Towards Object-Based Heuristics
Abstract
A survey and critique of previous work is given, and two object-based heuristics are developed. The structured nature of objects is the motivation for the nonaccidental alignment criterion; parallel lines within the object's bounding contour are related to the object-centered coordinate system. The regularity and symmetry inherent in many man-made objects is the motivation for the orthogonal basis constraint, an oblique set of coordinate axes in the image is presumed to be the projection of an orthogonal set of 3D coordinate axes in the scene. These heuristics are demonstrated on real and synthetic image contours.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Gross. "Towards Object-Based Heuristics." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223250Markdown
[Gross. "Towards Object-Based Heuristics." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/gross1992cvpr-object/) doi:10.1109/CVPR.1992.223250BibTeX
@inproceedings{gross1992cvpr-object,
title = {{Towards Object-Based Heuristics}},
author = {Gross, Ari David},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1992},
pages = {818-821},
doi = {10.1109/CVPR.1992.223250},
url = {https://mlanthology.org/cvpr/1992/gross1992cvpr-object/}
}