Field‐based robotic phenotyping of sorghum plant architecture using stereo vision

Abstract

Sorghum (Sorghum bicolor) is known as a major feedstock for biofuel production. To improve its biomass yield through genetic research, manually measuring yield component traits (e.g. plant height, stem diameter, leaf angle, leaf area, leaf number, and panicle size) in the field is the current best practice. However, such laborious and time-consuming tasks have become a bottleneck limiting experiment scale and data acquisition frequency. This paper presents a high-throughput field-based robotic phenotyping system which performed side-view stereo imaging for dense sorghum plants with a wide range of plant heights throughout the growing season. Our study demonstrated the suitability of stereo vision for field-based three-dimensional plant phenotyping when recent advances in stereo matching algorithms were incorporated.A robust data processing pipeline was developed to quantify the variations or morphological traits in plant architecture, which included plot-based plant height, plot-based plant width, convex hull volume, plant surface area, and stem diameter (semiautomated). These image-derived measurements were highly repeatable and showed high correlations with the in-field manual measurements. Meanwhile, manually collecting the same traits required a large amount of manpower and time compared to the robotic system. The results demonstrated that the proposed system could be a promising tool for large-scale field-based high-throughput plant phenotyping of bioenergy crops. K E Y W O R D Sbioenergy sorghum, high-throughput phenotyping, point cloud processing, stereo vision, yield component traits

MVS-Pheno: A Portable and Low-Cost Phenotyping Platform for Maize Shoots Using Multiview Stereo 3D Reconstruction

“…Field phenotyping platforms mainly consist of unmanned aerial vehicle (UAV) remote-sensing platforms [ 12 ], cable-suspended field phenotyping platforms [ 13 ], robotic field phenotyping platforms mounted on fixed rails [ 10 ], and tractor-driven field phenotyping systems [ 14 , 15 ]. Field phenotyping platforms are integrated with moveable sensors on robotic carriers that enable them to acquire morphological and physiological data from crops and are thus described as “sensor-to-plant” systems [ 16 ].…”

Novel Bayesian Networks for Genomic Prediction of Developmental Traits in Biomass Sorghum

“…There have been significant advances in field-based highthroughput phenotyping (HTP) technologies for the rapid measurement of plant traits over the growing season (Bao et al 2019;Pauli et al 2016). Measuring phenotypes at multiple time points over the life cycle of a plant can better describe the progression of growth and development (Muraya et al 2017).…”

Canopy density estimation in perennial horticulture crops using 3D spinning lidar SLAM

“…There are several previous works that review non‐destructive approaches (e.g., optical methods) for canopy structure estimation (Bao et al, 2019), but in this section, we focus on recent studies that consider lidar‐based solutions under various field conditions in perennial agricultural crops, such as vineyards and orchards. Non‐destructive lidar‐based solutions have advantages over optical methods such as producing direct measurements of canopy structure and being less affected by environmental conditions such as direct sun or day/night applicability.…”