During the Parkland, Florida, school shooting in 2018, the shooter was caught on a security camera pulling his rifle out of a duffle bag in the staircase 15 seconds before discharging the first round. However, the School Resource Officer didn’t enter the building because he wasn’t confident about the situation, and the Coral Springs Police Department had no idea what the shooter even looked like until 7 minutes and 30 seconds after the first round was fired.

If the video system had included technology to recognise the gun threat in real time, alerts could have been sent to the security team. An announcement could have been made right away for all students and faculty in Building 12 to barricade their doors, and law enforcement could have responded a lot faster to a real-time feed of timely and accurate information.

Automatically recognising gun threats

Actuate offers such a technology, which the company says enables existing security cameras to automatically recognise gun threats and notify security in real-time. The technology is centred around a convolutional neural network (CNN) that aims to replicate how a human brain would process information. This neural network is trained to recognise what hands holding a firearm look like from hundreds of thousands of images in a proprietary data set.

The technology is centred around a CNN that aims to replicate how a human brain would process information

Over time, the system is able to mathematically calculate what a gun threat in a security camera feed looks like with a high degree of accuracy (well over 99% detection accuracy within the first 5 seconds), according to Actuate.

Active shooter situations are often marred by chaos and confusion,” says Sonny Tai, Chief Executive Officer of Actuate. “People are in fight-or-flight response and prioritise immediate survival instead of reaching for their phones and calling 911. When the 911 calls are made, callers often provide delayed, conflicting, and inaccurate information, inhibiting law enforcement’s ability to respond.

Enhances law enforcement response

Tai says Actuate helps to clear up that chaos and confusion. He says: “It provides visual intelligence of the location of the shooter, what they look like, what direction they’re heading, and what they’re armed with. This real-time information enhances law enforcement response and enables building occupants to make critical decisions that maximise survivability."

It provides visual intelligence of the location of the shooter, what they look like, what direction they’re heading, and what they’re armed with
AI methods including deep learning enable high levels of accuracy in detecting weapons in real-time camera footage

Tai is a Marine Corps veteran and a social entrepreneur who co-founded Actuate with the mission of addressing America’s gun violence epidemic. The start of the company stems from Tai’s upbringing in South Africa, where gun violence rates are some of the highest in the world. Growing up, several of his family friends were personally impacted, resulting in a lifelong passion for the issue of gun violence.

In early 2018, Tai interviewed dozens of law enforcement leaders across the country and found that their biggest challenge in gun violence response was the lack of timely and accurate information. Actuate mitigates that challenge and enables both first responders and security staff to respond more rapidly, he says.

More than 99% accuracy in detecting weapons

Actuate's solution is completely AI-based, says Ben Ziomek, Chief Product Officer. AI methods including deep learning enable high levels of accuracy in detecting weapons in real-time camera footage. “Legacy, non-AI based solutions generally rely on older methods like motion detection, which is not reliable in differentiating between objects such as phones and firearms,” says Ziomek. “Our AI solution lets us achieve more than 99% accuracy in detecting weapons with an exceptionally low false-positive rate.

Ziomek runs engineering, data science, and operations for Actuate. Before joining the firm, he led teams of AI engineers and data scientists at Microsoft, leveraging AI to identify high-potential startups globally.

Actuate is a software-only solution that plugs into existing security camera hardware and software, including video management systems (VMS). Existing capabilities of a customer’s VMS does initial, basic analysis and then routes the remaining video to Actuate’s processing units for AI analysis. Alerts can then be sent back however a customer wants, including through a VMS. Actuate can also feed information into a PSIM or command-and-control system if requested by a customer.

Equipping customers with AI tools

As an early-stage company, Actuate is pursuing customers through multiple routes, including directly to end-users and via security integrators, distributors, and dealers. They are currently deployed at diverse customer sites including schools, office buildings, industrial facilities, and public buildings, says Ziomek.

Our current focus for the company is to get our technology into the hands of as many customers as possible

Our current focus for the company is to get our technology into the hands of as many customers as possible,” says Ziomek. “We are working closely with customers across segments and industries to equip them with the tools they need to make their spaces safer. We’re currently working on educating the market on our offerings, as this technology is very new to many security organisations.

There are no privacy or compliance concerns because Actuate stores no customer data until a weapon is detected, and even then the data is not cross-indexed with any sensitive information, says Ziomek.

Download PDF version Download PDF version

Author profile

Larry Anderson Editor, SecurityInformed.com & SourceSecurity.com

An experienced journalist and long-time presence in the US security industry, Larry is SourceSecurity.com's eyes and ears in the fast-changing security marketplace, attending industry and corporate events, interviewing security leaders and contributing original editorial content to the site. He leads SourceSecurity.com's team of dedicated editorial and content professionals, guiding the "editorial roadmap" to ensure the site provides the most relevant content for security professionals.

In case you missed it

How should the security industry promote diversity?
How should the security industry promote diversity?

Diversity in a company’s workforce is arguably more important now than ever. Societal awareness of the importance of diversity has grown, and many people see diversity as an important factor that reflects positively (or negatively) on a company’s culture and image in the marketplace. We asked this week’s Expert Panel Roundtable: What should the security industry do to promote workplace diversity?

