The wheat above-ground biomass （AGB） is an important index that shows the life activity of vegetation,which is of great significance for wheat growth monitoring and yield prediction.Traditional biomass estimation methods specifically include sample surveys and harvesting statistics.Although these methods have high estimation accuracy,they are time-consuming,destructive,and difficult to implement to monitor the biomass at a large scale.The main objective of this study is to optimize the traditional remote sensing methods to estimate the wheat AGBbased on improved convolutional features （CFs）.Low-cost unmanned aerial vehicles （UAV） were used as the main data acquisition equipment.This study acquired image data acquired by RGB camera （RGB） and multi-spectral（MS） image data of the wheat population canopy for two wheat varieties and five key growth stages.Then,field measurements were conducted to obtain the actual wheat biomass data for validation.Based on the remote sensing indices （RSIs）,structural features （SFs）,and CFs,this study proposed a new feature named AUR-50 （multi-source combination based on convolutional feature optimization） to estimate the wheat AGB.The results show that AUR-50 could estimate the wheat AGB more accurately than RSIs and SFs,and the average R 2 exceeded 0.77.In the overwintering period,AUR-50 MS （multi-source combination with convolutional feature optimization using multispectral imagery） had the highest estimation accuracy （R 2 of 0.88）.In addition,AUR-50 reduced the effect of the vegetation index saturation on the biomass estimation accuracy by adding CFs,where the highest R 2 was 0.69 at the flowering stage.The results of this study provide an effective method to evaluate the AGB in wheat with high throughput and a research reference for the phenotypic parameters of other crops.

Rodents are essential to the balance of the grassland ecosystem, but their population outbreak can cause major economic and ecological damage. Rodent monitoring is crucial for its scientific management, but traditional methods heavily depend on manual labor and are difficult to be carried out on a large scale. In this study, we used UAS to collect high–resolution RGB images of steppes in Inner Mongolia, China in the spring, and used various object detection algorithms to identify the holes of Brandt’s vole (Lasiopodomys brandtii). Optimizing the model by adjusting evaluation metrics, specifically, replacing classification strategy metrics such as precision, recall, and F1 score with regression strategy-related metrics FPPI, MR, and MAPE to determine the optimal threshold parameters for IOU and confidence. Then, we mapped the distribution of vole holes in the study area using position data derived from the optimized model. Results showed that the best resolution of UAS acquisition was 0.4 cm pixel–1, and the improved labeling method improved the detection accuracy of the model. The FCOS model had the highest comprehensive evaluation, and an R2 of 0.9106, RMSE of 5.5909, and MAPE of 8.27%. The final accuracy of vole hole counting in the stitched orthophoto was 90.20%. Our work has demonstrated that UAS was able to accurately estimate the population of grassland rodents at an appropriate resolution. Given that the population distribution we focus on is important for a wide variety of species, our work illustrates a general remote sensing approach for mapping and monitoring rodent damage across broad landscapes for studies of grassland ecological balance, vegetation conservation, and land management.

Fusarium head blight (FHB) has attracted much attention in food science and agriculture for its threat to wheat yields and food safety, due to the production of mycotoxins like deoxynivalenol (DON). Breeding of wheat varieties with improved FHB resistance is essential for controlling this disease. However, identifying resistance in different materials during variety selection remains time-consuming and labor-intensive. Therefore, this paper proposed a high-throughput method for the evaluation of FHB disease symptoms. It enabled the semiautomatic acquisition of images of individual wheat ears in a field environment with the aid of a field robot. The images obtained were semantically segmented to get a single wheat ear, from which the infected spikelets (ISs) were extracted, and then the disease degree was calculated. The results showed that the accuracy value of the individual wheat ear using DeepLabV3+ reached 0.996. The accuracy value of ISs was over 0.98. The mean Accuracy of this method for identifying the resistance of varieties was 0.967, and the precision of a single severity grade reached 0.980. The results indicate that the proposed method enables the acquisition and extraction of disease phenotype and rapid identification of resistance to FHB. The study also provides a reference for accurately identifying phenotypes of wheat ears in other field environments and for selecting and breeding other fungal-toxin-resistant varieties.

