Fuzzy logic control of a multispectral imaging sensor for in-field plant sensing

The development of an in-field plant sensing system for a site-specific application can protect the environment from excessive chemicals and save management cost while maintaining productivity. A multi-spectral imaging sensor has been introduced and widely used for in-field plant sensing. In order for a robust performance of the spectral imaging sensor under changes in ambient illumination, image quality must be maintained for proper spectral image analysis. Image formation that is affected by camera parameters was identified, and a controller was developed to compensate varying image intensity and to obtain the desired image quality. A fuzzy logic control algorithm was applied to automatically adjust the camera exposure and gain to control image brightness within a targeted gray level. Slow convergence and oscillation were regulated by dynamic membership functions with different weights in each image channel. Images affected by illumination disturbance quickly converged into a desired brightness image within a maximum of five iterations over the entire range of camera gains in all three spectral image channels. An application of in-field plant sensing using the fuzzy logic image controller was evaluated on corn crops for nitrogen detection. The normalized spectral response of the sensor was inversely correlated to a chlorophyll meter with −0.93 and −0.88 in red and green channels, respectively. The development of an image quality controller using fuzzy logic enhanced the reliable performance of the in-field plant sensing system.     

面向作物表型分析的大豆植株叶片语义重建

为解决三维扫描仪、多视图数据获取的三维点云因缺少语义信息导致难以从点云上判别植株器官部位问题,提出一种二维先验语义嵌入的大豆植株叶片三维语义建模方法：首先,基于Mask R-CNN模型对大豆叶片进行语义分割;然后,对分割结果和多视图数据进行立体重建融合学习,实现大豆植株叶片二维语义到三维叶片点云迁移,获得植株叶片点云语义信息,进而建立植株叶片三维语义模型。通过多组盆栽大豆植株试验对该模型进行验证,提取叶长和叶宽与人工实测数据进行对比分析,叶长和叶宽均方误差分别为2.53和1.52 mm,决定系数分别为0.97和0.89。结果表明,该方法能够便捷、精准地构建植株叶片三维语义模型。     

大白菜小株采种技术要点

本文主要介绍了利用大白菜自交不亲和系繁殖的纯度高、整齐度好的优良大白菜杂交种是获得丰产的关键，大白菜自交不亲和系主要是通过小株采种利用蕾期人工授粉的方法繁殖。     

Carbon dioxide compensation points in related plant species

Both high and low C0(2) compensation concentrations were found in the plant genera-Panicum, Cyperus, and Euphorbia. Within each genus, however, high and low compensations were found in different subgenera. Thus, they may not be genetically closely related. No significant differences in CO(2) compensation were found among 100 genetic lines of Triticum aestivum L. or among 20 lines of Hordeum vulgare L.     

Plant growth parameter estimation from sparse 3D reconstruction based on highly-textured feature points

Crop canopy spatial parameters are indicative of plant phenological growth stage and physiological condition, and their estimation is therefore of great interest for modeling and precision agriculture practices. Rapid increases in computing power have made stereovision models an attractive alternative to common single-image-based 2D methods, by allowing detailed estimation of the plant’s growth parameters regardless of imaging conditions. Models that have been proposed thus far are still limited in their application because of sensitivity to outdoor illumination conditions and the inherent difficulty in modeling complex plant shapes using only radiometric information. Assuming that not all of the plant-related pixels are essential for growth estimation, this study proposes a 3D reconstruction model that focuses on selected salient features on the plant surface, which are sufficient for obtaining growth characteristics. In addition, by introducing a hue-invariant model, the proposed algorithm shows robustness to diverse outdoor illumination conditions. The algorithm was tested under greenhouse and field conditions on corn, cotton, sunflower, tomato and black nightshade plants, from young seedlings to fully developed plant growth stages, and accurately estimated height (error ~4.5 %) and leaf cover area (error ~5 %). Furthermore, a strong correlation (r² ~0.92) was found between the plant’s estimated volume and measured biomass, yielding an accurate biomass estimator in the validation tests (error ~4.5 %). This estimation ability remained stable while applying the model on plants with varying densities (overlapping leaves) and imaging setups where the standard 2D based analyses failed, thus showing the 3D modeling contribution to robust growth estimation models.     

3D LiDAR感知的植物行信息提取方法与试验

目的 针对林间或冠层下等卫星信号严重遮挡的区域,提出一种面向农业机器人导航环境感知的低成本3D激光雷达(LiDAR)点云信息处理与植物行估计方法。方法 利用直通滤波器滤除感兴趣区域外的目标无关点;提出均值漂移聚类、扫描区域自适应的方法分割每棵植物主干,垂直投影主干点云估算中心点;利用最小二乘法拟合主干中心,估计植物行。分别在开阔地的仿真果园与水杉树林进行模拟试验与田间试验,以植物行向量与正东方夹角为指标,计算本研究提出的方法识别的植物行信息与GNSS卫星天线定位测得的植物行真值间的角度误差。结果 采用提出的3D LiDAR点云信息处理与植物行估计方法,模拟试验和田间试验对植物行识别误差平均值分别为0.79°和1.48°,最小值分别为0.12°和0.88°,最大值分别为1.49°和2.33°。结论 车载3D LiDAR能够有效估计水杉树植物行。该研究丰富了作物识别思路与方法,为无卫星信号覆盖区域的农业机器人无图导航提供了理论依据。     

番茄杂交制种技术要点

酒泉地区是全国最重要的制种基地,番茄制种面积很大,为保证种子的纯度,必须要有规范的制种技术.本文介绍了番茄制种过程中种子的处理,幼苗的管理,整枝的方式,并重点介绍了杂交制种技术,包括去雄、采粉、授粉等的具体操作方式.     

