基于距离度量学习的棉花品级分类方法研究

由于人工定级的方法存在如效率低、主观性强等诸多弊端,本文提出了1种经济有效的棉花品级分类方法。使用主成分分析法对数据集进行预处理,从而降低特征向量的维度;使用大边界k近邻算法学习得到1个马氏距离度量矩阵,从而实现对棉花图像的分析、特征提取等操作,使用距离度量学习、机器学习的技术来模拟人类的视觉感知;训练k近邻分类器,从而实现棉花品级的自动分类。通过试验证明了本文提出的方法可以有效现实棉花品级分类。     

基于ResNet卷积神经网络的绿茶种类识别模型构建

绿茶是我国种类最多、产量最大的茶类,外形是其分类的重要依据.图像分类是计算机视觉的核心技术之一,但其在茶叶领域的应用较少,茶类识别仍依赖感官审评方法.采集8种常见绿茶(丽水香茶、信阳毛尖、六安瓜片、太平猴魁、安吉白茶、碧螺春、竹叶青和龙井)共1713张图片,基于ResNet卷积神经网络,从识别模型的预测能力、收敛速度、...     

棉花种植方式和密度效应研究

以JX013为材料,在湖南浏阳研究了不同种植密度（18000、36000、54000株/hm2）、不同种植方式（直播、漂浮育苗移栽、营养钵育苗移栽）对棉花生长发育及产量、品质的影响。结果表明：在同一种植方式中,生育期随密度的增加而延长,株高、果枝数、单株成铃数随密度增高而降低,单位面积总铃数、籽棉产量随密度增高而增加;在同一密度下,生育期以直播棉最短,株高、果枝数、单位面积总铃数、籽棉产量以直播棉最大;不同处理对棉花铃重、衣分、衣指、子指、纤维品质影响不显著。     

棉花合理密度的决择分析

引用棉花合理密度的理论依据,分析了当前杂交棉密度过低的成因,同时提出了因生态区域、品种特性、种植方式、肥力水平致单椿可成果节数决择棉花种植密度的方法和因密栽培的配套技术。     

浅谈不同密度对棉花经济效益的影响

通过对湘杂棉8号在不同密度下的经济效益分析,结果表明：各密度处理间的成本差别主要表现在与密度有关的人工费用和种子成本上,密度越大,成本越高,在各处理中以30ooo株,hm^2的收益最高。     

鄂中棉区夏播棉花的密度与产量效应试验

通过对两个棉花品种5个种植密度试验,系统观察了不同密度条件下棉花个体、群体的生长发育与产量建成情况。结果表明：以种植密度75000株/hm2,棉花个体发育比较充分,成铃数在975000个/hm2以上,10月20日吐絮率在80％以上,11月10日前达到95％,皮棉产量水平接近1500 kg/hm2。密度过低时,群体难以达到较高产量;密度过高时,个体发育不充分,结铃部位上移,吐絮期明显推迟,不利于正常收获和作物茬口衔接。     

特早熟地区棉花密度与施肥技术研究

１９９５～１９９６年采用三因素二次饱和Ｄ－最优设计方法，对影响我区特早熟棉花生产的人为可控因子中密度、施纯Ｎ量、Ｐ２Ｏ５量三个因子进行了试验研究。建立了数学模型，提出了实现最高产量的密度、施纯Ｎ量、Ｐ２Ｏ５量的组合结构和达到最高产量密度时施纯Ｎ量、Ｐ２Ｏ５量的经济最佳组合结构，同时进行了氮、磷素化肥投入产出的经济效益分析     

再谈棉花的适宜种植密度

棉花的移栽密度一直是棉花生产上争论的主要栽培指标.随着品种的不断更新、全球气候变暖以及栽培制度的变革,棉花的种植密度也随之改变,现阶段究竟种植多大的棉花密度为适宜,很值得探讨.为此2007年作者开展了不同移栽密度的试验研究,现将试验结果总结如下.     

不同栽培密度对棉花产量及经济性状的影响

在高肥水的栽培条件下。研究了不同栽培密度下单株铃数、单铃重、表分及皮棉产量的变化，并进行关联度分析，并确定各因素与密度之间的关联序。蛄果表明．在12000-57000株／hm^2的栽培密度范围内，随着密度的增加，单株铃数逐渐减少．而单铃重、表分的变化很小，皮棉产量有下降的趋势，在12000株／hm^2栽培密度下皮棉产量最低。在21000株／hm^2的栽培密度下单株铃数最多、单铃重最大、皮棉产量最高。     

Estimation of chlorophyll content in Brassica napus based on unmanned aerial vehicle images

The chlorophyll content has a direct effect on photosynthesis of crops. In order to explore a quick and convenient method for estimating the chlorophyll content of Brassica napus and facilitate efficient crop monitoring, we measured the actual value of chlorophyll with a SPAD-502 chlorophyll detector, and collected aerial images of B. napus with an unmanned aerial vehicle(UAV) carrying a RGB camera in this study. The total number of 270samples collected images were divided into regions according...     

