The traditional visual rating system is labor-intensive, time-consuming, and prone to human error. Unmanned aerial vehicle (UAV) imagery-based vegetation indices (VI) have potential applications in high-throughput plant phenotyping. The study objective is to determine if UAV imagery provides accurate and consistent estimations of crop injury from herbicide application and its potential as an alternative to visual ratings. The study was conducted at the Kernen Crop Research Farm, University of Saskatchewan in 2016 and 2017. Fababean (Vicia faba L.) crop tolerance to nine herbicide tank mixtures was evaluated with 2 rates distributed in a randomized complete block design (RCBD) with 4 blocks. The trial was imaged using a multispectral camera with a ground sample distance (GSD) of 1.2cm, one week after the treatment application. Visual ratings of growth reduction and physiological chlorosis were recorded simultaneously with imaging. The optimized soil-adjusted vegetation index (OSAVI) was calculated from the thresholded orthomosaics. The UAV-based vegetation index (OSAVI) produced more precise results compared to visual ratings for both years. The coefficient of variation (CV) of OSAVI was 1 when compared to 18-43 for the visual ratings. Furthermore, Tukeys honestly significance difference (HSD) test yielded a more precise mean separation for the UAV-based vegetation index than visual ratings. The significant correlations between OSAVI and the visual ratings from the study suggest that undesirable variability associated with visual assessments can be minimized with the UAV-based approach. UAV-based imagery methods had greater precision than the visual-based ratings for crop herbicide damage. These methods have the potential to replace visual ratings and aid in screening crops for herbicide tolerance.

Unmanned aerial vehicle (UAV) imaging is a promising data acquisition technique for image-based plant phenotyping. However, UAV images have a lower spatial resolution than similarly equipped in field ground-based vehicle systems, such as carts, because of their distance from the crop canopy, which can be particularly problematic for measuring small-sized plant features. In this study, the performance of three deep learning-based super resolution models, employed as a pre-processing tool to enhance the spatial resolution of low resolution images of three different kinds of crops were evaluated. To train a super resolution model, aerial images employing two separate sensors co-mounted on a UAV flown over lentil, wheat and canola breeding trials were collected. A software workflow to pre-process and align real-world low resolution and high-resolution images and use them as inputs and targets for training super resolution models was created. To demonstrate the effectiveness of real-world images, three different experiments employing synthetic images, manually downsampled high resolution images, or real-world low resolution images as input to the models were conducted. The performance of the super resolution models demonstrates that the models trained with synthetic images cannot generalize to real-world images and fail to reproduce comparable images with the targets. However, the same models trained with real-world datasets can reconstruct higher-fidelity outputs, which are better suited for measuring plant phenotypes.

Plant breeding experiments typically contain a large number of plots, and obtaining phenotypic data is an integral part of most studies. Image-based plot-level measurements may not always produce adequate precision and will require sub-plot measurements. To perform image analysis on individual sub-plots, they must be segmented from plots, other sub-plots, and surrounding soil or vegetation. This study aims to introduce a semi-automatic workflow to segment irregularly aligned plots and sub-plots in breeding populations. Imagery from a replicated lentil diversity panel phenotyping experiment with 324 populations was used for this study. Image-based techniques using a convolution filter on an excess green index (ExG) were used to enhance and highlight plot rows and, thus, locate the plot center. Multi-threshold and watershed segmentation were then combined to separate plants, ground, and sub-plot within plots. Algorithms of local maxima and pixel resizing with surface tension parameters were used to detect the centers of sub-plots. A total of 3489 reference data points was collected on 30 random plots for accuracy assessment. It was found that all plots and sub-plots were successfully extracted with an overall plot extraction accuracy of 92%. Our methodology addressed some common issues related to plot segmentation, such as plot alignment and overlapping canopies in the field experiments. The ability to segment and extract phenometric information at the sub-plot level provides opportunities to improve the precision of image-based phenotypic measurements at field-scale.