Showing papers in "Plant Methods in 2017"

Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress.

Abstract: This review explores how imaging techniques are being developed with a focus on deployment for crop monitoring methods. Imaging applications are discussed in relation to both field and glasshouse-based plants, and techniques are sectioned into ‘healthy and diseased plant classification’ with an emphasis on classification accuracy, early detection of stress, and disease severity. A central focus of the review is the use of hyperspectral imaging and how this is being utilised to find additional information about plant health, and the ability to predict onset of disease. A summary of techniques used to detect biotic and abiotic stress in plants is presented, including the level of accuracy associated with each method.

TasselNet: counting maize tassels in the wild via local counts regression network

Abstract: Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations. This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel Maize Tassels Counting (MTC) dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed TasselNet is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large margins and achieves the overall best counting performance, with a mean absolute error of 6.6 and a mean squared error of 9.6 averaged over 8 test sequences. TasselNet can achieve robust in-field counting of maize tassels with a relatively high degree of accuracy. Our experimental evaluations also suggest several good practices for practitioners working on maize-tassel-like counting problems. It is worth noting that, though the counting errors have been greatly reduced by TasselNet, in-field counting of maize tassels remains an open and unsolved problem.

Comparison of three genomic DNA extraction methods to obtain high DNA quality from maize.

Abstract: The world’s top three cereals, based on their monetary value, are rice, wheat, and corn. In cereal crops, DNA extraction is difficult owing to rigid non-cellulose components in the cell wall of leaves and high starch and protein content in grains. The advanced techniques in molecular biology require pure and quick extraction of DNA. The majority of existing DNA extraction methods rely on long incubation and multiple precipitations or commercially available kits to produce contaminant-free high molecular weight DNA. In this study, we compared three different methods used for the isolation of high-quality genomic DNA from the grains of cereal crop, Zea mays, with minor modifications. The DNA from the grains of two maize hybrids, M10 and M321, was extracted using extraction methods DNeasy Qiagen Plant Mini Kit, CTAB-method (with/without 1% PVP) and modified Mericon extraction. Genes coding for 45S ribosomal RNA are organized in tandem arrays of up to several thousand copies and contain codes for 18S, 5.8S and 26S rRNA units separated by internal transcribed spacers ITS1 and ITS2. While the rRNA units are evolutionary conserved, ITS regions show high level of interspecific divergence and have been used frequently in genetic diversity and phylogenetic studies. In this study, the genomic DNA was then amplified with PCR using primers specific for ITS gene. PCR products were then visualized on agarose gel. The modified Mericon extraction method was found to be the most efficient DNA extraction method, capable to provide high DNA yields with better quality, affordable cost and less time.

A real-time phenotyping framework using machine learning for plant stress severity rating in soybean.

Abstract: Phenotyping is a critical component of plant research. Accurate and precise trait collection, when integrated with genetic tools, can greatly accelerate the rate of genetic gain in crop improvement. However, efficient and automatic phenotyping of traits across large populations is a challenge; which is further exacerbated by the necessity of sampling multiple environments and growing replicated trials. A promising approach is to leverage current advances in imaging technology, data analytics and machine learning to enable automated and fast phenotyping and subsequent decision support. In this context, the workflow for phenotyping (image capture → data storage and curation → trait extraction → machine learning/classification → models/apps for decision support) has to be carefully designed and efficiently executed to minimize resource usage and maximize utility. We illustrate such an end-to-end phenotyping workflow for the case of plant stress severity phenotyping in soybean, with a specific focus on the rapid and automatic assessment of iron deficiency chlorosis (IDC) severity on thousands of field plots. We showcase this analytics framework by extracting IDC features from a set of ~4500 unique canopies representing a diverse germplasm base that have different levels of IDC, and subsequently training a variety of classification models to predict plant stress severity. The best classifier is then deployed as a smartphone app for rapid and real time severity rating in the field. We investigated 10 different classification approaches, with the best classifier being a hierarchical classifier with a mean per-class accuracy of ~96%. We construct a phenotypically meaningful ‘population canopy graph’, connecting the automatically extracted canopy trait features with plant stress severity rating. We incorporated this image capture → image processing → classification workflow into a smartphone app that enables automated real-time evaluation of IDC scores using digital images of the canopy. We expect this high-throughput framework to help increase the rate of genetic gain by providing a robust extendable framework for other abiotic and biotic stresses. We further envision this workflow embedded onto a high throughput phenotyping ground vehicle and unmanned aerial system that will allow real-time, automated stress trait detection and quantification for plant research, breeding and stress scouting applications.

Panicle-SEG: a robust image segmentation method for rice panicles in the field based on deep learning and superpixel optimization

Abstract: Rice panicle phenotyping is important in rice breeding, and rice panicle segmentation is the first and key step for image-based panicle phenotyping. Because of the challenge of illumination differentials, panicle shape deformations, rice accession variations, different reproductive stages and the field’s complex background, rice panicle segmentation in the field is a very large challenge. In this paper, we propose a rice panicle segmentation algorithm called Panicle-SEG, which is based on simple linear iterative clustering superpixel regions generation, convolutional neural network classification and entropy rate superpixel optimization. To build the Panicle-SEG-CNN model and test the segmentation effects, 684 training images and 48 testing images were randomly selected, respectively. Six indicators, including Qseg, Sr, SSIM, Precision, Recall and F-measure, are employed to evaluate the segmentation effects, and the average segmentation results for the 48 testing samples are 0.626, 0.730, 0.891, 0.821, 0.730, and 76.73%, respectively. Compared with other segmentation approaches, including HSeg, i2 hysteresis thresholding and jointSeg, the proposed Panicle-SEG algorithm has better performance on segmentation accuracy. Meanwhile, the executing speed is also improved when combined with multithreading and CUDA parallel acceleration. Moreover, Panicle-SEG was demonstrated to be a robust segmentation algorithm, which can be expanded for different rice accessions, different field environments, different camera angles, different reproductive stages, and indoor rice images. The testing dataset and segmentation software are available online. In conclusion, the results demonstrate that Panicle-SEG is a robust method for panicle segmentation, and it creates a new opportunity for nondestructive yield estimation.

