Police to pilot AI system in crackdown on drivers blocking intersection traffic

Police will deploy AI-powered traffic cameras in Seoul next month to crack down on drivers who block traffic in intersections in one of the capital’s most persistent road complaints.

Police crack down on reckless driving, including blocking intersections and cutting in, at the Yonsei University intersection in Seodaemun District, western Seoul, on Nov. 4, as part of a traffic enforcement project. [NEWS1]

Police will deploy AI-powered traffic cameras in Seoul next month to crack down on drivers who block traffic in intersections.

The National Police Agency said Monday it will run a three-month pilot from December through February at the World Taekwondo Headquarters intersection in Gangnam District, southern Seoul, where the cameras will issue warnings to cars that stop inside a designated no-stop zone.

The system targets vehicles that enter the intersection on a green light and then obstruct cross traffic by remaining in the intersection after the light turns red. Cars forced to stop because of unavoidable emergencies, such as accidents, will not face enforcement.

The new equipment uses AI-based video analysis developed through the agency’s research program.

Police said the technology improves accuracy and allows red light, speeding and tailgating enforcement to be handled by a single device, cutting maintenance needs and improving efficiency.

Police plan to install similar cameras at 10 chronically congested intersections in 2026 and expand the program nationwide in 2027.

“Entering an intersection just because the light is green, or acting on the small selfish thought of ‘I will go first,’ threatens public safety," a police official said. "We will step up enforcement against tailgating to keep traffic moving and prevent accidents.”

The official also urged drivers to check for congestion ahead before entering an intersection, even when signals permit them to proceed.

This article was originally written in Korean and translated by a bilingual reporter with the help of generative AI tools. It was then edited by a native English-speaking editor. All AI-assisted translations are reviewed and refined by our newsroom. BY JEONG JAE-HONG [kim.juyeon2@joongang.co.kr]