South KoreaManufacturing2025 – ongoingKorea Iron & Steel (KISCO)
AI video analysis for scrap classification and truck inspection
KISCO demonstrated an AI scrap-classification system with reported accuracy of up to 90%
Problem
Scrap grading depended on inspectors' visual judgments, creating differences in quality assessments. The industry also faced difficulty recruiting inspection staff.
Approach
A government-supported development program demonstrated Bogonet's AI video-analysis system at KISCO's Changwon plant in November 2025. It covered scrap charging analysis and incoming-truck inspection. Vehicle tracking helped the system locate trucks arriving to unload scrap.
Results
Takeaway
The reported accuracy concerned a demonstrated classification system. Broader industry deployment remained prospective.
Categories
- Industry
- Manufacturing
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Government support program
- Evidence
- Vendor case study
Sources
Source summaries
Steel & Metal News described the demonstration at KISCO's Changwon plant. It reported classification accuracy of up to 90% for Bogonet's system and plans to expand industry adoption.
Full details are in the original sources.