Predicting grain yield using canopy hyperspectral reflectance in wheat breeding data

Abstract: Modern agriculture uses hyperspectral cameras to obtain hundreds of reflectance data measured at discrete narrow bands to cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra, depending on the camera. This information is used to construct vegetation indices (VI) (e.g., green normalized difference vegetation index or GNDVI, simple ratio or SRa, etc.) which are used for the prediction of primary traits (e.g., biomass). However, these indices only use some bands and are cultivar-specific; therefore they lose considerable information and are not robust for all cultivars. This study proposes models that use all available bands as predictors to increase prediction accuracy; we compared these approaches with eight conventional vegetation indexes (VIs) constructed using only some bands. The data set we used comes from CIMMYT’s global wheat program and comprises 1170 genotypes evaluated for grain yield (ton/ha) in five environments (Drought, Irrigated, EarlyHeat, Melgas and Reduced Irrigated); the reflectance data were measured in 250 discrete narrow bands ranging between 392 and 851 nm. The proposed models for the simultaneous analysis of all the bands were ordinal least square (OLS), Bayes B, principal components with Bayes B, functional B-spline, functional Fourier and functional partial least square. The results of these models were compared with the OLS performed using as predictors each of the eight VIs individually and combined. We found that using all bands simultaneously increased prediction accuracy more than using VI alone. The Splines and Fourier models had the best prediction accuracy for each of the nine time-points under study. Combining image data collected at different time-points led to a small increase in prediction accuracy relative to models that use data from a single time-point. Also, using bands with heritabilities larger than 0.5 only in Drought as predictor variables showed improvements in prediction accuracy.

Quantifying pruning impacts on olive tree architecture and annual canopy growth by using UAV-based 3D modelling

Abstract: Tree pruning is a costly practice with important implications for crop harvest and nutrition, pest and disease control, soil protection and irrigation strategies. Investigations on tree pruning usually involve tedious on-ground measurements of the primary tree crown dimensions, which also might generate inconsistent results due to the irregular geometry of the trees. As an alternative to intensive field-work, this study shows a innovative procedure based on combining unmanned aerial vehicle (UAV) technology and advanced object-based image analysis (OBIA) methodology for multi-temporal three-dimensional (3D) monitoring of hundreds of olive trees that were pruned with three different strategies (traditional, adapted and mechanical pruning). The UAV images were collected before pruning, after pruning and a year after pruning, and the impacts of each pruning treatment on the projected canopy area, tree height and crown volume of every tree were quantified and analyzed over time. The full procedure described here automatically identified every olive tree on the orchard and computed their primary 3D dimensions on the three study dates with high accuracy in the most cases. Adapted pruning was generally the most aggressive treatment in terms of the area and volume (the trees decreased by 38.95 and 42.05% on average, respectively), followed by trees under traditional pruning (33.02 and 35.72% on average, respectively). Regarding the tree heights, mechanical pruning produced a greater decrease (12.15%), and these values were minimal for the other two treatments. The tree growth over one year was affected by the pruning severity and by the type of pruning treatment, i.e., the adapted-pruning trees experienced higher growth than the trees from the other two treatments when pruning intensity was low (<10%), similar to the traditionally pruned trees at moderate intensity (10–30%), and lower than the other trees when the pruning intensity was higher than 30% of the crown volume. Combining UAV-based images and an OBIA procedure allowed measuring tree dimensions and quantifying the impacts of three different pruning treatments on hundreds of trees with minimal field work. Tree foliage losses and annual canopy growth showed different trends as affected by the type and severity of the pruning treatments. Additionally, this technology offers valuable geo-spatial information for designing site-specific crop management strategies in the context of precision agriculture, with the consequent economic and environmental benefits.

Selection and validation of reference genes for RT-qPCR analysis in potato under abiotic stress.

Abstract: Real-time quantitative PCR (RT-qPCR) is the most commonly used method for accurately detecting gene expression patterns. As part of RT-qPCR analysis, normalization of the data requires internal control gene(s) that display uniform expression under different biological conditions. However, no invariable internal control gene exists, and therefore more than one reference gene is needed to normalize RT-qPCR results. Identification of stable reference genes in potato will improve assay accuracy for selecting stress-tolerance genes and identifying molecular mechanisms conferring stress tolerance in this species. In the experiment, we assessed the expression of eight candidate internal control genes, namely elongation factor-1alpha (EF1α), actin, tubulin, glyceraldehyde-3-phosphate dehydrogenase (GAPDH), adenine phosphoribosyl transferase (APRT), 60S ribosomal protein L8 (L8), Cullin 3A (CUL3A), and exocyst complex component sec3 (sec3), in a diverse set of potato samples representing drought stress and osmotic stress challenges, and using geNorm, NormFinder, BestKeeper and RefFinder softwares. The results indicated that EF1α and sec3 were the most stably expressed genes in the potato under drought and osmotic stress conditions. This work will facilitate future work on gene expression studies in potato and also benefit other species of the Solanaceae, such as tomato.

