AI Spots Tunnel Hazards First at Busan's Yunsan Tunnel

CCTV and Radar Linked to Prevent Secondary Crashes Stopped Vehicles, Fallen Objects, Wrong-Way Driving Detected in Real Time Crash and Congestion Alerts Sent to Drivers Instantly Developed With 2.7 Billion Won in Government-Backed Funding

Society|
|
By Cho Won-jinbscity@sedaily.com
||
Scenario-based display examples of the artificial intelligence-based hazard detection system operating in Busan's Yunsan Tunnel. Photo courtesy of Busan Infrastructure Corp. - Seoul Economic Daily Society News from South Korea
Scenario-based display examples of the artificial intelligence-based hazard detection system operating in Busan's Yunsan Tunnel. Photo courtesy of Busan Infrastructure Corp.

BUSAN — An intelligent safety management system that uses artificial intelligence to detect hazards inside a tunnel before control room staff notice them is going into operation at Busan's Yunsan Tunnel.

Busan Infrastructure Corporation said on the 29th that it has installed an AI-based hazard detection system at the tunnel to prevent traffic accidents in real time and respond to sudden incidents. The system was jointly developed over 45 months by private specialist firms and university researchers, with a total of 2.7 billion won invested through a government-backed program.

The system combines AI with CCTV cameras and radar for real-time hazard detection. It automatically identifies stopped vehicles, fallen objects, wrong-way vehicles and pedestrians, as well as illegal lane changes and speeding vehicles. Previously, control room staff had to monitor CCTV screens continuously. Now the AI analyzes footage from inside the tunnel at all times and recognizes dangerous situations on its own.

Detected information is linked to variable message signs (VMS) inside the tunnel. When a crash or congestion occurs ahead, the signs automatically display warnings such as "Caution: congestion ahead" and "Reduce speed," and also show the distance to the point where the backup clears in real time. The setup goes beyond detecting an accident to helping following vehicles respond.

The corporation expects the system to cut the time between recognizing an incident and alerting drivers, lowering the risk of secondary crashes inside the tunnel, while also improving facility management efficiency through round-the-clock AI monitoring. Because it was jointly developed by local companies and research institutes, the corporation plans to use it as a smart safety management model that can be extended to other tunnels, underpasses and other urban infrastructure.

"AI technology is a core foundation for protecting citizens' lives and safety," a corporation official said. "We will actively adopt smart technology in urban infrastructure such as tunnels and roads to expand safety services that citizens can feel."

Original reporting by Cho Won-jin for Seoul Economic Daily.

AI-translated from Korean. Quotes from foreign sources are based on Korean-language reports and may not reflect exact original wording.

Watch · Seoul Economic Daily

More →
4:05

AI KEY

Preview
Korean Corporate Intelligence HubKOSPI · KOSDAQ · 12 sectors

A live, cap-weighted view of every KOSPI and KOSDAQ sector, with same-day Korean reporting distilled by company — built for foreign investors, correspondents and analysts who need to scan Korea before the next session.

Korea Company Atlas

Preview
Market Ontology · The Feedback LoopKFTC 2025 · 92 groups · 121,954 articles

An English ontology of the Korean market — how companies, the media, the government and the National Assembly move each other in a loop. Korea's named controlling persons and designated business groups are a mechanism, not a risk to be priced blind.

SIGNAL

Now live
English Edition · Capital MarketsM&A · IPO · PE · Fund Flows

SIGNAL English Edition is live — Korea's deal desk reporting in English. M&A, IPOs, private equity and fund flows, covered daily for global institutional investors. Browse free; subscriber-only scoops at the 50% intro rate.