Wheat (Triticum aestivum L.) leaf rust is the most common and widely distributed wheat disease. Non-destructive and real-time methods for monitoring wheat leaf rust can help prevent and control plant diseases in agricultural production. In this study, we obtained multispectral imagery of the wheat canopy acquired by an unmanned aerial vehicle, selected the vegetation index using the K-means algorithm (KA) and genetic algorithm (GA), and established a wheat leaf rust monitoring model based on the backpropagation neural network (BPNN) method. The results showed that the R-2 and RMSE of the KA-BPNN model were 0.902% and 5.45% for the modeling set, respectively, and 0.784% and 4.76% for the validation set, respectively; and the R-2 and RMSE of the GA-BPNN model was 0.922% and 4.88% for the modeling set, respectively, and 0.780% and 4.28% for the validation set, respectively. The prediction model after optimizing the variables using KA and GA had higher accuracy than the BPNN model, implying that using variable dimensionality reduction methods and complex machine learning algorithms to construct estimation models can improve model accuracy significantly. These models accurately monitored leaf rust in winter wheat, providing a theoretical basis and technical support for assessing plant diseases and screening disease-resistant wheat varieties.

The number of wheat ears is one of the most important factors in wheat yield composition. Rapid and accurate assessment of wheat ear number is of great importance for predicting grain yield and food security-related early warning signal generation. The current wheat ear counting methods rely on manual surveys, which are time-consuming, laborious, inefficient and inaccurate. Existing non-destructive wheat ear detection techniques are mostly applied to near-ground images and are difficult to apply to large-scale monitoring. In this study, we proposed a sampling survey method based on the unmanned aerial vehicle (UAV). Firstly, a small number of UAV images were acquired based on the five-point sampling mode. Secondly, an adaptive Gaussian kernel size was used to generate the ground truth density map. Thirdly, a density map regression network (DM-Net) was constructed and optimized. Finally, we designed an overlapping area of sub-images to solve the repeated counting caused by image segmentation. The MAE and MSE of the proposed model were 9.01 and 11.85, respectively. We compared the sampling survey method based on UAV images in this paper with the manual survey method. The results showed that the RMSE and MAPE of NM13 were 18.95 × 104/hm2 and 3.37%, respectively, and for YFM4, 13.65 × 104/hm2 and 2.94%, respectively. This study enables the investigation of the number of wheat ears in a large area, which can provide favorable support for wheat yield estimation.

The three-dimensional (3D) morphological information of wheat grains is an important parameter for discriminating seed health, wheat yield, and wheat quality. High-throughput acquisition of 3D indicators of wheat grains is of great importance for wheat cultivation management, genetic breeding, and economic value. Currently, the 3D morphology of wheat grains still relies on manual investigation, which is subjective, inefficient, and poorly reproducible. The existing 3D acquisition equipment is complicated to operate and expensive, which cannot meet the requirements of high-throughput phenotype acquisition. In this paper, an automatic, economical, and efficient method for the 3D morphometry of wheat grain is proposed. A line laser binocular camera was used to obtain high-quality point-cloud data. A wheat grain 3D model was constructed by point-cloud segmentation, finding, clustering, projection, and reconstruction. Based on this, 3D morphological indicators of wheat grains were calculated. The results show that the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the length were 0.2256 mm and 2.60%, the width, 0.2154 mm and 5.83%, the thickness, 0.2119 mm and 5.81%, and the volume, 1.7740 mm(3) and 4.31%. The scanning time was around 12 s and the data processing time was around 3.18 s under a scanning speed of 25 mm/s. This method can achieve the high-throughput acquisition of the 3D information of wheat grains, and it provides a reference for in-depth study of the 3D morphological indicators of wheat and other grains.

Thousand-grain weight is a key indicator of crop yield and an important parameter for evaluating cultivation measures. Existing methods based on image analysis are convenient but lack a counting algorithm that is suitable for multiple types of grains. This research develops an application program based on an Android device to quickly calculate the number of grains. We explore the short axis measurement method of the grains with morphological thought, and determine the relationship between the general corrosion threshold and the short axis. To solve the problem of calculating the number of grains in the connected area, the study proposes a corrosion algorithm based on the short axis and an improved corner point method. After testing a variety of crop grains and equipment, it was found that the method has high universality, supports grain counting with white paper as the background, and has high accuracy and calculation efficiency. The average accuracy rate is 97.9%, and the average time is less than 0.7 seconds. In addition, the difference between the average accuracy for various mobile phones and multiple crops is small. This research proposes a grain counting algorithm with a wide range of applications to meet the requirements of nonglare use in the field. The algorithm provides a fast, accurate, low-cost tool for counting grains of wheat, corn, mung bean, soybean, peanut, rapeseed, etc., which is less constrained by space and power conditions. The algorithm is highly adaptable and can provide a reference for the study of grain counting.