Non-invasive imaging of plant roots in different soils using magnetic resonance imaging (MRI)

Abstract: Root systems are highly plastic and adapt according to their soil environment. Studying the particular influence of soils on root development necessitates the adaptation and evaluation of imaging methods for multiple substrates. Non-invasive 3D root images in soil can be obtained using magnetic resonance imaging (MRI). Not all substrates, however, are suitable for MRI. Using barley as a model plant we investigated the achievable image quality and the suitability for root phenotyping of six commercially available natural soil substrates of commonly occurring soil textures. The results are compared with two artificially composed substrates previously documented for MRI root imaging. In five out of the eight tested substrates, barley lateral roots with diameters below 300 µm could still be resolved. In two other soils, only the thicker barley seminal roots were detectable. For these two substrates the minimal detectable root diameter was between 400 and 500 µm. Only one soil did not allow imaging of the roots with MRI. In the artificially composed substrates, soil moisture above 70% of the maximal water holding capacity (WHCmax) impeded root imaging. For the natural soil substrates, soil moisture had no effect on MRI root image quality in the investigated range of 50–80% WHCmax. Almost all tested natural soil substrates allowed for root imaging using MRI. Half of these substrates resulted in root images comparable to our current lab standard substrate, allowing root detection down to a diameter of 300 µm. These soils were used as supplied by the vendor and, in particular, removal of ferromagnetic particles was not necessary. With the characterization of different soils, investigations such as trait stability across substrates are now possible using noninvasive MRI.

Development of an efficient glucosinolate extraction method.

Abstract: Glucosinolates, anionic sulfur rich secondary metabolites, have been extensively studied because of their occurrence in the agriculturally important brassicaceae and their impact on human and animal health. There is also increasing interest in the biofumigant properties of toxic glucosinolate hydrolysis products as a method to control agricultural pests. Evaluating biofumigation potential requires rapid and accurate quantification of glucosinolates, but current commonly used methods of extraction prior to analysis involve a number of time consuming and hazardous steps; this study aimed to develop an improved method for glucosinolate extraction. Three methods previously used to extract glucosinolates from brassicaceae tissues, namely extraction in cold methanol, extraction in boiling methanol, and extraction in boiling water were compared across tissue type (root, stem leaf) and four brassicaceae species (B. juncea, S. alba, R. sativus, and E. sativa). Cold methanol extraction was shown to perform as well or better than all other tested methods for extraction of glucosinolates with the exception of glucoraphasatin in R. sativus shoots. It was also demonstrated that lyophilisation methods, routinely used during extraction to allow tissue disruption, can reduce final glucosinolate concentrations and that extracting from frozen wet tissue samples in cold 80% methanol is more effective. We present a simplified method for extracting glucosinolates from plant tissues which does not require the use of a freeze drier or boiling methanol, and is therefore less hazardous, and more time and cost effective. The presented method has been shown to have comparable or improved glucosinolate extraction efficiency relative to the commonly used ISO method for major glucosinolates in the Brassicaceae species studied: sinigrin and gluconasturtiin in B. juncea; sinalbin, glucotropaeolin, and gluconasturtiin in S. alba; glucoraphenin and glucoraphasatin in R. sativus; and glucosatavin, glucoerucin and glucoraphanin in E. sativa.

A robot-assisted imaging pipeline for tracking the growths of maize ear and silks in a high-throughput phenotyping platform.

Abstract: In maize, silks are hundreds of filaments that simultaneously emerge from the ear for collecting pollen over a period of 1–7 days, which largely determines grain number especially under water deficit. Silk growth is a major trait for drought tolerance in maize, but its phenotyping is difficult at throughputs needed for genetic analyses. We have developed a reproducible pipeline that follows ear and silk growths every day for hundreds of plants, based on an ear detection algorithm that drives a robotized camera for obtaining detailed images of ears and silks. We first select, among 12 whole-plant side views, those best suited for detecting ear position. Images are segmented, the stem pixels are labelled and the ear position is identified based on changes in width along the stem. A mobile camera is then automatically positioned in real time at 30 cm from the ear, for a detailed picture in which silks are identified based on texture and colour. This allows analysis of the time course of ear and silk growths of thousands of plants. The pipeline was tested on a panel of 60 maize hybrids in the PHENOARCH phenotyping platform. Over 360 plants, ear position was correctly estimated in 86% of cases, before it could be visually assessed. Silk growth rate, estimated on all plants, decreased with time consistent with literature. The pipeline allowed clear identification of the effects of genotypes and water deficit on the rate and duration of silk growth. The pipeline presented here, which combines computer vision, machine learning and robotics, provides a powerful tool for large-scale genetic analyses of the control of reproductive growth to changes in environmental conditions in a non-invasive and automatized way. It is available as Open Source software in the OpenAlea platform.

A nondestructive method to estimate the chlorophyll content of Arabidopsis seedlings

Abstract: Chlorophyll content decreases in plants under stress conditions, therefore it is used commonly as an indicator of plant health. Arabidopsis thaliana offers a convenient and fast way to test physiological phenotypes of mutations and treatments. However, chlorophyll measurements with conventional solvent extraction are not applicable to Arabidopsis leaves due to their small size, especially when grown on culture dishes. We provide a nondestructive method for chlorophyll measurement whereby the red, green and blue (RGB) values of a color leaf image is used to estimate the chlorophyll content from Arabidopsis leaves. The method accommodates different profiles of digital cameras by incorporating the ColorChecker chart to make the digital negative profiles, to adjust the white balance, and to calibrate the exposure rate differences caused by the environment so that this method is applicable in any environment. We chose an exponential function model to estimate chlorophyll content from the RGB values, and fitted the model parameters with physical measurements of chlorophyll contents. As proof of utility, this method was used to estimate chlorophyll content of G protein mutants grown on different sugar to nitrogen ratios. This method is a simple, fast, inexpensive, and nondestructive estimation of chlorophyll content of Arabidopsis seedlings. This method lead to the discovery that G proteins are important in sensing the C/N balance to control chlorophyll content in Arabidopsis.

