High-throughput Plant Phenotyping Research Articles

Dual-stage color calibration of UAV imagery using multivariate regression and deep learning

Accurate color representation in UAV-based imagery is critical in high-throughput plant phenotyping and precision agriculture for monitoring crop health and identifying nutrient deficiencies or water stress. However, achieving color accuracy is challenging due to varying lighting conditions and flight altitudes in UAV operations. To overcome these challenges, we propose an automated dual-phase approach for consistent color calibration in UAV imagery, integrating traditional color calibration methods with cutting-edge deep learning algorithms. In the first phase, we derived a color calibration matrix (M) for four color boards placed within the imaging area. This involved mapping the observed color values in the UAV images to their true color values, as measured by a colorimeter, using multivariate linear regression (MLR). The individual matrices from each board were then merged into a single, weighted average matrix, which was then applied to the UAV images for color correction, resulting in standardized color outputs. In the second phase, we developed a deep learning model, trained on the MLR-corrected images as a ground truth. This model assigns varying weights for different pixels across the image scene, translating the image from a distorted to a color-corrected image using image-to-image regression without manual intervention. We validated this approach using 184 UAV images of various sizes, ranging from 3969 × 2589 to 15257 × 15098 pixels, captured under a wide array of lighting conditions and altitudes. The results show that our deep learning model significantly outperforms existing methods, with a marginal color error of 1.52 %. This two-phase color correction method greatly improves operational efficiency by removing the necessity for physical color boards in each image and allowing for automated processing after training.

High-throughput digital imaging and detection of morpho-physiological traits in tomato plants under drought

Abstract Advances in informatics, robotics, and imaging techniques make it possible to use state-of-the-art digital reconstruction technologies for high-throughput plant phenotyping (HTPP) affected by stress factors, as well as for the ontology of their structural and functional traits. Digital imaging of structural and functional features of the aboveground part of plants is non-destructive and plants can be monitored throughout their entire life cycle. In the experiment with tomato plants (Solanum lycopersicum L.; cv. Gruzanski zlatni) grown in controlled environmental conditions and affected by gradual soil dehydration, we evaluated phenotypic traits and phenotypic plasticity by the PlantScreenTM platform using digital imaging of plant optical signals. In this study, 25 different morpho-physiological traits of the plant were evaluated during the precise control and monitoring of the water content in the soil. Different levels of plant water supply induced statistically significant differences in the formation of individual phenotypic traits. Several plant traits have been identified that are characterized by low variability in both well-hydrated and water-stressed conditions, as well as traits with high phenotypic plasticity. Geometric traits (especially Isotop, Round-2top, and Compside) showed a relatively low level of drought-induced phenotypic plasticity. However, functional and chemometric characteristics (ΔF/F′m, Rfd, Water-1, and ARI-1) showed the potential to exhibit rapid plasticity in water-stressed conditions. Our results confirmed that a high-throughput phenotyping methodology coupled with advanced statistical analysis tools can be successfully applied to characterize crop stress responses and identify traits associated with crop stress tolerance.

A fast high throughput plant phenotyping system using YOLO and Chan-Vese segmentation

A fast high throughput plant phenotyping system using YOLO and Chan-Vese segmentation

High-throughput physiological phenotyping of crop evapotranspiration at the plot scale

