Development of a Peanut Canopy Measurement System Using a Ground-Based LiDAR Sensor

Calibrating ultrasonic sensor measurements of crop canopy heights: a case study of maize and wheat

Canopy height serves as an important dynamic indicator of crop growth in the decision-making process of field management. Compared with other commonly used canopy height measurement techniques, ultrasonic sensors are inexpensive and can be exposed in fields for long periods of time to obtain easy-to-process data. However, the acoustic wave characteristics and crop canopy structure affect the measurement accuracy. To improve the ultrasonic sensor measurement accuracy, a four-year (2018-2021) field experiment was conducted on maize and wheat, and a measurement platform was developed. A series of single-factor experiments were conducted to investigate the significant factors affecting measurements, including the observation angle (0-60°), observation height (0.5-2.5 m), observation period (8:00-18:00), platform moving speed with respect to the crop (0-2.0 m min-1), planting density (0.2-1 time of standard planting density), and growth stage (maize from three-leaf to harvest period and wheat from regreening to maturity period). The results indicated that both the observation angle and planting density significantly affected the results of ultrasonic measurements (p-value< 0.05), whereas the effects of other factors on measurement accuracy were negligible (p-value > 0.05). Moreover, a double-input factor calibration model was constructed to assess canopy height under different years by utilizing the normalized difference vegetation index and ultrasonic measurements. The model was developed by employing the least-squares method, and ultrasonic measurement accuracy was significantly improved when integrating the measured value of canopy heights and the normalized difference vegetation index (NDVI). The maize measurement accuracy had a root mean squared error (RMSE) ranging from 81.4 mm to 93.6 mm, while the wheat measurement accuracy had an RMSE from 37.1 mm to 47.2 mm. The research results effectively combine stable and low-cost commercial sensors with ground-based agricultural machinery platforms, enabling efficient and non-destructive acquisition of crop height information.

A Point-Cloud Segmentation Network Based on SqueezeNet and Time Series for Plants

The phenotyping of plant growth enriches our understanding of intricate genetic characteristics, paving the way for advancements in modern breeding and precision agriculture. Within the domain of phenotyping, segmenting 3D point clouds of plant organs is the basis of extracting plant phenotypic parameters. In this study, we introduce a novel method for point-cloud downsampling that adeptly mitigates the challenges posed by sample imbalances. In subsequent developments, we architect a deep learning framework founded on the principles of SqueezeNet for the segmentation of plant point clouds. In addition, we also use the time series as input variables, which effectively improves the segmentation accuracy of the network. Based on semantic segmentation, the MeanShift algorithm is employed to execute instance segmentation on the point-cloud data of crops. In semantic segmentation, the average Precision, Recall, F1-score, and IoU of maize reached 99.35%, 99.26%, 99.30%, and 98.61%, and the average Precision, Recall, F1-score, and IoU of tomato reached 97.98%, 97.92%, 97.95%, and 95.98%. In instance segmentation, the accuracy of maize and tomato reached 98.45% and 96.12%. This research holds the potential to advance the fields of plant phenotypic extraction, ideotype selection, and precision agriculture.

A comparative study on point cloud down-sampling strategies for deep learning-based crop organ segmentation

The 3D crop data obtained during cultivation is of great significance to screening excellent varieties in modern breeding and improvement on crop yield. With the rapid development of deep learning, researchers have been making innovations in aspects of both data preparation and deep network design for segmenting plant organs from 3D data. Training of the deep learning network requires the input point cloud to have a fixed scale, which means all point clouds in the batch should have similar scale and contain the same number of points. A good down-sampling strategy can reduce the impact of noise and meanwhile preserve the most important 3D spatial structures. As far as we know, this work is the first comprehensive study of the relationship between multiple down-sampling strategies and the performances of popular networks for plant point clouds. Five down-sampling strategies (including FPS, RS, UVS, VFPS, and 3DEPS) are cross evaluated on five different segmentation networks (including PointNet +  + , DGCNN, PlantNet, ASIS, and PSegNet). The overall experimental results show that currently there is no strict golden rule on fixing down-sampling strategy for a specific mainstream crop deep learning network, and the optimal down-sampling strategy may vary on different networks. However, some general experience for choosing an appropriate sampling method for a specific network can still be summarized from the qualitative and quantitative experiments. First, 3DEPS and UVS are easy to generate better results on semantic segmentation networks. Second, the voxel-based down-sampling strategies may be more suitable for complex dual-function networks. Third, at 4096-point resolution, 3DEPS usually has only a small margin compared with the best down-sampling strategy at most cases, which means 3DEPS may be the most stable strategy across all compared. This study not only helps to further improve the accuracy of point cloud deep learning networks for crop organ segmentation, but also gives clue to the alignment of down-sampling strategies and a specific network.

