Hong KongPublic sector2023 – ongoingHong Kong Housing Authority
AI analysis of drone images for external-wall acceptance inspections
Hong Kong housing inspectors trialled AI analysis of drone photographs to find wall defects
Problem
Inspectors previously examined external walls by looking out of windows. Narrow viewing angles and obstructing pipes limited what they could see and created safety risks.
Approach
The Housing Department trialled drone photography at Yue Chun House, Kam Fai Court and Dip Tsui Court. AI organised and examined the images to identify defects such as cracks and flaking paint. Supervisory staff validated findings and instructed contractors to rectify defects.
Results
No published figures
Takeaway
The workflow moved image capture outside the building while keeping acceptance decisions with supervisory staff. Suitable weather remained a condition for drone flights.
Categories
- Size
- Large enterprise
- Industry
- Public sector
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
The department described trials that combined drone photographs with AI-assisted defect detection. Staff reviewed the findings before requesting repairs. It reported qualitative improvements in inspection speed and safety without publishing measured savings.
Full details are in the original sources.