ContextPlatforms and instrumentation for Field High-Throughput Plant Phenotyping (FHTPP) are well developed to measure important traits for crop breeding and agronomic studies. However, the research has focused on morphological and spectral traits; and approaches to estimate major physiological processes such as evapotranspiration (ET) for small experimental plots are lacking. ObjectiveIn this study, we put forward a new analytical framework to estimate plot-scale ET by integrating frequent phenotyping data (multispectral and thermal infrared images, canopy reflectance, and LiDAR point clouds) from a FHTPP system (known as NU-Spidercam), the weather data, a simplified two-source energy balance model, and reference ET and crop coefficient calculation. MethodsThe new plot-scale ET method was tested on five field experiments involving maize and soybean crops over two growing seasons, with the different treatment levels of irrigation water. Estimated plot-scale ET was accumulated across the growing reason for each plot, and its association with grain yield was investigated with regression analysis. ResultsThe result showed that plot-scale accumulated ET captured the seasonal trend of plot water use and clearly differentiated the irrigation treatments. Strong linear correlations were observed between plot-scale ET and grain yield, with R2 values ranging from 0.35 to 0.93 (average R2 = 0.71). Plot-scale ET appeared to be a more steady and stronger predictor of grain yield across the seasons than several other morphological and spectral traits including crop height, green pixel fraction, canopy temperature depression, and red-edge normalized difference vegetation index. ConclusionHigh spatial and temporal resolution of the field phenotyping data, along with the new analytical framework reported, successfully estimated ET at small plot scale, which is difficult to achieve with other systems or methods. SignificancesOur work of estimating ET at the plot-scale can be adopt to other ground-based platforms and drones, thus empowers physiologists, breeders, and agronomists for high-throughput phenotyping of water-use related traits and drought response evaluation.

Bagging Improves the Performance of Deep Learning-Based Semantic Segmentation with Limited Labeled Images: A Case Study of Crop Segmentation for High-Throughput Plant Phenotyping.

Advancements in imaging, computer vision, and automation have revolutionized various fields, including field-based high-throughput plant phenotyping (FHTPP). This integration allows for the rapid and accurate measurement of plant traits. Deep Convolutional Neural Networks (DCNNs) have emerged as a powerful tool in FHTPP, particularly in crop segmentation-identifying crops from the background-crucial for trait analysis. However, the effectiveness of DCNNs often hinges on the availability of large, labeled datasets, which poses a challenge due to the high cost of labeling. In this study, a deep learning with bagging approach is introduced to enhance crop segmentation using high-resolution RGB images, tested on the NU-Spidercam dataset from maize plots. The proposed method outperforms traditional machine learning and deep learning models in prediction accuracy and speed. Remarkably, it achieves up to 40% higher Intersection-over-Union (IoU) than the threshold method and 11% over conventional machine learning, with significantly faster prediction times and manageable training duration. Crucially, it demonstrates that even small labeled datasets can yield high accuracy in semantic segmentation. This approach not only proves effective for FHTPP but also suggests potential for broader application in remote sensing, offering a scalable solution to semantic segmentation challenges. This paper is accompanied by publicly available source code.

Development of a mobile, high-throughput, and low-cost image-based plant growth phenotyping system.

Nondestructive plant phenotyping forms a key technique for unraveling molecular processes underlying plant development and response to the environment. While the emergence of high-throughput phenotyping facilities can further our understanding of plant development and stress responses, their high costs greatly hinder scientific progress. To democratize high-throughput plant phenotyping, we developed sets of low-cost image- and weight-based devices to monitor plant shoot growth and evapotranspiration. We paired these devices to a suite of computational pipelines for integrated and straightforward data analysis. The developed tools were validated for their suitability for large genetic screens by evaluating a cowpea (Vigna unguiculata) diversity panel for responses to drought stress. The observed natural variation was used as an input for a genome-wide association study, from which we identified nine genetic loci that might contribute to cowpea drought resilience during early vegetative development. The homologs of the candidate genes were identified in Arabidopsis (Arabidopsis thaliana) and subsequently evaluated for their involvement in drought stress by using available T-DNA insertion mutant lines. These results demonstrate the varied applicability of this low-cost phenotyping system. In the future, we foresee these setups facilitating the identification of genetic components of growth, plant architecture, and stress tolerance across a wide variety of plant species.

Effects of exogenous glycine betaine on growth and development of tomato seedlings under cold stress.

