Seconds Matter: How AI Can Augment Security Cameras to Detect Threats
With public companies like IBM, Microsoft and Amazon halting the sale of facial recognition technology to public and private sectors, the security industry is seeking alternative innovations that don’t compromise privacy. While retailers and commercial buildings have comprehensive security camera systems, many don’t have the capability to detect a potential threat, like an active shooter situation, before it happens, and are instead used forensically.
Active shooter situations remain one of the biggest threats to public safety; this year alone, there have been 242 mass shootings. In the past year, it’s become more common for shootings to take place at festivals, schools, big-box retail stores, or places of worship. Because, public spaces often rely on humans actively monitoring multiple security cameras, it puts others at risk as cameras are unable to detect and manage a threat in real-time, which can mean the difference of critical seconds that save lives.
As a result, companies and schools are investing in a broad range of security systems to help combat violent threats and upgrade outdated security cameras. Specifically, AI-powered objects and weapons detection for safety and security can actively address threats without compromising privacy. Weapons detection uses computer vision to actively identify objects in video feeds.
Once a weapon is accurately detected, alerts are sent to security and/or 911 Dispatch, allowing for faster crisis response times. Because the system is constantly learning and updating, detection becomes even more precise and allows for greater accuracy when dealing with sensitive situations like with active shooters.
For example, in 2019, Rancocas Valley Regional High School (RVRHS) in Mount Holly, N.J., installed an AI weapon detection system that integrated with their legacy security system, adding an additional layer to their safety-first protocols. In its initial pilot of the technology, RVRHS scripted a series of active shooter drills with 60 police officers from six local townships and integrated with Burlington County 911 Dispatch.
The first set of drills did not use weapons detection technology, and officers had to rely upon simulated 911 calls and role-playing to determine the location of the threat. In the second set of drills, weapons detection technology was deployed, and responding officers interacted directly with their 911 Dispatch to locate and neutralize the threat.
On average, response time from the first notification of an active shooter to the first contact with the active shooter was reduced by 50% when using weapons detection technology.
Also, 911 Dispatch was able to continuously update responding officers on suspect location, physical description, weapon type and disposition when using weapons detection, which improved tactical situational awareness by responding units. Lastly, 911 Dispatch was able to conduct real-time forensics with weapons detection, which ultimately resulted in identifying a shooter hiding among students. Many schools, like RVRHS, have increasingly needed to make an investment in safety and security a top priority, despite that being completely separate to their areas of expertise.
Security technology has needed to evolve for some time because our outdated systems are putting the public at risk. With companies and schools becoming more proactive than reactive, they’re taking an active role in preventing these situations from occurring. Because there are so many vulnerabilities in our public spaces, it’s important to invest in the right kind of technology to curb violence, support faster first responder times, and ultimately invest in the safety of our cities.