Geometrical Learning from Multiple Stereo Views Through Monocular Based Feature Grouping

Abstract

A geometrical learning system is described which constructs automatically the geometric model of indoor environments from multiple stereo views. The produced model includes not only 3-D segments initially provided by a stereo vision system, but also 3-D feature groups. Feature grouping helps to predict the position of a given view with respect to the current model and allows one to correct noisy features by the geometric constraints of feature groups. This 3-D feature grouping is based on a monocular process working on the 2-D segments associated with one source image of a stereo view. Experimental results are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Thirion and Quan. "Geometrical Learning from Multiple Stereo Views Through Monocular Based Feature Grouping." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139577

Markdown

[Thirion and Quan. "Geometrical Learning from Multiple Stereo Views Through Monocular Based Feature Grouping." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/thirion1990iccv-geometrical/) doi:10.1109/ICCV.1990.139577

BibTeX

@inproceedings{thirion1990iccv-geometrical,
  title     = {{Geometrical Learning from Multiple Stereo Views Through Monocular Based Feature Grouping}},
  author    = {Thirion, Eric and Quan, Long},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1990},
  pages     = {481-484},
  doi       = {10.1109/ICCV.1990.139577},
  url       = {https://mlanthology.org/iccv/1990/thirion1990iccv-geometrical/}
}