Material identification in bulk scrap recycling using optical and spectral imaging
Machine learning–based material identification for bulk scrap recycling using optical and spectral imaging. The approach predicts material composition in heterogeneous scrap streams to guide robotic sorting, improving efficiency and yield. It uses low-cost hyperspectral cameras combined with optical imaging to support segmentation and classification, along with robotic motion planning and yield estimate reporting.
Overview
This solution leverages the fusion of optical and spectral imaging with machine and deep learning models to improve material identification in bulk scrap recycling. By predicting the material type composition of raw scrap streams, the technology can guide robotic systems in sorting decisions, enhancing efficiency and yield. The approach is positioned as a low-cost alternative to traditional spectroscopy, intended for use with heterogeneous scrap materials.
Technical specifications
Key features:
- Integration of low-cost hyperspectral cameras with optical imaging for enhanced material classification
- Machine and deep learning models for segmentation and classification of scrap materials
- Motion planning strategies for robotic systems to optimize sorting efficiency
- Capability to generate yield estimate reports using advanced computational techniques
The system uses distinct spectral fingerprints of materials for classification, combined with optical imaging to improve segmentation and yield calculations. Robotic sorting is guided by advanced motion planning algorithms based on classifier outputs.
Technology readiness level
This solution is at Technology Readiness Level 6, indicating it has been demonstrated in relevant environments. Future validation will involve further development and testing phases, focusing on model implementation and robotic system optimization, with support from Maastricht University.
About Maastricht University
Maastricht University is a comprehensive public research university with a distinctly international outlook, located in the heart of the Meuse‑Rhine cross‑border region. Its formal integration with the Maastricht UMC+ academic medical center enables seamless clinical collaboration and translation for industry partners. UM is a founding partner of the Brightlands campuses—regional research and technology parks that co‑locate university labs, startups, corporates, and shared facilities—linking Maastricht to the Chemelot industrial site and to neighboring ecosystems in Aachen, Eindhoven, and Hasselt. Research is supported by competitive European and Dutch funding, including programmes of the European Commission and the Dutch Research Council (NWO). A dedicated Knowledge Transfer Office supports IP strategy, licensing, and venture creation for collaborations with companies.
delivered to your inbox.