Eff-3DPSeg: 3D Organ-Level Plant Shoot Segmentation Using Annotation-Efficient Deep Learning

Reliable and automated 3-dimensional (3D) plant shoot segmentation is a core prerequisite for the extraction of plant phenotypic traits at the organ level. Combining deep learning and point clouds can provide effective ways to address the challenge. However, fully supervised deep learning methods require datasets to be point-wise annotated, which is extremely expensive and time-consuming. In our work, we proposed a novel weakly supervised framework, Eff-3DPSeg, for 3D plant shoot segmentation. First, high-resolution point clouds of soybean were reconstructed using a low-cost photogrammetry system, and the Meshlab-based Plant Annotator was developed for plant point cloud annotation. Second, a weakly supervised deep learning method was proposed for plant organ segmentation. The method contained (a) pretraining a self-supervised network using Viewpoint Bottleneck loss to learn meaningful intrinsic structure representation from the raw point clouds and (b) fine-tuning the pretrained model with about only 0.5% points being annotated to implement plant organ segmentation. After, 3 phenotypic traits (stem diameter, leaf width, and leaf length) were extracted. To test the generality of the proposed method, the public dataset Pheno4D was included in this study. Experimental results showed that the weakly supervised network obtained similar segmentation performance compared with the fully supervised setting. Our method achieved 95.1%, 96.6%, 95.8%, and 92.2% in the precision, recall, F1 score, and mIoU for stem-leaf segmentation for the soybean dataset and 53%, 62.8%, and 70.3% in the AP, AP@25, and AP@50 for leaf instance segmentation for the Pheno4D dataset. This study provides an effective way for characterizing 3D plant architecture, which will become useful for plant breeders to enhance selection processes. The trained networks are available at https://github.com/jieyi-one/EFF-3DPSEG.

Fast reconstruction method of three-dimension model based on dual RGB-D cameras for peanut plant

BACKGROUND

Plant shape and structure are important factors in peanut breeding research. Constructing a three-dimension (3D) model can provide an effective digital tool for comprehensive and quantitative analysis of peanut plant structure. Fast and accurate are always the goals of the plant 3D model reconstruction research.

RESULTS

We proposed a 3D reconstruction method based on dual RGB-D cameras for the peanut plant 3D model quickly and accurately. The two Kinect v2 were mirror symmetry placed on both sides of the peanut plant, and the point cloud data obtained were filtered twice to remove noise interference. After rotation and translation based on the corresponding geometric relationship, the point cloud acquired by the two Kinect v2 was converted to the same coordinate system and spliced into the 3D structure of the peanut plant. The experiment was conducted at various growth stages based on twenty potted peanuts. The plant traits' height, width, length, and volume were calculated through the reconstructed 3D models, and manual measurement was also carried out during the experiment processing. The accuracy of the 3D model was evaluated through a synthetic coefficient, which was generated by calculating the average accuracy of the four traits. The test result showed that the average accuracy of the reconstructed peanut plant 3D model by this method is 93.42%. A comparative experiment with the iterative closest point (ICP) algorithm, a widely used 3D modeling algorithm, was additionally implemented to test the rapidity of this method. The test result shows that the proposed method is 2.54 times faster with approximated accuracy compared to the ICP method.

CONCLUSIONS

The reconstruction method for the 3D model of the peanut plant described in this paper is capable of rapidly and accurately establishing a 3D model of the peanut plant while also meeting the modeling requirements for other species' breeding processes. This study offers a potential tool to further explore the 3D model for improving traits and agronomic qualities of plants.

