Search

Real-time analysis of UAV low-altitude remote sensing images at airborne terminals facilitates the timely monitoring of weeds in the farmland. Aiming at the real-time identification of rice weeds by UAV low-altitude remote sensing, two improved identification models, MobileNetV2-UNet and FFB-BiSeNetV2, were proposed based on the semantic segmentation models U-Net and BiSeNetV2, respectively. The MobileNetV2-UNet model focuses on reducing the amount of calculation of the original model parameters, and the FFB-BiSeNetV2 model focuses on improving the segmentation accuracy of the original model. In this study, we first tested and compared the segmentation accuracy and operating efficiency of the models before and after the improvement on the computer platform, and then transplanted the improved models to the embedded hardware platform Jetson AGX Xavier, and used TensorRT to optimize the model structure to improve the inference speed. Finally, the real-time segmentation effect of the two improved models on rice weeds was further verified through the collected low-altitude remote sensing video data. The results show that on the computer platform, the MobileNetV2-UNet model reduced the amount of network parameters, model size, and floating point calculations by 89.12%, 86.16%, and 92.6%, and the inference speed also increased by 2.77 times, when compared with the U-Net model. The FFB-BiSeNetV2 model improved the segmentation accuracy compared with the BiSeNetV2 model and achieved the highest pixel accuracy and mean Intersection over Union ratio of 93.09% and 80.28%. On the embedded hardware platform, the optimized MobileNetV2-UNet model and FFB-BiSeNetV2 model inferred 45.05 FPS and 40.16 FPS for a single image under the weight accuracy of FP16, respectively, both meeting the performance requirements of real-time identification. The two methods proposed in this study realize the real-time identification of rice weeds under low-altitude remote sensing by UAV, which provide a reference for the subsequent integrated operation of plant protection drones in real-time rice weed identification and precision spraying.

Leaf area index (LAI) is used to predict crop yield, and unmanned aerial vehicles (UAVs) provide new ways to monitor LAI. In this study, we used a fixed-wing UAV with multispectral cameras for remote sensing monitoring. We conducted field experiments with two peanut varieties at different planting densities to estimate LAI from multispectral images and establish a high-precision LAI prediction model. We used eight vegetation indices (VIs) and developed simple regression and artificial neural network (BPN) models for LAI and spectral VIs. The empirical model was calibrated to estimate peanut LAI, and the best model was selected from the coefficient of determination and root mean square error. The red (660 nm) and near-infrared (790 nm) bands effectively predicted peanut LAI, and LAI increased with planting density. The predictive accuracy of the multiple regression model was higher than that of the single linear regression models, and the correlations between Modified Red-Edge Simple Ratio Index (MSR), Ratio Vegetation Index (RVI), Normalized Difference Vegetation Index (NDVI), and LAI were higher than the other indices. The combined VI BPN model was more accurate than the single VI BPN model, and the BPN model accuracy was higher. Planting density affects peanut LAI, and reflectance-based vegetation indices can help predict LAI.

Unmanned aerial vehicle (UAV) remote sensing platforms allow for normalized difference vegetation index (NDVI) values to be mapped with a relatively high resolution, therefore enabling an unforeseeable ability to evaluate the influence of the operation parameters on the quality of the thus acquired data. In order to better understand the effects of these parameters, we made a comprehensive evaluation on the effects of the solar zenith angle (SZA), the time of day (TOD), the flight altitude (FA) and the growth level of paddy rice at a pixel-scale on UAV-acquired NDVI values. Our results show that: (1) there was an inverse relationship between the FA (≤100 m) and the mean NDVI values, (2) TOD and SZA had a greater impact on UAV–NDVIs than the FA and the growth level; (3) Better growth levels of rice—measured using the NDVI—could reduce the effects of the FA, TOD and SZA. We expect that our results could be used to better plan flight campaigns that aim to collect NDVI values over paddy rice fields.

