Communications of the ACM
With Commercial Satellite Imagery, Computer Learns to Quickly Find Missile Sites in China
The study used commercially available remote sensing satellite imagery of one-meter resolution.
Credit: Gifex
A new study says deep machine learning algorithms can help the military defense and intelligence communities analyze satellite imagery.
Researchers from the Center for Geospatial Intelligence at the University of Missouri used a deep learning neural network to assist human analysts in visual searches for surface-to-air missile sites over a large area in southeastern China. The results showed that the computer performed an average search time of only 42 minutes for an area of approximately 90,000 square kilometers. By comparison, North Korea is about 120,000 square kilometers.
"This was more than 80 times more efficient than a traditional human visual search," says University of Missouri electrical engineering and computer science professor Curt Davis, the center's director.
From SpaceNews
View Full Article
No entries found