Sustaining yield and nutritional quality of peanuts in harsh environments: Physiological and molecular basis of drought and heat stress tolerance

Climate change is significantly impacting agricultural production worldwide. Peanuts provide food and nutritional security to millions of people across the globe because of its high nutritive values. Drought and heat stress alone or in combination cause substantial yield losses to peanut production. The stress, in addition, adversely impact nutritional quality. Peanuts exposed to drought stress at reproductive stage are prone to aflatoxin contamination, which imposes a restriction on use of peanuts as health food and also adversely impact peanut trade. A comprehensive understanding of the impact of drought and heat stress at physiological and molecular levels may accelerate the development of stress tolerant productive peanut cultivars adapted to a given production system. Significant progress has been achieved towards the characterization of germplasm for drought and heat stress tolerance, unlocking the physiological and molecular basis of stress tolerance, identifying significant marker-trait associations as well major QTLs and candidate genes associated with drought tolerance, which after validation may be deployed to initiate marker-assisted breeding for abiotic stress adaptation in peanut. The proof of concept about the use of transgenic technology to add value to peanuts has been demonstrated. Advances in phenomics and artificial intelligence to accelerate the timely and cost-effective collection of phenotyping data in large germplasm/breeding populations have also been discussed. Greater focus is needed to accelerate research on heat stress tolerance in peanut. A suits of technological innovations are now available in the breeders toolbox to enhance productivity and nutritional quality of peanuts in harsh environments. A holistic breeding approach that considers drought and heat-tolerant traits to simultaneously address both stresses could be a successful strategy to produce climate-resilient peanut genotypes with improved nutritional quality.

Proximal and remote sensing in plant phenomics: 20 years of progress, challenges, and perspectives

Plant phenomics (PP) has been recognized as a bottleneck in studying the interactions of genomics and environment on plants, limiting the progress of smart breeding and precise cultivation. High-throughput plant phenotyping is challenging owing to the spatio-temporal dynamics of traits. Proximal and remote sensing (PRS) techniques are increasingly used for plant phenotyping because of their advantages in multi-dimensional data acquisition and analysis. Substantial progress of PRS applications in PP has been observed over the last two decades and is analyzed here from an interdisciplinary perspective based on 2972 publications. This progress covers most aspects of PRS application in PP, including patterns of global spatial distribution and temporal dynamics, specific PRS technologies, phenotypic research fields, working environments, species, and traits. Subsequently, we demonstrate how to link PRS to multi-omics studies, including how to achieve multi-dimensional PRS data acquisition and processing, how to systematically integrate all kinds of phenotypic information and derive phenotypic knowledge with biological significance, and how to link PP to multi-omics association analysis. Finally, we identify three future perspectives for PRS-based PP: (1) strengthening the spatial and temporal consistency of PRS data, (2) exploring novel phenotypic traits, and (3) facilitating multi-omics communication.

Exploration of Alternative Approaches to Phenotyping of Late Leaf Spot and Groundnut Rosette Virus Disease for Groundnut Breeding

Late leaf spot (LLS), caused by Nothopassalora personata (Berk. & M.A Curt.), and groundnut rosette disease (GRD), [caused by groundnut rosette virus (GRV)], represent the most important biotic constraints to groundnut production in Uganda. Application of visual scores in selection for disease resistance presents a challenge especially when breeding experiments are large because it is resource-intensive, subjective, and error-prone. High-throughput phenotyping (HTP) can alleviate these constraints. The objective of this study is to determine if HTP derived indices can replace visual scores in a groundnut breeding program in Uganda. Fifty genotypes were planted under rain-fed conditions at two locations, Nakabango (GRD hotspot) and NaSARRI (LLS hotspot). Three handheld sensors (RGB camera, GreenSeeker, and Thermal camera) were used to collect HTP data on the dates visual scores were taken. Pearson correlation was made between the indices and visual scores, and logistic models for predicting visual scores were developed. Normalized difference vegetation index (NDVI) (r = -0.89) and red-green-blue (RGB) color space indices CSI (r = 0.76), v* (r = -0.80), and b* (r = -0.75) were highly correlated with LLS visual scores. NDVI (r = -0.72), v* (r = -0.71), b* (r = -0.64), and GA (r = -0.67) were best related to the GRD visual symptoms. Heritability estimates indicated NDVI, green area (GA), greener area (GGA), a*, and hue angle having the highest heritability (H ² > 0.75). Logistic models developed using these indices were 68% accurate for LLS and 45% accurate for GRD. The accuracy of the models improved to 91 and 84% when the nearest score method was used for LLS and GRD, respectively. Results presented in this study indicated that use of handheld remote sensing tools can improve screening for GRD and LLS resistance, and the best associated indices can be used for indirect selection for resistance and improve genetic gain in groundnut breeding.