The purpose of this study is to determine a method for quickly and accurately estimating the chlorophyll content of peanut plants at different plant densities. This was explored using leaf spectral reflectance to monitor peanut chlorophyll content to detect sensitive spectral bands and the optimum spectral indicators to establish a quantitative model. Peanut plants under different plant density conditions were monitored during three consecutive growth periods, single-photon avalanche diode (SPAD) and hyperspectral data derived from the leaves under the different plant density conditions were recorded. By combining arbitrary bands, indices were constructed across the full spectral range (350&ndash, 2500 nm) based on blade spectra: the normalized difference spectral index (NDSI), ratio spectral index (RSI), difference spectral index (DSI) and soil-adjusted spectral index (SASI). This enabled the best vegetation index reflecting peanut-leaf SPAD values to be screened out by quantifying correlations with chlorophyll content, and the peanut leaf SPAD estimation models established by regression analysis to be compared and analyzed. The results showed that the chlorophyll content of peanut leaves decreased when plant density was either too high or too low, and that it reached its maximum at the appropriate plant density. In addition, differences in the spectral reflectance of peanut leaves under different chlorophyll content levels were highly obvious. Without considering the influence of cell structure as chlorophyll content increased, leaf spectral reflectance in the visible (350&ndash, 700 nm): near-infrared (700&ndash, 1300 nm) ranges also increased. The spectral bands sensitive to chlorophyll content were mainly observed in the visible and near-infrared ranges. The study results showed that the best spectral indicators for determining peanut chlorophyll content were NDSI (R520, R528), RSI (R748, R561), DSI (R758, R602) and SASI (R753, R624). Testing of these regression models showed that coefficient of determination values based on the NDSI, RSI, DSI and SASI estimation models were all greater than 0.65, while root mean square error values were all lower than 2.04. Therefore, the regression model established according to the above spectral indicators was a valid predictor of the chlorophyll content of peanut leaves.

Nondestructive estimation of the biophysical properties of crops provide quick and real time information of crop health under wide range of environment.  The chlorophyll content is an important indicator of crop health and widely used for determination of nutritional status of the crops real time in precision agriculture.  Advancement in the low altitude remote sensing (LARS) technologies such as Unmanned Aerial vehicles (UAVs) provides high temporal and spatial resolution solution for nondestructive, rapid and accurate estimation of biophysical properties of various crops.  The main objective of this study was to evaluate the high resolution multispectral UAV images for nondestructive and real time estimation of the kinnow tree leaves chlorophyll content in district Sargodha, Pakistan.  Kinnow tree leaves chlorophyll contents were measured manually using chlorophyll meter (SPAD-502 Minolta) in the kinnow orchard along with GPS positions in district Sargodha.  The UAVs images were also acquired during the same time when ground-truthing campaign for kinnow leaves chlorophyll content was performed. Vegetation indices including Normalized Difference Vegetation Index (NDVI), Transformed Normalized Difference Vegetation Index (TNDVI), Modified Chlorophyll Absorbed Ratio Index (MCARI2), Soil adjusted vegetation Index (SAVI) and Modified soil adjusted vegetation index (MSAVI2) were derived by multispectral UAV images for chlorophyll estimation.  The regression analysis was performed between ground-truthing data of chlorophyll content and UAV derived vegetation indices for predicting kinnow leave chlorophyll content model. MSAVI2 and TNDVI were proved to be more robust indices to estimate the chlorophyll content in the kinnow orchard with the highest coefficients of determination ( R 2 ) 0.89 and 0.85 respectively.  The results showed that the multispectral UAV can be used for accurately estimation of chlorophyll content and assess crop health status in a wider range which will help in managing crop nutrition requirement in real time in the kinnow orchard. Keywords: Chlorophyll content, kinnow orchard, Multispectral UAV, Vegetation indices DOI: 10.33440/j.ijpaa.20180101.0001 Citation: Tahir M N, Naqvi S Z A, Lan Y B, Zhang Y L, Wang Y K, Afzal M, et al.  Real time monitoring chlorophyll content based on vegetation indices derived from multispectral UAVs in the kinnow orchard.  Int J Precis Agric Aviat, 2018; 1(1): 24–31.

In order to accurately explore the droplets distribution characteristics on the ground and space during the aerial spray process, a single-pass application test based on the determination of effective swath by a Bell206L4 helicopter was carried out. The accurate effective swath width of the helicopter spray operation was obtained, and the cumulative and spatial drift characteristics of droplet deposition when the helicopter used different aerial nozzles under natural environment were systematically analyzed. The results showed that the average effective swath width of three different types of nozzle were 25.3 m (CP02), 29.7 m (CP03) and 29.3 m (CP04) with an average flight altitude of 11 m and velocity of 17 m/s. The average deposition volume in the effective swath area of each sampling line was in the range of 1.208-2.735 ?L/cm 2 . Most of the droplets in each application were concentrated near the route and the adjacent locations of the effective swath area. In addition, the droplets with small size were trend to drift, and the increased nozzle orifice size was beneficial to reduce drift. In terms of spatial drift distribution, small-sized droplets usually gathered in the upper space, larger-sized droplets were easy to gather in the middle space, and the medium-sized droplets were trend to gather in the lower space. The research results were helpful to optimize the spray plan and provide reference for precision aerial application. Keywords: aerial spray, droplet deposition, spatial drift, effective swath, helicopter, precision agricultural DOI: 10.33440/j.ijpaa.20210401.145 Citation: Yao W X, Guo S, Yu F H, Du W, Meng Y H, Wang J, Chen P C, et al. Droplet deposition and spatial drift distribution characteristics of aerial spraying based on the determination of effective swath. Int J Precis Agric Aviat, 2021; 4(1): 36–43.

