Milestone Systems, a company in data-driven video technology, announced a generative AI-powered video analytics plug-in for its XProtect video management software, developed in collaboration with NVIDIA. Designed to help operators contextualize alarms and focus on what truly matters, the new tool automates video review, filters out false alarms and, based on initial findings, could reduce up to 30% of operator alarm fatigue.

Today’s video systems capture vast amounts of data, yet reviewing footage remains time consuming and largely manual. Milestone Systems’ new XProtect plug-in addresses this challenge by leveraging generative AI to automatically summarize, contextualize and validate video content in real time.

Key capabilities include:

• Automated Incident Reports: Selected video clips are instantly converted into incident summaries and structured reports.
• Event Validation: The plug-in can be configured to analyze motion events and validate alarms, reducing false positives and improving alert handling. This feature is fully integrated with the XProtect rule engine.
• Contextual Bookmark Summaries: Bookmarked footage is automatically summarized using natural-language output.

The plug-in integrates directly with the XProtect rule engine and is deployable on-premises or in the cloud to support compliance and deployment flexibility.

This new solution is built on Milestone’s Hafnia Vision Language Model (VLM) trained on 75,000 hours of ethically sourced, real-world video data from either Europe or the U.S., using NVIDIA Cosmos Curator for data preparation and running either on cloud infrastructure or regional data centers powered by NVIDIA. It leverages the NVIDIA Cosmos Reason VLM.

“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,” said Thomas Jensen, CEO, Milestone Systems. “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.”

Milestone is also introducing a VLM-as-a-service via APIs, allowing developers, integrators and partners to build their own generative AI solutions regardless of the video management platform in use.