Search

ObjectiveIn recent years, there has been a significant increase in the severity of leaf diseases in maize, with a noticeable trend of mixed occurrence. This poses a serious threat to the yield and quality of maize. However, there is a lack of studies that combine the identification of different types of leaf diseases and their severity classification, which cannot meet the needs of disease prevention and control under the mixed occurrence of different diseases and different severities in actual maize fields.MethodsA method was proposed for identifying the types of typical leaf diseases in maize and classifying their severity using hyperspectral technology. Hyperspectral data of three leaf diseases of maize: northern corn leaf blight (NCLB), southern corn leaf blight (SCLB) and southern corn rust (SCR), were obtained through greenhouse pathogen inoculation and natural inoculation. The spectral data were preprocessed by spectral standardization, SG filtering, sensitive band extraction and vegetation index calculation, to explore the spectral characteristics of the three leaf diseases of maize. Then, the inverse frequency weighting method was utilized to balance the number of samples to reduce the overfitting phenomenon caused by sample imbalance. Relief-F and variable selection using random forests (VSURF) method were employed to optimize the sensitive spectral features, including band features and vegetation index features, to construct models for disease type identification based on the full stages of disease development (including all disease severities) and for individual disease severities using several representative machine learning approaches, demonstrating the effectiveness of the research method. Furthermore, the study individual occurrence severity classification models were also constructed for each single maize leaf disease, including the NCLB, SCLB and SCR severity classification models, respectively, aiming to achieve full-process recognition and disease severity classification for different leaf diseases. Overall accuracy (OA) and Macro F1 were used to evaluate the model accuracy in this study.Results and DiscussionThe research results showed significant spectrum changes of three kinds of maize leaf diseases primarily focusing on the visible (550-680 nm), red edge (740-760 nm), near-infrared (760-1 000 nm) and shortwave infrared (1 300-1 800 nm) bands. Disease-specific spectral features, optimized based on disease spectral response rules, effectively identified disease species and classify their severity. Moreover, vegetation index features were more effective in identifying disease-specific information than sensitive band features. This was primarily due to the noise and information redundancy present in the selected hyperspectral sensitive bands, whereas vegetation index could reduce the influence of background and atmospheric noise to a certain extent by integrating relevant spectral signals through band calculation, so as to achieve higher precision in the model. Among several machine learning algorithms, the support vector machine (SVM) method exhibited better robustness than random forest (RF) and decision tree (DT). In the full stage of disease development, the optimal overall accuracy (OA) of the disease classification model constructed by SVM based on vegetation index reached 77.51%, with a Macro F1 of 0.77, representing a 28.75% increase in OA and 0.30 higher of Macro F1 compared to the model based on sensitive bands. Additionally, the accuracy of the disease classification model with a single severity of the disease increased with the severity of the disease. The accuracy of disease classification during the early stage of disease development (OA=70.31%) closely approached that of the full disease development stage (OA=77.51%). Subsequently, in the moderate disease severity stage, the optimal accuracy of disease classification (OA=80.00%) surpassed the optimal accuracy of disease classification in the full disease development stage. Furthermore, the optimal accuracy of disease classification under severe severity reached 95.06%, with a Macro F1 of 0.94. This heightened accuracy during the severity stage can be attributed to significant changes in pigment content, water content and cell structure of the diseased leaves, intensifying the spectral response of each disease and enhancing the differentiation between different diseases. In disease severity classification model, the optimal accuracy of the three models for maize leaf disease severity all exceeded 70%. Among the three kinds of disease severity classification results, the NCLB severity classification model exhibited the best performance. The NCLB severity classification model, utilizing SVM based on the optimal vegetation index features, achieved an OA of 86.25%, with a Macro F1 of 0.85. In comparison, the accuracy of the SCLB severity classification model (OA=70.35%, Macro F1=0.70) and SCR severity classification model (OA=71.39%, Macro F1=0.69) were lower than that of NCLB.ConclusionsThe aforementioned results demonstrate the potential to effectively identify and classify the types and severity of common leaf diseases in maize using hyperspectral data. This lays the groundwork for research and provides a theoretical basis for large-scale crop disease monitoring, contributing to precision prevention and control as well as promoting green agriculture.

