Milestone’s Developer Summit 2025 successfully took place at the historic Carlsberg Museum in Copenhagen.
According to the company, the summit provided a stage for a new era of open platform development, responsible AI and the Hafnia Hackathon.
“The best minds and the best ideas”
Sebastian Döllner, VP of Technology Partnerships & Open Platform, said: “Technology is evolving faster than ever and no single company has all the answers.
“The winners are those who can bring together the best technologies, the best minds and the best ideas. The essence of Milestone’s open platform is to empower innovation.
“We’re building more than video management software – we’re building an ecosystem that allows partners and customers to innovate on top of it.”
Keynotes, workshops and VLMs
Milestone explains that with keynotes from NVIDIA, AWS, Dell and Intel, breakout workshops and the Hafnia Hackathon, participants from all over the globe were able to share insights and predictions on what the future might look like.
Whilst attending the summit, AI developers from 15 different countries had early access to Milestone’s upcoming specialised Visual Learning Model (VLM)
Milestone’s VLM has been developed using NVIDIA Cosmos-Reason and was also post-trained with Hafnia’s domain-specific data library to better understand city-specific visuals, languages, symbols, events, weather, lighting and more.
Hafnia Hackathon
The summit also included the announcement of the Hackathon challenge winners. The Hackathon challenge saw industry professionals create innovative integrations with third-party applications and leverage the VLM via API to enhance smart city solutions.
Milestone explained that millions of video cameras capture valuable footage that could improve everyday life, yet much of this potential remains untapped due to the time-consuming task of reviewing and analysing countless hours of video to uncover meaningful insights.
In addition to the specialised VLM, Milestone said it also launched a generative AI-powered plugin for XProtect Video Management Software.
The upcoming generative AI-powered plugin for XProtect is designed to improve traffic management across cities, ports, airports and other urban areas.
The company highlights that it delivers advanced video intelligence by automatically converting video footage into detailed written reports, summaries and validated real-time alerts.
Out of the participating developers, six were shortlisted and a panel of judges from Milestone and NVIDIA selected the top three.
“Relevant and useful in real life”
The winner of the Hackathon was announced as Thomas Kreutz, who used Hafnia’s VLM API to turn live city cameras into instant, privacy-aware answers to real-time questions.
He said: “I wanted to build something that is relevant and useful in real life.
“What I liked the most about the hackathon was how easy it was to get started.
“The API and documentation made it simple to build a demo quickly, brainstorm more ideas and try them out.”
“Promising for the future”
Thomas Kreutz took home €5,000 and the NVIDIA Jetson AGX Thor Developer Kit.
Roland Harwood, Community Lead – Hafnia, commented: “We are very impressed with the innovative integrations from all finalists but Thomas Kreutz and Ask The City really nailed it.
“The hackathon success is promising for the future use of our platform and data library to train computer vision models on compliantly sourced, curated, extensively annotated and anonymised real-world data.”
Finalists
Milestone states that the six Hackathon finalists included:
- Ask The City / Thomas Kreutz – Turned live city cameras into instant, privacy-aware answers to real-time questions. Users are able to pick a place on the map, ask in natural language and get a response derived only from the last few seconds of video. This was powered by Hafnia’s VLM API
- VLM for Emergency Response / Flynn Owen, Dan Towers & Tom Aldridge (Blaize) – Leveraged edge AI devices to generate events and contextualise, triage and create response plans for emergency situations in near real-time
- SmartMap / Gabriel Crosnier de Bellaistre (Citilog) – Used Hafnia’s VLM to unify incident detection, traffic levels and weather/visibility data into live map overlays with operator-ready actions, enabling faster decisions and better visualisation
- RevoFlow / Rawinder Singh – A no-code workflow builder that let security integrators create AI-powered video analytics through drag-and-drop design, powered by Milestone’s VLM API. Milestone adds that this was the Audience Award winner
- Clipnotes / Magnus Guldberg Pedersen Converted short video clips into structured, interpretable insights in seconds using Hafnia’s VLM
- Hafnia Video Event Analyser / Jojy Saju Josephs – A multimedia intelligence platform that used a VLM API to analyse images and video, generate semantic metadata and enable advanced search, summarisation and event detection
