Manage episode 244663786 series 2541695
“A Low-Cost Automated System for High-Throughput Phenotyping of Single Oat Seeds” with James Clohessy.
A Rube Goldberg machine is a machine intentionally designed to complete a simple task using overly complicated steps. James Clohessy and his team are doing just the opposite. Using machine learning, web cameras, open software, and photogrammetry techniques, they’re developing low cost, high-throughput, high efficiency phenotyping systems. With these systems, researchers can save hours of time that would normally be spent on taking individual seed measurements by hand, such as height, width, and color, all while gaining greater detail about the seed such as volume and density.
Listen in to learn more about James’ new system as well as:
- What are phenotyping and photogrammetry?
- What are some of the applications of knowing seed size, color, and weight?
- What are some of the limitations of high-throughput phenotyping?
- What are some of the future applications of these machine learning systems?
If you would like more information about this topic, this episode’s paper is available here: https://doi.org/10.2135/tppj2018.07.0005
This paper is always freely available.
If you would like to find transcripts for this episode or sign up for our newsletter, please visit our website: http://fieldlabearth.libsyn.com/
Contact us at firstname.lastname@example.org or on Twitter @FieldLabEarth if you have comments, questions, or suggestions for show topics, and if you want more content like this don’t forget to subscribe.
Cornell Plant Breeding and Genetics Section: https://plbrgen.cals.cornell.edu/
Dr. Guo’s Easy PPC program: http://park.itc.u-tokyo.ac.jp/Field-Phenomics/ninolab/PhenotypingTools/EasyPCC.html
HeatSync Labs: https://www.heatsynclabs.org/
Field, Lab, Earth is copyrighted to the American Society of Agronomy, Crop Science Society of America, and Soil Science Society of America.