The XyloTron: Flexible, Open-Source, Image-Based Macroscopic Field Identification of Wood Products

Authors

Prabu Ravindran, Blaise J. Thompson, Richard K. Soares, Alex C. Wiedenhoeft

Abstract

Forests, estimated to contain two thirds of the world’s biodiversity, face existential threats due to illegal logging and land conversion. Efforts to combat illegal logging and to support sustainable value chains are hampered by a critical lack of affordable and scalable technologies for field-level inspection of wood and wood products. To meet this need we present the XyloTron, a complete, self-contained, multi-illumination, field-deployable, open-source platform for field imaging and identification of forest products at the macroscopic scale. The XyloTron platform integrates an imaging system built with off-the-shelf components, flexible illumination options with visible and UV light sources, software for camera control, and deep learning models for identification. We demonstrate the capabilities of the XyloTron platform with example applications for automatic wood and charcoal identification using visible light and human-mediated wood identification based on ultra-violet illumination and discuss applications in field imaging, metrology, and material characterization of other substrates.

Shop Contributions

Blaise Thompson worked closely with Alex C. Wiedenhoeft et. al. in the design and construction of the next-generation XyloScope. This all-in-one plant imaging device combines a camera with an integrated lighting assembly. The lighting assembly offers both white light and ultraviolet (UV) illumination, with UV being used to image sample florescence patterns. The position of the lights with the XyloScope can be adjusted using a simple rail system that also delivers power. The drive circuitry and controls for the lighting circuit are integrated into the XyloScope to create an all-in-one facile imaging tool. Internal 3D printed supports make the entire assembly mechanically robust and easy to replicate. The XyloScope is the hardware component of the XyloScope platform, which also contains custom software and machine learning models to form a complete wood identification solution.

Read the full article at: https://doi.org/10.3389/fpls.2020.01015