DocumentCode
2474088
Title
Determining linear shape change: toward automatic generation of object recognition programs
Author
Ikeuchi, Katsushi ; Hong, Ki Sang
Author_Institution
Sch. of Comput. Sci., Carnegie-Mellon Univ., Pittsburgh, PA, USA
fYear
1989
fDate
4-8 Jun 1989
Firstpage
450
Lastpage
457
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
Keywords
computerised pattern recognition; 3-D object-localization; aspect classification; computerised pattern recognition; face correspondences; geometric compiler; linear shape change; object library; object recognition programs; Classification tree analysis; Computer science; Equations; Libraries; Object recognition; Position measurement; Predictive models; Program processors; Shape; Target recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89., IEEE Computer Society Conference on
Conference_Location
San Diego, CA
ISSN
1063-6919
Print_ISBN
0-8186-1952-x
Type
conf
DOI
10.1109/CVPR.1989.37887
Filename
37887
Link To Document