In order to quickly and accurately extract the fraction vegetation cover (FVC) of winter wheat, the unmanned aerial vehicle (UAV) was used to obtain the visible light image of winter wheat during the green returned stage, and the estimation ability of winter wheat FVC based on visible light vegetation index and texture feature was explored, 8 texture features of winter wheat images were extracted by gray-level co-occurrence matrix, and 3 visible light vegetation indices of VDVI, NGBDI and GRVI were calculated. According to the characteristics of vegetation and soil blue & green and green & red bands in the research field, the green-red combined vegetation index (GRDI) and green-blue combined vegetation index (GBVI) were constructed. In addition, regression models of vegetation cover were established using 5 vegetation indices and 8 texture features respectively. The results showed that the regression model established by GRDI had the highest accuracy among vegetation indices with R 2 value of 0.9245, RMSE value of 0.02677, and nRMSE value of 5.74%. Therefore, the GRDI model was selected in this paper to generate FVC level distribution map, which provided a basis for winter wheat growth monitoring and field management. Keywords: winter wheat, FVC, UAV remote sensing technology, texture feature, vegetation index construction DOI:  10.33440/j.ijpaa.20190202.44.  Citation: Yang H B, Zhao J, Lan Y B, Lu L Q, Li Z M. Fraction vegetation cover extraction of winter wheat based on spectral information and texture features obtained by UAV.  Int J Precis Agric Aviat, 2019; 2(2): 54–61.

Crop yield prediction is of great practical significance for farmers to make reasonable decisions, such as decisions on crop insurance, storage demand, cash flow budget, fertilizer, water and other input factors. The traditional yield measurement method is sampling surveys, which require a large area of destructive sampling of cotton fields and consume considerable time and labor costs. This study established a cotton yield estimation model based on time series Unmanned Aerial Vehicle (UAV) remote sensing data. The U-Net semantic segmentation network is used to recognize and extract the boll opening pixels in high-resolution visible images, and the boll opening pixel percentage (BOP) is calculated according to the network extraction results. By combining the multispectral images and the pixel coverage of cotton bolls, a Bayesian regularization BP (back propagation) neural network was used to predict cotton yields. In order to simplify the input parameters of the model, the stepwise sensitivity analysis method is used to eliminate redundant variables and obtain the optimal input feature set. The experimental results show that the R2 of the proposed model is 0.853 at the scale of 0.81 m2 (average results of ten-fold cross validation). This study provides a method that can simultaneously meet the requirements of large-area and small-scale forecasting of cotton yields and provides a new idea for cotton yield measurement and breeding screening.

Vertical heterogeneity of the canopy is being increasingly recognized in remote estimates of vegetative properties. Given the current limited knowledge of this issue, this paper investigated the effects of different vertical distributions of crop structure [e.g., leaf angle (LA) and leaf area index (LAI)] and biochemical parameters [e.g., chlorophyll a and b content $(\text{Chl}_{{a}+{b}})$ and water content $(W_{c})$ ] on canopy reflectance and vegetation indices (VIs). A recently developed multiple-layer canopy reflectance model (MRTM) was tested for winter wheat and used to run a simulation analysis of different canopy scenarios. The results showed that the MRTM performed well to model winter wheat canopy reflectance with regard to spikes and vertical distributions of leaf properties. The vertical profiles of LA and LAI influenced canopy reflectance at almost all wavelengths, whereas the vertical profile of $\text{Chl}_{{a}+{b}}$ mainly affected reflectance in the visible region, and that of $W_{c}$ only affected reflectance in the near-infrared region. Changes in vertical distribution of the LA resulted in clear variations in VIs related to the LA, LAI, and $\text{Chl}_{{a}+{b}}$ estimates. The vertical LAI and $\text{Chl}_{{a}+{b}}$ profiles mainly influenced the VIs related to the LAI and $\text{Chl}_{{a}+{b}}$ estimates. The $W_{c}$ vertical profile primarily affected the VIs used to estimate crop water properties. The sensitivities of the VIs were mainly associated with the spectral responses and penetration characteristics of the bands they used. These findings suggest that the sensitivity of VIs to the vertical distributions of crop parameters should be considered when establishing models for remote crop monitoring.