基于TOPSIS法评价无人机喷施脱叶催熟剂的效果

研究无人机喷施不同脱叶催熟剂对棉花的影响,并进行综合评价,为集成棉花轻简化栽培技术提供依据。采用无人机喷施脱吐隆、瑞脱龙,搭配乙烯利,以清水为对照,用方差分析以及多重比较方法分析脱吐隆与乙烯利混剂喷施2次、瑞脱龙与乙烯利混剂喷施2次、脱吐隆与乙烯利单剂各喷施1次、瑞脱龙与乙烯利单剂各喷施1次4个处理对棉花农艺性状、产量、品质的影响,并用基于变异系数权重的逼近理想解排序法（Technique for order preference by similarity to an ideal solution,TOPSIS法）进行综合评价。分析表明, 4个处理间脱叶率、吐絮率差异不显著,但均显著高于清水对照;各处理对产量构成因子及除短纤维指数外的其余品质指标没有显著影响。TOPSIS法的评价结果表明,无人机喷施条件下,各处理的综合评价结果为脱吐隆与乙烯利混剂喷施2次＞脱吐隆与乙烯利单剂各喷施1次＞瑞脱龙与乙烯利单剂各喷施1次＞瑞脱龙与乙烯利混剂喷施2次＞清水对照。可知,无人机喷施脱吐隆与乙烯利混剂2次条件下,棉花11个性状综合表现最优。     

无人机遥感及深度学习在油菜冻害识别中的应用研究

气象灾害是影响我国农作物产量及农业可持续发展的重要因素,低温冻害导致油菜生长发育迟缓和大幅度减产.便捷、精准地识别和评估油菜冻害不仅为精准农田管理提供依据而且对培育抗冻品种有重要意义.本研究借助低空无人机遥感技术,用大疆精灵无人机Phantom 4 Pro V2.0,搭载2000万像素RGB相机,对生长88天正处于越冬...     

基于无人机遥感的花生氮营养反演研究

氮素是影响花生生长发育的重要因素之一,目前传统凯氏定氮法测定步骤繁琐且需要时间较长,而无人 机遥感具有实时、灵活、低成本的特点,因此,为实现对花生氮含量的快速、无损、准确监测,本研究利用大疆精灵4 号无人机搭载的可见光相机,获取不同生育期的可见光影像,运用神经网络算法,建立叶片数字图像彩色信息和叶 片氮含量的关系模型。结果表明,利用数字图像指标作为网络输入向量时,所构建模型的平均绝对偏差为1.5左 右,且以r、g、b(r=R/(R+G+B), g=G/(R+G+B), b=B/(R+G+B))和a, b, c (a=R+G, b=R+B, c=G+B)两种组合参数拟合效果最 好,平均绝对偏差为0.2左右,和真实值相差较小。通过检验发现,两种方法都能准确地预测出花生叶片氮含量,所 构建模型能快速、无损地测定花生植株的肥料状况。     

常温弥雾植保无人机喷施不同剂型吡虫啉防治棉田蚜虫效果

为明确搭载常温弥雾系统的植保无人机（简称为“常温弥雾植保无人机”）喷施不同剂型吡虫啉对棉田蚜虫防治效果（防效）的差异,选择乳油、可湿性粉剂、水分散粒剂和可溶液剂吡虫啉,按照相同有效成分用量42 g·hm－2在山东省临清市棉田喷雾进行苗期蚜虫防治。结果：常温弥雾植保无人机施药,叶片正反面的雾滴密度、雾滴覆盖率在4种剂型间差异均不显著;可湿性粉剂在叶片正反面的单位面积药液沉积量均最少,其中叶片反面的单位面积药液沉积量显著低于其他3种剂型;可湿性粉剂的农药利用率显著低于水分散粒剂和可溶液剂。从4种剂型田间防效看,可溶液剂最好,药后1～7 d防效为68.86%～83.07%,其次是水分散粒剂（药后1～7 d防效为65.34%～80.27%）和乳油（药后1～7 d防效为63.40%～79.18%）,这3种剂型间差异不显著;可湿性粉剂防效显著低于其他剂型,药后3 d为66.98%,药后7 d为58.73%。试验结果表明,采用常温弥雾植保无人机在棉花苗期施药对蚜虫的防效较好,且乳油、水分散粒剂和可溶液剂剂型的吡虫啉防效更佳。     

Droplet deposition and control effect of insecticides sprayed with an unmanned aerial vehicle against plant hoppers

