Verkada has unveiled its latest advancement in physical security technology with the introduction of AI-powered deterrence.
This solution aims to enhance crime prevention by proactively detecting and issuing warnings to potential intruders before escalating to an alarm. This innovation seeks to fill a notable void in traditional security systems, which typically respond only after an incident has occurred.
Utilising advanced AI capabilities
The deterrence feature leverages advanced vision, audio, and language models to analyse video footage for unauthorized activities, such as loitering. When detecting such behaviour, the system issues AI-generated messages that take into account specific scene contexts, such as clothing description or location of the individual, and adjusts the deterrence measures over time if the individual remains. For enhanced effectiveness with repeat offenders, the system can alter the voice used for deterrence.
For enhanced effectiveness with repeat offenders, the system can alter the voice used for deterrence
"AI-powered deterrence represents a fundamental shift that we've been driving for our customers: moving from reactive to proactive security," stated Brandon Davito, Senior Vice President of Product and Operations at Verkada. "We're delivering on Verkada's goal of building safer, smarter communities in a very real and tangible way when our customers have the ability to stop an incident before it escalates. This impact will only scale as we continue to invest in bringing even more AI-powered capabilities into Verkada Command."
Intelligent security workflows
Organisations can tailor the AI-powered deterrence to craft intelligent workflows that trigger escalation only when necessary.
An example of this system in action includes detecting loitering outside a property after hours. Initially, the system issues a gentle reminder, but if loitering persists, it escalates to context-aware messages followed by a final warning. Should the intruder continue to loiter, the system raises an alarm and can be programmed to activate sirens, engage live security agents, notify internal teams, or contact the police.
Minimising false alarms
This method allows various organisations—like car dealerships, schools, and businesses—to protect their assets without triggering unnecessary alarms.
These alerts can be seamlessly relayed to external applications such as PowerBI and Tableau via webhooks
Furthermore, Verkada has introduced advanced AI-powered alerting features, including compound alerts, which activate notifications only when multiple specified conditions are met. For instance, a customer can configure alerts for individuals crossing a restricted line without wearing a hard hat or for people tagged as persons of interest. These alerts can be seamlessly relayed to external applications such as PowerBI and Tableau via webhooks.
Enhancements in building entry
Verkada has expanded its AI-powered offerings in building access through enhancements in its intercoms and visitor management systems to provide a more seamless and customised entry experience:
- Live translation: This feature allows two-way translation at a Verkada intercom, facilitating natural conversation between the visitor and the responder. Supported languages include English, Spanish, French, German, Japanese, Portuguese, Italian, Dutch, Hindi, and Russian, with more languages planned for inclusion.
- AI-powered voice directory: Visitors can express their intent without needing specific extensions or names. For example, a visitor could say, "I'm here for an interview at Verkada," and the system will direct the call to the appropriate contact.
- Biometric ID verification: Provides additional security by comparing visitor ID images with facial captures taken at a Verkada kiosk.
Streamlining incident reporting
To facilitate faster investigations and reporting, Verkada has introduced AI-powered incident summaries, offering automatic descriptions for archived video footage within incident reports. This feature complements over 174 new AI functionalities and product updates introduced over the past year, which have improved efficiencies for security professionals. These updates include:
- Unified timeline: Merges video events of interest across multiple cameras into a cohesive, map-based timeline.
- AI-powered alerts: Customisable detection alerts tailored to specific activities and industries.
- Operator view: Centralises alerts into a ticket-based system with a structured workflow.
- Retail analytics: Utilises computer vision to analyse queue wait times, occupancy trends, and sales conversion metrics.
Verkada, a pioneer in AI-powered physical security technology, announces the availability of AI-powered deterrence, a novel solution that proactively helps prevent crime by detecting and warning potential intruders before raising an alarm.
This innovation from Verkada addresses a critical gap in traditional security systems, which only react after a break-in has occurred.