Low temperature is a type of abiotic stress affecting the tomato (Solanum lycopersicum) growth. Understanding the mechanisms and utilization of exogenous substances underlying plant tolerance to cold stress would lay the foundation for improving temperature resilience in this important crop. Our study is aiming to investigate the effect of exogenous glycine betaine (GB) on tomato seedlings to increase tolerance to low temperatures. By treating tomato seedlings with exogenous GB under low temperature stress, we found that 30 mmol/L exogenous GB can significantly improve the cold tolerance of tomato seedlings. Exogenous GB can influence the enzyme activity of antioxidant defense system and ROS levels in tomato leaves. The seedlings with GB treatment presented higher Fv/Fm value and photochemical activity under cold stress compared with the control. Moreover, analysis of high-throughput plant phenotyping of tomato seedlings also supported that exogenous GB can protect the photosynthetic system of tomato seedlings under cold stress. In addition, we proved that exogenous GB significantly increased the content of endogenous abscisic acid (ABA) and decreased endogenous gibberellin (GA) levels, which protected tomatoes from low temperatures. Meanwhile, transcriptional analysis showed that GB regulated the expression of genes involved in antioxidant capacity, calcium signaling, photosynthesis activity, energy metabolism-related and low temperature pathway-related genes in tomato plants. In conclusion, our findings indicated that exogenous GB, as a cryoprotectant, can enhance plant tolerance to low temperature by improving the antioxidant system, photosynthetic system, hormone signaling, and cold response pathway and so on.

Phenotyping of Drought-Stressed Poplar Saplings Using Exemplar-Based Data Generation and Leaf-Level Structural Analysis.

Drought stress is one of the main threats to poplar plant growth and has a negative impact on plant yield. Currently, high-throughput plant phenotyping has been widely studied as a rapid and nondestructive tool for analyzing the growth status of plants, such as water and nutrient content. In this study, a combination of computer vision and deep learning was used for drought-stressed poplar sapling phenotyping. Four varieties of poplar saplings were cultivated, and 5 different irrigation treatments were applied. Color images of the plant samples were captured for analysis. Two tasks, including leaf posture calculation and drought stress identification, were conducted. First, instance segmentation was used to extract the regions of the leaf, petiole, and midvein. A dataset augmentation method was created for reducing manual annotation costs. The horizontal angles of the fitted lines of the petiole and midvein were calculated for leaf posture digitization. Second, multitask learning models were proposed for simultaneously determining the stress level and poplar variety. The mean absolute errors of the angle calculations were 10.7° and 8.2° for the petiole and midvein, respectively. Drought stress increased the horizontal angle of leaves. Moreover, using raw images as the input, the multitask MobileNet achieved the highest accuracy (99% for variety identification and 76% for stress level classification), outperforming widely used single-task deep learning models (stress level classification accuracies of <70% on the prediction dataset). The plant phenotyping methods presented in this study could be further used for drought-stress-resistant poplar plant screening and precise irrigation decision-making.

Research on the application method of agricultural machinery engineering automation based on multimodal characteristics

Abstract Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise management. The purpose of this paper is to apply agricultural mechanical engineering automation to wheat yield prediction, and a UAV multimodal data wheat yield prediction model is developed using the RMGF algorithm. Different data sources, such as vertical distribution of terrain and spatial variability, canopy height and wheat plant height, canopy temperature difference, vegetation spectral characteristics, and vegetation index, were extracted using an agricultural UAV. Then GF decomposition algorithm based on MSD decomposes the multimodal image into an approximate image and detail image, and after optimization of the fused weight map using RSA, the fused image is obtained by IMST according to the optimized weight map. The model was used to carry out regression analysis of yield prediction for three types of wheat, heat-tolerant, medium heat-tolerant, and high-temperature-sensitive, and finally predicted the wheat yield from 2015 to 2024 in a production area. It was found that the R² of the RMGF multimodal model in this paper predicted the three kinds of wheat yields as 0.7936, 0.8609, and 0.9262 with excellent accuracy results. The predicted yields were basically in line with the actual yields in the high-yield portion, with large prediction errors above 9000 kg/ha. The prediction error for wheat was within 0-2.26%, and the predicted yield in a main wheat production area was 7050 kg/ha in 2024. This study provides a feasible method for large-scale yield estimation in the main production area, which contributes to high-throughput plant phenotyping and agricultural precision reform.