Wheat (Triticum aestivum L.) is an essential crop that is widely consumed globally. The tiller density is an important factor affecting wheat yield. Therefore, it is necessary to measure the number of tillers during wheat cultivation and breeding, which requires considerable labor and material resources. At present, there is no effective high-throughput measurement method for tiller number estimation, and the conventional tiller survey method cannot accurately reflect the spatial variation of wheat tiller density within the whole field. Therefore, in order to meet the demand for the thematic map of wheat tiller density at the field scale for the variable operation of nitrogen fertilizer, the multispectral images of wheat in Feekes growth stages 2–3 were obtained by unmanned aerial vehicle (UAV), and the characteristic parameters of the number of tillers were used to construct a model that could accurately estimate the number of tillers. Based on the vegetation index (VIs), this work proposed a gradual change features (GCFs) approach, which can greatly improve the disadvantages of using VIs to estimate tiller number, better reflect the tiller status of the wheat population, and have good results on the estimation of tiller in common models. A Lasso + VIs + GCFs method was constructed for accurate estimation of tiller number in multiple growth periods and fertilizer-treated wheat, with an average RMSE of fewer than 9 tillers per square meter, average MAE less than 8 tillers per square meter, and R2 above 0.7. The results of the study not only proposed a high-throughput measurement method for the number of tillers but also provided a reference for the estimation of tiller number and other agronomic parameters.

利用无人机获取小麦孕穗期和开花期的RGB图像,通过图像处理获取小麦图像颜色指数和纹理特征指数,并在小麦收获后测定实际产量.通过分析各颜色指数、纹理特征指数与小麦产量之间的相关性,筛选出各生育期与小麦产量相关性最高的颜色指数和纹理特征指数,建立小麦产量预测模型并进行验证.结果表明:小麦孕穗期和开花期图像颜色指数与产量相关性均较好,纹理特征指数与产量相关性不够理想.孕穗期与产量相关性最高的颜色指数为VARI,相关系数达0.862,利用单一颜色指数VARI构建小麦产量预测模型验证的决定系数(R2)为0.725,模拟均方根误差(RMSE)为494.52 kg·hm-2;开花期与产量相关性最高的颜色指数为ExR,相关系数为-0.851,利用单一颜色指数ExR构建小麦产量预测模型验证的R2为0.709 2,模拟RMSE为499.72 kg·hm-2;使用孕穗期颜色指数VARI和纹理特征指数CON相结合构建的产量预测模型验证得到R2和RMSE分别为0.740 6和489.19 kg·hm-2,较单一颜色指数模型分别提升2.15％和减小1.08％.使用开花期颜色指数ExR和纹理特征指数ASM相结合构建的产量预测模型验证得到R2和RMSE分别为0.735 4和491.24 kg·hm-2,较单一颜色指数模型分别提升3.69％和减小1.70％.上述结果说明,用无人机图像颜色指数可以建立有效的产量估测模型,将颜色指数和纹理特征指数相结合建立的估产模型较单一颜色指数建立的模型精度高.

赤霉病是影响小麦产量和品质的主要病害之一.为快速、有效地监测小麦赤霉病的发生情况,利用数码相机对人工接种赤霉病菌的小麦田进行RGB图像获取,在图像预处理基础上,对Deeplabv3+网络模型进行调参和训练.以轻量化网络MobileNet V2为网络编码模块,利用空洞卷积技术建立基于深度学习网络的小麦赤霉病发病麦穗的识别与检测模型,并用实测数据对模型进行验证和评价.结果 表明,该模型的平均精度为0.9692,损失函数Loss为0.1030,平均交并比MIoU为0.793,模型识别与检测效果较好.上述结果为小麦赤霉病的检测与识别提供新的手段.

Background: Three-dimensional (3D) laser scanning technology could rapidly extract the surface geometric features of maize plants to achieve non-destructive monitoring of maize phenotypes. However, extracting the phenotypic parameters of maize plants based on laser point cloud data is challenging. Methods: In this paper, a rotational scanning method was used to collect the data of potted maize point cloud from different perspectives by using a laser scanner. Maize point cloud data were grid-reconstructed and aligned based on greedy projection triangulation algorithm and iterative closest point (ICP) algorithm, and the random sampling consistency algorithm was used to segment the stem and leaf point clouds of single maize plant to obtain the plant height and leaf parameters. Results: The results showed that the R 2 between the predicted plant height and the measured plant height was above 0.95, and the R 2 of the predicted leaf length, leaf width and leaf area were 0.938, 0878 and 0.956 respectively when compared with the measured values. Conclusions: The 3D reconstruction of maize plants using the laser scanner showed a good performance, and the phenotypic parameters obtained based on the reconstructed 3D model had high accuracy. The results were helpful to the practical application of plant 3D reconstruction and provided guidance for plant parameter acquisition and theoretical methods for intelligent agricultural research.

