Share Email Print

Proceedings Paper

Target detection using co-occurrence matrix segmentation and its hardware implementation
Author(s): John Eric Auborn; James Martin Fuller Jr.; Howard M. McCauley
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A number of acquisition, tracking, and classification algorithms have been developed to deal with various image processing problems in the laboratory. Typically these are too complicated to implement in a low-cost, real-time processor. Using image data in many real-time applications requires a system with very high data rates, low power dissipation, and a small packaging volume. A processor architecture suitable for these applications have been developed, and a co-occurrence matrix target detection algorithm adapted and demonstrated in computer simulation and real-time hardware. A histogram or gray-level distribution is often used to select a threshold for image segmentation. This is often inadequate, as the histograms tend to be noisy and exhibit many small peaks. Co-occurrence matrix based segmentation allows homogeneous regions of an image to be identified and separated from a cluttered background. Results are shown for target segmentation using representative infrared imagery and real-time hardware.

Paper Details

Date Published: 1 August 1991
PDF: 7 pages
Proc. SPIE 1482, Acquisition, Tracking, and Pointing V, (1 August 1991); doi: 10.1117/12.45700
Show Author Affiliations
John Eric Auborn, Naval Weapons Ctr. (United States)
James Martin Fuller Jr., Naval Weapons Ctr. (United States)
Howard M. McCauley, Naval Weapons Ctr. (United States)

Published in SPIE Proceedings Vol. 1482:
Acquisition, Tracking, and Pointing V
Michael K. Masten; Larry A. Stockum, Editor(s)

© SPIE. Terms of Use
Back to Top