Crops have diverse structures and complex growth environments. RGB image data can reflect the texture and color features of plants accurately, while 3D data contains information about crop volume. The combination of RGB image and 3D point cloud data can achieve the extraction of two-dimensional and three-dimensional phenotypic parameters of crops, which is of great significance for the research of phenomics methods. In this study, potatoe plants were chosen as the research subject, and RGB cameras and laser scanners were used to collect 50 potato RGB images and 3D laser point cloud data. The segmentation accuracy of four deep learning semantic segmentation methods, OCRNet, UpNet, PaNet, and DeepLab v3+, were compared and analyzed for the RGB images. OCRNet, which demonstrated higher accuracy, was used to perform semantic segmentation on top-view RGB images of potatoes. Mean shift clustering algorithm was optimized for laser point cloud data processing, and single-plant segmentation of laser point cloud data was completed. Stem and leaf segmentation of single-plant potato point cloud data were accurately performed using Euclidean clustering and K-Means clustering algorithms. In addition, a strategy was proposed to establish a one-to-one correspondence between RGB images and point clouds of single-plant potatoes using pot numbering. 8 2D phenotypic parameters and 10 3D phenotypic parameters, including maximum width, perimeter, area, plant height, volume, leaf length, and leaf width, etc., were extracted from RGB images and laser point clouds, respectively. Finally, the accuracy of three representative and easily measurable phenotypic parameters, leaf number, plant height, and maximum width were evaluated. The mean absolute percentage errors (MAPE) were 8.6%, 8.3% and 6.0%, respectively, while the root mean square errors (RMSE) were 1.371 pieces, 3.2 cm and 1.86 cm, respectively, and the determination coefficients (R2) were 0.93, 0.95 and 0.91, respectively. The research results indicated that the extracted phenotype parameters can accurately and efficiently reflect the growth status of potatoes. Combining the RGB image data of potatoes with three-dimensional laser point cloud data can fully exploit the advantages of the rich texture and color characteristics of RGB images and the volumetric information provided by three-dimensional point clouds, achieving non-destructive, efficient, and high-precision extraction of two-dimensional and three-dimensional phenotype parameters of potato plants. The achievements of this study could not only provide important technical support for the cultivation and breeding of potatoes but also provide strong support for phenotype-based research.

Three-dimensional point clouds, as an advanced imaging technique, enable researchers to capture plant traits more precisely and comprehensively. The task of plant segmentation is crucial in plant phenotyping, yet current methods face limitations in computational cost, accuracy, and high-throughput capabilities. Consequently, many researchers have adopted 3D point cloud technology for organ-level segmentation, extending beyond manual and 2D visual measurement methods. However, analyzing plant phenotypic traits using 3D point cloud technology is influenced by various factors such as data acquisition environment, sensors, research subjects, and model selection. Although the existing literature has summarized the application of this technology in plant phenotyping, there has been a lack of in-depth comparison and analysis at the algorithm model level. This paper evaluates the segmentation performance of various deep learning models on point clouds collected or generated under different scenarios. These methods include outdoor real planting scenarios and indoor controlled environments, employing both active and passive acquisition methods. Nine classical point cloud segmentation models were comprehensively evaluated: PointNet, PointNet++, PointMLP, DGCNN, PointCNN, PAConv, CurveNet, Point Transformer (PT), and Stratified Transformer (ST). The results indicate that ST achieved optimal performance across almost all environments and sensors, albeit at a significant computational cost. The transformer architecture for points has demonstrated considerable advantages over traditional feature extractors by accommodating features over longer ranges. Additionally, PAConv constructs weight matrices in a data-driven manner, enabling better adaptation to various scales of plant organs. Finally, a thorough analysis and discussion of the models were conducted from multiple perspectives, including model construction, data collection environments, and platforms. [ABSTRACT FROM AUTHOR]

Phenotyping robots have the potential to obtain crop phenotypic traits on a large scale with high throughput. Autonomous navigation technology for phenotyping robots can significantly improve the efficiency of phenotypic traits collection. This study developed an autonomous navigation method utilizing an RGB‐D camera, specifically designed for phenotyping robots in field environments. The PP‐LiteSeg semantic segmentation model was employed due to its real‐time and accurate segmentation capabilities, enabling the distinction of crop areas in images captured by the RGB‐D camera. Navigation feature points were extracted from these segmented areas, with their three‐dimensional coordinates determined from pixel and depth information, facilitating the computation of angle deviation (α) and lateral deviation (d). Fuzzy controllers were designed with α and d as inputs for real‐time deviation correction during the walking of phenotyping robot. Additionally, the method includes end‐of‐row recognition and row spacing calculation, based on both visible and depth data, enabling automatic turning and row transition. The experimental results showed that the adopted PP‐LiteSeg semantic segmentation model had a testing accuracy of 95.379% and a mean intersection over union of 90.615%. The robot's navigation demonstrated an average walking deviation of 1.33 cm, with a maximum of 3.82 cm. Additionally, the average error in row spacing measurement was 2.71 cm, while the success rate of row transition at the end of the row was 100%. These findings indicate that the proposed method provides effective support for the autonomous operation of phenotyping robots. [ABSTRACT FROM AUTHOR]