WOFOST模型是目前常用的作物模型之一.采用2015 2017年区域气象站点的气象数据、土壤数据、作物数据等,利用OAT方法进行模型参数敏感性分析,结合最小二乘法、“试错法”等,并借鉴前人研究结果,基于不同密度和氮肥处理水平,针对冬小麦发育参数出苗到开花积温(TSUM1)、开花到成熟积温(TSUM2)以及生长参数比叶面积(SLATB)、最大CO2同化速率(AMAXTB)进行冬小麦参数调整,实现WOFOST模型本地化.结果 表明:WOFOST模型模拟冬小麦LAI的R2、RMSE、NRMSE分别为0.817 8、0.58、27.9％,模拟叶、茎、穗和地上部总生物量的R2、RMSE、NRMSE分别为0.783 2～0.953 1、315.55～986.15 kg·hm-2、10.1％～29.8％,模拟产量的R2、RMSE、NRMSE分别为0.585 2、799.96 kg· hm-2、15.9％,与实测值均有较好的一致性.这一研究说明WOFOST模型能较好地模拟研究区域冬小麦的生长发育状况.

为了实现基于无人机的小麦产量快速预测,通过不同种植密度、氮肥和品种的田间试验,应用无人机航拍获取小麦生育前期(越冬前期和拔节期)的RGB图像,通过图像处理获取小麦田间颜色和纹理特征指数,并在小麦收获后测定实际产量.通过分析不同颜色和纹理特征指数与小麦产量的关系,筛选出适合小麦产量预测的颜色和纹理特征指数,建立小麦产量预测模型并进行验证.结果 表明,小麦生育前期图像颜色指数与产量的相关性较好,而纹理特征指数相关性较差.对越冬前期利用单一颜色指数NDI构建的产量预测模型验证时,R2为0.541,RMSE为671.26 kg·hm-2;对拔节期用单一颜色指数VARI构建的产量预测模型验证时,R2为0.603,RMSE为639.78 kg· hm-2,预测结果比较理想,但不是最优.对越冬前期颜色指数NDI和纹理特征指数ENT相结合构建的产量预测模型验证时,R2和RMSE分别为0.629和611.82kg·hm-2,比单一颜色指数模型分别提升16.27％和减小8.85％;对拔节期颜色指数VARI和纹理特征指数COR相结合构建的产量预测模型验证时,R2和RMSE分别为0.746和510.29 kg·hm-2,较单一颜色指数模型分别提升23.71％和减小20.24％.上述结果说明,将无人机图像颜色和纹理特征指数相结合建立的估产模型精度较高,可在小麦生育前期对产量进行有效预测.

BACKGROUND:The number grain per panicle of rice is an important phenotypic trait and a significant index for variety screening and cultivation management. The methods that are currently used to count the number of grains per panicle are manually conducted, making them labor intensive and time consuming. Existing image-based grain counting methods had difficulty in separating overlapped grains.RESULTS:In this study, we aimed to develop an image analysis-based method to quickly quantify the number of rice grains per panicle. We compared the counting accuracy of several methods among different image acquisition devices and multiple panicle shapes on both Indica and Japonica subspecies of rice. The linear regression model developed in this study had a grain counting accuracy greater than 96% and 97% for Japonica and Indica rice, respectively. Moreover, while the deep learning model that we used was more time consuming than the linear regression model, the average counting accuracy was greater than 99%.CONCLUSIONS:We developed a rice grain counting method that accurately counts the number of grains on a detached panicle, and believe this method can be a huge asset for guiding the development of high throughput methods for counting the grain number per panicle in other crops.

Biomass and the chlorophyll content are important indicators to measure the growth and development of grasslands. Modeling using hyperspectral data is an important means to monitor grassland growth and development. In this paper, we studied Mexican maize grass, hybrid Pennisetum and hybrid Sudan grass under different soil texture treatments and determined the correlation between the canopy reflectance spectrum and plant growth status in different soil textures based on hyperspectral data. Our results showed that, under different soil texture treatments, the emergence rate of Mexican maize grass and hybrid Pennisetum did not differ significantly, whereas that of hybrid Sudan grass indicated a significant difference. Under different soil texture treatments, the trend of plant height variation was consistent. In terms of different types of grassland, it is generally feasible to establish a grassland yield spectral model based on the vegetation indexes NDVI and RVI, and the leaf SPAD values of the three types of grassland best fit the spectral parameter red edge area.