Helminthosporium leaf blotch (HLB) is a serious disease of wheat causing yield reduction globally. Usually, HLB disease is controlled by uniform chemical spraying, which is adopted by most farmers. However, increased use of chemical controls have caused agronomic and environmental problems. To solve these problems, an accurate spraying system must be applied. In this case, the disease detection over the whole field can provide decision support information for the spraying machines. The objective of this paper is to evaluate the potential of unmanned aerial vehicle (UAV) remote sensing for HLB detection. In this work, the UAV imagery acquisition and ground investigation were conducted in Central China on April 22th, 2017. Four disease categories (normal, light, medium, and heavy) were established based on different severity degrees. A convolutional neural network (CNN) was proposed for HLB disease classification. The experiments on data preprocessing, classification, and hyper-parameters tuning were conducted. The overall accuracy and standard error of the CNN method was 91.43% and 0.83%, which outperformed other methods in terms of accuracy and stabilization. Especially for the detection of the diseased samples, the CNN method significantly outperformed others. Experimental results showed that the HLB infected areas and healthy areas can be precisely discriminated based on UAV remote sensing data, indicating that UAV remote sensing can be proposed as an efficient tool for HLB disease detection.

Rapid acquisition and mapping of normalized difference vegetation index (NDVI) values is essential for a timely evaluation of nitrogen use efficiency (NUE) in sustainable agriculture. The zonal nutrient management techniques for sustainable agriculture require timely and efficient NDVI data collection and analysis capabilities, – a need that is still rarely addressed. However, as with the use of manned aircraft, the primary limitation of established unmanned aerial vehicle (UAV) imaging technologies is the limited time window for large-area data collection. Furthermore, as the spatial resolution increases, the post-processing time generally becomes longer. To overcome problems associated with the need for rapid data acquisition and post-processing, we have developed a UAV-based sensor system called the Accurate and Speed Scanner (AS-Scanner). The data acquisition accuracy and NDVI mapping speed of the system were assessed. According to the results of a ground-level experiment, the mean absolute error (MAE) between the reflectance data of the AS-Scanner and the corresponding data of the ASD FieldSpec 3 spectrometer is less than 1.11%. Furthermore, results of a plot-level experiment suggest that the NDVI values of a raw point cloud from AS-Scanner-based UAV platform (AS-NDVI) and UAV-mounted MicaSense RedEdge camera (REG-NDVI) are highly correlated (0.54

Traditional artificial statistical methods of hailstorm damage assessment are often inefficient, subjective, time-consuming, and inaccurate. The use of drones for high-resolution remote sensing imaging enables large-scale, rapid assessment of a target area. The purpose of this study was to use multispectral imaging techniques to promptly and accurately assess the damage degree of hail in crops. In this experiment, cotton was used as the research target, and the experiment was carried out after a hail disaster that occurred during the flowering and boll stage of cotton development. A hail vegetation index (HGVI) was constructed and compared with the classification results of other vegetation indices on the hail disaster degree. It was concluded that: (i) both the hail vegetation index HGVI and the previous vegetation index, ratio vegetation index, are suitable tools of classification for grading cotton hail disasters, with both indices having a Kappa coefficient over 0.85 and a median Kappa coefficient greater than 0.9; (ii) the method used in this study is suitable for simple classification based on multispectral images; (iii) this study explains the possibility of classifying hail damage degrees based on multispectral images. Subsequent research can further diagnose and classify hail disasters during different periods and improve the accuracy and completeness of classification.

Single boll weight is the main factor of cotton yield and a key index used to evaluate the quality of cotton. Predicting the single boll weight in a large area is important for variety selection and yield improvement. A model was established to predict the single boll weight by using the multitemporal high-resolution visible light remote sensing data obtained from UAV. Specifically, remote sensing data were collected for 29 fields in the Changji, Shihezi and Shawan areas in northern Xinjiang during the blooming period and boll opening stage. Five circular areas with a radius of 1 m were selected from each field as the ground investigation area for collection of the cotton boll samples. Fully convolutional networks (FCN) was used to recognize and extract bolls at the boll opening stage in the remote sensing images as a dependent variable of the model. Correlation analysis was carried out by combining VDVI (Visible-band difference vegetation index) at the flowering and boll setting stages, VDVI at boll opening stages, VDVI at boll opening areas (Extracted by FCN) and RGB mean values, then use the least squares linear regression and BP neural networks to model the upper, middle, lower cotton layers and average single boll weight in investigation area. Subsequently, K-fold cross-validation was performed to evaluate the results. The results showed that the results of the least squares linear regression (R2 = 0.8162) and BP neural networks (R2 = 0.8170) were nearly equivalent. The percentage of boll opening in the area and VDVI at the flowering and boll setting stages were highly correlated with upper single boll weight. This study proposes a method to realize the large scale prediction of single boll weight, which provided a new idea for cotton yield prediction and breeding screening.