A small unmanned aerial vehicle (UAV) that can spray pesticide with high efficiency and with no damage to crops is required for the timely and effective spraying of small fields and/or those in hilly mountains. The current study aimed to illuminate the influence of spraying parameters, such as operation height and operation velocity, of the UAV on droplet deposition on the rice canopy and protection efficacy against plant hoppers. Droplets of 480 g l⁻¹ chlorpyrifos·(Regent EC) (at a dose of 432 g a.i. ha⁻¹, spray volume rate of approximately 15 l ha⁻¹) were collected using water-sensitive paper, and the coverage rates of the droplets on the rice canopy and lower layer were statistically analyzed. The deposition and distribution of droplets in the late stage of rice growth were closely related to the operational height and velocity of crop spraying as executed by the UAV, further affecting insect control. The spraying parameters for preventing plant hoppers were then optimized. When the spraying height was 1.5 m and the spraying velocity 5 m s⁻¹, the droplet deposition in the lower layer was maximized, and the droplets exhibited the most uniform distribution (CV = 23%). The insecticidal efficacy was 92%–74% from 3 to 10 days after spraying insecticide. Both the insecticidal efficacy and the persistence period were greater than those achieved with a hand lance operated from a stretcher-mounted sprayer (at dose of 432 g a.i. ha⁻¹, spray volume rate of approximately 750 l ha⁻¹), especially on the 5th day, indicating that UAV had a low-volume and highly concentrated spray pattern to enhance the duration of efficacy. This work offers a basis for the optimized design, improved performance, and rational application of UAV.     

助剂对无人机喷施棉花脱叶剂作业效果的影响

采用极飞3WWDZ-15A多旋翼植保机喷施棉花脱叶剂“棉田阔笑”（540 g·L^－1噻苯隆·敌草隆悬浮剂）,通过布置雾滴测试卡研究了雾滴在棉花冠层的沉积分布情况,结合田间脱叶催熟效果调查及棉花纤维品质检测,研究了烷基乙基磺酸盐、农健飞和倍达通3种助剂对棉花脱叶催熟效果、棉花产量主要构成因素和纤维品质指标的影响。结果表明：采用无人机喷施脱叶剂,雾滴沉积分布满足脱叶剂施药要求。添加助剂的3个处理药后30 d脱叶率达到85.53%～100%,显著高于未添加助剂的处理。添加农健飞、倍达通助剂处理的棉花吐絮率分别为66.22%和60.73%,显著优于未添加助剂的处理。助剂对棉花铃重和衣分及纤维品质主要指标无不利影响。     

Prediction of cotton yarn properties using support vector machine

This paper presents a support vector machine (SVM) regression approach to forecast the properties of cotton yarns produced on ring and rotor spinning technologies from the fibre properties measured by HVI and AFIS. Prediction performance of SVM models have been compared against those of the artificial neural network (ANN) models. A k-fold cross validation technique is applied to assess the expected generalization accuracies of both SVM and ANN models. The investigation indicates that the yarn properties can be predicted with a very high degree of accuracy using SVM models and the prediction performance of SVM models are better than that of ANN models.     

Classification of crops and weeds from digital images: A support vector machine approach

In most agricultural systems, one of the major concerns is to reduce the growth of weeds. In most cases, removal of the weed population in agricultural fields involves the application of chemical herbicides, which has had successes in increasing both crop productivity and quality. However, concerns regarding the environmental and economic impacts of excessive herbicide applications have prompted increasing interests in seeking alternative weed control approaches. An automated machine vision system that can distinguish crops and weeds in digital images can be a potentially cost-effective alternative to reduce the excessive use of herbicides. In other words, instead of applying herbicides uniformly on the field, a real-time system can be used by identifying and spraying only the weeds. This paper investigates the use of a machine-learning algorithm called support vector machine (SVM) for the effective classification of crops and weeds in digital images. Our objective is to evaluate if a satisfactory classification rate can be obtained when SVM is used as the classification model in an automated weed control system. In our experiments, a total of fourteen features that characterize crops and weeds in images were tested to find the optimal combination of features that provides the highest classification rate. Analysis of the results reveals that SVM achieves above 97% accuracy over a set of 224 test images. Importantly, there is no misclassification of crops as weeds and vice versa.     

无人机施药防治南疆棉田不同发生程度蚜虫效果及关键时期

依据药剂的田间推荐使用剂量,通过无人机喷施双丙环虫酯可分散液剂、氟啶·啶虫脒水分散粒剂和螺虫·噻嗪酮悬浮剂3种药剂,测定其对不同发生程度棉花蚜虫的防治效果（防效）,为明确无人机施药防治南疆不同发生程度棉花蚜虫的效果和关键时期提供依据。结果显示,在药后3 d、7 d和14 d,3种药剂对棉花蚜虫轻度发生区（0%＜蚜害指数≤25%）的防效均最高,对中度发生区（25%＜蚜害指数≤50%）的防效次之,对极严重发生区（75%＜蚜害指数≤100%）的防效最差。表明随着棉花蚜虫发生程度的加重和3种药剂用药量的增加,对棉花蚜虫的防效却在降低;在棉花蚜虫轻度、中度发生期进行无人机喷药防治,效果好且用药量低。