Stress phenotyping analysis leveraging autofluorescence image sequences with machine learning.

Autofluorescence-based imaging has the potential to non-destructively characterize the biochemical and physiological properties of plants regulated by genotypes using optical properties of the tissue. A comparative study of stress tolerant and stress susceptible genotypes of Brassica rapa with respect to newly introduced stress-based phenotypes using machine learning techniques will contribute to the significant advancement of autofluorescence-based plant phenotyping research. Autofluorescence spectral images have been used to design a stress detection classifier with two classes, stressed and non-stressed, using machine learning algorithms. The benchmark dataset consisted of time-series image sequences from three Brassica rapa genotypes (CC, R500, and VT), extreme in their morphological and physiological traits captured at the high-throughput plant phenotyping facility at the University of Nebraska-Lincoln, USA. We developed a set of machine learning-based classification models to detect the percentage of stressed tissue derived from plant images and identified the best classifier. From the analysis of the autofluorescence images, two novel stress-based image phenotypes were computed to determine the temporal variation in stressed tissue under progressive drought across different genotypes, i.e., the average percentage stress and the moving average percentage stress. The study demonstrated that both the computed phenotypes consistently discriminated against stressed versus non-stressed tissue, with oilseed type (R500) being less prone to drought stress relative to the other two Brassica rapa genotypes (CC and VT). Autofluorescence signals from the 365/400 nm excitation/emission combination were able to segregate genotypic variation during a progressive drought treatment under a controlled greenhouse environment, allowing for the exploration of other meaningful phenotypes using autofluorescence image sequences with significance in the context of plant science.

Using Infrared Thermography for High-Throughput Plant Phenotyping.

Infrared thermography offers a rapid, noninvasive method for measuring plant temperature, which provides a proxy for stomatal conductance and plant water status and can therefore be used as an index for plant stress. Thermal imaging can provide an efficient method for high-throughput screening of large numbers of plants. This chapter provides guidelines for using thermal imaging equipment and illustrative methodologies, coupled with essential considerations, to access plant physiological processes.

Quercus petraea (Matt.) Liebl. from the Thayatal National Park in Austria: Selection of Potentially Drought-Tolerant Phenotypes

The increasing demand for climate-adapted seeds and planting material poses a challenge due to the limited availability, particularly for tree species such as oaks. National parks, known for their large-standing diversity and a wide range of habitats, can serve as valuable sources for identifying trees suitable for both the initiation of tree breeding and conservation strategies. This study aimed to identify valuable forest genetic resources of the Thayatal National Park in Austria by selecting potentially drought-tolerant phenotypes. For this purpose, we selected 404 mature trees of Quercus petraea (Matt.) Liebl. from eight populations growing on medium to dry sites in eight populations. Further, we characterized them for autochthony, genetic structure, genetic diversity using genetic markers (plastid- and nuclear-SSRs) and estimated their age. Finally, we applied wood core analysis to estimate tree response to historical drought events to identify the possible drought-tolerant phenotypes. The age of the trees ranged from 29 to 245 years (as of the year 2023). All Q. petraea trees were inhabiting a plastid haplotype 17a, autochthonous for this area. Nevertheless, the genetic structure estimated by ten nuSSRs revealed a pronounced structure in the dataset, largely caused by young trees exhibiting lower genetic diversity. A total of 85 elite potentially drought-tolerant trees were finally selected based on their morphological response (resistance, recovery ability, resilience, and relative resilience) to three historical drought events (1992–1994, 1947, 1917). The intrinsic water use efficiency and its difference (iWUE and DWiWUE), estimated by isotope analysis of δ13C of latewood in wet (1987) and dry (1994) years, did not correlate with any of the drought response traits (Rt, Rc, Rs, rRs). We discuss the further use of the selected oak trees for the establishment of seed stands and orchards to enhance seed production and the integration of other omics approaches, such as large-scale high-throughput plant phenotyping (HTPP) and transcriptomics, for in-depth analyses of drought tolerance of selected phenotypes.

WheatLFANet: in-field detection and counting of wheat heads with high-real-time global regression network

BackgroundDetection and counting of wheat heads are of crucial importance in the field of plant science, as they can be used for crop field management, yield prediction, and phenotype analysis. With the widespread application of computer vision technology in plant science, monitoring of automated high-throughput plant phenotyping platforms has become possible. Currently, many innovative methods and new technologies have been proposed that have made significant progress in the accuracy and robustness of wheat head recognition. Nevertheless, these methods are often built on high-performance computing devices and lack practicality. In resource-limited situations, these methods may not be effectively applied and deployed, thereby failing to meet the needs of practical applications.ResultsIn our recent research on maize tassels, we proposed TasselLFANet, the most advanced neural network for detecting and counting maize tassels. Building on this work, we have now developed a high-real-time lightweight neural network called WheatLFANet for wheat head detection. WheatLFANet features a more compact encoder-decoder structure and an effective multi-dimensional information mapping fusion strategy, allowing it to run efficiently on low-end devices while maintaining high accuracy and practicality. According to the evaluation report on the global wheat head detection dataset, WheatLFANet outperforms other state-of-the-art methods with an average precision AP of 0.900 and an R2 value of 0.949 between predicted values and ground truth values. Moreover, it runs significantly faster than all other methods by an order of magnitude (TasselLFANet: FPS: 61).ConclusionsExtensive experiments have shown that WheatLFANet exhibits better generalization ability than other state-of-the-art methods, and achieved a speed increase of an order of magnitude while maintaining accuracy. The success of this study demonstrates the feasibility of achieving real-time, lightweight detection of wheat heads on low-end devices, and also indicates the usefulness of simple yet powerful neural network designs.

Field phenotyping for African crops: overview and perspectives.

Improvements in crop productivity are required to meet the dietary demands of the rapidly-increasing African population. The development of key staple crop cultivars that are high-yielding and resilient to biotic and abiotic stresses is essential. To contribute to this objective, high-throughput plant phenotyping approaches are important enablers for the African plant science community to measure complex quantitative phenotypes and to establish the genetic basis of agriculturally relevant traits. These advances will facilitate the screening of germplasm for optimum performance and adaptation to low-input agriculture and resource-constrained environments. Increasing the capacity to investigate plant function and structure through non-invasive technologies is an effective strategy to aid plant breeding and additionally may contribute to precision agriculture. However, despite the significant global advances in basic knowledge and sensor technology for plant phenotyping, Africa still lags behind in the development and implementation of these systems due to several practical, financial, geographical and political barriers. Currently, field phenotyping is mostly carried out by manual methods that are prone to error, costly, labor-intensive and may come with adverse economic implications. Therefore, improvements in advanced field phenotyping capabilities and appropriate implementation are key factors for success in modern breeding and agricultural monitoring. In this review, we provide an overview of the current state of field phenotyping and the challenges limiting its implementation in some African countries. We suggest that the lack of appropriate field phenotyping infrastructures is impeding the development of improved crop cultivars and will have a detrimental impact on the agricultural sector and on food security. We highlight the prospects for integrating emerging and advanced low-cost phenotyping technologies into breeding protocols and characterizing crop responses to environmental challenges in field experimentation. Finally, we explore strategies for overcoming the barriers and maximizing the full potential of emerging field phenotyping technologies in African agriculture. This review paper will open new windows and provide new perspectives for breeders and the entire plant science community in Africa.

High-Throughput Plant Phenotyping System Using a Low-Cost Camera Network for Plant Factory

Plant phenotyping has been widely studied as an effective and powerful tool for analyzing crop status and growth. However, the traditional phenotyping (i.e., manual) is time-consuming and laborious, and the various types of growing structures and limited room for systems hinder phenotyping on a large and high-throughput scale. In this study, a low-cost high-throughput phenotyping system that can be flexibly applied to diverse structures of growing beds with reliable spatial–temporal continuities was developed. The phenotyping system was composed of a low-cost phenotype sensor network with an integrated Raspberry Pi board and camera module. With the distributed camera sensors, the system can provide crop imagery information over the entire growing bed in real time. Furthermore, the modularized image-processing architecture supports the investigation of several phenotypic indices. The feasibility of the system was evaluated for Batavia lettuce grown under different light periods in a container-type plant factory. For the growing lettuces under different light periods, crop characteristics such as fresh weight, leaf length, leaf width, and leaf number were manually measured and compared with the phenotypic indices from the system. From the results, the system showed varying phenotypic features of lettuce for the entire growing period. In addition, the varied growth curves according to the different positions and light conditions confirmed that the developed system has potential to achieve many plant phenotypic scenarios at low cost and with spatial versatility. As such, it serves as a valuable development tool for researchers and cultivators interested in phenotyping.

OPEN leaf: an open-source cloud-based phenotyping system for tracking dynamic changes at leaf-specific resolution in Arabidopsis.

The first draft of the Arabidopsis genome was released more than 20 years ago and despite intensive molecular research, more than 30% of Arabidopsis genes remained uncharacterized or without an assigned function. This is in part due to gene redundancy within gene families or the essential nature of genes, where their deletion results in lethality (i.e., the dark genome). High-throughput plant phenotyping (HTPP) offers an automated and unbiased approach to characterize subtle or transient phenotypes resulting from gene redundancy or inducible gene silencing; however, access to commercial HTPP platforms remains limited. Here we describe the design and implementation of OPEN leaf, an open-source phenotyping system with cloud connectivity and remote bilateral communication to facilitate data collection, sharing and processing. OPEN leaf, coupled with our SMART imaging processing pipeline was able to consistently document and quantify dynamic changes at the whole rosette level and leaf-specific resolution when plants experienced changes in nutrient availability. Our data also demonstrate that VIS sensors remain underutilized and can be used in high-throughput screens to identify and characterize previously unidentified phenotypes in a leaf-specific time-dependent manner. Moreover, the modular and open-source design of OPEN leaf allows seamless integration of additional sensors based on users and experimental needs.

DQLRFMG: Design of an Augmented Fusion of Deep Q Learning with Logistic Regression and Deep Forests for Multivariate Classification and Grading of Fruits

Accurate categorization and grading of fruits are essential in numerous fields, including agriculture, food processing, and distribution. This paper addresses the need for an advanced model capable of classifying and grading fruits more effectively than existing methods. Traditional approaches are limited by their lower precision, accuracy, recall, area under the curve (AUC), and delay. In order to overcome these obstacles, the proposed model combines the capabilities of Deep Q Learning (DQL) for classification and Logistic Regression (LR) with Deep Forests for fruit grading process. Three distinct datasets were used to evaluate the model: the Kaggle - Fruits 360 Dataset, the FRont Experimental System for High throughput plant phenotyping Datasets, and ImageNet samples. In multiple respects, comparative analysis demonstrates that the proposed model outperforms existing methods. Specifically, it achieves a remarkable 4.9% improvement in precision, 5.5% improvement in accuracy, 4.5% improvement in recall, 3.9% improvement in AUC, and an 8.5% reduction in delay levels. Utilizing the strengths of both DQL and LR with Deep Forests, the proposed model achieves its superior performance. DQL, a technique for reinforcement learning, provides the ability to learn and make decisions based on the feedback from the environment. By combining DQL and LR, the classification accuracy is improved, allowing for the precise identification of fruit varieties including Mango, Apple. Papaya, etc. In addition, Deep Forests, a novel framework for ensemble learning, is utilized for fruit grading. Deep Forests utilizes decision trees to effectively capture complex patterns in the data, allowing for dependable and robust fruit grading. Experimental findings indicate that the combination of DQL and LR with Deep Forests yields remarkable performance improvements in fruit classification and grading tasks. Improved precision, accuracy, recall, AUC, and delay indicate the model's superiority over existing methods. This research contributes to the field of fruit classification and grading by developing a sophisticated model that can support a variety of applications in the agriculture, food processing, and distribution industries.

