Economic analysis for smart sprayer application in wild blueberry fields

The wild blueberry industry is spending over $80 million CAD per year on agrochemicals for 93 000 ha under production in North America. A pressing need to reduce agro-chemical usage and production cost has resulted in the development of a smart sprayer for spot-application of agrochemicals in wild blueberry fields. This paper encompasses the economic analysis to determine the potential savings for spot-applications of agrochemicals using a smart sprayer. The economic analysis compared the smart sprayer with two other commercially available sprayers (basic and swath control). The swath control sprayer and smart sprayer both featured GPS auto-steer and boom section control to reduce over-spray in already applied areas based on GPS position. The basic sprayer used a foam marker for guidance with no swath control management. The smart sprayer featured a machine vision system that automatically detected target areas in the field further reducing agrochemical input by shutting individual nozzles off in non-target areas in the field. The cost analysis was performed to compare the different features of the sprayer technologies, i.e., base sprayer, additional technology, training, usage, repair and maintenance. The additional components installed on the smart sprayer were justified in terms of agrochemicals/water savings via spot-applications, tractor fuel and operator’s time. The application total cost was $2052 ha^?1 using the basic sprayer, $1799 ha^?1 using the swath control sprayer, and $1138 ha^?1 using the smart sprayer over a 2 year production cycle of the selected fields that were used in this study. The payback period ranged from 2.0 years (60 ha field size) to 9.8 years (20 ha field size) using the swath control sprayer. The payback period ranged from 11 months (60 ha field size) to 3.5 years (20 ha field size) when using the smart sprayer. Results revealed that the smart sprayer had significant advantage from both an environmental and economic perspective over the other two sprayers.     

Sensing and control system for spot-application of granular fertilizer in wild blueberry field

An automated sensing and control system (hardware and software) was developed for real-time spot-application of granular fertilizer in mowed wild blueberry fields. The custom hardware system was incorporated into a commercial pneumatic granular fertilizer spreader. Custom software for the sensing and control system was developed by combining color co-occurrence matrix based texture analysis and g-ratio algorithms in C++ to acquire and process images in real-time to differentiate mowed wild blueberry plants from bare spots and weeds. The performance accuracy of the spot-applicable fertilizer spreader was evaluated both in laboratory simulation and real-time field tests. Simulation results reported that the accuracy of the developed system was 94.9 %. Real-time field tests reported that the system produced acceptable results at ground speeds of 1.6 and 3.2 km h^?1 for the spot-application of fertilizer at target areas (in plant areas only) within the field. Results also indicated that the ground speed of 4.8 km h^?1 was unacceptable, which could be due to blurred images at high speed and surface unevenness of the wild blueberry field. Spot-application of fertilizer using the modified fertilizer spreader could save fertilizer for the wild blueberry producers.     

Spot-application of fungicide for wild blueberry using an automated prototype variable rate sprayer

Wild blueberry producers apply fungicide uniformly without considering significant bare spots in the field. The wrong or over use of fungicide in bare spots results in an increased cost of production and threatens the environment. An automated prototype variable rate (VR) sprayer was used for spot-application (SA) of Chlorothalonil (Bravo^®) fungicide in a wild blueberry field. Eighteen 6.1 m wide test tracks were selected in the field and bare spots were mapped using a real-time kinematics-global positioning system (RTK-GPS). Six plots were selected randomly for three different application rates. Water sensitive papers (WSP) were placed in foliage and bare spots in SA and uniform-application (UA) tracks. The percent area coverage (PAC) of WSP with both SA and UA in foliage and bare spot areas were calculated. Plant growth parameters were measured from all 108 randomly selected plots in SA, UA and control (CN) tracks for comparison. Plant images were taken over six selected plots in each of the 18 tracks. Images were analyzed using custom developed software to calculate the percentage of green pixels (PGP) for determining the effect of Bravo^® on plant health. Fruit yield parameters were also measured from selected plots for comparison. Non-significance of the t test for SA versus UA plant targets’ PAC indicated that there was no significant bias in the SA with saving (9.90–51.22 %) and SA was accurate. Bravo^® did not show any significant difference on plant growth parameters among SA, UA and CN. However, PGP, floral bud and harvestable yield of SA and UA were significantly increased over CN. Therefore, a VR sprayer could be used for SA of fungicides in wild blueberry cropping system to reduce chemical usage and maintain crop productivity.     

