ML Anthology

Using Automatically Constructed View-Independent Relational Model in 3D Object Recognition

Shujun Zhang, Geoffrey D. Sullivan, Keith D. Baker
ECCV 1992 pp. 778-786
doi:10.1007/3-540-55426-2_88 /eccv/1992/zhang1992eccv-using/

Abstract

This paper describes and demonstrates a view-independent relational model (VIRM) in a vision system designed for recognising a known 3D object from single monochromatic images. The aim is to derive a model of an object able to effect recognition without invoking pose information. The system inspects a CAD model of the object from a number of different viewpoints to identify relatively view-independent relationships among component parts of the object. These relations are represented in the form of a hypergraph. The VIRM can be searched using a best-first technique to obtain hypotheses of vehicle poses which match image features.

PDF ECCV Semantic Scholar

Cite

Text

Zhang et al. "Using Automatically Constructed View-Independent Relational Model in 3D Object Recognition." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_88

Markdown

[Zhang et al. "Using Automatically Constructed View-Independent Relational Model in 3D Object Recognition." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/zhang1992eccv-using/) doi:10.1007/3-540-55426-2_88

BibTeX

@inproceedings{zhang1992eccv-using,
  title     = {{Using Automatically Constructed View-Independent Relational Model in 3D Object Recognition}},
  author    = {Zhang, Shujun and Sullivan, Geoffrey D. and Baker, Keith D.},
  booktitle = {European Conference on Computer Vision},
  year      = {1992},
  pages     = {778-786},
  doi       = {10.1007/3-540-55426-2_88},
  url       = {https://mlanthology.org/eccv/1992/zhang1992eccv-using/}
}