ML Anthology

Identification and 3D Description of 'shallow' Environmental Structure in a Sequence of Images

Harpreet S. Sawhney, Allen R. Hanson
CVPR 1991 pp. 179-185
doi:10.1109/CVPR.1991.139684 /cvpr/1991/sawhney1991cvpr-identification/

Abstract

A framework is presented for segmenting shallow structures from their background over a sequence of images. Shallowness is first quantified as affine describability. This is embedded in a tracking system within which hypothesized model structures undergo a cycle of prediction and model-matching. Structures emerge either as shallow or non-shallow based on their affine trackability. This paper rejects continuity heuristics for purely image motion in favor of temporal continuity defined as the consistency of generic 3-D models, namely shallow structures.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Sawhney and Hanson. "Identification and 3D Description of 'shallow' Environmental Structure in a Sequence of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139684

Markdown

[Sawhney and Hanson. "Identification and 3D Description of 'shallow' Environmental Structure in a Sequence of Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/sawhney1991cvpr-identification/) doi:10.1109/CVPR.1991.139684

BibTeX

@inproceedings{sawhney1991cvpr-identification,
  title     = {{Identification and 3D Description of 'shallow' Environmental Structure in a Sequence of Images}},
  author    = {Sawhney, Harpreet S. and Hanson, Allen R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {179-185},
  doi       = {10.1109/CVPR.1991.139684},
  url       = {https://mlanthology.org/cvpr/1991/sawhney1991cvpr-identification/}
}