In order to alleviate the difficulties in collecting indexes for the analysis of farmland weed communities, we implemented a computer vision technology-based method for the identification of farmland weeds at the species level. By using the super-green and maximum interclass difference methods to obtain a green vegetation binary image, we were able to separate weeds from cultivated crops through multiple etching and the removal of small areas. A BP (back propagation) neural network was used for weed recognition, and the morphological characteristics of the weeds and each region were selected following etching to construct the input matrix of the recognition model for training and testing the BP network. After experimenting with the computational vision method for the identification of five weed species, we discovered that the recognition accuracy rate reached 96%. The results showed that the computer vision method could quickly and accurately extract a weed community analysis index, thereby providing a reference for the intelligent analysis of weed communities.

The number of cultivated wheat seedlings per unit area allows calculation of plant density. Wheat seedling density provides emergence data and this is useful for improving crop management. The number of wheat seedlings is typically determined by visual counts but this is time-consuming and laborious. We obtained field digital images of 1st to 3rd leaf stage wheat seedlings. The seedlings were extracted using an image analysis technique that calculated the coverage degree of the seedlings and the number of angular points of overlapping leaves. The wheat seedling quantity estimation model was constructed using multivariate regression analysis. The model parameters included coverage degree, number of angular points, variety coefficient, and leaf age. Introduction of the number of angular points increased the accuracy of the single coverage degree model. The R-2 value was consistently > 0.95 when the model was applied to different varieties, indicating that the model was adaptable for different varieties. As the leaf stage or density increased, the accuracy of the model declined, but the minimum R-2 remained > 0.87, indicating good adaptability of the model to seedlings with different leaf ages and densities. This method is an effective means for counting wheat seedlings in the 1st to the 3rd leaf stages.

Rice lodging not only causes difficulty in harvest operations, but also drastically reduces yield. Rice lodging assessment contributes greatly to rice plantation and crop field management. In this study, we collected visible and thermal infrared images with an unmanned aerial vehicle. Then, based on hybrid image analysis and field investigation, we established a comprehensive rice lodging recognition model using a particle swarm optimization and support vector machine algorithm. The results showed that color and texture features were different between lodged and non-lodged rice plants. Moreover, the temperature was distinct between lodging and non lodging areas, with lodged rice having higher canopy temperature. The developed model based on the visible and thermal infrared images was validated using different Indica and Japonica rice cultivars. The model had a false positives rate and false negatives rate of less than 10%, and estimated lodging rate with an R-2 greater than 0.9. These results indicated that combination of visible and thermal infrared images feature significantly increased the rice lodging recognition accuracy. The developed model can be used to monitor rice lodging and estimate the lodging rate.

Nondestructive acquisition agronomic parameters of wheat (Triticum aestivum L.) growth status and appropriate evaluation are important to wheat management. This study was performed to construct a model for the estimation of wheat dry weight (DW), leaf area index (LAI), tiller number (TN), and nitrogen accumulation (NC) using image analysis techniques. Wheat groups were constructed under different levels of planting density and nitrogen fertilizer treatments. Images were taken during the early tillering stage using a digital camera. The estimation model for agronomic parameters was then constructed using the stepwise linear regression method, and the evaluation model for wheat group growth status was built using a back‐propagation (BP) neural network. The results show that estimation model proposed in this study offers more accurate simulation of agronomic parameters than the single‐parameter model; the R2 values of DW, LAI, and NC are all >0.8, and the TNs reached 0.72. The average R2 value of the analog values and the measured values using the wheat population growth state evaluation model based on the BP neural network were 0.83. The wheat population growth state evaluation model established using these four agronomic parameters can reflect the status of the wheat groups and provide new evidence for wheat nondestructive diagnosis and field management.

Crop temperature is derived from the energy exchange between the crop and the environment,the change of crop temperature is an effective monitoring indicator of crop growth.Infrared thermal imaging technology can reflect the surface temperature of the object through the infrared thermal radiation of the object.Currently,crop temperature is always explored as an affiliated issue from the aspect of energy budget instead of a synthetic and logic consideration.In order to analysis the causes of crop temperature comprehensively,this paper made a brief review on crop temperature from external reason,internal reason and monitoring method;introduced the factors of affecting temperature,including variety characteristics,growth period,different organs,light,temperature,water,CO2,wet,wind,planting density,fertilization,etc.Also,the application of thermal infrared technology in the monitoring of crop growth status was described.Finally,the problems existing in the field of crop monitoring were summarized,and the future research was prospected.