Weed control is necessary in rice cultivation, but the excessive use of herbicide treatments has led to serious agronomic and environmental problems. Suitable site-specific weed management (SSWM) is a solution to address this problem while maintaining the rice production quality and quantity. In the context of SSWM, an accurate weed distribution map is needed to provide decision support information for herbicide treatment. UAV remote sensing offers an efficient and effective platform to monitor weeds thanks to its high spatial resolution. In this work, UAV imagery was captured in a rice field located in South China. A semantic labeling approach was adopted to generate the weed distribution maps of the UAV imagery. An ImageNet pre-trained CNN with residual framework was adapted in a fully convolutional form, and transferred to our dataset by fine-tuning. Atrous convolution was applied to extend the field of view of convolutional filters, the performance of multi-scale processing was evaluated, and a fully connected conditional random field (CRF) was applied after the CNN to further refine the spatial details. Finally, our approach was compared with the pixel-based-SVM and the classical FCN-8s. Experimental results demonstrated that our approach achieved the best performance in terms of accuracy. Especially for the detection of small weed patches in the imagery, our approach significantly outperformed other methods. The mean intersection over union (mean IU), overall accuracy, and Kappa coefficient of our method were 0.7751, 0.9445, and 0.9128, respectively. The experiments showed that our approach has high potential in accurate weed mapping of UAV imagery.

Detection and monitoring are the first essential step for effective management of sheath blight (ShB), a major disease in rice worldwide. Unmanned aerial systems have a high potential of being utilized to improve this detection process since they can reduce the time needed for scouting for the disease at a field scale, and are affordable and user-friendly in operation. In this study, a commercialized quadrotor unmanned aerial vehicle (UAV), equipped with digital and multispectral cameras, was used to capture imagery data of research plots with 67 rice cultivars and elite lines. Collected imagery data were then processed and analyzed to characterize the development of ShB and quantify different levels of the disease in the field. Through color features extraction and color space transformation of images, it was found that the color transformation could qualitatively detect the infected areas of ShB in the field plots. However, it was less effective to detect different levels of the disease. Five vegetation indices were then calculated from the multispectral images, and ground truths of disease severity and GreenSeeker measured NDVI (Normalized Difference Vegetation Index) were collected. The results of relationship analyses indicate that there was a strong correlation between ground-measured NDVIs and image-extracted NDVIs with the R2 of 0.907 and the root mean square error (RMSE) of 0.0854, and a good correlation between image-extracted NDVIs and disease severity with the R2 of 0.627 and the RMSE of 0.0852. Use of image-based NDVIs extracted from multispectral images could quantify different levels of ShB in the field plots with an accuracy of 63%. These results demonstrate that a customer-grade UAV integrated with digital and multispectral cameras can be an effective tool to detect the ShB disease at a field scale.

Leaf area index (LAI) and biomass are frequently used target variables for agricultural and ecological remote sensing applications. Ground measurements of winter wheat LAI and biomass were made from March to May 2014 in the Yangling district, Shaanxi, Northwest China. The corresponding remotely sensed data were obtained from the earth-observation satellites Huanjing (HJ) and RADARSAT-2. The objectives of this study were (1) to investigate the relationships of LAI and biomass with several optical spectral vegetation indices (OSVIs) and radar polarimetric parameters (RPPs), (2) to estimate LAI and biomass with combined OSVIs and RPPs (the product of OSVIs and RPPs (COSVI-RPPs)), (3) to use multiple stepwise regression (MSR) and partial least squares regression (PLSR) to test and compare the estimations of LAI and biomass in winter wheat, respectively. The results showed that LAI and biomass were highly correlated with several OSVIs (the enhanced vegetation index (EVI) and modified triangular vegetation index 2 (MTVI2)) and RPPs (the radar vegetation index (RVI) and double-bounce eigenvalue relative difference (DERD)). The product of MTVI2 and DERD (R2 = 0.67 and RMSE = 0.68, p < 0.01) and that of MTVI2 and RVI (R2 = 0. 68 and RMSE = 0.65, p < 0.01) were strongly related to LAI, and the product of the optimized soil adjusted vegetation index (OSAVI) and DERD (R2 = 0.79 and RMSE = 148.65 g/m2, p < 0.01) and that of EVI and RVI (R2 = 0. 80 and RMSE = 146.33 g/m2, p < 0.01) were highly correlated with biomass. The estimation accuracy of LAI and biomass was better using the COSVI-RPPs than using the OSVIs and RPPs alone. The results revealed that the PLSR regression equation better estimated LAI and biomass than the MSR regression equation based on all the COSVI-RPPs, OSVIs, and RPPs. Our results indicated that the COSVI-RPPs can be used to robustly estimate LAI and biomass. This study may provide a guideline for improving the estimations of LAI and biomass of winter wheat using multisource remote sensing data.

