There’s just too much data in large aerial images for humans to process.

L3Harris Technologies Inc (NYSE: LHX), a global aerospace and defense technology company, is building a new platform that will apply AI to help make sense of aerial data for the military.

L3Harris will create training data and workflows. These will enable a machine learning tool to process data for the Department of Defense and derive actionable intelligence from it.

Military intelligence analysts have many queries from large aerial imagery datasets. These could be, for example, identifying an object, counting the number of objects or closely monitoring a place. But they are unable to cope with the sheer volume of data.

Challenge of assimilating data

“In general, there’s a big challenge with the amount of remote sensing data that are coming down, whether that’s from space or airborne assets,” said Will Rorrer, principal of business development for geospatial and image processing at L3Harris. (Military & Aerospace Electronics)

“We really can’t look at in its entirety — certainly not exploit it in its entirety — by traditional means (with) purely human analysts,” he added.

However, a computer algorithm could help here – “That’s where there’s a natural adoption of machine learning type of techniques.”

L3Harris will use its existing repertoire of modeling and simulation tools for the DoD’s algorithm. Developed over nearly 30 years, these will create a database of training data (“very good fake imagery”).

“We’ve taken that technology that was essentially developed for another reason and pivoted (to using it) as a source of synthetic training data for these neural net applications,” says Rorrer.

Furthermore, the output from the algorithm would mesh with the DoD’s systems at the “backend.”

The training data forms the “frontend.” L3Harris is responsible for both of these.

The “middle” portion is the algorithm and there are a lot of options for this. Even commercial neural network applications can do the job.

“But we must address the front end and the back end of that in DoD space,” according to Rorrer.

Related Story:   Artificial Intelligence: AI-Controlled Robot Tanks Soon