Repeated Multiview Imaging for Estimating Seedling Tiller Counts of Wheat Genotypes Using Drones

Abstract

Early generation breeding nurseries with thousands of genotypes in single-row plots are well suited to capitalize on high throughput phenotyping. Nevertheless, methods to monitor the intrinsically hard-to-phenotype early development of wheat are yet rare. We aimed to develop proxy measures for the rate of plant emergence, the number of tillers, and the beginning of stem elongation using drone-based imagery. We used RGB images (ground sampling distance of 3 mm pixel-1) acquired by repeated flights (≥ 2 flights per week) to quantify temporal changes of visible leaf area. To exploit the information contained in the multitude of viewing angles within the RGB images, we processed them to multiview ground cover images showing plant pixel fractions. Based on these images, we trained a support vector machine for the beginning of stem elongation (GS30). Using the GS30 as key point, we subsequently extracted plant and tiller counts using a watershed algorithm and growth modeling, respectively. Our results show that determination coefficients of predictions are moderate for plant count (R2=0.52), but strong for tiller count (R2=0.86) and GS30 (R2=0.77). Heritabilities are superior to manual measurements for plant count and tiller count, but inferior for GS30 measurements. Increasing the selection intensity due to throughput may overcome this limitation. Multiview image traits can replace hand measurements with high efficiency (85–223%). We therefore conclude that multiview images have a high potential to become a standard tool in plant phenomics.

Field Phenomics: Will It Enable Crop Improvement?

“…Where higher-resolution imagery is available, for example, either from in-field buggies [ 46 ] or UAV, it becomes possible to undertake more sophisticated image analysis to identify individual plants [ 101 , 102 ], leaves [ 103 ], tillers [ 104 ], or even wheat heads [ 105 , 106 ]. This opens up a wide range of phenotyping possibilities that include selection for characters such as ear density and inflorescence size.…”

Phenomics data processing: Extracting dose-response curve parameters from high-resolution temperature courses and repeated field-based wheat height measurements

“…As an independent random measurement errors was assumed, the parameter σ was fixed to the well-known measurement error of Structure-from-Motion based height estimations (Roth et al, 2020), herein the simulation input σ m (Table 1). Parameters were optimized using the method L-BFGS-B of the base R function optim .…”

High-throughput field crop phenotyping: current status and challenges

“…Additionally, they found that the model parameters and GLAI dynamics were highly heritable (0.65 ≤ H 2 ≤ 0.98). Similarly, Roth et al (2020) estimated the beginning of stem elongation, the rate of plant emergence, and the number of tillers of wheat seedlings by SVM and crop modelling based on timeseries multi-view angle UAS RGB images at an altitude of 18 m, achieving a tiller number estimation accuracy of R 2 = 0.86. Ubbens et al (2020) proposed the latent space phenotype (LSP) to evaluate time-course phenotypic changes caused by abiotic stress factors, such as drought, nitrogen deficiency, and salinity.…”