At a busy downtown intersection where cars, scooters, cyclists and pedestrians cross paths, Raleigh traffic engineers are testing a new approach to managing congestion as the city continues to grow.
Using existing traffic cameras paired with artificial intelligence and mapping software, the city is analyzing how people and vehicles move through select intersections in near real time. City officials say the goal is not to eliminate traffic but to make signals operate more efficiently and safely, especially in areas with heavy pedestrian activity.
“One of the core challenges of traffic engineering is moving vehicles efficiently,” said Jed Niffenegger, Raleigh’s city transportation manager. “We can’t change the fact that an intersection is busy. What we can do is make sure it’s operating as efficiently as possible.”
The pilot program relies on computer vision technology that converts live video into data. Software tracks turning movements, traffic volumes and different modes of travel, replacing a manual process that once required staff to stand at intersections and count vehicles by hand.
“The cameras allow us to make changes much more quickly,” Niffenegger said. “With analytics, the amount of work it takes has been reduced to a fraction of what it used to be.”
Raleigh has roughly 250 closed-circuit traffic cameras citywide. For now, the AI system can analyze data from about 10 to 12 cameras at a time because of computing limits. Transportation staff rotate intersections into the program based on where signal timing studies or corridor reviews are underway, including along Glenwood Avenue and in parts of downtown.
The technology allows engineers to fine-tune signal timing during peak hours, sometimes by only a few seconds, based on real-world conditions rather than assumptions.
“We’ll look at the evening rush and see whether a signal is running too long or needs to start a little later,” Niffenegger said. “It’s about fine-tuning what we’re already doing.”
City officials say that focus on intersections matters. While widening roads has long been used to relieve congestion, engineers say intersections are often the true bottlenecks.
“If we can maximize efficiency at intersections, we can delay costly road-widening projects,” Niffenegger said. “That saves money and allows us to invest in other places where it can have a bigger impact.”
James Alberque, Raleigh’s emerging technology manager, said the project is part of a broader effort to better understand how the city moves as its population grows. Raleigh surpassed 500,000 residents last year, putting new pressure on streets that were not designed for current traffic volumes.
“Cameras record video, and we’re turning that video into data,” Alberque said. “That data helps traffic engineers understand what’s happening across the city, not just at one camera at one moment.”
The data is visualized using a high-resolution, three-dimensional model of Raleigh, sometimes called a digital twin. City staff can compare traffic conditions before and after signal changes and evaluate whether adjustments are working as intended.
The pilot initially focused on vehicle traffic. After validating those results, the city expanded the analysis to include pedestrians and bicycles, particularly in downtown areas with heavy foot traffic and scooter use.
“We wanted to understand all modes of transportation,” Alberque said. “GIS allows us to integrate traffic data with other information and analyze it in one place.”
City officials emphasized that privacy protections are built into the system. The city does not store video or collect personally identifiable information. The data is limited to anonymous counts, such as whether an object is a vehicle, pedestrian or bicycle, aggregated in 15-minute intervals.
“There’s no identifying information at all,” Alberque said. “We’re not recording video.”
The technology is not used to automatically change signal timing. Instead, the data is reviewed by engineers and used to inform decisions, with humans remaining in control throughout the process.
During the pilot, the city has validated the AI results by running manual counts alongside the software. Alberque said more than a dozen test cases have been reviewed so far, helping staff build confidence in the accuracy of the data.
Beyond traffic management, Raleigh’s camera network already supports other city departments. Police, 911 dispatchers and stormwater crews use the cameras during emergencies, including flooding events, to better understand conditions on the ground.
Scaling the system beyond the pilot phase would require additional investment. Alberque said the city has so far relied on existing infrastructure and limited resources while testing the technology’s potential.
“The technology is advancing very quickly,” he said. “We’re trying to be thoughtful about how we invest so we’re making good decisions as this evolves.”
For now, city leaders say the pilot offers a way to improve safety and efficiency at busy intersections without expanding roadways, an approach they see as increasingly important as Raleigh continues to grow.