Determining Linear Shape Change: Toward Automatic Generation of Object Recognition Programs
Abstract
A 3-D object-localization task may be divided into two parts. First, one visible region is classified into one of the aspects of the 3-D object where an aspect is defined as a topologically equivalent class of appearances. Then, the precise attitude and position of the object are determined within one aspect. The authors generate a program to determine the precise attitude and position of an object within one aspect, provided that the face correspondences are given as the result of aspect classification. They establish rules (to define each free coordinate system at each aspect) and correspondences between model edges and image edges, and iteratively solve the transformation equation to determine the object's attitude and position using these correspondences. To turn the strategy into a runnable program, an object library and a geometric compiler are prepared.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Ikeuchi and Hong. "Determining Linear Shape Change: Toward Automatic Generation of Object Recognition Programs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1989. doi:10.1109/CVPR.1989.37887Markdown
[Ikeuchi and Hong. "Determining Linear Shape Change: Toward Automatic Generation of Object Recognition Programs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1989.](https://mlanthology.org/cvpr/1989/ikeuchi1989cvpr-determining/) doi:10.1109/CVPR.1989.37887BibTeX
@inproceedings{ikeuchi1989cvpr-determining,
title = {{Determining Linear Shape Change: Toward Automatic Generation of Object Recognition Programs}},
author = {Ikeuchi, Katsushi and Hong, Ki Sang},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1989},
pages = {450-457},
doi = {10.1109/CVPR.1989.37887},
url = {https://mlanthology.org/cvpr/1989/ikeuchi1989cvpr-determining/}
}