云南野生蓝莓加工技术

蓝莓(Blueberry)属杜鹃花科越桔亚科越桔属常绿灌木小浆果果树,又称越桔、乌鸦果、蓝浆果。全世界约有450种,中国约有90种,24变种,2亚种[1]。蓝莓适宜在北半球大部分地区生长,其果实和叶广泛用于食品工业和医药方面[2]。中国大兴安岭、小兴安岭,华南、华中、华东、西南山区发现     

Estimation of the rootzone depth above a gravel layer (in wild blueberry fields) using electromagnetic induction method

Wild blueberry (Vaccinium angustifolium Ait.) fields in the north east Canada are naturally grown in a course textured thin layer of soil and below this layer is a soilless layer of gravel. The root zone depth of this crop varies from 10 to 15 cm. Investigating the depth to the gravel layer below the course textured soil is advantageous, as it affects the water holding capacity of the root zone. Water and nutrient management are the two primary determinants of crop yield and the amount of leaching. The objective of this study was to estimate the depth to the gravel layer using DualEM-2 instrument. A C++ program written in Visual Studio 2010 was used to develop mathematical models for estimating the depth to the gravel layer from the outputs of DualEM-2 sensor. Two wild blueberry fields were selected in central Nova Scotia, Canada to evaluate the performance of DualEM-2 instrument in estimating the rootzone depth above the gravel layer. The mid points of squares created by grid lines were used as the sampling points at each experimental site. The actual depth to the interface was measured manually at selected grid points (n = 50). The apparent ground conductivity (EC_a) values of DualEM-2 were recorded and the depth to the interface was estimated for the same sampling points within the selected fields. The fruit yield samples were also collected from the same grid points to identify the impact of the depth to the gravel layer on crop yield. After calibrations, comprehensive surveys were conducted and the actual and estimated depths to the interface were established. The interpolated maps of fruit yield, and the actual (z_in) and estimated (\( {\text{z}}_{\text{in}}^{*} \)) depths to the interface were created in ArcGIS 10 software. Results indicated that the z_in was significantly correlated with \( {\text{z}}_{\text{in}}^{*} \) for the North River (R ² = 0.73; RMSE = 0.27 m) and the Carmel (R ² = 0.45; RMSE = 0.20 m) sites. Results revealed that the areas with shallow depth to the gravel layer were low yielding, indicating that the variation in the depth to the gravel layer can have an impact on crop productivity. Non-destructive estimations of the depth to the gravel layer can be used to develop erosion control strategies, which will result in an increased crop production.     

基于机器视觉的温室蓝莓花期蜜蜂授粉监测

为评估日光温室蓝莓开花窗口期内授粉蜜蜂投放量的合理性,基于机器视觉对蓝莓的蜜蜂授粉次数进行统计。针对检测环境复杂、目标尺度小、易被遮挡等问题,对数据集进行改进泊松融合数据增强处理;并优化设计YOLOv5模型结构,通过引入GAM注意力机制和Transformer模块,增强模型特征提取能力,特征金字塔网络采用BiFPN结构及CARAFE模块补充上下文信息;使用EIoU损失函数和Soft NMS边界框筛选算法,提高边界框的定位精度,解决目标遮挡漏检问题。结果显示,改进后网络的平均精度均值达到96.6%,较原网络提高3.5个百分点,在GPU上对单张蓝莓授粉图像的平均检测时间为11.4 ms。研究结果表明,本研究建立的模型的识别准确度、检测速度及鲁棒性能满足对蓝莓的蜜蜂授粉次数的实时监测。     

我国烤烟育苗的几种主要方式探讨

\t\t\t\t\t目的\t\t\t\t\t为了满足烟苗快速、准确、自动间苗的要求,提出了基于机器视觉的穴盘烟苗自动间苗算法研究,避免传统的人眼观察效率低、随意性大等缺陷。\t\t\t\t\t\t\t\t\t\t\t\t\t方法\t\t\t\t\t采用基于Lab空间下的K-means聚类彩色图像分割算法,根据矩阵行列求和法,在两峰之间取像素坐标,定位其区域位置,把穴盘分割成128个单元格,将目标区域转化为二值图像。通过分别比较烟苗的圆形度、长宽比和矩形度,发现这3种成分的同一形态特征有一定差异,可作单、多株及空穴烟苗识别参数。利用幼苗植株的面积和周长,在不同生长期设定一个合适阈值,实现自动间苗的目的。\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t结果\t\t\t\t\t仿真和数据分析表明：取圆形度1.256 6、长宽比1.571 4、矩形度0.716 5的区分效果最好。取面积分布在111~243 (像素),周长分布在16~33 (像素)可以判定为壮苗。在MATLAB R2015a环境下开发了机器视觉烟苗自动间苗软件系统。\t\t\t\t\t\t\t\t\t\t\t\t\t结论\t\t\t\t\t烟苗数目正确识别率达到97.04%以上,空穴位置达到100%,间苗位置及壮苗识别平均准确率分别达到94.76%和89.58%,为进一步开发基于机器视觉的烟苗自动间苗机提供了理论基础和技术支持。\t\t\t\t     