Plant height is a key indicator to dynamically measure crop health and overall growth status, which is widely used to estimate the biological yield and final grain yield of crops. The traditional manual measurement method is subjective, inefficient, and time-consuming. And the plant height obtained by sampling cannot evaluate the height of the whole field. In the last decade, remote sensing technology has developed rapidly in agriculture, which makes it possible to collect crop height information with high accuracy, high frequency, and high efficiency. This paper firstly reviewed the literature on obtaining plant height by using remote sensing technology for understanding the research progress of height estimation in the field. Unmanned aerial vehicle (UAV) platform with visible-light camera and light detection and ranging (LiDAR) were the most frequently used methods. And main research crops included wheat, corn, rice, and other staple food crops. Moreover, crop height measurement was mainly based on near-field remote sensing platforms such as ground, UAV, and airborne. Secondly, the basic principles, advantages, and limitations of different platforms and sensors for obtaining plant height were analyzed. The altimetry process and the key techniques of LiDAR and visible-light camera were discussed emphatically, which included extraction of crop canopy and soil elevation information, and feature matching of the imaging method. Then, the applications using plant height data, including the inversion of biomass, lodging identification, yield prediction, and breeding of crops were summarized. However, the commonly used empirical model has some problems such large measured data, unclear physical significance, and poor universality. Finally, the problems and challenges of near-field remote sensing technology in plant height acquisition were proposed. Selecting appropriate data to meet the needs of cost and accuracy, improving the measurement accuracy, and matching the plant height estimation of remote sensing with the agricultural application need to be considered. In addition, we prospected the future development was prospected from four aspects of 1) platform and sensor, 2) bare soil detection and interpolation algorithm, 3) plant height application research, and 4) the measurement difference of plant height between agronomy and remote sensing, which can provide references for future research and method application of near-field remote sensing height measurement.

To cope with the challenges posed by the rapid growth of world population and global environmental changes, scholars should employ genetic and phenotypic analyses to breed crop varieties with improved responses to limited resource environments and soil conditions to increase crop yield and quality. Therefore, the efficient, accurate, and non-destructive measurement of crop phenotypic traits, and the dynamic quantification of phenotypic traits are urgently needed for crop phenotypic research, and breeding as well as for modern agricultural development. In this study, cotton plants were taken as research objects, and the multi-temporal point cloud data of cotton plants were collected by using three-dimensional laser scanning technology. The multi-temporal point clouds of three cotton plants at four time points were collected. First, RANSAC algorithm was implemented for main stem extraction on the original point cloud data of cotton plants, then region growing based clustering was carried out for leaf segmentation. Plant height was estimated by calculating the end points of the segmented main stem. Leaf length and width measurements were conducted on the segmented leaf parts. In addition, the volume was also estimated through the convex hull of the original point cloud of plant cotton. Then, multi-temporal point clouds of plants were registered, and organ correspondence was constructed with the Hungarian method. Finally, dynamic quantification of phenotypic traits including plant volume, plant height, leaf length, leaf width, and leaf area were calculated and analyzed. The overall performance of the approaches achieved a matching rate through a series of experiments, and the traits extracted by using of point cloud showed high correlation with the manually measured ones. The relative error between plant height and manual measurement results did not exceed 1.0%. The estimated leaf length and width on point clouds were highly correlated with the manually measured ones, and the coefficient of determination was nearly 1.0. The proposed 3D phenotyping methodology can be introduced and used to other crops for phenotyping.

China is the largest producer and consumer of rice, and the classification of filled/unfilled rice grains is of great significance for rice breeding and genetic analysis. The traditional method for filled/unfilled rice grain identification was generally manual, which had the disadvantages of low efficiency, poor repeatability, and low precision. In this study, we have proposed a novel method for filled/unfilled grain classification based on structured light imaging and Improved PointNet++. Firstly, the 3D point cloud data of rice grains were obtained by structured light imaging. And then the specified processing algorithms were developed for the single grain segmentation, and data enhancement with normal vector. Finally, the PointNet++ network was improved by adding an additional Set Abstraction layer and combining the maximum pooling of normal vectors to realize filled/unfilled rice grain point cloud classification. To verify the model performance, the Improved PointNet++ was compared with six machine learning methods, PointNet and PointConv. The results showed that the optimal machine learning model is XGboost, with a classification accuracy of 91.99%, while the classification accuracy of Improved PointNet++ was 98.50% outperforming the PointNet 93.75% and PointConv 92.25%. In conclusion, this study has demonstrated a novel and effective method for filled/unfilled grain recognition. [ABSTRACT FROM AUTHOR]