Revised pothole detection now guides Korean expressway repairs

South Korea's Board of Audit and Inspection found that the expressway corporation's pothole detection reached 79.6% average accuracy after a fix, up from 14.7% at seven branches.

  • 2 an organization

    The board reports that accuracy rose from 14.7% at seven branches in March 2024 to 79.6% on average and that crews now use the system for expressway repairs.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent audit report supports the benefit.

Compared with

The same system at seven branches in March 2024, before the corporation revised its grading. Measured.

Without the system
14.7% (76 of 517 detections needed repair)
With it
79.6% on average, 95.5% for the urgent-repair group
The system’s part
Not isolated. The board compares the system's accuracy before and after the corporation changed its grading, so both figures concern the system itself. It does not compare repair work with and without the system. The board counts the system among the AI products of public bodies, but it does not say how the system was trained.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
Pothole detection system (포트홀 감지시스템)
Made by
Korea Expressway Corporation, Road Traffic Research Institute (한국도로공사 도로교통연구원)
Used by
Korea Expressway Corporation (한국도로공사)
Where
South Korea (national expressway network)
Stage
In routine use
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Inspecting Equipment, Structures, or Materials, Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Audit report, by authors with no tie to the system.

    Board of Audit and Inspection of Korea (감사원). 감사보고서 - 인공지능 대비실태 Ⅰ(신뢰성 확보 분야) - [Performance audit report, AI preparedness I: ensuring reliability]. Report dated December 2025, published 5 January 2026. Chapter 3, section 4, printed pp. 49-50.

    이후 위 공사는 [표 36]과 같이 도로파손 부위의 너비와 측정값의 신뢰도를 기준으로 포트홀을 긴급 보수군, 위험군, 후보군 등 3개 유형으로 구분할 수 있도록 포트홀 감지시스템 성능을 개선한 결과 탐지 정확도가 개선(평균 79.6%, 긴급 보수군 95.5%)되면서 고속도로 보수업무 수행에 본격 활용되고 있다.

Details

AI system

Workflow

Cameras mounted on vehicles filmed the expressway surface, and the system flagged damaged spots automatically. The corporation graded detections into urgent, hazard and candidate groups by damage width and measurement confidence.

Follow-up

Conditions for replication

The detection criteria must match the repair standard of the crews who act on the results. Developers must learn the repair standard from the department that carries out repairs.

Entry details

Sector

Road maintenance.

Purpose

The Korea Expressway Corporation's Road Traffic Research Institute built the system to find damage that needs repair on expressways, in images from cameras on vehicles.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). Revised pothole detection now guides Korean expressway repairs (AIBD-0702). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0702.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions