Rice lodging severely affects harvest yield. Traditional evaluation methods and manual on-site measurement are found to be time-consuming, labor-intensive, and cost-intensive. In this study, a new method for rice lodging assessment based on a deep learning UNet (U-shaped Network) architecture was proposed. The UAV (unmanned aerial vehicle) equipped with a high-resolution digital camera and a three-band multispectral camera synchronously was used to collect lodged and non-lodged rice images at an altitude of 100 m. After splicing and cropping the original images, the datasets with the lodged and non-lodged rice image samples were established by augmenting for building a UNet model. The research results showed that the dice coefficients in RGB (Red, Green and Blue) image and multispectral image test set were 0.9442 and 0.9284, respectively. The rice lodging recognition effect using the RGB images without feature extraction is better than that of multispectral images. The findings of this study are useful for rice lodging investigations by different optical sensors, which can provide an important method for large-area, high-efficiency, and low-cost rice lodging monitoring research.

Accurate detection of weeds in farmland can help reduce pesticide use and protect the agricultural environment. To develop intelligent equipment for weed detection, this study used an imaging spectrometer system, which supports micro-scale plant feature analysis by acquiring high-resolution hyper spectral images of corn and a number of weed species in the laboratory. For the analysis, the object-oriented classification system with segmentation and decision tree algorithms was utilized on the hyper spectral images to extract shape and texture features of eight species of plant leaves, and then, the spectral identification characteristics of different species were determined through sensitive waveband selection and using vegetation indices calculated from the sensitive band data of the images. On the basis of the comparison and analysis of the combined characteristics of spectra, shape, and texture, it was determined that the spectral characteristics of the ratio vegetation index of R677/R710 and the normalized difference vegetation index, shape features of shape index, area, and length, as well as the texture feature of the entropy index could be used to build a discrimination model for corn and weed species. Results of the model evaluation showed that the Global Accuracy and the Kappa coefficient of the model were both over 95%. In addition, spectral and shape features can be regarded as the preferred characteristics to develop a device of weed identification from the view of accessibility to crop/weeds discriminant features, according to different roles of various features in classifying plants. Therefore, the results of this study provide valuable information for the portable device development of intelligent weed detection.

Fusarium head blight (FHB), one of the most prevalent and damaging infection diseases of wheat, affects quality and safety of associated food. In this study, to realize the early accurate monitoring of FHB, a diagnostic model of disease severity was proposed based on the fusion features of image and spectral features. First, the hyperspectral image of FHB infected in the range of the 400–1000 nm spectrum was collected, and the color parameters of wheat ear and spot region were segmented based on image features. Twelve sensitive bands were extracted using the successive projection algorithm, gray-scale co-occurrence matrix, and RGB color model. Four texture features were extracted from each feature band image as texture variables, and nine color feature variables were extracted from R, G, and B component images. Texture features with high correlation and color features were selected to participate in the final model building parameters via correlation analysis. Finally, the particle swarm optimization support vector machine (PSO-SVM) algorithm was used to build the model based on the diagnosis model of disease severity of FHB with different combinations of characteristic variables. The experimental results showed that the PSO-SVM model based on spectral and color feature fusion was optimal. Moreover, the accuracy of the training and prediction set was 95% and 92%, respectively. The method based on fusion features of image and spectral features can accurately and effectively diagnose the severity of FHB, thereby providing a technical basis for the timely and effective control of FHB and precise application of a pesticide.

Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Due to the complexity of the field environment as well as differences in size, shape, texture, and color gradation among the leaves, purple leaf segmentation is difficult. In this study, we used a U-Net model for segmenting purple rapeseed leaves during the seedling stage based on unmanned aerial vehicle (UAV) RGB imagery at the pixel level. With the limited spatial resolution of rapeseed images acquired by UAV and small object size, the input patch size was carefully selected. Experiments showed that the U-Net model with the patch size of 256 × 256 pixels obtained better and more stable results with a F-measure of 90.29% and an Intersection of Union (IoU) of 82.41%. To further explore the influence of image spatial resolution, we evaluated the performance of the U-Net model with different image resolutions and patch sizes. The U-Net model performed better compared with four other commonly used image segmentation approaches comprising support vector machine, random forest, HSeg, and SegNet. Moreover, regression analysis was performed between the purple rapeseed leaf ratios and the measured N content. The negative exponential model had a coefficient of determination (R²) of 0.858, thereby explaining much of the rapeseed leaf purpling in this study. This purple leaf phenotype could be an auxiliary means for monitoring crop growth status so that crops could be managed in a timely and effective manner when nitrogen stress occurs. Results demonstrate that the U-Net model is a robust method for purple rapeseed leaf segmentation and that the accurate segmentation of purple leaves provides a new method for crop nitrogen stress monitoring.