Genomic Bayesian functional regression models with interactions for predicting wheat grain yield using hyper-spectral image data

Abstract: Modern agriculture uses hyperspectral cameras that provide hundreds of reflectance data at discrete narrow bands in many environments. These bands often cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra. With the bands, vegetation indices are constructed for predicting agronomically important traits such as grain yield and biomass. However, since vegetation indices only use some wavelengths (referred to as bands), we propose using all bands simultaneously as predictor variables for the primary trait grain yield; results of several multi-environment maize (Aguate et al. in Crop Sci 57(5):1–8, 2017) and wheat (Montesinos-Lopez et al. in Plant Methods 13(4):1–23, 2017) breeding trials indicated that using all bands produced better prediction accuracy than vegetation indices. However, until now, these prediction models have not accounted for the effects of genotype × environment (G × E) and band × environment (B × E) interactions incorporating genomic or pedigree information. In this study, we propose Bayesian functional regression models that take into account all available bands, genomic or pedigree information, the main effects of lines and environments, as well as G × E and B × E interaction effects. The data set used is comprised of 976 wheat lines evaluated for grain yield in three environments (Drought, Irrigated and Reduced Irrigation). The reflectance data were measured in 250 discrete narrow bands ranging from 392 to 851 nm (nm). The proposed Bayesian functional regression models were implemented using two types of basis: B-splines and Fourier. Results of the proposed Bayesian functional regression models, including all the wavelengths for predicting grain yield, were compared with results from conventional models with and without bands. We observed that the models with B × E interaction terms were the most accurate models, whereas the functional regression models (with B-splines and Fourier basis) and the conventional models performed similarly in terms of prediction accuracy. However, the functional regression models are more parsimonious and computationally more efficient because the number of beta coefficients to be estimated is 21 (number of basis), rather than estimating the 250 regression coefficients for all bands. In this study adding pedigree or genomic information did not increase prediction accuracy.

Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images.

Abstract: Hyperspectral imaging is an emerging means of assessing plant vitality, stress parameters, nutrition status, and diseases. Extraction of target values from the high-dimensional datasets either relies on pixel-wise processing of the full spectral information, appropriate selection of individual bands, or calculation of spectral indices. Limitations of such approaches are reduced classification accuracy, reduced robustness due to spatial variation of the spectral information across the surface of the objects measured as well as a loss of information intrinsic to band selection and use of spectral indices. In this paper we present an improved spatial-spectral segmentation approach for the analysis of hyperspectral imaging data and its application for the prediction of powdery mildew infection levels (disease severity) of intact Chardonnay grape bunches shortly before veraison. Instead of calculating texture features (spatial features) for the huge number of spectral bands independently, dimensionality reduction by means of Linear Discriminant Analysis (LDA) was applied first to derive a few descriptive image bands. Subsequent classification was based on modified Random Forest classifiers and selective extraction of texture parameters from the integral image representation of the image bands generated. Dimensionality reduction, integral images, and the selective feature extraction led to improved classification accuracies of up to $$0.998\pm 0.003$$ for detached berries used as a reference sample (training dataset). Our approach was validated by predicting infection levels for a sample of 30 intact bunches. Classification accuracy improved with the number of decision trees of the Random Forest classifier. These results corresponded with qPCR results. An accuracy of 0.87 was achieved in classification of healthy, infected, and severely diseased bunches. However, discrimination between visually healthy and infected bunches proved to be challenging for a few samples, perhaps due to colonized berries or sparse mycelia hidden within the bunch or airborne conidia on the berries that were detected by qPCR. An advanced approach to hyperspectral image classification based on combined spatial and spectral image features, potentially applicable to many available hyperspectral sensor technologies, has been developed and validated to improve the detection of powdery mildew infection levels of Chardonnay grape bunches. The spatial-spectral approach improved especially the detection of light infection levels compared with pixel-wise spectral data analysis. This approach is expected to improve the speed and accuracy of disease detection once the thresholds for fungal biomass detected by hyperspectral imaging are established; it can also facilitate monitoring in plant phenotyping of grapevine and additional crops.

Acquiring and preprocessing leaf images for automated plant identification: understanding the tradeoff between effort and information gain

Abstract: Automated species identification is a long term research subject. Contrary to flowers and fruits, leaves are available throughout most of the year. Offering margin and texture to characterize a species, they are the most studied organ for automated identification. Substantially matured machine learning techniques generate the need for more training data (aka leaf images). Researchers as well as enthusiasts miss guidance on how to acquire suitable training images in an efficient way. In this paper, we systematically study nine image types and three preprocessing strategies. Image types vary in terms of in-situ image recording conditions: perspective, illumination, and background, while the preprocessing strategies compare non-preprocessed, cropped, and segmented images to each other. Per image type-preprocessing combination, we also quantify the manual effort required for their implementation. We extract image features using a convolutional neural network, classify species using the resulting feature vectors and discuss classification accuracy in relation to the required effort per combination. The most effective, non-destructive way to record herbaceous leaves is to take an image of the leaf’s top side. We yield the highest classification accuracy using destructive back light images, i.e., holding the plucked leaf against the sky for image acquisition. Cropping the image to the leaf’s boundary substantially improves accuracy, while precise segmentation yields similar accuracy at a substantially higher effort. The permanent use or disuse of a flash light has negligible effects. Imaging the typically stronger textured backside of a leaf does not result in higher accuracy, but notably increases the acquisition cost. In conclusion, the way in which leaf images are acquired and preprocessed does have a substantial effect on the accuracy of the classifier trained on them. For the first time, this study provides a systematic guideline allowing researchers to spend available acquisition resources wisely while yielding the optimal classification accuracy.

