A company that uses artificial intelligence to detect firearms in active shooting settings has been awarded a US$1.25 million grant by the US Air Force to integrate the technology into existing unmanned aerial vehicles.
This is the third R&D grant the Air Force has awarded to ZeroEasy, whose core business is protecting schools with its gun detection video analytics platform.
With ZeroEyes technology, the camera in a flying drone can be used to locate a firearm as soon as it appears, report it to a weapons specialist at an operations center to assess the threat, and Instruct to take action – all within three to five seconds.
“A quarter of active shootings occur on government property, and we will do everything we can to protect our airmen,” Dover AFB Chief Innovation Officer Captain Nicholas Martini said in a statement.
“ZeroEasy’s technology not only provides another layer of security,” he adds, “it will also enable us to reduce our investment in security personnel and utilize our manpower for more mission-critical tasks.”
In addition to the Dover award, ZeroEyes has a $750,000 grant for drone-robot enabled active shooter deterrence at Ellsworth AFB, SD, and a $1.2 million grant for unmanned ground vehicle automated threat detection at Minot AFB, ND.
“DoD was impressed by what we had and asked us if we could apply our technology to mobile cameras, unmanned aerial systems and unmanned ground vehicles,” said co-founder Sam Alimo, ZeroEas chief revenue officer.
Alimo, along with the four other founders of ZeroEasy, are all former leaders of the Navy SEALs team. He said his company’s technology could be very valuable in a war zone.
“When you’re on a mission, the base for protection is often low so having an extra layer of security with drones that can detect someone with a gun in a crowd of people without it, would be a huge asset.” ,” he said.
He explained that the Air Force grant will enable ZeroEyes to adapt its technology, which is currently used on stationary video cameras, on mobile platforms as well as on robotic dogs. “First responders like the idea of walking a gun detection dog in an active shooter situation rather than a human being,” he said.
Optimizing on-the-go vehicles could also open up other business possibilities for ZeroEyes. “A lot of third-party logistics companies and sporting arenas ask us for the technology,” Alimo explained. “Playgrounds want the ability to follow a drone around the stands.”
Last week, ZeroEyes announced that its gun detection system was being deployed at Vassar Public Schools, located 45 minutes from Oxford High School in Michigan, the scene of a mass shooting in November 2021 that killed four students and seven people were injured. including a teacher. After shooting, Oxford began a pilot program with ZeroEyes.
“I stumbled upon the ZeroEas at a superintendent’s convention. I didn’t know anything about them,” confessed Vassar Public School superintendent Dot Blackwell.
“What surprises me about the product is that it’s very active,” she told TechNewsWorld. “Someone who is ex-military or law enforcement is looking at frames from our cameras 24/7, and me and law enforcement will be alerted in seconds.”
“In these situations, the first few seconds are the key in stopping them,” she said.
Alaimo explained that the ZeroEyes technology can be used with any existing security camera system. “It can identify an object and send an alert to first responders in three to five seconds,” Alimo said. “However, we have a human in the loop because no algorithm will ever have 100% certainty on anything.”
ZeroEasy’s machine learning models have been trained with thousands of samples – everything from snub-nosed revolvers to semi-automatic pistols to submachine guns to assault rifles to shotguns and hunting rifles, he said.
“When the algorithm sees what it thinks is a gun, it will send an alert to our surveillance center,” he continued. “The center is staffed with veterans and law enforcement personnel who are very comfortable in these situations. He has the final say on what a gun is. This way, we ensure that our customers never get false positives. ,
“This process is very fast,” he said. “The camera will see the gun. The image will be sent to our surveillance center, and the surveillance will be sent to the customer in three to five seconds.
Although images are being piped into ZeroEyes’ monitoring center from across the country, it can accommodate workflows with a modest number of analysts.
“The algorithm is such that we don’t get overwhelmed by false positives,” Alimo said. “It’s manageable to the point that we’ve been able to scale to a million cameras without a massive surveillance center.”
“Right now,” he continued, “we are in 30 states and we have less than a dozen analysts in our surveillance center.”
“We have identified hundreds of guns, some of them real, some of them not real, some of them fake, some of them sharp guns,” he said.
Once a potential threat has been identified, the threat system can be notified in a number of ways.
“We have several mechanisms in place to notify customers if some of them don’t work,” Alimo said. “There is a call tree to make sure that no matter what happens, we can find someone on the phone. We also have a mobile app that sends notifications with the shooter’s image, the shooter’s exact location, and a bread crumb trail.
“We also have desktop notifications and integrations with an organization called RapidSOS,” he continued. “They are integrated with 93% of public safety answering points nationwide.”
“A school often tells us to send our alerts to Rapid SOS,” he said, “so first responders can get notification at the same time as a principal so both can enforce their safety protocols simultaneously.”
The combination of artificial intelligence and surveillance video may raise red flags among privacy advocates, but ZeroEyes seems to have covered those grounds. It says its AI does not record, store or share videos or images of students or others, ensuring that privacy is maintained.