No matter where people go throughout the day, chances are they’ve been caught on camera – at work, at the bank, at school or in a mall. And sometimes those cameras pick up a crime, like a shooting. But what if those cameras could help before the trigger was pulled?
A Virginia security company said it could.
“This particular technology, I think, represents a breakthrough,” said Dave Fraser, CEO of Leesburg-based Omnilert. His company uses artificial intelligence to monitor video cameras for potential violence.
“It detects handguns and rifles by essentially taking the place of a human being. Looking at video feeds. Does it 24 hours a day,” he said.
It is estimated that there are 70 million security cameras in the United States, but according to an industry survey, less than 1% of them are monitored live by a human.
Fraser said his product is always alert.
“Never takes a coffee break, never gets tired, and never loses focus,” he said.
The AI technology uses security cameras that most businesses already have in place, potentially saving costs, and is already being used in locations across the country and in the DC area, Fraser said.
“In this area we have schools, shopping malls and banks using it,” he said.
Joe Belfiore is one such client. A retired DC police officer of 13 years now working in the security industry, he’s seen his share of gun violence.
“Everyone has security patrols, everyone has video cameras,” he said. “Do they work well together?”
He has been running the technology for a few months on some cameras in apartment complexes he works with in the district.
“I would describe it as, say, an early warning system for the potential for gun violence, like a smoke detector for gun violence. You have a picture, you know, of who might be carrying a gun at a place. So it’s really helpful,” he said.
Fraser demonstrated how the technology works for News4.
“The red box indicates that the weapon was indeed detected,” Fraser said.
Once the technology detects a firearm, within seconds it transmits that information to a designated operator who confirms the threat and activates a security plan, Fraser said. This could include contacting the police, sending warnings by text, email with signage or sirens, and even locking the doors of the establishment.
When asked how AI can tell the difference between a potential shooter and a police officer walking in with a gun, Fraser explained, “The technology doesn’t just recognize firearms. It actually has to identify that there is a threat.”
“The weapon actually has to be brandished for it to be considered a threat,” he said. “There are a lot of people opening doors or law enforcement officers, security guards.”
He said the technology is also trained to identify other common objects that might look like a gun.
“Ninety percent of the time it’s a phone or some other object in people’s hands,” Fraser said.
During the Belfiore pilot program, he said the technology got false positives with cellphones. He added that it gets smarter over time.
A company spokesperson told News4 that false positives are encountered by all detection technologies and that Belfiore “was one of the first users of Omnilert Gun Detect, and there have been countless updates. update of the AI during this period”.
Over the summer, the AI detected a weapon in one of the buildings in Belfiore, he said.
“I think it can focus attention and resources on brewing issues,” he said. “Yes, so I see it as potentially very promising.”
Fraser said no active shooters have yet been caught with the new technology – hundreds of firearms have already been detected.
“As he is used more, we have more intelligence to be able to train him and make him better and better,” he said.
Reported by Shawn Yancy, produced by Rick Yarborough, shot by Steve Jones and edited by Jeff Piper.