DARPA's CT2WS System Reads Minds To Establish Threat Levels

 Augmented Reality

A new DARPA project involving a threat detection system uses “mind reading.” The Cognitive Technology Threat Warning System (CT2WS) uses a combination of a digital imaging system, computer algorithms and an electroencephalogram (EEG) to help observers scan areas for threats with much greater accuracy by making them aware of things that they’ve seen, but aren’t consciously aware of.

R

emember Tony Stark's augmented reality lenses from the Iron Man movies, where data is projected in front of him  for targeting and navigation? 

Now such threat-detecting devices aren't just the fantasy of films. The U.S. military is developing binoculars that read the user's own subconscious brainwaves to help identify threats from afar.

The goggles, announced this week by the U.S. Defense Advanced Research Project Agency, have been given project name "Cognitive Technology Threat Warning System" -- or CT2WS for short.

DARPA intends to build a "120 megapixel camera capable of scanning across 120 degrees of view" to replace your soldier's conventional binoculars, according to The Register. These can take multiple images with each scan and feed them to a software program to identify potential threats.

However, for DARPA, this system alone was nearly inopperable, because nearly half the "threats" the best software program identifies aren't threats at all, making them effectively useless for soldiers in the field.

The strategy now is to combine the system with the user's perceptions of the field of view.  

"CT2WS built on the concept that humans are inherently adept at detecting the unusual," the DARPA announcement of the threat-detection system reads. In less vague terms, this means that clever DARPA engineers had the idea to attach the binoculars to an electroencephalogram (EEG) cap, which actually "monitors brain signals in real-time." The brainwaves and pictures snapped by the binoculars are transmitted to a laptop or another powerful computer, which crunches the data and flags noteworthy images that contain enemies lurking in the distance.

The addition of the EEG cap has cut the false-positive rate from 47 percent to only 9 percent. Add to that commercial radar, and the system is 100 percent effective in identifying enemies in field tests, DARPA claims.

How does this work so well? It turns out humans can accurately perceive such threats -- just not consciously. Our unconscious minds are very good at sorting enemy soldiers from unusually-shaped bushes. This means that if you show a soldier an image of a far-away 'something', the soldier may not be able to tell you whether it's a bush or combatant -- but show him the image for a tenth of a second,and the subconscious mind will fire off a distinctive brainwave called a "P-300" when the 'something' seems like a threat.

The use of EEG-based human filtering significantly reduces the amount of false alarms. The cognitive algorithms can also highlight many events that would otherwise be considered irrelevant but are actually indications of threats or targets, such as a bird flying by or a branch’s swaying. In testing of the full CT2WS kit, absent radar, the sensor and cognitive algorithms returned 810 false alarms per hour. When a human wearing the EEG cap was introduced, the number of false alarms dropped to only five per hour, out of a total of 2,304 target events per hour, and a 91 percent successful target recognition rate.

DARPA said in 2007 that the binoculars should have a range of "1,000 to 10,000 meters" and be able to spot moving vehicles from up to 6 miles away, according toWired.

This is not the first EEG-enabled device that has been announced this year: Recently EEG seems to have hit its stride, with NeuroSky's popular Necomimi toy hitting stores and scientists at the University of California at Irvine announcing the first successful test of mind-controlled robotic legs.

SOURCE  Huffington Post

By 33rd Square

Subscribe to 33rd Square