ChannelLife UK - Industry insider news for technology resellers
Realistic security cameras monitoring modern cityscape with data automation

Milestone unveils generative AI plug-in for smarter video analytics

Fri, 7th Nov 2025

Milestone Systems has announced a generative AI-powered video analytics plug-in for its XProtect video management software, developed in collaboration with NVIDIA. The company aims to reduce the time and effort required to review video footage, automate incident reporting, and help operators focus more effectively on critical events.

Automation focus

The new plug-in is intended to address the growing demand faced by operators as video surveillance systems generate increasingly large volumes of footage. By introducing automation, Milestone Systems states that the plug-in can summarise, contextualise, and validate video content in real time. Core capabilities include incident report automation, event validation, and natural language summaries of bookmarked footage.

The automated incident reporting function instantly converts selected video clips into structured summaries, which the company says can reduce the time spent on manual documentation. The event validation feature analyses motion events and checks alarms, promising a reduction in false positives and an improvement in overall alert handling. This process is fully integrated with the existing XProtect rule engine.

Contextual summaries allow operators to quickly triage incidents by providing natural-language descriptions of bookmarked footage, limiting the need to review every clip individually.

Deployment flexibility

The plug-in can be deployed either on-premises or in the cloud, providing options to accommodate different compliance and security requirements across organisations. Integration with the XProtect rule engine also means that customers can deploy the tool within their current operational frameworks without significant additional infrastructure.

AI training and compliance

The solution is built on Milestone's Hafnia Vision Language Model (VLM), which is trained with more than 75,000 hours of ethically sourced, real-world video data from Europe and the US. Data preparation uses NVIDIA Cosmos Curator and the platform runs either through cloud infrastructure or regional data centres supported by NVIDIA. Milestone leverages NVIDIA Cosmos Reason VLM as a part of this set-up.

"With this new XProtect plug-in, we are making advanced video intelligence accessible to cities, organizations, and operators everywhere who manage traffic systems - helping them unlock new levels of efficiency, safety, and insight. XProtect users will get access to state-of-the-art generative AI capabilities, and our partners will be able to build value on top of those new capabilities now available within XProtect. It truly marks a pivotal step in our mission to transform how the world manages and learns from visual data, responsibly and at scale." said Thomas Jensen, Chief Executive Officer, Milestone Systems

Market adoption

According to Milestone, municipalities such as Genoa in Italy and Dubuque in Iowa are among the early users of the capability, reflecting a trend among cities towards using advanced artificial intelligence for improved traffic management.

Ecosystem development

Alongside the plug-in, Milestone is introducing a VLM as a Service solution via application programming interfaces. This will allow independent developers, systems integrators and partners to build their own generative AI solutions using Milestone's video language models, regardless of their chosen video management platform.

Milestone intends to showcase the new plug-in's real-time incident summarisation abilities and benchmarking tools in partnership with Vaidio. Milestone will also reveal more about the Hafnia VLM's capabilities at its upcoming developer summit, where the results of a related hackathon will be announced.

Follow us on:
Follow us on LinkedIn Follow us on X
Share on:
Share on LinkedIn Share on X