Share Email Print

Proceedings Paper

Feed-forward neural networks to solve the closely-spaced objects problem
Author(s): Thomas J. Bartolac; Ed P. Andert Jr.
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We have applied a feed-forward neural network to the task of resolving closely-spaced objects (CSO). Traditional algorithmic methods are computationally expensive or numerically unstable, and techniques based on ad hoc rules are too subjective. Our approach relies on the principle that a sufficiently complex neural network can approximate an arbitrary function to an arbitrary degree of accuracy. We train a neural network to approximate the multi- dimensional function that maps from detector signal space to CSO parameter space, using an aggressive Hessian-based training algorithm and training set examples synthesized from the known inverse function. We find two important empirical results: we can simultaneously identify when the training set size is sufficient to adequately represent the mapping function, and when the network has achieved optimum generalization capability, for a given degree of network complexity. Thus we can predict the network and training set sizes necessary to achieve a given mission performance. Finally, we show how such a network can be used to provide sub-pixel resolution capabilities for missions observing both single objects and CSOs, as part of a real-time 2D sensor processor.

Paper Details

Date Published: 6 July 1994
PDF: 12 pages
Proc. SPIE 2235, Signal and Data Processing of Small Targets 1994, (6 July 1994); doi: 10.1117/12.179087
Show Author Affiliations
Thomas J. Bartolac, Sparta, Inc. (United States)
Ed P. Andert Jr., Conceptual Systems & Software (United States)

Published in SPIE Proceedings Vol. 2235:
Signal and Data Processing of Small Targets 1994
Oliver E. Drummond, Editor(s)

© SPIE. Terms of Use
Back to Top