Lockheed Martin (NYSE: LMT) developed a satellite imagery recognition system using open-source deep learning libraries to quickly identify and classify objects or targets in large areas across the world, potentially saving image analysts countless hours manually categorizing and labeling items within an image.
Global Automated Target Recognition (GATR) runs in the cloud. Fast GPU’s let GATR scan a large area very quickly, while deep learning methods automate object recognition and reduce the need for extensive algorithm training.
GATR teaches itself the identifying characteristics of an object area or target, for example, learning how to distinguish between a cargo plane and a military transport jet. The system scales quickly to scan large areas, including entire countries. GATR uses deep learning techniques common in the commercial sector and can identify ships, airplanes, buildings, seaports, and many other categories.
GATR has a high accuracy rate at well over 90 percent on the models tested so far. As an example, it took only two hours to search the entire state of Pennsylvania for fracking sites – an area of 120,000 square kilometers, or 46,332 square miles.
GATR builds on research Pritt’s team (Mark Pritt, Senior Fellow at Lockheed Martin and principle investigator for GATR) pioneered during an Intelligence Advanced Research Projects Activity (IARPA) challenge, called the "Functional Map of the World". The Lockheed Martin team was the only team from a company who placed in the top five.
Maria Demaree, VP and GM of Lockheed Martin Space Mission Solutions, said there’s more commercial satellite data than ever available today, and up until now, identifying objects has been a largely manual process. Artificial Intelligence models such as GATR keep analysts in control while letting them focus on higher-level tasks.
Mark Pritt, Senior Fellow at Lockheed Martin and principle investigator for GATR, added that this system teaches itself the defining characteristics of an object, saving valuable time training an algorithm and ultimately letting an image analyst focus more on their mission.