Image Based Plant Phenotyping: The PhenoSorg Project

In this project we are investigating image based plant phenotyping. Our traget crop is Sorghum. We are doing field based image acquisition using UAVs and ground based sensing. Energy sorghum is a high yielding crop used to produce biofuel. Estimating the properties of plants (i.e, phenotyping) is critical to predict its biomass. Our team focuses on estimating phenotypic traits such as plant locations, number of plants per plot, Leaf Area Index, canopy cover, leaf length and width, and the number of leaves per plant. We analyze these properties in real field conditions instead of in a controlled environment such as a greenhouse. We process images collected from Unmanned Aerial Vehicles (UAVs) and a custom mobile ground platform (the PhenoRover). The goal of this research is to develop a set of tools to precisely and quickly phenotype hundreds of thousands of sorghum plants on a daily basis.

This project is part of the Purdue TERRA Project.

The TERRA Project has assembled a multidisciplinary team of outstanding technical experts, with complementary skills and background in computer vision, machine learning, remote sensing, plant breeding and genetics, digital photogrammetry, as well as UAV technology.

This work is supported by the Advanced Research Projects Agency-Energy (ARPA-E) as part of the Automated Sorghum Phenotyping and Trait Development Platform program.

The information, data, or work presented herein was funded in part by the Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy, under Award Number DE-AR0000593. The views and opinions of the authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.