Share Email Print
cover

Proceedings Paper

Locally connected network for real-time target detection
Author(s): Gregory M. Budzban; Arthur V. Forman; Richard Skoblick
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The detection of human-made objects with low false alarm rates in lit imagery remains a technically challenging problem. In addition, many currently proposed systems for autonomous air vehicles require the algorithms to process images at the rate of 30 frames/second (real-time). Parallel distributed processes, such as neural networks, offer potential solutions to problems of this complexity. The current algorithm takes advantage of the presence of both long straight lines and curvature points in human-made objects. These features are among those recognized pre-attentively by the human visual system. It is a generalization of work done by Sha'Ashua and Ullman at MIT on the extraction of so-called salient features. The addition of curvature detection, however, is what allows the algorithm to achieve acceptable false alarm rates. On simulated FUR imagery taken from the U.S. Army C2NVEO terrain board, low false alarm rates have been achieved while maintaining 100% target detection.

Paper Details

Date Published: 1 April 1992
PDF: 6 pages
Proc. SPIE 1623, The 20th AIPR Workshop: Computer Vision Applications: Meeting the Challenges, (1 April 1992); doi: 10.1117/12.58072
Show Author Affiliations
Gregory M. Budzban, Southern Illinois Univ. (United States)
Arthur V. Forman, Martin Marietta Corp. (United States)
Richard Skoblick, Martin Marietta Corp. (United States)


Published in SPIE Proceedings Vol. 1623:
The 20th AIPR Workshop: Computer Vision Applications: Meeting the Challenges

© SPIE. Terms of Use
Back to Top