PSegNet: Simultaneous Semantic and Instance Segmentation for Point Clouds of Plants

Phenotyping of plant growth improves the understanding of complex genetic traits and eventually expedites the development of modern breeding and intelligent agriculture. In phenotyping, segmentation of 3D point clouds of plant organs such as leaves and stems contributes to automatic growth monitoring and reflects the extent of stress received by the plant. In this work, we first proposed the Voxelized Farthest Point Sampling (VFPS), a novel point cloud downsampling strategy, to prepare our plant dataset for training of deep neural networks. Then, a deep learning network—PSegNet, was specially designed for segmenting point clouds of several species of plants. The effectiveness of PSegNet originates from three new modules including the Double-Neighborhood Feature Extraction Block (DNFEB), the Double-Granularity Feature Fusion Module (DGFFM), and the Attention Module (AM). After training on the plant dataset prepared with VFPS, the network can simultaneously realize the semantic segmentation and the leaf instance segmentation for three plant species. Comparing to several mainstream networks such as PointNet++, ASIS, SGPN, and PlantNet, the PSegNet obtained the best segmentation results quantitatively and qualitatively. In semantic segmentation, PSegNet achieved 95.23%, 93.85%, 94.52%, and 89.90% for the mean Prec, Rec, F1, and IoU, respectively. In instance segmentation, PSegNet achieved 88.13%, 79.28%, 83.35%, and 89.54% for the mPrec, mRec, mCov, and mWCov, respectively.

High-throughput field crop phenotyping: current status and challenges

In contrast to the rapid advances made in plant genotyping, plant phenotyping is considered a bottleneck in plant science. This has promoted high-throughput plant phenotyping (HTP) studies, resulting in an exponential increase in phenotyping-related publications. The development of HTP was originally intended for use as indoor HTP technologies for model plant species under controlled environments. However, this subsequently shifted to HTP for use in crops in fields. Although HTP in fields is much more difficult to conduct due to unstable environmental conditions compared to HTP in controlled environments, recent advances in HTP technology have allowed these difficulties to be overcome, allowing for rapid, efficient, non-destructive, non-invasive, quantitative, repeatable, and objective phenotyping. Recent HTP developments have been accelerated by the advances in data analysis, sensors, and robot technologies, including machine learning, image analysis, three dimensional (3D) reconstruction, image sensors, laser sensors, environmental sensors, and drones, along with high-speed computational resources. This article provides an overview of recent HTP technologies, focusing mainly on canopy-based phenotypes of major crops, such as canopy height, canopy coverage, canopy biomass, and canopy stressed appearance, in addition to crop organ detection and counting in the fields. Current topics in field HTP are also presented, followed by a discussion on the low rates of adoption of HTP in practical breeding programs.

Development of a Low-Cost System for 3D Orchard Mapping Integrating UGV and LiDAR

Growing evaluation in the early stages of crop development can be critical to eventual yield. Point clouds have been used for this purpose in tasks such as detection, characterization, phenotyping, and prediction on different crops with terrestrial mapping platforms based on laser scanning. 3D model generation requires the use of specialized measurement equipment, which limits access to this technology because of their complex and high cost, both hardware elements and data processing software. An unmanned 3D reconstruction mapping system of orchards or small crops has been developed to support the determination of morphological indices, allowing the individual calculation of the height and radius of the canopy of the trees to monitor plant growth. This paper presents the details on each development stage of a low-cost mapping system which integrates an Unmanned Ground Vehicle UGV and a 2D LiDAR to generate 3D point clouds. The sensing system for the data collection was developed from the design in mechanical, electronic, control, and software layers. The validation test was carried out on a citrus crop section by a comparison of distance and canopy height values obtained from our generated point cloud concerning the reference values obtained with a photogrammetry method. A 3D crop map was generated to provide a graphical view of the density of tree canopies in different sections which led to the determination of individual plant characteristics using a Python-assisted tool. Field evaluation results showed plant individual tree height and crown diameter with a root mean square error of around 30.8 and 45.7 cm between point cloud data and reference values.

