'Best Paper' goes to our paper on computer vision applications of TERRA REF data at CVPPA 2021!

Oct. 11, 2021
10 figures displaying example data from the TERRA-REF gantry system. from top left, RGB image, RGB soil mask, RGB close up; 3D-scanner data depth, reflectance, and surface normals, point cloud, thermal, PSII fluorescence, Hyperspectral

A paper led by our group (LeBauer et al 2021) describes how the TERRA REF dataset can contribute to efforts in the computer vision domain. In it, we describe how public domain data generated by the TERRA REF project can be used by the Machine Learning and Computer Vision research communities.

It was awarded "best paper" based on reviewer scores at the Computer Vision for Plant Phenotyping in Agriculture (CVPPA) workshop at the ICCV 2021. The award was shared in part with another paper on TERRA REF data led by our collaborator Abby Stylianou (Stylianou et al., 2021).
 

David LeBauer, Max Burnette, Noah Fahlgren, Rob Kooper, Kenton McHenry, Abby Stylianou; What Does TERRA-REF's High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community? Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 1409-1415 (link)

Abby Stylianou, Robert Pless, Nadia Shakoor, Todd Mockler; Classification and Visualization of Genotype x Phenotype Interactions in Biomass Sorghum. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021, pp. 1352-1361 (link)