How a Technology Called FeatureTrace Will Automate Military Surveillance

https://www.reutersconnect.com/all?id=tag%3Areuters.com%2C2012%3Anewsml_GM1E8B21HMG01&share=true
February 17, 2021 Topic: Security Region: Americas Blog Brand: The Buzz Tags: FeatureTraceSensorsAIFuture WarfareSurveillance

How a Technology Called FeatureTrace Will Automate Military Surveillance

The technology gathers and anaylizes images that are then checked over by a human intelligence analyst.

Surveillance cameras, drone sensors and space-spaced satellite reconnaissance technologies are all designed make instant object determinations, perform data analyses and quickly identify items of interest. This is a process which can be both extremely complex and challenging for force commanders looking to navigate unknown terrain or fast-changing combat dynamics on the ground below.

An extensive, elaborate database of factors, facts, variables and identifiable geographical features are all part of a broader interpretive calculus necessary to provide images, video feeds or renderings to human decision makers. A technology-focused industry firm which does work with Department of Defnese called CACI is developing a new software application called FeatureTrace to improve or expedite this process.

“Our software breaks down an image into bite size pieces for processing by the neural network. The output is a fully processed image with all the features identified with up to 97 percent accuracy,” Brian No, CACI Manager of AI Research & Development, said in a company essay.

The main sought-after advantage with FeatureTrace is, among other things, to reduce the amount of time required to generate a “finished image.”

“FeatureTrace refines the neural network’s output to make the image much crisper and formatted in a way that an analyst can immediately use that image in any geospatial software tool of their choice,” No added.

A CACI essay says FeatureTrace uses Deep Learning to automate the collection of features such as roads, buildings, and lakes, contained within satellite imagery. Once the process is complete, an analyst then quality checks the results. Building upon this progress, CACI is now working to expand the analytical purview of FeatureTrace to move beyond features such as roads and building to extract “different features, such as hydrography, waterways, and powerlines.”

Space sensors are taking on new measures of urgency as the need for real-time, globally focused intelligence, surveillance, and reconnaissance (ISR) continues to grow in importance. Newer long-range, high fidelity space sensors, coupled with faster data processing, are being developed to analyze, compare and interpret otherwise disconnected geographical variables such as weather, terrain or urban mapping specifics. This is not only crucial to well-known space military missions such missile launch warning operations using Space Based Infrared sensors or navigational systems but a growing number of technologies relied upon or used by military forces.

As more platforms develop an ability to share targeting information and coordinate in real time across vast distances and changing geographical and atmospheric conditions, there will be an ever-increasing need to transmit identified geographical detail between combat nodes. This would pertain greatly to targeting, enemy force movements and other conditions likely to impact warfare dynamics. Therefore, identifying features and details of great significance and sharing them through high-fidelity rapid imaging, it seems, could offer a large margin of difference when it comes to combat operations.

Kris Osborn is the defense editor for the National Interest. Osborn previously served at the Pentagon as a Highly Qualified Expert with the Office of the Assistant Secretary of the Army—Acquisition, Logistics & Technology. Osborn has also worked as an anchor and on-air military specialist at national TV networks. He has appeared as a guest military expert on Fox News, MSNBC, The Military Channel, and The History Channel. He also has a Masters Degree in Comparative Literature from Columbia University.

Image: Reuters.