Share Email Print

Proceedings Paper

Invariant methods for model transfer and object reconstruction based on multiple reference images
Author(s): Eamon B. Barrett; Gregory O. Gheen; Paul Max Payton
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Invariant methods for object representation and model matching develop relationships among object and image features that are independent of the quantitative values of the camera parameters of object orientation, hence the term invariant. Three-dimensional models of objects of scenes can be reconstructed and transferred to new images, given a minimum of two reference images and a sufficient number of corresponding points in the images. By using multiple reference images, redundancy can be exploited to increase robustness of the procedure to pixel measurement errors and systematic errors (i.e., discrepancies in the camera model). We present a general method for deriving invariant relationships based on two or more images. Simulations of model transfer and reconstruction demonstrate the positive effect of additional reference images on the robustness of invariant procedures. Pixel measurement error is simulated by adding random noise to coordinate values of the features in the reference images.

Paper Details

Date Published: 23 March 1995
PDF: 12 pages
Proc. SPIE 2421, Image and Video Processing III, (23 March 1995); doi: 10.1117/12.205480
Show Author Affiliations
Eamon B. Barrett, Lockheed Missiles & Space Co., Inc. (United States)
Gregory O. Gheen, Lockheed Missiles & Space Co., Inc. (United States)
Paul Max Payton, Lockheed Missiles & Space Co., Inc. (United States)

Published in SPIE Proceedings Vol. 2421:
Image and Video Processing III
Robert L. Stevenson; Sarah A. Rajala, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?