Skip to main content

A.I. security camera can identify guns with 99 percent accuracy

Athena Security Camera System and Alarm Demo Video

The U.S. company Athena Security has developed a smart camera system which is reportedly 99 percent accurate when it comes to spotting guns in video footage. It can then be used to alert law enforcement automatically, potentially saving lives in the process. The technology is already being employed at Archbishop Wood High School in Warminster, Pennsylvania, among other locations.

Recommended Videos

“The technology works by using computer vision A.I. algorithms to detect objects, and also measure the velocity of objects to determine what are clients are looking for,” Chris Ciabarra, chief technical officer and co-founder of Athena Security, told Digital Trends. “The main hardware technologies use CUDA cores by Nvidia for the processing of the information and Nvidia’s DGX-1 box, which we think has the fastest GPUs on the market, for processing our computer vision algorithms.”

In a scenario like a school shooting, Ciabarra says that the system would result in the police being called within minutes of a shooter (or would-be shooter) pulling out a gun for the first time. In a best-case scenario, the Athena Gun Detection System might serve as enough of a deterrent that causes the gunman to flee before shooting anyone. In a worst-case scenario, it would still mean police arriving more quickly on the scene, and potentially medics being alerted to the situation more rapidly as well.

Athena Security

“[The technology] is ready to go, and we are installing [it] into schools that want the students to be safe, corporations that value their employees’ safety, and homes that want to protect themselves and their loved ones,” Ciabarra continued.

Installing the technology is as simple as providing Athena with the IP address being used by an existing security camera system, after which the company will take over and plug it into their cloud-based system. In the event that no cameras are yet installed, Athena can also provide these as part of its package.

While protecting against potential shootings has so far grabbed the most press coverage, Ciabarra notes that the same technology can also be used to identify potentially less lethal incidents, such as a fight or a slip and fall. The camera tech can additionally be connected to other third-party security technologies — for instance, making it possible to stop elevators or lock security doors in the event that a certain behavior is identified.

Luke Dormehl
Former Digital Trends Contributor
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Arlo Go 2 is an LTE-enabled security camera that goes anywhere, works anywhere
Arlo Go 2

Smart security cameras have always suffered from one major limitation: The need for a Wi-Fi connection. The new Arlo Go 2 LTE/Wi-Fi Security Camera doesn't have that restriction. This smart security camera is designed to monitor locations like a vacation home or a remote construction site where Wi-Fi might not always be available. It works off a 4G LTE cellular data plan to provide continuous connectivity without interruptions.

The Arlo Go 2 is powered by a swappable, rechargeable battery that eliminates the need for cords and wiring. This makes it ideal for out of the way installations, allowing you to more effectively hide your security camera out of sight. It also has a weather-resistant design that means it can work just as well outside your home as in.

Read more
Nvidia’s latest A.I. results prove that ARM is ready for the data center
Jensen Huang at GTX 2020.

Nvidia just published its latest MLPerf benchmark results, and they have are some big implications for the future of computing. In addition to maintaining a lead over other A.I. hardware -- which Nvidia has claimed for the last three batches of results -- the company showcased the power of ARM-based systems in the data center, with results nearly matching traditional x86 systems.

In the six tests MLPerf includes, ARM-based systems came within a few percentage points of x86 systems, with both using Nvidia A100 A.I. graphics cards. In one of the tests, the ARM-based system actually beat the x86 one, showcasing the advancements made in deploying different instruction sets in A.I. applications.

Read more
iPhone camera can be damaged by motorcycle vibrations, Apple says
iphone 12 pro vs 11 cameras

Apple has quietly added a new section to its support pages warning that motorcycle vibrations can damage an iPhone’s camera over time.

As per Apple: “Exposing your iPhone to high amplitude vibrations within certain frequency ranges, specifically those generated by high-power motorcycle engines, can degrade the performance of the camera system.”

Read more