AI-Based Tech Will Spot Guns in Security Cameras

This post is also available in: עברית (Hebrew)

The overall number of mass shootings in the U.S. in 2017 reached 346 events. Mass shootings are defined as an event in which four or more people are shot, not including the gunman. Technologies of various sorts have been offered up as potential ways to mitigate gun violence. Schools were equipped with metal detectors, for example, and introducing airport-style body scanners was also considered.

The balancing act for administrators and technologists is to introduce new equipment designed to increase safety without militarizing schools or compromising privacy, according to zdnet.com.

A new AI camera system can identify guns in crowds using security camera video. The system is one of a growing number of technologies aimed at preventing gun crime. Cameras can also alert police to the presence of an active shooter, potentially reducing response time.

Athena Security, an AI company that utilizes computer vision for security applications, was founded over the backdrop of the Las Vegas shooting, when its co-founders realized that they could create an AI-powered system that would accurately recognize any crime or weapon and alert police in real time.

One of the major challenges during development was to create a computer vision algorithm that continuously monitors cameras without reporting too many false positives, a weakness of past attempts at AI gun detection technology.

The system is powered by the NVIDIA 2080 RTX graphics card and can be integrated into current camera security networks. The solution is marketed to schools and retailers.