Communications of the ACM
New Algorithms For Computerized, Large-Scale Surveillance
A synthetic scene showing two buildings as seen from above. The buildings are visible because image analysts used algebra to make them more distinct.
Credit: Myoung An and Richard Tolimieri / dB Research
The U.S. Air Force has adapted the advanced algebraic theories of mathematicians Myoung An and Richard Tolimieri to improve its object and target detection technology. The methodology was used to make reviewing photographic, video, and radar images to facilitate military planning more effective. Researchers at the Air Force Research Laboratory (AFRL) expect the algebraic structures to cut the time overhead for reviewing large amounts of surveillance material by 99 percent. The algebraic theories will lead to enhancements for detecting subtle patterns or features in conditions such as dust, fog, bushes, and other visual obstructions.
"One challenge of the research is the matching of the algebraic structure to the data and problems at hand," says AFRL lead researcher Richard A. Albanese. "We are applying algebraic structures to data index sets and in this way finding patterns that were not easily detectable before."
Myoung An and Tolimieri assisted the U.S. Navy with a related technology that uses sonar to detect shallow water mines.
From Wright-Patterson Air Force Base
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
No entries found