AI crossing cameras to alert train drivers at Nonsan and Boseong

AI system

System: AI-based intelligent CCTV for railway crossings (supplier not named)
Model: Not assessed
Release: Not assessed
Application developer: Not named
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: A national accident-prevention plan following fatal crossing accidents. Pilot sites chosen where accidents occurred the previous year.
Human oversight: Not assessed
Relation to AI: Planned system; the sources describe the intended function and rollout sequence only.
AI contribution: Not assessed

Outcome identifiers: Not assessed
Benefit: Kyunghyang Shinmun (11 Feb 2026): MOLIT's crossing-accident plan from March 2026 includes AI intelligent CCTV piloted in Q1 at two crossings where 2025 accidents occurred; 36 crossing accidents in ...
Category: Increased Product Safety
Status: Not assessed
Beneficiary groups: Society. Organizations. People.
Beneficiaries: Not assessed
Reach: Not assessed
Distribution and access: Not assessed
Duration: Not assessed
Expected?: Yes
Costs and harms: Not assessed

Participants: Developer: Not named. Operator: Ministry of Land, Infrastructure and Transport (South Korea), planned.
Jurisdictions: Operator: South Korea.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: Pilot results support rollout. Alerts reach drivers early enough to stop.
Replication attempts: 1 follow-up entries. Benefit recurred: 1.
Later findings: The sources report the announcement of 11 February 2026. No subsequent installation or results from the Nonsan or Boseong pilots are established.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: Society. Organizations. People.
Depth: Not assessed
Reasons: Society: No outcome is documented. Organizations: No outcome is documented. People: No outcome is documented.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Railway safety. Level-crossing obstacle detection.
Purpose: The AI CCTV is intended to detect vehicles or pedestrians trapped in crossings and warn approaching train drivers in time to stop.
Dates: Date basis unassessed: 2026 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 3fdbb43dd896…

News report Independent author

최미랑 (11 Feb 2026). 철도건널목에 차량 갇히면 기관사에게 정보 전송···인공지능 CCTV 도입. 경향신문.
Registry label Independent author

OECD AI Incidents and Hazards Monitor, incident 2026-02-11-4404: South Korea Deploys AI CCTV to Prevent Railway Crossing Accidents (labelled AI hazard).