基于机器视觉的水稻秧苗图像分割

水稻秧苗的识别是水稻插秧机自主导航系统的关键内容之一。针对插秧机机器视觉导航中稻田图像秧苗与背景分割问题,建立了基于RGB（红绿蓝）颜色空间的秧苗表面颜色模型。通过颜色特征对秧苗图像进行处理,使用Photoshop软件获取秧苗部分和背景R,G,B分量值;通过对G R值与G B值的分析统计,发现两者之间存在分界关系：各自的权重与各分量的乘积之和为某个定值;为方便分析,选取权值a,b为05,即ExG因子,采用Otsu法获取定值最佳值,最大程度分割出目标和背景。与适合于大多数绿色作物的传统RGB法进行比较,并采用分割质量因子和算法运算时间作为评判标准,分析各算法的综合性能。试验发现,ExG因子结合Otsu分割法分割效果相对理想、稳定性更高,而且耗时更短。     

Deep learning-based identification system of weeds and crops in strawberry and pea fields for a precision agriculture sprayer

Precision Agriculture - Controlling weed infestation through chemicals (herbicides & pesticides) is essential for crop yield. However, excessive use of these chemicals has caused severe...     

机器视觉对农田中定位基准线的识别

针对机器视觉对作物行定位困难问题,给出一种基于Hough变换的作物行视觉定位方法。根据农田作物行图像的信息特点,运用2G-R-B灰度变换加大图像类间距离,采用最大类间方差法(OTSU)分割作物行与背景图像,采用5像素×1像素结构元素图像膨胀法对作物行形态进行修正并缩小或消除作物行和背景中的孔洞,采用中间线检测准定位基准线图像处理方法提取代表作物行走向的准定位基准线,采用Hough变换得到真正的定位基准线及其参数。采用400像素×300像素的白菜作物行图像进行实验,经本方法进行图像处理后,得到每条作物行单一的最能反映作物行走向的准定位基准线,再经Hough变换得到清晰、准确的定位基准线。所得到的定位基准线很好地代表了作物行走向,表明本方法能够得到较好的定位效果。     

Machine vision for counting fruit on mango tree canopies

Machine vision technologies hold the promise of enabling rapid and accurate fruit crop yield predictions in the field. The key to fulfilling this promise is accurate segmentation and detection of fruit in images of tree canopies. This paper proposes two new methods for automated counting of fruit in images of mango tree canopies, one using texture-based dense segmentation and one using shape-based fruit detection, and compares the use of these methods relative to existing techniques:—(i) a method based on K-nearest neighbour pixel classification and contour segmentation, and (ii) a method based on super-pixel over-segmentation and classification using support vector machines. The robustness of each algorithm was tested on multiple sets of images of mango trees acquired over a period of 3 years. These image sets were acquired under varying conditions (light and exposure), distance to the tree, average number of fruit on the tree, orchard and season. For images collected under the same conditions as the calibration images, estimated fruit numbers were within 16 % of actual fruit numbers, and the F1 measure of detection performance was above 0.68 for these methods. Results were poorer when models were used for estimating fruit numbers in trees of different canopy shape and when different imaging conditions were used. For fruit-background segmentation, K-nearest neighbour pixel classification based on colour and smoothness or pixel classification based on super-pixel over-segmentation, clustering of dense scale invariant feature transform features into visual words and bag-of-visual-word super-pixel classification using support vector machines was more effective than simple contrast and colour based segmentation. Pixel classification was best followed by fruit detection using an elliptical shape model or blob detection using colour filtering and morphological image processing techniques. Method results were also compared using precision–recall plots. Imaging at night under artificial illumination with careful attention to maintaining constant illumination conditions is highly recommended.     

手动喷雾器WS-16型的性能及在棉蚜防治中的应用

新型手动喷雾器WS-16型的额定流量和喷出的药液附着率分别比工农-16型提高35%和10%以上;用于防治棉花蚜虫,WS-16型喷雾器的两种喷头的防效都极显著优于工农-16型切向喷头,且工效提高25%以上;在应用中还表现出省力、不渗漏、药液利用率高等特点,具有推广价值.     