Non-destructive, high-content analysis of wheat grain traits using X-ray micro computed tomography.

Abstract: Wheat is one of the most widely grown crop in temperate climates for food and animal feed. In order to meet the demands of the predicted population increase in an ever-changing climate, wheat production needs to dramatically increase. Spike and grain traits are critical determinants of final yield and grain uniformity a commercially desired trait, but their analysis is laborious and often requires destructive harvest. One of the current challenges is to develop an accurate, non-destructive method for spike and grain trait analysis capable of handling large populations. In this study we describe the development of a robust method for the accurate extraction and measurement of spike and grain morphometric parameters from images acquired by X-ray micro-computed tomography (μCT). The image analysis pipeline developed automatically identifies plant material of interest in μCT images, performs image analysis, and extracts morphometric data. As a proof of principle, this integrated methodology was used to analyse the spikes from a population of wheat plants subjected to high temperatures under two different water regimes. Temperature has a negative effect on spike height and grain number with the middle of the spike being the most affected region. The data also confirmed that increased grain volume was correlated with the decrease in grain number under mild stress. Being able to quickly measure plant phenotypes in a non-destructive manner is crucial to advance our understanding of gene function and the effects of the environment. We report on the development of an image analysis pipeline capable of accurately and reliably extracting spike and grain traits from crops without the loss of positional information. This methodology was applied to the analysis of wheat spikes can be readily applied to other economically important crop species.

Recent achievements obtained by chloroplast transformation.

Abstract: Chloroplasts play a great role for sustained wellbeing of life on the planet. They have the power and raw materials that can be used as sophisticated biological factories. They are rich in energy as they have lots of pigment-protein complexes capable of collecting sunlight, in sugar produced by photosynthesis and in minerals imported from the plant cell. Chloroplast genome transformation offers multiple advantages over nuclear genome which among others, include: integration of the transgene via homologus recombination that enables to eliminate gene silencing and position effect, higher level of transgene expression resulting into higher accumulations of foreign proteins, and significant reduction in environmental dispersion of the transgene due to maternal inheritance which helps to minimize the major critic of plant genetic engineering. Chloroplast genetic engineering has made fruit full progresses in the development of plants resistance to various stresses, phytoremediation of toxic metals, and production of vaccine antigens, biopharmaceuticals, biofuels, biomaterials and industrial enzymes. Although successful results have been achieved, there are still difficulties impeding full potential exploitation and expansion of chloroplast transformation technology to economical plants. These include, lack of species specific regulatory sequences, problem of selection and shoot regeneration, and massive expression of foreign genes resulting in phenotypic alterations of transplastomic plants. The aim of this review is to critically recapitulate the latest development of chloroplast transformation with special focus on the different traits of economic interest.

A high-throughput stereo-imaging system for quantifying rape leaf traits during the seedling stage

Abstract: The fitness of the rape leaf is closely related to its biomass and photosynthesis. The study of leaf traits is significant for improving rape leaf production and optimizing crop management. Canopy structure and individual leaf traits are the major indicators of quality during the rape seedling stage. Differences in canopy structure reflect the influence of environmental factors such as water, sunlight and nutrient supply. The traits of individual rape leaves traits indicate the growth period of the rape as well as its canopy shape. We established a high-throughput stereo-imaging system for the reconstruction of the three-dimensional canopy structure of rape seedlings from which leaf area and plant height can be extracted. To evaluate the measurement accuracy of leaf area and plant height, 66 rape seedlings were randomly selected for automatic and destructive measurements. Compared with the manual measurements, the mean absolute percentage error of automatic leaf area and plant height measurements was 3.68 and 6.18%, respectively, and the squares of the correlation coefficients (R2) were 0.984 and 0.845, respectively. Compared with the two-dimensional projective imaging method, the leaf area extracted using stereo-imaging was more accurate. In addition, a semi-automatic image analysis pipeline was developed to extract 19 individual leaf shape traits, including 11 scale-invariant traits, 3 inner cavity related traits, and 5 margin-related traits, from the images acquired by the stereo-imaging system. We used these quantified traits to classify rapes according to three different leaf shapes: mosaic-leaf, semi-mosaic-leaf, and round-leaf. Based on testing of 801 seedling rape samples, we found that the leave-one-out cross validation classification accuracy was 94.4, 95.6, and 94.8% for stepwise discriminant analysis, the support vector machine method and the random forest method, respectively. In this study, a nondestructive and high-throughput stereo-imaging system was developed to quantify canopy three-dimensional structure and individual leaf shape traits with improved accuracy, with implications for rape phenotyping, functional genomics, and breeding.

