Hwaseong's pothole detectors work better after an upgrade

South Korea's Board of Audit and Inspection found that pothole detectors in Hwaseong City's vehicles reached 90% accuracy in May 2025. An upgrade had matched them to the city's repair standard.

  • 1 an organization

    The board reports that operating efficiency improved and that the city measured 90% accuracy, but it gives no figure for the change in repair work.

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

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

An independent research report supports the benefit.

Compared with

The same terminals before the upgrade of December 2024 to June 2025. Assumed without a measurement.

The system’s part
Not isolated. The 90% figure comes from the city's own test of the upgraded terminals. The board does not compare repair work with and without the system. It counts the system among commercial AI products and notes that such products need further training on local data, but it does not describe this system's model.
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): 82 vehicle terminals and an operating system bought under the Hwaseong intelligent transport system project
Made by
Not named (the vendor's name is redacted in the public report)
Used by
Hwaseong City (화성시), Gyeonggi Province, road management department
Where
Hwaseong, Gyeonggi Province, South Korea
Stage
In routine use
Date
Kind
Aggregate result
Broad benefit
Inspecting Equipment, Structures, or Materials, Identifying Objects, Actions, and Events
Last revised
31 October 2026

Sources

  1. 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. 50-52.

    그 결과 2025년 5월 화성시가 포트홀 감지시스템 단말기의 성능을 시험한 결과 포트홀 탐지 정확도가 90%로 개선된 것으로 나타났고, 도로파손 위치 정보도 사용자가 알기 쉽게 도로명 주소 등이 제공되고 있어 위 시스템의 운용 효율성이 향상48)되었다.

Details

AI system

Workflow

Terminals in 82 city vehicles filmed the road and flagged potholes automatically. The upgrade graded potholes by width against the city's repair standard and gave locations as street addresses and GPS coordinates.

Follow-up

Conditions for replication

The city's repair standard must be written into the system's performance requirements. Commercial AI products need further training on local data to perform as expected.

Entry details

Sector

Road maintenance.

Purpose

A vendor whose name is redacted in the public report built the system to detect potholes and fallen objects from terminals in city 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). Hwaseong's pothole detectors work better after an upgrade (AIBD-0703). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0703.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions