DocumentCode :
1263423
Title :
Recognition of planar objects in 3-D space from single perspective views using cross ratio
Author :
Lei, Guo
Author_Institution :
Dept. of Inf. Eng., Xidian Univ., Xi´´an, China
Volume :
6
Issue :
4
fYear :
1990
fDate :
8/1/1990 12:00:00 AM
Firstpage :
432
Lastpage :
437
Abstract :
An approach for recognition of a planar polygon from a single 2-D perspective projection using the basic viewpoint invariant cross-ratio (CR) is presented. The shape CR-descriptor of a spatial planar polygon, i.e. the CR sequence extracted from its single projective image, is proposed. The minimum mean square error is used as the matching criterion. Examples are given. The approach can be directly applied to the recognition and motion analysis of 3-D objects that contain planar polygons
Keywords :
computational geometry; pattern recognition; picture processing; cross ratio; minimum mean square error; motion analysis; pattern recognition; planar object recognition; planar polygon; single projective image; Chromium; Computer vision; Data mining; Helium; Image recognition; Mean square error methods; Motion analysis; Object recognition; Parallel processing; Shape;
fLanguage :
English
Journal_Title :
Robotics and Automation, IEEE Transactions on
Publisher :
ieee
ISSN :
1042-296X
Type :
jour
DOI :
10.1109/70.59368
Filename :
59368
Link To Document :
بازگشت