Next-Gen AI for Smart Cities

Open platform unlocks trusted video data and best-in-class video analytics for smarter, safer cities.

• By Howard Carder
• Jul 29, 2025

The future of smart city technology is not being shaped in Silicon Valley — it is taking root in Dubuque, Iowa. With a population of about 60,000, this mid-sized city has become a live testbed for AI-driven traffic management thanks to a unique public-private collaboration led by Milestone Systems. Project Hafnia demonstrates how cities can transform urban mobility and safety through Responsible Technology—without costly infrastructure overhauls.

Challenge: High-Potential AI, Low-Quality Data
Despite extensive camera deployments, cities often struggle to derive real-time intelligence from video. AI models trained on synthetic or generic datasets often underperform in complex, real-world environments. High false-positive rates make them impractical for daily operations, especially in time-critical applications like traffic management, preventing municipalities from gaining the real-time insights needed to improve mobility, safety, and emergency response.

Solution: Public-Private Innovation in Action
Project Hafnia, led by Milestone Systems, brought together the city of Dubuque and Vaidio (formerly IronYun) to develop a high-performance, real-world AI model. Milestone led the 12-month project from first concept to full-scale deployment, investing in cloud-based AI training and professional video annotation. Unlike conventional vendor-customer setups, this collaboration was structured with shared value in mind: each party contributed expertise, resources, and infrastructure, aligning toward a common goal.

At the heart of this success story is Milestone’s investment in creating a secure, high-quality, and legally compliant data library that supports transparency and data traceability requirements in evolving AI regulations. Milestone transformed the city’s raw traffic footage into valuable AI training material. This investment paid off dramatically, with model accuracy jumping from 80% to more than 95%. Below that threshold, false positives are too frequent, undermining usability. Above it, cities unlock new levels of accuracy and insight.

Results: Scalable, Transferable, Trusted
With more than 100 traffic cameras participating in the trial, Project Hafnia validated AI performance in the field across a range of changing light, weather and traffic patterns. The resulting platform is scalable and transferable, giving other cities a tested blueprint for AI-enhanced urban operations. AI models originally developed for traffic monitoring (vehicle classification, pedestrian tracking, anomaly detection) can now be repurposed to support public safety, emergency response, and infrastructure planning across departments.

“What makes this project unique is our approach to data,” said Søren Raagard Jensen, executive product enablement manager at Milestone Systems. “The public-private innovation structure gives us access to real-world scenarios that simply can’t be replicated in a lab. We’ve invested thousands of hours in annotating video data so that Vaidio can train their models on footage that precisely matches what they’ll encounter in production environments.”

A New Framework for Public-Private Innovation
Beyond the technical achievements, the project set up a new template for collaboration between cities, technology vendors and platform providers. Rather than a traditional vendor-customer relationship, the collaboration ran on balanced value exchange principles.

“This wasn’t about selling a product to the city,” Raagard Jensen said. “We established a framework where all participants; Dubuque, Vaidio, traffic experts, and Milestone, contributed expertise, resources and infrastructure to make this a success.”

The collaboration brought together diverse perspectives and created a forward-looking solution that evolved organically. From concept to working prototype to full-scale deployment, every participant helped shape the outcome.

“Working closely with Milestone and the City of Dubuque allowed us to fine-tune our AI models to address the specific challenges of urban traffic management,” said David Jenkins, vice president of Software Architecture at Vaidio. “Training our models on real-world video data rather than simulated scenarios made all the difference. It’s why our solution performs so well in actual city environments where lighting, weather, and traffic patterns are constantly changing.”

Harnessing the Power of Quality Data
Dave Ness, Dubuque’s traffic engineering manager, has overseen the evolution of the city’s camera network — from a modest traffic detection system to a sophisticated AI-ready video infrastructure.

“A couple of decades ago, we started out with just 20 cameras for traffic detection. Now we have over 1,400 cameras citywide, with access to many more when you include our partners like the county and school district,” Ness said. “After seeing the success of the AI initial deployment, we’re planning to expand this technology across hundreds more cameras throughout the city in the coming months.”

This transformation reflects Dubuque’s long-standing commitment to smart infrastructure and Milestone’s approach to building capabilities incrementally, not through sweeping, disruptive overhauls, but through focused, collaborative innovation.

Compliance and Transparency at the Core
As regulatory frameworks like the EU AI Act continue to evolve, data traceability and legal compliance have become essential. Milestone addresses these challenges by creating a transparent, documented data supply chain that future-proofs analytics solutions against evolving regulatory requirements.

Milestone’s data library stands apart by offering complete traceability. Every frame of video used in AI training — thousands of hours of footage — is documented with its source, processing history, and usage permissions. This approach also empowers municipalities to prepare for future transparency requirements under AI regulations such as the EU AI Act. In parallel, Milestone adheres to established data protection regulations like the EU GDPR, which provide foundational safeguards for processing and handling personal data. This meticulous process not only ensures compliance, but it also establishes a foundation for ethical, Responsible AI development.

Thomas Jensen, CEO of Milestone Systems, emphasized the broader vision: “At Milestone, we believe that AI innovation starts with trusted data and open collaboration. Project Hafnia proves that with the right platform, even mid-sized cities like Dubuque can lead the way in responsible, data-driven transformation. This is a blueprint for how cities everywhere can harness AI to improve safety, mobility and quality of life — all while staying in control of their data.”

The Road Ahead: A Model for Cities Worldwide
Project Hafnia not only proved that real-world AI could work, but it also showed that it can scale, ethically and collaboratively.

“We’re just scratching the surface of what’s possible,” Ness said. “As we continue to refine and develop new features with Milestone and Vaidio, we’re opening up possibilities we hadn’t even considered before. The power of AI to transform urban management is remarkable. It’s giving us insights and capabilities that would have been impossible with traditional methods, all while helping us make our city safer and more efficient for residents.”

Project Hafnia is more than a traffic management success story. It is a living prototype of how cities — big or small — can unlock the full potential of AI by investing in data, partnerships, and transparency.