This paper describes the design and evaluation of an airborne multispectral imaging system based on two identical consumer-grade cameras for agricultural remote sensing. The cameras are equipped with a full-frame complementary metal oxide semiconductor (CMOS) sensor with 5616 × 3744 pixels. One camera captures normal color images, while the other is modified to obtain near-infrared (NIR) images. The color camera is also equipped with a GPS receiver to allow geotagged images. A remote control is used to trigger both cameras simultaneously. Images are stored in 14-bit RAW and 8-bit JPEG files in CompactFlash cards. The second-order transformation was used to align the color and NIR images to achieve subpixel alignment in four-band images. The imaging system was tested under various flight and land cover conditions and optimal camera settings were determined for airborne image acquisition. Images were captured at altitudes of 305–3050 m (1000–10,000 ft) and pixel sizes of 0.1–1.0 m were achieved. Four practical application examples are presented to illustrate how the imaging system was used to estimate cotton canopy cover, detect cotton root rot, and map henbit and giant reed infestations. Preliminary analysis of example images has shown that this system has potential for crop condition assessment, pest detection, and other agricultural applications.

The study investigated the use of aerial multispectral imagery and ground-based hyperspectral data for the discrimination of different crop types and timely detection of cotton plants over large areas. Airborne multispectral imagery and ground-based spectral reflectance data were acquired at the same time over three large agricultural fields in Burleson Co., Texas during the 2010 growing season. The discrimination accuracy of aerial- and ground-based data was examined individually; then a multi-sensor data fusion technique was applied on both datasets in order to improve the accuracy of discrimination. The individual classification accuracy of data taken with the aerial- and ground-based sensors were 90% and 93.3%, respectively. In comparison, the accuracy of discriminating crop types with fused data was 100% in the calibration and only 3.33% misclassification in the cross-validation. These results suggest that data fusion techniques could greatly enhance our ability to detect cotton from other plants.

Aerial application of herbicides is a common tool in agricultural field management. The objective of this study was to evaluate the efficacy of glyphosate herbicide applied using aircraft fitted with both conventional and emerging aerial nozzle technologies. A weedy field was set up in a randomised complete block experimental design using three replicates. Four aerial spray technology treatments, electrostatic nozzles with charging off, electrostatic nozzles with charging on, conventional flat-fan hydraulic nozzles and rotary atomisers, were tested. To evaluate the glyphosate efficacy and performance of aerial spray technologies, spectral reflectance measurements were acquired using a ground-based sensing system for all treatment plots. Three measurements were taken at 1, 8, and 17 days after treatment (DAT). The statistical analyses indicated that glyphosate applied with different methods killed the weeds effectively compared to untreated areas at 17 DAT. Conventional flat-fan nozzles and rotary atomisers performed better than the electrostatic nozzles with charging off. There was no evidence to show that the electrostatic nozzle performed better with charging on or charging off. The results could provide applicators with guidance equipment configurations that can result in herbicide savings and optimised applications in other crops.

Remote sensing can be a rapid, accurate, and simple method for assessing pest damage on plants. The objectives of this study were to identify spectral wavelengths sensitive to cotton aphid infestation. Then, the normalized difference spectral indices (NDSI) and ratio spectral indices (RSI) based on the leaf spectrum were obtained within 350–2500 nm, and their correlation with infestation were qualified. The results showed that leaf spectral reflectance decreased in the visible range (350–700 nm) and the near-infrared range (NIR, 700–1300 nm) as aphid damage severity increased, and significant differences were found in blue, green, red, NIR and short-wave infrared (SWIR) band regions between different grades of aphid damage severity. Decrease in Chlorophyll a (Chl a) pigment was more significant than that in Chlorophyll (Chl b) in the infested plants and the Chl a/b ratio showed a decreasing trend with increase in aphid damage severity. The sensitive spectral bands were mainly within NIR and SWIR ranges. The best spectral indices NDSI (R678, R1471) and RSI (R1975, R1904) were formulated with these sensitive spectral regions through reducing precise sampling method. These new indices along with 16 other stress related indices compiled from literature were further tested for their ability to detect aphid damage severity. The two indices in this study showed significantly higher coefficients of determination (R2 of 0.81 and 0.81, p &lt, 0.01) and the least RMSE values (RMSE of 0.50 and 0.49), and hence have potential application in assessing aphid infestation severity in cotton.

Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery.