Detecting spikes of wheat plants using neural networks with Laws texture energy

Abstract: The spike of a cereal plant is the grain-bearing organ whose physical characteristics are proxy measures of grain yield. The ability to detect and characterise spikes from 2D images of cereal plants, such as wheat, therefore provides vital information on tiller number and yield potential. We have developed a novel spike detection method for wheat plants involving, firstly, an improved colour index method for plant segmentation and, secondly, a neural network-based method using Laws texture energy for spike detection. The spike detection step was further improved by removing noise using an area and height threshold. The evaluation results showed an accuracy of over 80% in identification of spikes. In the proposed method we also measure the area of individual spikes as well as all spikes of individual plants under different experimental conditions. The correlation between the final average grain yield and spike area is also discussed in this paper. Our highly accurate yield trait phenotyping method for spike number counting and spike area estimation, is useful and reliable not only for grain yield estimation but also for detecting and quantifying subtle phenotypic variations arising from genetic or environmental differences.

TIPS: a system for automated image-based phenotyping of maize tassels

Abstract: The maize male inflorescence (tassel) produces pollen necessary for reproduction and commercial grain production of maize. The size of the tassel has been linked to factors affecting grain yield, so understanding the genetic control of tassel architecture is an important goal. Tassels are fragile and deform easily after removal from the plant, necessitating rapid measurement of any shape characteristics that cannot be retained during storage. Some morphological characteristics of tassels such as curvature and compactness are difficult to quantify using traditional methods, but can be quantified by image-based phenotyping tools. These constraints necessitate the development of an efficient method for capturing natural-state tassel morphology and complementary automated analytical methods that can quickly and reproducibly quantify traits of interest such as height, spread, and branch number. This paper presents the Tassel Image-based Phenotyping System (TIPS), which provides a platform for imaging tassels in the field immediately following removal from the plant. TIPS consists of custom methods that can quantify morphological traits from profile images of freshly harvested tassels acquired with a standard digital camera in a field-deployable light shelter. Correlations between manually measured traits (tassel weight, tassel length, spike length, and branch number) and image-based measurements ranged from 0.66 to 0.89. Additional tassel characteristics quantified by image analysis included some that cannot be quantified manually, such as curvature, compactness, fractal dimension, skeleton length, and perimeter. TIPS was used to measure tassel phenotypes of 3530 individual tassels from 749 diverse inbred lines that represent the diversity of tassel morphology found in modern breeding and academic research programs. Repeatability ranged from 0.85 to 0.92 for manually measured phenotypes, from 0.77 to 0.83 for the same traits measured by image-based methods, and from 0.49 to 0.81 for traits that can only be measured by image analysis. TIPS allows morphological features of maize tassels to be quantified automatically, with minimal disturbance, at a scale that supports population-level studies. TIPS is expected to accelerate the discovery of associations between genetic loci and tassel morphology characteristics, and can be applied to maize breeding programs to increase productivity with lower resource commitment.

A novel 3D imaging system for strawberry phenotyping

Abstract: Accurate and quantitative phenotypic data in plant breeding programmes is vital in breeding to assess the performance of genotypes and to make selections. Traditional strawberry phenotyping relies on the human eye to assess most external fruit quality attributes, which is time-consuming and subjective. 3D imaging is a promising high-throughput technique that allows multiple external fruit quality attributes to be measured simultaneously. A low cost multi-view stereo (MVS) imaging system was developed, which captured data from 360° around a target strawberry fruit. A 3D point cloud of the sample was derived and analysed with custom-developed software to estimate berry height, length, width, volume, calyx size, colour and achene number. Analysis of these traits in 100 fruits showed good concordance with manual assessment methods. This study demonstrates the feasibility of an MVS based 3D imaging system for the rapid and quantitative phenotyping of seven agronomically important external strawberry traits. With further improvement, this method could be applied in strawberry breeding programmes as a cost effective phenotyping technique.

Development of a phenotyping platform for high throughput screening of nodal root angle in sorghum.

Abstract: In sorghum, the growth angle of nodal roots is a major component of root system architecture. It strongly influences the spatial distribution of roots of mature plants in the soil profile, which can impact drought adaptation. However, selection for nodal root angle in sorghum breeding programs has been restricted by the absence of a suitable high throughput phenotyping platform. The aim of this study was to develop a phenotyping platform for the rapid, non-destructive and digital measurement of nodal root angle of sorghum at the seedling stage. The phenotyping platform comprises of 500 soil filled root chambers (50 × 45 × 0.3 cm in size), made of transparent perspex sheets that were placed in metal tubs and covered with polycarbonate sheets. Around 3 weeks after sowing, once the first flush of nodal roots was visible, roots were imaged in situ using an imaging box that included two digital cameras that were remotely controlled by two android tablets. Free software (openGelPhoto.tcl) allowed precise measurement of nodal root angle from the digital images. The reliability and efficiency of the platform was evaluated by screening a large nested association mapping population of sorghum and a set of hybrids in six independent experimental runs that included up to 500 plants each. The platform revealed extensive genetic variation and high heritability (repeatability) for nodal root angle. High genetic correlations and consistent ranking of genotypes across experimental runs confirmed the reproducibility of the platform. This low cost, high throughput root phenotyping platform requires no sophisticated equipment, is adaptable to most glasshouse environments and is well suited to dissect the genetic control of nodal root angle of sorghum. The platform is suitable for use in sorghum breeding programs aiming to improve drought adaptation through root system architecture manipulation.

Quantification of seed–soil contact of sugar beet ( Beta vulgaris ) using X-ray Computed Tomography

Abstract: Seed–soil contact is important to ensure successful germination, however, there is a paucity of reported studies that have quantified the microstructure at and around this critical interface, mainly due to the opacity of soil. Here we describe a novel methodology to non-destructively calculate the seed–soil contact area using X-ray Computed Tomography. Under controlled conditions, we observed that seed–soil contact was strongly influenced by the size and type of seed, with a seed–soil contact of ca. 15% for naked sugar beet seeds compared to ca. 32% for pelleted and coated seeds. Similar results were obtained for seeds sampled from the field albeit with a higher spatial variability. By application of this new quantification method it is hoped seed enhancement technologies can be optimised and ultimately seedbed preparation improved to ensure better germination.