Why face recognition as a credential is the ideal choice for access control?
Why face recognition as a credential is the ideal choice for access control?

In the field of access control, face recognition has come a long way. Once considered too slow to authenticate people's identities and credentials in high traffic conditions, face recognition technology has evolved to become one of the quickest, most effective access control identity authentication solutions across all industries. Advancements in artificial intelligence and advanced neural network (ANN) technology from industry leaders like Intel have improved the accuracy and efficiency of face recognition. However, another reason the technology is gaining traction is due to the swiftly rising demand for touchless access control solutions that can help mitigate the spread of disease in public spaces. Effective for high volumes Face recognition eliminates security risks and is also virtually impossible to counterfeit Modern face recognition technology meets all the criteria for becoming the go-to solution for frictionless access control. It provides an accurate, non-invasive means of authenticating people's identities in high-traffic areas, including multi-tenant office buildings, industrial sites, and factories where multiple shifts per day are common. Typical electronic access control systems rely on people providing physical credentials, such as proximity cards, key fobs, or Bluetooth-enabled mobile phones, all of which can be misplaced, lost, or stolen. Face recognition eliminates these security risks and is also virtually impossible to counterfeit. Affordable biometric option Although there are other biometric tools available, face recognition offers significant advantages. Some technologies use hand geometry or iris scans, for example, but these options are generally slower and more expensive. This makes face recognition a natural application for day-to-day access control activities, including chronicling time and attendance for large workforces at construction sites, warehouses, and agricultural and mining operations. In addition to verifying personal credentials, face recognition can also identify whether an individual is wearing a facial covering in compliance with government or corporate mandates regarding health safety protocols. Beyond securing physical locations, face recognition can also be used to manage access to computers, as well as specialised equipment and devices. Overcoming challenges with AI So how did face recognition become so reliable when the technology was once dogged by many challenges, including difficulties with camera angles, certain types of facial expressions, and diverse lighting conditions? Thanks to the emergence of so-called "convolutional" neural network-based algorithms, engineers have been able to overcome these roadblocks. SecurOS FaceX face recognition solution FaceX is powered by neural networks and machine learning which makes it capable of authenticating a wide range of faces One joint effort between New Jersey-based Intelligent Security Systems (ISS) and tech giant Intel has created the SecurOS FaceX face recognition solution. FaceX is powered by neural networks and machine learning which makes it capable of authenticating a wide range of faces and facial expressions, including those captured under changing light, at different resolution levels, and varying distances from the video camera. Secure video management system A common face recognition system deployment begins with IP video cameras that feed footage into a secure video management system connected to a video archive. When the software initially enrolls a person’s face, it creates a "digital descriptor" that is stored as a numeric code that will forever be associated with one identity. The system encrypts and stores these numeric codes in a SQL database. For the sake of convenience and cost savings, the video server CPU performs all neural network processes without requiring any special GPU cards. Unique digital identifiers The next step involves correlating faces captured in a video recording with their unique digital descriptors on file. The system can compare newly captured images against large databases of known individuals or faces captured from video streams. Face recognition technology can provide multi-factor authentication, searching watchlists for specific types of features, such as age, hair colour, gender, ethnicity, facial hair, glasses, headwear, and other identifying characteristics including bald spots. Robust encryption SED-compatible drives rely on dedicated chips that encrypt data with AES-128 or AES-256 To support privacy concerns, the entire system features an encrypted and secure login process that prevents unauthorized access to both the database and the archive. An additional layer of encryption is available through the use of Self-Encrypting Drives (SEDs) that hold video recordings and metadata. SED-compatible drives rely on dedicated chips that encrypt data with AES-128 or AES-256 (short for Advanced Encryption Standard). Anti-spoofing safeguards How do face recognition systems handle people who try to trick the system by wearing a costume mask or holding up a picture to hide their faces? FaceX from ISS, for example, includes anti-spoofing capabilities that essentially check for the "liveliness" of a given face. The algorithm can easily flag the flat, two-dimensional nature of a face mask, printed photo, or image on a mobile phone and issue a "spoof" alarm. Increased speed of entry Incorporating facial recognition into existing access control systems is straightforward and cost-effective Incorporating facial recognition into existing access control systems is straightforward and cost-effective. Systems can operate with off-the-shelf security cameras and computers. Users can also leverage existing infrastructure to maintain building aesthetics. A face recognition system can complete the process of detection and recognition in an instant, opening a door or turnstile in less than 500ms. Such efficiency can eliminate hours associated with security personnel checking and managing credentials manually. A vital tool Modern face recognition solutions are infinitely scalable to accommodate global enterprises. As a result, face recognition as a credential is increasingly being implemented for a wide range of applications that transcend traditional access control and physical security to include health safety and workforce management. All these capabilities make face recognition a natural, frictionless solution for managing access control, both in terms of performance and cost.

What are the challenges and benefits of mobile access control?
What are the challenges and benefits of mobile access control?

There is a broad appeal to the idea of using a smartphone or wearable device as a credential for physical access control systems. Smartphones already perform a range of tasks that extend beyond making a phone call. Shouldn’t opening the door at a workplace be among them? It’s a simple idea, but there are obstacles for the industry to get there from here. We asked this week’s Expert Panel Roundtable: What are the challenges and benefits of mobile access control solutions?