SPOT: Scanning plant IoT facility for high-throughput plant phenotyping

Many plant phenotyping platforms have been kept out of the reach of smaller labs and institutions due to high cost and proprietary software. The Scanning Plant IoT (SPOT) Facility, located at the University of Florida, is a mobile, laboratory-based platform that facilitates open-source collection of high-quality, interoperable plant phenotypic data. It consists of three main sensors: a hyperspectral sensor, a thermal camera, and a LiDAR camera. Real-time data from the sensors can be collected in its 10 ft. × 10 ft. scanning region. The mobility of the device allows its use in large growth chambers, environmentally controlled rooms, or greenhouses. Sensors are oriented nadir and positioned via computer numerical control of stepper motors. In a preliminary experiment, data gathered from SPOT was used to autonomously and nondestructively differentiate between cultivars.

Pitfalls and potential of high-throughput plant phenotyping platforms.

Automated high-throughput plant phenotyping (HTPP) enables non-invasive, fast and standardized evaluations of a large number of plants for size, development, and certain physiological variables. Many research groups recognize the potential of HTPP and have made significant investments in HTPP infrastructure, or are considering doing so. To make optimal use of limited resources, it is important to plan and use these facilities prudently and to interpret the results carefully. Here we present a number of points that users should consider before purchasing, building or utilizing such equipment. They relate to (1) the financial and time investment for acquisition, operation, and maintenance, (2) the constraints associated with such machines in terms of flexibility and growth conditions, (3) the pros and cons of frequent non-destructive measurements, (4) the level of information provided by proxy traits, and (5) the utilization of calibration curves. Using data from an Arabidopsis experiment, we demonstrate how diurnal changes in leaf angle can impact plant size estimates from top-view cameras, causing deviations of more than 20% over the day. Growth analysis data from another rosette species showed that there was a curvilinear relationship between total and projected leaf area. Neglecting this curvilinearity resulted in linear calibration curves that, although having a high r2 (> 0.92), also exhibited large relative errors. Another important consideration we discussed is the frequency at which calibration curves need to be generated and whether different treatments, seasons, or genotypes require distinct calibration curves. In conclusion, HTPP systems have become a valuable addition to the toolbox of plant biologists, provided that these systems are tailored to the research questions of interest, and users are aware of both the possible pitfalls and potential involved.

Enhancing Crop Improvement through Synergistic Integration of Advanced Plant Breeding and Proximal Remote Sensing Techniques: A Review

Accelerating crop improvement with enhanced adaptability to changing climatic conditions and meeting the ever-increasing global food demand requires urgent action. To achieve this, we must employ advanced molecular breeding techniques, such as marker-assisted selection, marker-assisted backcrossing, genomic selection, genome editing, and targeted mutation. However, these approaches demand the screening of large populations to identify potential genes and genotypes. Unfortunately, a significant bottleneck lies in the absence of high-throughput plant phenotyping methods that can rapidly and cost-effectively facilitate data-driven genotype selection in plant breeding. Traditional phenotyping methods, reliant on trained experts, are slow, expensive, labour-intensive, subjective, and often require destructive sampling. Proximal remote sensing technologies, including RGB imaging, thermal imaging, hyperspectral imaging, multispectral imaging, and fluorescence imaging, offer a non-destructive and rapid collection of detailed phenotypic data, providing valuable insights into various plant traits at different growth stages. High-throughput phenotyping platforms, such as Conveyor-Type Indoor, Benchtop-Type Indoor, Unmanned Aerial Platform (UAP), and Manned Aerial Platform (MAP), utilize a combination of the aforementioned remote sensing technologies. This review article aims to explore the integration of proximal remote sensing and molecular breeding approaches, showcasing how this synergistic approach can expedite crop improvement efforts. By emphasizing the benefits, challenges, and future prospects of this integrative approach, we hope to pave the way for sustainable and productive agriculture, ensuring food security in the face of changing environmental conditions.