Share Email Print

Proceedings Paper

Improved neural network modeling of inverse lens distortion
Author(s): Jason P. de Villiers; Jaco Cronje; Fred Nicolls
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Inverse lens distortion modelling allows one to find the pixel in a distorted image which corresponds to a known point in object space, such as may be produced by RADAR. This paper extends recent work using neural networks as a compromise between processing complexity, memory usage and accuracy. The already encouraging results are further enhanced by considering different neuron activation functions, architectures, scaling methodologies and training techniques.

Paper Details

Date Published: 3 June 2011
PDF: 9 pages
Proc. SPIE 8056, Visual Information Processing XX, 80560L (3 June 2011); doi: 10.1117/12.884065
Show Author Affiliations
Jason P. de Villiers, Council for Scientific and Industrial Research (South Africa)
Univ. of Cape Town (South Africa)
Jaco Cronje, Council for Scientific and Industrial Research (South Africa)
Fred Nicolls, Univ. of Cape Town (South Africa)

Published in SPIE Proceedings Vol. 8056:
Visual Information Processing XX
Zia-ur Rahman; Stephen E. Reichenbach; Mark Allen Neifeld, 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?