Share Email Print

Proceedings Paper

Parallel Algorithms For Automatic Target Identification Using CO2 Laser Radar Imagery
Author(s): Arthur V. Forman Jr.; Daniel J. Sullivan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper describes a parallel implementation of algorithms for automatic target identification using a CO2 laser radar sensor, which provides pixel-registered visual, infrared, relative range and Doppler (motion) images. Images are preprocessed to remove artifacts and speckle and to detect edges. The processed images are then passed to a transformation which provides a representation independent of translation, rotation, and scaling of the input scene. The transformed image is designed to be input to a neural network to extract features representative of the targets. This paper also discusses three-dimensional transformation of range images for pattern matching and the implementation of algorithms in a single instruction, multiple data (SIMD) parallel architecture.

Paper Details

Date Published: 6 December 1989
PDF: 10 pages
Proc. SPIE 1154, Real-Time Signal Processing XII, (6 December 1989); doi: 10.1117/12.962382
Show Author Affiliations
Arthur V. Forman Jr., Martin Marietta Electronic Systems (United States)
Daniel J. Sullivan, Martin Marietta Electronic Systems (United States)

Published in SPIE Proceedings Vol. 1154:
Real-Time Signal Processing XII
J. P. Letellier, 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?