Using UAV LiDAR to Extract Vegetation Parameters of Inner Mongolian Grassland

The accurate estimation of grassland vegetation parameters at a high spatial resolution is important for the sustainable management of grassland areas. Unmanned aerial vehicle (UAV) light detection and ranging (LiDAR) sensors with a single laser beam emission capability can rapidly detect grassland vegetation parameters, such as canopy height, fractional vegetation coverage (FVC) and aboveground biomass (AGB). However, there have been few reports on the ability to detect grassland vegetation parameters based on RIEGL VUX-1 UAV LiDAR (Riegl VUX-1) systems. In this paper, we investigated the ability of Riegl VUX-1 to model the AGB at a 0.1 m pixel resolution in the Hulun Buir grazing platform under different grazing intensities. The LiDAR-derived minimum, mean, and maximum canopy heights and FVC were used to estimate the AGB across the entire grazing platform. The flight height of the LiDAR-derived vegetation parameters was also analyzed. The following results were determined: (1) The Riegl VUX-1-derived AGB was predicted to range from 29 g/m2 to 563 g/m2 under different grazing conditions. (2) The LiDAR-derived maximum canopy height and FVC were the best predictors of grassland AGB (R2 = 0.54, root-mean-square error (RMSE) = 64.76 g/m2). (3) For different UAV flight altitudes from 40 m to 110 m, different flight heights showed no major effect on the derived canopy height. The LiDAR-derived canopy height decreased from 9.19 cm to 8.17 cm, and the standard deviation of the LiDAR-derived canopy height decreased from 3.31 cm to 2.35 cm with increasing UAV flight altitudes. These conclusions could be useful for estimating grasslands in smaller areas and serving as references for other remote sensing datasets for estimating grasslands in larger areas.

Challenges and Opportunities in Machine-Augmented Plant Stress Phenotyping

Plant stress phenotyping is essential to select stress-resistant varieties and develop better stress-management strategies. Standardization of visual assessments and deployment of imaging techniques have improved the accuracy and reliability of stress assessment in comparison with unaided visual measurement. The growing capabilities of machine learning (ML) methods in conjunction with image-based phenotyping can extract new insights from curated, annotated, and high-dimensional datasets across varied crops and stresses. We propose an overarching strategy for utilizing ML techniques that methodically enables the application of plant stress phenotyping at multiple scales across different types of stresses, program goals, and environments.

Harnessing High-throughput Phenotyping and Genotyping for Enhanced Drought Tolerance in Crop Plants

Development of drought-tolerant cultivars is one of the challenging tasks for the plant breeders due to its complex inheritance and polygenic regulation. Evaluating genetic material for drought tolerance is a complex process due to its spatiotemporal interactions with environmental factors. The conventional breeding approaches are costly, lengthy, and inefficient to achieve the expected gain in drought tolerance. In this regard, genomics-assisted breeding (GAB) offers promise to develop cultivars with improved drought tolerance in a more efficient, quicker, and cost-effective manner. The success of GAB depends upon the precision in marker-trait association and estimation of genomic estimated breeding values (GEBVs), which mostly depends on coverage and precision of genotyping and phenotyping. A wide gap between the discovery and practical use of quantitative trait loci (QTL) for crop improvement has been observed for many important agronomical traits. Such a limitation could be due to the low accuracy in QTL detection, mainly resulting from low marker density and manually collected phenotypes of complex agronomic traits. Increasing marker density using the high-throughput genotyping (HTG), and accurate and precise phenotyping using high-throughput digital phenotyping (HTP) platforms can improve the precision and power of QTL detection. Therefore, both HTG and HTP can enhance the practical utility of GAB along with a faster characterization of germplasm and breeding material. In the present review, we discussed how the recent innovations in HTG and HTP would assist in the breeding of improved drought-tolerant varieties. We have also discussed strategies, tools, and analytical advances made on the HTG and HTP along with their pros and cons.