Ground penetrating radar: a case study for estimating root bulking rate in cassava ( Manihot esculenta Crantz)

Abstract: Understanding root traits is a necessary research front for selection of favorable genotypes or cultivation practices. Root and tuber crops having most of their economic potential stored below ground are favorable candidates for such studies. The ability to image and quantify subsurface root structure would allow breeders to classify root traits for rapid selection and allow agronomist the ability to derive effective cultivation practices. In spite of the huge role of Cassava (Manihot esculenta Crantz), for food security and industrial uses, little progress has been made in understanding the onset and rate of the root-bulking process and the factors that influence it. The objective of this research was to determine the capability of ground penetrating radar (GPR) to predict root-bulking rates through the detection of total root biomass during its growth cycle. Our research provides the first application of GPR for detecting below ground biomass in cassava. Through an empirical study, linear regressions were derived to model cassava bulking rates. The linear equations derived suggest that GPR is a suitable measure of root biomass (r = .79). The regression analysis developed accounts for 63% of the variability in cassava biomass below ground. When modeling is performed at the variety level, it is evident that the variety models for SM 1219-9 and TMS 60444 outperform the HMC-1 variety model (r2 = .77, .63 and .51 respectively). Using current modeling methods, it is possible to predict below ground biomass and estimate root bulking rates for selection of early root bulking in cassava. Results of this approach suggested that the general model was over predicting at early growth stages but became more precise in later root development.

Fine-grained recognition of plants from images

Abstract: Fine-grained recognition of plants from images is a challenging computer vision task, due to the diverse appearance and complex structure of plants, high intra-class variability and small inter-class differences. We review the state-of-the-art and discuss plant recognition tasks, from identification of plants from specific plant organs to general plant recognition “in the wild”. We propose texture analysis and deep learning methods for different plant recognition tasks. The methods are evaluated and compared them to the state-of-the-art. Texture analysis is only applied to images with unambiguous segmentation (bark and leaf recognition), whereas CNNs are only applied when sufficiently large datasets are available. The results provide an insight in the complexity of different plant recognition tasks. The proposed methods outperform the state-of-the-art in leaf and bark classification and achieve very competitive results in plant recognition “in the wild”. The results suggest that recognition of segmented leaves is practically a solved problem, when high volumes of training data are available. The generality and higher capacity of state-of-the-art CNNs makes them suitable for plant recognition “in the wild” where the views on plant organs or plants vary significantly and the difficulty is increased by occlusions and background clutter.

A fast, efficient chromatin immunoprecipitation method for studying protein-DNA binding in Arabidopsis mesophyll protoplasts.

Abstract: Binding of transcription factors to their target sequences is a primary step in the regulation of gene expression and largely determines gene regulatory networks Chromatin immunoprecipitation (ChIP) is an indispensable tool used to investigate the binding of DNA-binding proteins (eg, transcription factors) to their target sequences in vivo ChIP assays require specific antibodies that recognize endogenous target transcription factors; however, in most cases, such specific antibodies are unavailable To overcome this problem, many ChIP assays use transgenic plants that express epitope-tagged transcription factors and immunoprecipitate the protein with a tag-specific antibody However, generating transgenic plants that stably express epitope-tagged proteins is difficult and time-consuming Here, we present a rapid, efficient ChIP protocol using transient expression in Arabidopsis mesophyll protoplasts that can be completed in 4 days We provide optimized experimental conditions, including the amount of transfected DNA and the number of protoplasts We also show that the efficiency of our ChIP protocol using protoplasts is comparable to that obtained using transgenic Arabidopsis plants We propose that our ChIP method can be used to analyze in vivo interactions between tissue-specific transcription factors and their target sequences, to test the effect of genotype on the binding of a transcription factor within a protein complex to its target sequences, and to measure temperature-dependent binding of a transcription factor to its target sequence The rapid and simple nature of our ChIP assay using Arabidopsis mesophyll protoplasts facilitates the investigation of in vivo interactions between transcription factors and their target genes

The combination of gas-phase fluorophore technology and automation to enable high-throughput analysis of plant respiration.

Abstract: Mitochondrial respiration in the dark (R dark) is a critical plant physiological process, and hence a reliable, efficient and high-throughput method of measuring variation in rates of R dark is essential for agronomic and ecological studies. However, currently methods used to measure R dark in plant tissues are typically low throughput. We assessed a high-throughput automated fluorophore system of detecting multiple O2 consumption rates. The fluorophore technique was compared with O2-electrodes, infrared gas analysers (IRGA), and membrane inlet mass spectrometry, to determine accuracy and speed of detecting respiratory fluxes. The high-throughput fluorophore system provided stable measurements of R dark in detached leaf and root tissues over many hours. High-throughput potential was evident in that the fluorophore system was 10 to 26-fold faster per sample measurement than other conventional methods. The versatility of the technique was evident in its enabling: (1) rapid screening of R dark in 138 genotypes of wheat; and, (2) quantification of rarely-assessed whole-plant R dark through dissection and simultaneous measurements of above- and below-ground organs. Variation in absolute R dark was observed between techniques, likely due to variation in sample conditions (i.e. liquid vs. gas-phase, open vs. closed systems), indicating that comparisons between studies using different measuring apparatus may not be feasible. However, the high-throughput protocol we present provided similar values of R dark to the most commonly used IRGA instrument currently employed by plant scientists. Together with the greater than tenfold increase in sample processing speed, we conclude that the high-throughput protocol enables reliable, stable and reproducible measurements of R dark on multiple samples simultaneously, irrespective of plant or tissue type.