基于机器视觉葡萄叶片还原糖含量的检测系统

[目的]针对传统农业生产中,测定葡萄叶片还原糖的方法效率低、成本高的问题,本文提出了基于机器视觉的葡萄叶片还原糖含量的检测系统。[方法]通过对田间葡萄叶片进行采集,以光谱化学实验方法测得的葡萄叶片还原糖含量为基础,利用LabVIEW和MATLAB软件平台开发了一种葡萄叶片还原糖含量的检测系统。采用颜色一阶矩、二阶矩和灰度共生矩阵的综合特征参数来提取葡萄叶片颜色和纹理特征,并将该特征向量作为输入向量构建以径向基为核函数的支持向量机(SVM)分类器模型,利用SVM分类模型对采集到的480幅葡萄叶片进行实例分析。[结果]该系统测试结果正确率达88.125%,颜色和纹理各特征分量与还原糖含量之间具有高度相关性。[结论]本系统测试结果精度高,耗时短,系统工作稳定,为农田葡萄叶片含糖量的测定提供了有效的检测手段,对提高田间农作物实时测试效率具有重要意义。     

高地隙植保机速度自动控制系统研制

针对当前高地隙植保机自动化程度不高、作业时行驶速度变化较大影响施药质量等问题,设计具备手动、自动切换功能的速度自动控制系统。以雷沃ARBOS高地隙植保机为研究平台,采用机电一体化控制方法对其变速执行机构、速度控制过程与特性进行分析,采用基于比例微分算法的速度控制方法,实时计算并控制速度执行机构的动作,实现行驶速度的自动调节。田间试验表明,高地隙植保机速度自动控制系统能够按照速度指令控制静液压行走驱动系统的输出,在平均行驶速度为0.21、0.83和0.94 m/s时,最大速度控制误差分别为0.05、0.10和0.10 m/s,满足高地隙植保机行驶速度控制的基本要求。     

Colour based detection of volunteer potatoes as weeds in sugar beet fields using machine vision

The possible spread of late blight from volunteer potato plants requires the removal of these plants from arable fields. Because of high labour, energy, and chemical demands, a method of automatic detection and removal is needed. The development and comparison of two colour-based machine vision algorithms for in-field volunteer potato plant detection in two sugar beet fields are discussed. Evaluation of the results showed that both methods gave closely matched results within fields, although large differences exist between the fields. At plant level, in one field up to 97% of the volunteer potato plants were correctly classified. In another field, only 49% of the volunteer plants were correctly identified. The differences between the fields were higher than the differences between the methods used for plant classification.     

基于单片机的施药机速度模拟系统设计

【目的】设计基于单片机的施药机行驶速度模拟系统,为施药机变量控制系统性能试验提供支持。【方法】模拟系统由上位机和下位机两部分组成,下位机以单片机为核心,上位机软件采用C#语言编写,在基于.NET平台上开发,通过上、下位机之间的通信实现对施药机行驶速度的模拟。【结果】施药机的模拟速度为0.6~1.4m/s时,最大相对误差为4.72%,系统能够实现施药机行驶速度的模拟;系统能够输出的行驶速度函数有一次函数、二次函数和三角函数,其响应曲线与理论曲线的相关系数分别为0.992 2和0.969 6和0.995 0。【结论】所设计的施药机行驶速度模拟系统具有较高的测量精度,且操作方便,可以满足施药机变量控制系统性能试验中车速按特定规律精确变化的要求。     

An RFID-based solution for monitoring sprayer movement in an orchard/vineyard

Pesticide application monitoring and long-term data recording in the field is typically the first step in fruit traceability. In a spray monitoring and guiding system, identification of the sprayer movement is a key part of technology. Although Global Navigation Satellite System (GNSS) is a widely used system to obtain location information, in an orchard/vineyard, especially one in which the trees/plants have tall and large canopies, the continuity and stability of the GNSS signal may decrease dramatically and lead to failure of guidance. A Radio Frequency Identification Devices (RFID) solution for identifying sprayer travel was proposed, and a spray monitoring and guiding system was designed based on this solution. In-lab system simulation test and field test results showed that the system could distinguish the travel direction of the sprayer, identify its location in the field, record flow rate information, calculate sprayed volume, and show all the above information on a computer screen in real-time when the RFID reader had successfully registered each RFID card. For the monitoring and guiding system with one antenna on each side, which required the cards and the antennas to be at the same height, the best relative position was found by placing the card parallel to the antenna. The results of tests in the field showed that an improved system with two antennas on each side, which only required the cards to be put in the band with a width of 0.26 m between the centers of the two antennas, worked better with the best antenna angle of 125° when the speed of the sprayer was less than 1.8 m/s.     

Change in agrochemical properties of sod-podzolic soil during long-term fertilization

The characteristics of the long-term use of organic and mineral fertilizers on sod-podzolic soil are revealed. It is shown that the systematic 40-year application of moderate fertilizer doses has a favorable impact on the indices of its potential and effective fertility and ecological balance is maintained in the environment.