Eluviant, a prominent player in artificial intelligence, has introduced Aurora Flow, a generative AI model tailored for large-scale video surveillance.
This model, already deployed in active settings, is designed to function across numerous cameras almost in real time, even in environments completely disconnected from external networks. Aurora Flow addresses a significant challenge in commercial video intelligence: interpreting sequences of movements and events over time, not just individual video frames.
AI video understanding
The launch is an extension of Eluviant's existing AI platform, which has been utilised by various enterprise organisations.
This platform features a self-learning engine that detects unforeseen events without supervision
This platform features a self-learning engine that detects unforeseen events without supervision, combined with the Aurora vision-language model that has been used in live alert decisions for the last year and a half. Aurora Flow's capability to recognise movement patterns and interpret behaviour in near real time opens new possibilities for organisations in highly secure and sensitive settings, such as detecting equipment tampering, unsafe climbing, and hazardous driving more accurately than previously possible.
Enterprise-scale video intelligence
"We believe Aurora Flow is a frontier AI model in surveillance and a step change in what video intelligence can deliver, moving beyond detection and into genuine understanding of behaviours and actions in complex real-world environments," stated Callum Wilson, Founder and Co-CEO of Eluviant. "It addresses a challenge that traditional video analytics has struggled to solve efficiently: understanding what is happening when a single still frame is not enough. Things like fighting, climbing, and theft have typically required human eyes to detect them accurately. Now we can help operators gain a clearer picture of what does and doesn’t need their urgent attention."
Eluviant was established in 2017 and has since demonstrated that video surveillance infrastructures can offer much more than basic security. With industries now recognising the operational potential within their camera systems, there is an expanding market for enterprise-level video intelligence, estimated to reach $30 billion by the decade's end.
Rapid evolution of video intelligence
Eluviant’s solutions are trusted across various demanding operational settings
Previously known as IntelexVision, the company has rebranded to Eluviant, reflecting the swift advancements in video intelligence amid the rise of AI and their aspiration to continue pioneering in computer vision for video surveillance.
Callum added, "Everything we have built under the IntelexVision name — our technology, customer relationships, and hard-won understanding of what enterprise deployments actually require — is the foundation this moment stands on. This is what that work was always building towards: the capability to deliver video intelligence at scale, securely, in the real world. Our new identity is our statement of intent and we intend to continue leading this movement, having already helped shape it for the better part of a decade."
Eluviant’s solutions are trusted across various demanding operational settings, from retail and critical infrastructure to construction and smart cities. Whether it involves loss prevention, anomaly detection, or incident response, Eluviant’s AI solutions are designed to fulfil the needs of organisations requiring reliable, scalable AI across complex, multi-camera environments in real-time.
AI company Eluviant announces the launch of Aurora Flow, a generative AI model built for enterprise-scale video surveillance deployments. The solution has already been deployed in live environments and can operate across multiple cameras in near real time, including in fully isolated environments with no external network connectivity.
Aurora Flow represents a significant technical milestone by solving one of the most challenging problems facing large-scale commercial deployments of video intelligence: analysing not just what is visible in individual video frames, but what is happening across a sequence of movements and events over time.
AI video understanding
This builds on Eluviant's proven AI platform, which has been deployed by a range of enterprise organisations for years. The platform combines an unsupervised self-learning engine that identifies genuinely unforeseen events, with the company's vision-language model (Aurora) that has been embedded in the live alert decision-making for the past 18 months.
By recognising movement patterns and contextualising behaviour in near real time, Aurora Flow unlocks use cases previously out of reach for organisations operating in the world's most secure and sensitive environments. Equipment tampering, unsafe climbing in dangerous environments, and dangerous driving are just a few of the behaviours that can be more accurately identified using AI video understanding.
Enterprise-scale video intelligence
“We believe Aurora Flow is a frontier AI model in surveillance and a step change in what video intelligence can deliver, moving beyond detection and into genuine understanding of behaviours and actions in complex real-world environments,” Callum Wilson, Founder and Co-CEO of Eluviant, said. “It addresses a challenge that traditional video analytics has struggled to solve efficiently: understanding what is happening when a single still frame is not enough. Things like fighting, climbing, and theft have typically required human eyes to detect them accurately. Now we can help operators gain a clearer picture of what does and doesn’t need their urgent attention.”
Founded in 2017, Eluviant has spent nearly a decade demonstrating that existing video surveillance infrastructure can deliver far more than a security measure. Today, organisations across every sector are recognising the untapped operational value sitting within their existing camera networks, driving a growing market for enterprise-scale video intelligence that is expected to be worth $30bn by the end of the decade.
Rapid evolution of video intelligence
Formerly IntelexVision, the company today steps forward under the new name and brand identity, Eluviant, which reflects both the rapid evolution of video intelligence in the age of AI and the company's ambition to continue pushing the boundaries of what’s possible in computer vision for video surveillance.
"Everything we have built under the IntelexVision name — our technology, customer relationships, and hard-won understanding of what enterprise deployments actually require — is the foundation this moment stands on,” Callum added. “This is what that work was always building towards: the capability to deliver video intelligence at scale, securely, in the real world. Our new identity is our statement of intent and we intend to continue leading this movement, having already helped shape it for the better part of a decade."
Eluviant's technology is trusted across a range of demanding operational environments, from retail and critical infrastructure to construction and smart cities. Whether supporting loss prevention, anomaly detection, or rapid incident response, its solutions are built to meet the needs of organisations that require reliable, scalable AI across complex, multi-camera environments in real-time.