Establishment of integrated protocols for automated high throughput kinetic chlorophyll fluorescence analyses.

Abstract: Automated plant phenotyping has been established as a powerful new tool in studying plant growth, development and response to various types of biotic or abiotic stressors. Respective facilities mainly apply non-invasive imaging based methods, which enable the continuous quantification of the dynamics of plant growth and physiology during developmental progression. However, especially for plants of larger size, integrative, automated and high throughput measurements of complex physiological parameters such as photosystem II efficiency determined through kinetic chlorophyll fluorescence analysis remain a challenge. We present the technical installations and the establishment of experimental procedures that allow the integrated high throughput imaging of all commonly determined PSII parameters for small and large plants using kinetic chlorophyll fluorescence imaging systems (FluorCam, PSI) integrated into automated phenotyping facilities (Scanalyzer, LemnaTec). Besides determination of the maximum PSII efficiency, we focused on implementation of high throughput amenable protocols recording PSII operating efficiency (ΦPSII). Using the presented setup, this parameter is shown to be reproducibly measured in differently sized plants despite the corresponding variation in distance between plants and light source that caused small differences in incident light intensity. Values of ΦPSII obtained with the automated chlorophyll fluorescence imaging setup correlated very well with conventionally determined data using a spot-measuring chlorophyll fluorometer. The established high throughput operating protocols enable the screening of up to 1080 small and 184 large plants per hour, respectively. The application of the implemented high throughput protocols is demonstrated in screening experiments performed with large Arabidopsis and maize populations assessing natural variation in PSII efficiency. The incorporation of imaging systems suitable for kinetic chlorophyll fluorescence analysis leads to a substantial extension of the feature spectrum to be assessed in the presented high throughput automated plant phenotyping platforms, thus enabling the simultaneous assessment of plant architectural and biomass-related traits and their relations to physiological features such as PSII operating efficiency. The implemented high throughput protocols are applicable to a broad spectrum of model and crop plants of different sizes (up to 1.80 m height) and architectures. The deeper understanding of the relation of plant architecture, biomass formation and photosynthetic efficiency has a great potential with respect to crop and yield improvement strategies.

An image analysis pipeline for automated classification of imaging light conditions and for quantification of wheat canopy cover time series in field phenotyping

Abstract: Robust segmentation of canopy cover (CC) from large amounts of images taken under different illumination/light conditions in the field is essential for high throughput field phenotyping (HTFP). We attempted to address this challenge by evaluating different vegetation indices and segmentation methods for analyzing images taken at varying illuminations throughout the early growth phase of wheat in the field. 40,000 images taken on 350 wheat genotypes in two consecutive years were assessed for this purpose. We proposed an image analysis pipeline that allowed for image segmentation using automated thresholding and machine learning based classification methods and for global quality control of the resulting CC time series. This pipeline enabled accurate classification of imaging light conditions into two illumination scenarios, i.e. high light-contrast (HLC) and low light-contrast (LLC), in a series of continuously collected images by employing a support vector machine (SVM) model. Accordingly, the scenario-specific pixel-based classification models employing decision tree and SVM algorithms were able to outperform the automated thresholding methods, as well as improved the segmentation accuracy compared to general models that did not discriminate illumination differences. The three-band vegetation difference index (NDI3) was enhanced for segmentation by incorporating the HSV-V and the CIE Lab-a color components, i.e. the product images NDI3*V and NDI3*a. Field illumination scenarios can be successfully identified by the proposed image analysis pipeline, and the illumination-specific image segmentation can improve the quantification of CC development. The integrated image analysis pipeline proposed in this study provides great potential for automatically delivering robust data in HTFP.

Application of 3D printing to prototype and develop novel plant tissue culture systems.

Abstract: Due to the complex process of designing and manufacturing new plant tissue culture vessels through conventional means there have been limited efforts to innovate improved designs. Further, development and availability of low cost, energy efficient LEDs of various spectra has made it a promising light source for plant growth in controlled environments. However, direct replacement of conventional lighting sources with LEDs does not address problems with uniformity, spectral control, or the challenges in conducting statistically valid experiments to assess the effects of light. Prototyping using 3D printing and LED based light sources could help overcome these limitations and lead to improved culture systems. A modular culture vessel design in which the fluence rate and spectrum of light are independently controlled was designed, prototyped using 3D printing, and evaluated for plant growth. This design is compatible with semi-solid and liquid based culture systems. Observations on morphology, chlorophyll content, and chlorophyll fluorescence based stress parameters from in vitro plants cultured under different light spectra with similar overall fluence rate indicated different responses in Nicotiana tabacum and Artemisia annua plantlets. This experiment validates the utility of 3D printing to design and test functional vessels and demonstrated that optimal light spectra for in vitro plant growth is species-specific. 3D printing was successfully used to prototype novel culture vessels with independently controlled variable fluence rate/spectra LED lighting. This system addresses several limitations associated with current lighting systems, providing more uniform lighting and allowing proper replication/randomization for experimental plant biology while increasing energy efficiency. A complete procedure including the design and prototyping of a culture vessel using 3D printing, commercial scale injection molding of the prototype, and conducting a properly replicated experiment are discussed. This open source design has the scope for further improvement and adaptation and demonstrates the power of 3D printing to improve the design of culture systems.