Board lumber grading using deep learning semantic segmentation techniques

US10830755B2 · kind B2 · utility

Assignee

• LUCIDYNE TECHNOLOGIES, INC. · US

Inventors

• Revathy Narasimhan · Santa Clara, US
• Patrick Freeman · Brownsville, US
• Hayden Michael Aronson · Corvallis, US
• Kevin Johnsrude · Corvallis, US
• Chris Mosbrucker · Philomath, US
• Dan Robin · Seattle, US
• Ryan T. Shear · Corvallis, US
• Joseph H. Weintraub · Cheltenham, US
• Eric N. Mortensen · Albany, US

Key dates

• Filing date: Feb 21, 2020
• Grant date: Nov 10, 2020
• Expiry date: Feb 21, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30161
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

A method of board lumber grading is performed in an industrial environment on a machine learning framework configured as an interface to a machine learning-based deep convolutional network that is trained end-to-end, pixels-to-pixels on semantic segmentation. The method uses deep learning techniques that are applied to semantic segmentation to delineate board lumber characteristics, including their sizes and boundaries.