USA: Lockheed Martin has announced the marketing of a new artificial intelligence (AI) product that could help analysts to identify certain objects in satellite imagery. While demonstrating, the AI product searched the state of Pennsylvania and in just two hours was able to locate every site in the state.
The company displayed the system for the first time to the public at GEOINT 2019 conference that is being attended by intelligence analysts from National Geospatial Intelligence Agency and the National Reconnaissance Office. According to Mark Pritt, senior fellow at Lockheed Martin who assisted in developing the system said, “The so-called global automated target recognition system could be used to find any type of objects in satellite imagery, saving analysts a lot of time and manual labor.”
Analysis of satellite imagery is a growing and crowded industry where defense equipment suppliers compete with commercial players. Lockheed Martin has decided to commercialize the system that was primarily designed to compete with Intelligence Advanced Research Projects Activity “Functional Map of the World” challenge last year. The team from Lockheed Martin was the only American team that came second from 69 participants.
Pritt added, “Today there’s still a lot of manual labor involved in identifying what you’re seeing in those images, they are time consuming to classify and label.” IARPA had contestants who could develop automated techniques to precisely classify points of interest from satellite imagery.
Pritt said there are many companies that offer satellite imagery recognition systems that quickly identify and classify objects in areas across the world, but few provide global coverage. “With our tool, the user can draw a box anywhere in the world and hit the button,” he said. “The system will go search for objects of interest such as fracking wells, airplanes or refugee camps.” The objects of interest show up as icons on the map and the user can click on the icon to get a closer look.
Lockheed’s target recognition system uses satellite imagery from major commercial vendors like Maxar and Planet. With sharper 30cm resolution images, the system can distinguish between a cargo plane and a military transport jet, for example. It uses deep learning techniques common in the commercial sector to identify ships, airplanes, buildings and seaports.