Incorporate scene context
Leveraging the latest large vision, audio, and language models, Verkada's AI-powered deterrence feature analyses footage from video security cameras to detect unauthorised behaviour like loitering and automatically triggers a sequence of AI-generated messages that incorporate scene context, such as describing a person's clothing or location, and escalate deterrence measures over time if the person remains on site. The system can also even change the voice for each deterrence incident for greater effectiveness against repeat offenders.
"AI-powered deterrence represents a fundamental shift that we've been driving for our customers: moving from reactive to proactive security," said Brandon Davito, Senior Vice President of Product and Operations at Verkada. "We're delivering on Verkada's goal of building safer, smarter communities in a very real and tangible way when our customers have the ability to stop an incident before it escalates. This impact will only scale as we continue to invest in bringing even more AI-powered capabilities into Verkada Command."
Creating intelligent workflows
Organisations can configure AI-powered deterrence to create intelligent workflows that begin with detection and escalate only when needed. Here is an example of how Verkada's system might respond to a person loitering outside of a property after-hours:
- Initial warning upon detection of the person loitering: "A reminder that this is private property. Please come back during business hours."
- If loitering continues, a context-aware message: "Hey you, with the red hoodie and backpack, you can't be here at this time. Please leave now before our alarms are triggered."
- If loitering continues, a final warning: "Hey, this is your final warning. If you don't leave now, I'll have to take immediate action."
- If loitering continues, an Alarm is raised and Verkada's system can be configured to activate a siren/strobe, initiate live agent talk-down, notify a contact list of internal security teams, or dispatch the police.
Unnecessary alarm activations
This approach enables car dealerships to deter catalytic converter thieves, schools to prevent graffiti vandalism, and businesses to protect outdoor assets – all without unnecessary alarm activations. Verkada also announced the availability of more advanced AI-powered alerting capabilities, including compound alerts, which enable customers to trigger notifications only when multiple conditions that they specify are met.
For example, a customer could ask Verkada Command to send them an alert when a person crosses a restricted line and is not wearing a hard hat. Or, they could choose to set up loitering alerts only for individuals who have been identified as a person of interest. All of Verkada's intelligent alerts are now able to be pushed seamlessly to external applications outside of Verkada Command, like PowerBI and Tableau, through newly available webhooks.
AI-powered functionality
Verkada introduced new AI-powered functionality across its intercoms and visitor management product to make building entry even more seamless and personalised:
- Live translation, which enables two-way translation for a visitor at a Verkada Intercom and the person answering the call. Both sides speak naturally, and the system handles the translation instantly. English, Spanish, French, German, Japanese, Portuguese, Italian, Dutch, Hindi, and Russian are supported today, with plans to expand.
- AI-powered voice directory, which enables visitors to speak their intent without needing the exact extension, name, or precise department they need. For example, a visitor to a multi-tenant building can simply say "I'm here for an interview at Verkada" or "I'm here to repair the water leak on the third floor," and Verkada's system will route each call to the appropriate organisation and contact.
- Biometric ID verification, which provides an extra layer of security for verifying the identities of visitors by comparing the image from a visitor's driver's license to their face captured by a Verkada Guest check-in kiosk.
AI-powered incident summaries
To continue speeding up investigations and reporting, Verkada introduced AI-powered incident summaries, which automatically generate descriptions for video archives that are saved within an incident report.
These latest announcements build on more than 174 new AI features and product updates Verkada has delivered to customers in the past year that unlock new efficiency for security professionals, including:
- AI-powered unified timeline, which visually reconstructs and unifies video events of people and vehicles of interest across all of a site's cameras into a single, map-based timeline.
- AI-powered alerts that include activity- and industry-specific detections for organisations.
- Operator view that centralises alerts into a ticket-based system with a structured workflow.
- Retail analytics that leverage computer vision to understand queue wait times, occupancy trends, sales conversion metrics, and more.
