DARPA Develops Cognitive Threat Detection System for Soldiers
September 22, 2012 11:04 AM
comment(s) - last by
Cognitive Technology Threat Warning System (CT2WS)
DARPA found that using all three devices in the threat detection unit at the same time helped soldiers detect 91 percent of threats
DARPA is currently testing a new way for soldiers to
from far away via cognitive tools.
Currently, soldiers can depend on drones and advanced radar to keep an eye on surrounding threats, but neither of these instruments are available 24/7. Instead, soldiers are left with cameras, portable radars or binoculars to spot an oncoming attack, but DARPA reports that these tools lead to a 47 percent or greater miss rate because they just don't advance human vision enough.
To address these issues, DARPA created the Cognitive Technology Threat Warning System (CT2WS) program back in 2008. As a result of that, a CT2WS toolkit has been developed for use on the battlefield.
The CT2WS toolkit has three main devices: a video camera with 120 megapixels, 120-degree field of view, tripod and electro-optical capabilities; cognitive visual processing algorithms that detect threats and run on laptops, and a electroencephalogram (EEG) cap that checks the soldier's
and records when a threat is detected.
The prototype was tested in Yuma Proving Ground in Arizona, tropical terrain in Hawaii and open terrain in California's Camp Roberts. During testing, DARPA found that using all three devices at the same time helped soldiers detect 91 percent of threats.
Also, the system had a very low false alarm rate. The tools are capable of understanding that a bird flying by is just a bird; not a threat. According to testing of the CT2WS unit, the devices returned only about 5 false alarms per hour. Before the EEG cap, this number was about 810 false alarms per hour.
"DARPA set out to solve a common challenge for forward troops: how can you reliably detect potential threats and targets of interest without making it a resource drain?" said Gill Pratt, DARPA program manager. "The prototype system has demonstrated an extremely low false alarm rate, a detection rate in the low nineties, all while reducing the load on the operator."
DARPA will continue testing the CT2WS system, shipping it over to the Army's Night Vision Lab next.
This article is over a month old, voting and posting comments is disabled
9/24/2012 12:34:47 PM
A) all citizens WANT to reason with you
B) that you're perception of reasoning is theirs. Hint: Its not.
"Intel is investing heavily (think gazillions of dollars and bazillions of engineering man hours) in resources to create an Intel host controllers spec in order to speed time to market of the USB 3.0 technology." -- Intel blogger Nick Knupffer
Quick Note: U.S. Military's Headless Cheetah Robot Can Outrun Any Human
September 17, 2012, 10:28 AM
New Device Sends Signals Directly from Brain to Muscles, Paralyzed Patients Could Benefit
April 20, 2012, 4:40 PM
Creationists are Mad About Google Doodle Depicting Evolution
November 24, 2015, 8:48 PM
DHS and TSA: Whoops, We Missed That 73 Airport Employees May be Terrorists
November 19, 2015, 2:16 PM
Star Wars Spinoff Film "Rogue One", Theme Park Attractions Announced
August 17, 2015, 12:20 PM
SpaceX Falcon 9's Seventh Supply Mission to ISS Ends w/ Fiery Stage 1 Explosion
June 28, 2015, 1:10 PM
Cool Science Video: Glowing Millipede Prowls the Nevada Desert
May 18, 2015, 12:00 PM
Newly Discovered Costa Rican Glass Frog is Kermit's Doppelgänger
April 22, 2015, 11:26 AM
Latest Blog Posts
Sceptre Airs 27", 120 Hz. 1080p Monitor/HDTV w/ 5 ms Response Time for $220
Dec 3, 2014, 10:32 PM
Costco Gives Employees Thanksgiving Off; Wal-Mart Leads "Black Thursday" Charge
Oct 29, 2014, 9:57 PM
"Bear Selfies" Fad Could Turn Deadly, Warn Nevada Wildlife Officials
Oct 28, 2014, 12:00 PM
The Surface Mini That Was Never Released Gets "Hands On" Treatment
Sep 26, 2014, 8:22 AM
ISIS Imposes Ban on Teaching Evolution in Iraq
Sep 17, 2014, 5:22 PM
More Blog Posts
Copyright 2016 DailyTech LLC. -
Terms, Conditions & Privacy Information