AI-based visual gun detection can be used to secure schools, stadiums, retail, healthcare and more, says Mark Franken, Vice President of Marketing at Omnilert.
Gun violence and mass shootings are on the rise across the US and occur in nearly every sector of business.
For each of the last three years alone, there have been more than 600 mass shootings – almost two a day on average.
This alarming trend has resulted in the loss of more than one million lives from gun violence since 1990.
Clearly, a new layer of protection is needed and AI visual gun detection has emerged as one of the most promising solutions.
In this article, we’ll look at what this exciting new technology is and how it is already being used in a variety of industries today to protect against active shooter threats.
Unlike other layers of security such as audio gunshot detection, AI visual detection is designed to give emergency response teams advance warning before shots are fired so lives can be saved.
The system can identify a weapon in a fraction of a second and either an integrated or external monitoring service or internal security team can verify that threat in a few seconds more.
It then only takes two more seconds to activate a response that can include dispatching police, locking doors, sounding alarms and automating other responses to notify those in harm’s way and save lives.
Some of the more advanced AI visual gun detection systems can also send both still images and a short video clip when a threat is detected to provide more context to security personnel and first responders.
This critical feature can ensure threats are quickly verified before lives are lost.
During an event, the system can also deliver ongoing situational awareness about the location and details of the shooter so important decisions can be made based on the timeliest data.
AI visual gun detection software can be easily integrated with existing IP-based video cameras, so it extends a company’s existing investment in video surveillance and transforms a forensic tool into a powerful preventive system.
AI-powered monitoring provides multiple benefits including that it is on and working 24/7/365 and unlike human monitoring, it never gets tired, loses concentration or has a sick day, which means it can significantly help those in charge of security be more successful at keeping their facilities safe.
Identifying active shooter gun threats, not simply guns, involves a multi-step process:
Assess: it first assesses frames of video to identify a body – a torso, arms, legs, etc.
It’s not looking for individuals or trying to identify a person, just the shape of a body without reference to color, gender or other identifying personal attributes.
Detect: the AI then works as a gun detector, searching for a handgun or long gun in close proximity to the body.
A wide range of handguns, shotguns, rifles and military-style weapons are distinguished by the AI, while inert objects such as cell phones, hand-tools, common office objects and more are identified to diminish possible false positives.
Analyze: multiple frames of video are analyzed in sequence to establish a coherent track on the threat, reducing spurious or false detections.
The relationship of the gun to the arm and hand of the body is then analyzed to bring additional clarity to the situation and help determine, with a high level of confidence, if an actual gun detection is in fact an active shooter threat before an alert is shared for human verification.
Once an active shooter has been verified, the speed and detail of the subsequent actions and communications that need to happen will have a profound impact on whether lives are saved or lost.
That is why it’s important to have a system that has strong mass communications capability and has been integrated to work with a facility’s existing platforms such as video management, emergency notification, access control, control room, real-time crime center platforms and other communication systems.
To highlight the power of AI visual gun detection, below are two use cases where it’s being leveraged in a university/health campus and K-12 school to save lives if an active shooter ever comes on campus.
Located in Arizona, the Sonoran University campus spans across 8.5 acres and serves approximately 400 students and 200 staff and faculty members as well as more than 14,000 patients that are treated annually at the university’s onsite public medical center.
There were cameras already installed on campus and all they had to do was integrate AI visual gun detection software with cameras located in strategic locations both inside and outside each building.
As explained by Paul Collins, Senior Director of IT at Sonoran University: “We believe visual gun detection is the missing link in having the best system possible for keeping our students, staff and patients safe while on our campus.
“Students want to feel safe when they come to campus and by layering this technology on top of our existing security system, we can help alleviate that concern.”
Below is an example of the sequence of events that could take place if an active shooter incident was to occur on the Sonoran campus:
The Baltimore County School District is home to more than 111,094 students in pre-K to 12th grade and over 21,000 staff members.
Tasked with the responsibility to keep students and staff safe in its more than 176 schools and programs, the district installed AI visual gun detection with over 7,000 existing cameras both inside and outside its buildings.
This is the largest installation of the advanced technology in the US.
According toDr Myriam Rogers, Superintendent of Baltimore County Public Schools (BCPS): “We are pleased to have this new weapons detection system as part of our comprehensive plan to enhance school safety.
“The Omnilert system has been operating in and around all of our school buildings and it has been tested and verified.
“Select BCPS staff and Baltimore County Police Department personnel, including school resource officers, are designated to receive alerts when a firearm is present.
“We are grateful that we have this additional tool to use in our efforts to deter and detect weapons on school property.”
Ensuring that both interior and exterior cameras at each campus are equipped with AI visual gun detection is key for keeping Baltimore County Public Schools safe from active shooters and gun violence.
In fact, the K-12 School Shooting database recently published research showing that 80% of school shootings happen in the exteriors of schools, which is why it’s so important to have a multi-layered security strategy that proactively monitors activity on the grounds surrounding the school, as well indoors.
No one can predict an active shooter incident, but we can – and must – be prepared to respond and save lives if one occurs.
Adding intelligence to a surveillance system a facility already has invested in can save significant time and money, while also providing a strong layer of protection against active shooters.
AI visual gun detection should become as ubiquitous as having fire alarms installed in a building and when that happens, our world will be a much safer place.
This article was originally published in the July edition of Security Journal Americas. To read your FREE digital edition, click here.