Share Email Print
cover

Proceedings Paper

Three-dimensional model alignment without computing pose
Author(s): Joseph L. Mundy; Paul Max Payton; Michael H. Brill; Eamon B. Barrett; Richard P. Welty
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Most current object recognition systems are based on a 3D model which is used to describe the image projection of an object over all viewpoints. We introduce a new technique which can predict the geometry of an object under projective transformation. The object geometry is represented by a set of corresponding features taken from two views. The projected geometry can be constructed in any third view, using a viewpoint invariant derived from the correspondences.

Paper Details

Date Published: 1 April 1992
PDF: 13 pages
Proc. SPIE 1623, The 20th AIPR Workshop: Computer Vision Applications: Meeting the Challenges, (1 April 1992); doi: 10.1117/12.58060
Show Author Affiliations
Joseph L. Mundy, General Electric Co. (United States)
Paul Max Payton, Lockheed Missiles & Space Co., Inc. (United States)
Michael H. Brill, Science Applications International Corp. (United States)
Eamon B. Barrett, Lockheed Missiles & Space Co., Inc. (United States)
Richard P. Welty, Infologic (United States)


Published in SPIE Proceedings Vol. 1623:
The 20th AIPR Workshop: Computer Vision Applications: Meeting the Challenges

© SPIE. Terms of Use
Back to Top