Grain protein content (GPC) is an important indicator of wheat quality. Earlier estimation of wheat GPC based on remote sensing provided effective decision to adapt optimized strategies for grain harvest, which is of great significance for agricultural production. The objectives of this field study are: (i) To assess the ability of spectral vegetation indices (VIs) of Sentinel 2 data to detect the wheat nitrogen (N) attributes related to the grain quality of winter wheat production, and (ii) to examine the accuracy of wheat N status and GPC estimation models based on different VIs and wheat nitrogen parameters across Analytical Spectra Devices (ASD) and Unmanned Aerial Vehicle (UAV) hyper-spectral data-simulated sentinel data and the real Sentinel-2 data. In this study, four nitrogen parameters at the wheat anthesis stage, including plant nitrogen accumulation (PNA), plant nitrogen content (PNC), leaf nitrogen accumulation (LNA), and leaf nitrogen content (LNC), were evaluated for their relationship between spectral parameters and GPC. Then, a multivariate linear regression method was used to establish the wheat nitrogen and GPC estimation model through simulated Sentinel-2A VIs. The coefficients of determination ( $R^2$ ) of four nitrogen parameter models were all greater than 0.7. The minimum $R^2$ of the prediction model of wheat GPC constructed by four nitrogen parameters combined with VIs was 0.428 and the highest $R^2$ was 0.467. The normalized root mean square error (nRMSE) of the four nitrogen estimation models ranged from 26.333% to 29.530% when verified by the ground-measured data collected from the Beijing suburbs, and the corresponding nRMSE for the GPC-predicted models ranged from 17.457% to 52.518%. The accuracy of the estimated model was verified by UAV hyper-spectral data which had resized to different spatial resolution collected from the National Experimental Station for Precision Agriculture. The normalized root mean square error (nRMSE) of the four nitrogen estimation models ranged from 16.9% to 37.8%, and the corresponding nRMSE for the GPC-predicted models ranged from 12.3% to 13.2%. The relevant models were also verified by Sentinel-2A data collected in 2018 while the minimum nRMSE for GPC invert model based on PNA was 7.89% and the maximum nRMSE of the GPC model based on LNC was 12.46% in Renqiu district, Hebei province. The nRMSE for the wheat nitrogen estimation model ranged from 23.200% to 42.790% for LNC and PNC. These data demonstrate that freely available Sentinel-2 imagery can be used as an important data source for wheat nutrition and grain quality monitoring.

Fusarium head blight (FHB) is a major disease threatening worldwide wheat production. FHB is a short cycle disease and is highly destructive under conducive environments. To provide technical support for the rapid detection of the FHB disease, we proposed to develop a new Fusarium disease index (FDI) based on the spectral data of 374–1050 nm. This study was conducted through the analysis of reflectance spectral data of healthy and diseased wheat ears at the flowering and filling stages by hyperspectral imaging technology and the random forest method. The characteristic wavelengths selected were 570 nm and 678 nm for the late flowering stage, 565 nm and 661 nm for the early filling stage, 560 nm and 663 nm for the combined stage (combining both flowering and filling stages) by random forest. FDI at each stage was derived from the wavebands of each corresponding stage. Compared with other 16 existing spectral indices, FDI demonstrated a stronger ability to determine the severity of the FHB disease. Its determination coefficients (R²) values exceeded 0.90 and the RMSEs were less than 0.08 in the models for each stage. Furthermore, the model for the combined stage performed better when used at single growth stage, but its effect was weaker than that of the models for the two individual growth stages. Therefore, using FDI can provide a new tool to detect the FHB disease at different growth stages in wheat.