SBIR Phase II: Computer Vision for Merchandizing Forest Products

The broader impact of this Small Business Innovation Research (SBIR) Phase II project is the advancement of a practical artificial intelligence–based system using computer vision methods applicable in the product supply chain. The technology will enable more consistent decisions, reduce costly misclassification of products and, improve value recovery. From a scientific and technological perspective, the project advances the understanding of mechanisms governing the reliable deployment and performance stability of multi-task computer vision systems. This Small Business Innovation Research (SBIR) Phase II project aims build on a field-validated prototype developed in Phase I and focuses on advancing computer vision methods. The project will develop and validate a multi-task learning framework capable of highly reliable operation under variable lighting, occlusion, vibration, and remote conditions. Additional research will investigate real-time performance optimization, object tracking across handling stages, and integration of operator guidance to support optimal processing decisions. The anticipated technical outcomes include improved accuracy, higher inference rates, and validated performance thresholds suitable for commercial deployment. Together, these results will demonstrate that advanced perception and decision-support systems can deliver robust and practical solutions for complex deployment settings. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.