV 1996 pp. 697-708
doi:10.1007/BFB0015579 /eccv/1996/kanatani1996eccv-automatic/

Abstract

The structure-from-motion algorithm from two views fails if the object is a planar surface or the camera motion is a pure rotation. This paper presents a new scheme for automatically detecting these anomalies without using any knowledge about the noise in the images. This judgment does not involve any empirically adjustable thresholds, either. The basic principle of our scheme is to choose a model that has “higher predicting capability” measured by the geometric information criterion (geometric AIC) .

PDF ECCV Semantic Scholar

Cite

Text

Kanatani. "Automatic Singularity Test for Motion Analysis by an Information Criterion." European Conference on Computer Vision, 1996. doi:10.1007/BFB0015579

Markdown

[Kanatani. "Automatic Singularity Test for Motion Analysis by an Information Criterion." European Conference on Computer Vision, 1996.](https://mlanthology.org/eccv/1996/kanatani1996eccv-automatic/) doi:10.1007/BFB0015579

BibTeX

@inproceedings{kanatani1996eccv-automatic,
  title     = {{Automatic Singularity Test for Motion Analysis by an Information Criterion}},
  author    = {Kanatani, Ken-ichi},
  booktitle = {European Conference on Computer Vision},
  year      = {1996},
  pages     = {697-708},
  doi       = {10.1007/BFB0015579},
  url       = {https://mlanthology.org/eccv/1996/kanatani1996eccv-automatic/}
}