Spatial modeling and variability analysis of soil and crop canopy coverage has been accomplished using aerial multispectral images. Multispectral imagery was acquired using an MS-4100 multispectral camera at different flight altitudes over a 40 ha cotton field. After the acquired images were geo-registered and processed, spatial relationships between the aerial images and ground-based soil conductivity and NDVI (normalized difference vegetation index) measurements were estimated and compared using two spatial analysis approaches (model-driven spatial regression and data-driven geostatistics) and one non-spatial approach (multiple linear regression). Comparison of the three approaches indicated that OLS (ordinary least squares) solutions from multiple linear regression models performed worst in modeling ground-based soil conductivity and NDVI with high AIC (Akaike information criterion) (-668.3 to 2980) and BIC (Bayesian information criterion) (-642.4 to 3006) values. Spatial regression and geostatistics performed much better in modeling soil conductivity, with low AIC (2698 to 2820) and BIC (2732 to 2850) values. For modeling ground-based NDVI, the AIC and BIC values were -681.7 and -652.1, respectively, for spatial error regression and -679.8 and -646.5, respectively, for geostatistics, which were only moderate improvements over OLS (-668.3 and -642.4). Validation of the geostatistical models indicated that they could predict soil conductivity much better than the corresponding multiple linear regression models, with lower RMSE (root mean squared error) values (0.096 to 0.186, compared to 0.146 to 0.306). Results indicated that the aerial images could be used for spatial modeling and prediction, and they were informative for spatial prediction of ground soil and canopy coverage variability. The methods used for this study could help deliver baseline data for crop monitoring with remote sensing and establish a procedure for general crop management.

Remote sensing is being used with Global Positioning Systems, Geographic Information Systems, and variable rate technology to ultimately help farmers maximize the economic and environmental benefits of crop pest management through precision agriculture. Airborne remote sensing is flexible and versatile because fields can be flown at variable altitude depending on the spatial resolution required. Although the use of airborne hyperspectral remote sensing in agricultural research and applications has been steadily increasing in the last decade, the airborne multispectral technique is still a good source of crop, soil, or ground cover information. The MS-4100 is a multispectral camera that produces and aligns images from different bands with a built-in prism. Data can be analyzed from the composite image or individual band images. The camera system evaluated herein uses a camera control system to physically compensate for roll, pitch, and yaw and maintain the camera at vertical nadir orientation. This article describes the automated airborne multi-spectral imaging system and image processing using sample imagery to demonstrate the capability and potential of the system for crop pest management.

Spraying droplets deposition, spatial distribution and drafting scope are very important evaluation factors for spraying effect and nozzle performance. Existing detection methods is to place the material such as humidity paper, glass, dishes or nylon ropes in a different location, to collect droplets, then to quantify by chemical analysis. High-speed & High-resolution cameras are also used to capture fog area. However, there was no an effective system that could visually detect the 3D spatial distribution of the droplets. A droplets detecting system, which included the laser sensor, computer, data logger and software, was built to measure droplets distribution and drafting. The system based on different reflection characteristics of laser from different substances, the LMS511 Pro, which could get multi-echo and produced by SICK Company Germany, was selected as the sensor to scan droplets. The computer and software adopted the scan data from sensor connected with Ethernet cable, achieved the detection target to identify and calculated the spatial position of the droplet. The superimposed time domain model of droplet spatial distribution was established further. The 3D space spray field quantitative model which was obtained based on algorithm of scatter feature extraction, could distribute spraying droplets deposition, spatial distribution and drafting scope. Results of test showed that the system is effective for assessing spray mist field in indoor and outdoor, could use to visually detect and comparison spatial distribution of droplets for the research of aerial spraying, nozzle or sprinkler irrigation developing, such as sprinkler and nozzle performance tests, or wind tunnel experiments.

This paper introduces a laser scanner based measurement system for measuring crop/tree geometric characteristics. The measurement system, which is mounted on a Unmanned Ground Vehicle (UGV), contains a SICK LMS511 PRO laser scanner, a GPS, and a computer. The LMS511 PRO scans objects within distance up to 80 meters with a scanning frequency of 25 up to 100Hz and with an angular resolution of 0.1667° up to 1°. With an Ethernet connection, this scanner can output the measured values in real time. The UGV is a WIFI based remotely controlled agricultural robotics system. During field tests, the laser scanner was mounted on the UGV vertically to scan crops or trees. The UGV moved along the row direction with certain average travel speed. The experimental results show that the UGV's travel speed significantly affects the measurement accuracy. A slower speed produces more accurate measuring results. With the developed measurement system, crop/tree canopy height, width, and volume can be accurately measured in a real-time manner. With a higher spatial resolution, the original data set may even provide useful information in predicting crop/tree growth and productivity. In summary, the UGV based measurement system developed in this research can measure the crop/tree geometric characteristics with good accuracy and will work as a step stone for our future UGV based intelligent agriculture system, which will include variable rate spray and crop/tree growth and productivity prediction through analyzing the measured results of the laser scanner system.

Precision Aerial Application needs support from ground-based data. An electronic Unmanned Ground Vehicle (UGV) System was developed for data acquisition in fields. The UGV is 4 wheels droved with remote control. The UGV system was used to collect real-time crop condition. The system did experiment in fields for measuring cotton height and canopy temperature, a Sick laser sensor and an Aprogee infrared sensor were used for crop height and temperature. It has higher accuracy than manual. This system also could connect with other sensors and be used in other applications of precision agriculture.

The laser sensor is widely used in agriculture application. A laser sensor, SICK LMS 511 Lite, is introduced in this paper. The use methods, data processing program and calculation method of the coordinates are described. The application specific examples are given in crop height measurement based UGV system, citrus shape scanning and 3D model building, and drifting detecting and distribution of spraying droplets. All of these would provide a reference for future applications in precision agriculture.

In the regions short of water, the adjustment of cropping structure is also an important measure to save water in agriculture besides water-saving irrigation techniques and cultivation techniques. This paper describes a method of water saving and high efficient water usage by adjusting the different crop water requirements. Based on the matching degree between water requirement at different crop-growing stages, the regional precipitation, and 3S (GIS, GPS and Remote Sensing) technologies, a planting structure optimization model with multiple objectives such as water saving and economic and ecological benefits in the irrigated area was established. Using the Wuquan Irrigation District in Baojixia as an example, the model was optimized with Ant Colony Algorithm. There are two plans. Plan A is for balancing development and Plan B is for enlarging economic crops. The total water requirements for irrigation district of Plan A and Plan B is respectively 85.4% and 83.4% of the present status. The net income of Plan A is lower by 5.4% and the Plan B is higher by 7.1% than design level years. Meanwhile the income of Plan A is lower by 5.9% and the Plan B is higher by 7.3% than in drought years. The coupling degree of precipitation of Plan A and Plan B is respectively higher 12.6% and 15.6% than level years while higher by 17.5% and 28.6% than drought years. The comparison between the two plans of controlled optimization shows that the second one is the better readjustment plan because, without changing the planting area, the structure optimization helps not only maintain the sustainable development of the environment but also improve the economic income dramatically.

Advanced remote sensing technologies provide researchers an innovative way to collect spatial data in precision agriculture. Sensor information and spatial analysis together allow for a completely understanding of the spatial complexity of a field and its crop. The objective of the study was to describe field variability in the Normalized Difference Vegetative Index (NDVI) and characterize the spatial structure of NDVI data by geostatistical variogram analysis. Data sets at three different sampling densities were investigated and compared to characterize NDVI variation within the specified study area. Variograms were computed by Matheron’s method of moments (MoM) estimator and fitted by theoretical models. The fitted spherical model was determined to be the best model for the data analysis in the study. The range of spatial dependence of the NDVI data was 40 m for sampling area 4x3 m2. It offers a good guidance for site-specific management of a 1-ha soybean, such as nitrogen application and irrigation.

Area-wide pest management essentially represents coordinated adoption of integrated pest management to conduct preventive suppression of a pest species throughout its geographic distribution. Scientists and researchers in area-wide pest management programs have been developing, integrating, and evaluating multiple strategies and technologies into a systems approach for management of field and crop insect pests. Remote sensing, Global Positioning Systems, geographic information systems, and variable rate technology are additional tools that scientists can implement to help farmers maximize the economic and environmental benefits of area-wide pest management through precision agriculture.

Advanced remote sensing technologies provide researchers an innovative way to collect spatial data in precision agriculture. Sensor information and spatial analysis together allow for a detailed understanding of the spatial complexity of a field and its crop. The objective of the study was to describe field variability in the normalized difference vegetation index (NDVI) and characterize the spatial structure of NDVI data by geostatistical variogram analysis. Data sets at three different sampling densities were investigated and compared to characterize NDVI variation within the specified study area. Variograms were computed by Matheron's method of moments (MoM) estimator and fitted by theoretical models. The fitted spherical model was determined to be the best model for the data analysis in the study. The range of spatial dependence of the NDVI data was 40 m for a sampling area of 4 m × 3 m. Knowing the amount of remotely sensed data needed to characterize the spatial variation of the field with NDVI allows us to save sampling costs and prescribe site-specific nitrogen and other agrichemical applications.