基于X3D的虚拟植物建模与可视化研究

本文在阐述X3D虚拟现实技术的基础上,介绍并分析了基于X3D虚拟植物建模的关键技术和优势,进一步探讨了基于X3D虚拟现实技术植物建模的原理与方法,最后,针对国内外应用现状,提出了应用中出现的问题,并为未来的研究方向进行了展望。     

基于WEB的无人机三维仿地飞行规划在农业植保中的应用

【目的】我国是一个农业大国,农业生产在我国占着举足轻重的地位,无人机植保在农业生产中应用越来越广泛,极大地促进了农业植保的快速发展。建立易操作的智能化平台更有利于无人机植保的快速推广应用。【方法】文章提出了建立基于Web的无人机飞行规划平台,在平台中集成影像和DEM等各类数据,由专业技术人员进行远程三维仿地飞行规划,普通用户只需要在移动飞行规划平台上同步下载规划任务,完成傻瓜式的一键飞行,顺利完成植保任务。【结果】通过实地实验测试,文章中的研究方案可以智能化地完成农业植保任务,显著提高无人机植保的安全性和易用性。【结论】针对现代化农业植保中存在的问题,文章提出的基于WEB的无人机三维仿地飞行规划在农业植保中的应用方案,可以有效解决无人机植保操控复杂、技术程度要求高等问题,提升了农业植保的信息化、智能化程度。     

Ground truth evaluation of computer vision based 3D reconstruction of synthesized and real plant images

There is an increasing interest in using 3D computer vision in precision agriculture. This calls for better quantitative evaluation and understanding of computer vision methods. This paper proposes a test framework using ray traced crop scenes that allows in-depth analysis of algorithm performance and finds the optimal hardware and light source setup before investing in expensive equipment and field experiments. It was expected to be a valuable tool to structure the otherwise incomprehensibly large information space and to see relationships between parameter configurations and crop features. Images of real plants with similar structural categories were annotated manually for comparison in order to validate the performance results on the synthesised images. The results showed substantial correlation between synthesized and real plants, but only when all error sources were accounted for in the simulation. However, there were exceptions where there were structural differences between the virtual plant and the real plant that were unaccounted for by its category. The test framework was evaluated to be a valuable tool to uncover information from complex data structures.     

生物法生产25-羟基维生素D3条件优化

[目的]优化25-羟基维生素D3[25(OH)VD_3]的转化条件,提高25(OH)VD3产量。[方法]通过单因素试验和正交试验对菌株UV-FY-141转化生产25(OH)VD_3的条件进行优化。[结果]确定其最佳发酵培养基:葡萄糖15.00g,蛋白胨20.00g,NaCl5.00g,CaCO_32.00g,FeSO_4·7H-2O0.01g,去离子水1000mL。优化后转化条件:发酵初始pH6.5,发酵温度为28℃,发酵时摇床转速为200r/min,发酵时间为72h。在优化条件下,25(OH)VD3产量由原来的9.460mg/L提高到13.130mg/L,提高了38.79%。[结论]采用优化后的转化条件,可显著提高25(OH)VD_3的产量。     

绞股蓝新品种恩五叶蜜的特性及栽培要点

利用湖北的绞股蓝品种资源 ,经过 10a的品种选育、区域示范 ,于国内首先选育了有效成分和营养成分含量高、特征口感清凉蜜甜、高产抗病虫的新品种“恩五叶蜜” ,并研究了它的品种特性和绿色产品栽培要点。     

三维轮廓匹配的多尺度技术

采用多尺度分析技术实现三维轮廓曲线匹配.三维轮廓曲线通过不同尺度的Gaussian函数滤波和等距重采样,将曲率和挠率的乘积为局部极大值的点作为轮廓曲线的特征点,利用特征点将轮廓分段,对轮廓曲线进行Fourier变换得到Fourier描述符;选择Fourier描述符的低频分量构成三维轮廓曲线的特征矢量,通过比较特征矢量决定2条轮廓是否相似;在2条轮廓相似的基础上,实现三维物体轮廓曲线的匹配.结果表明本文提出的算法具有快速、准确、效果好等特点.     

三维表面轮廓的测量技术

简要介绍了用于三维表面轮廓测量的接触式和非接触式两种测量方法的优缺点，重点阐述了实体光栅法、正弦波相位调制法和白先相移干涉法三种非接触式测量方法的原理。提出了用白光相移干涉法进行三维表面轮廓测量应采用的系统结构和算法。     

关于玉米双株高产种植技术要点的思考

目前,在科学技术快速发展情况下,玉米种植技术也得到了提高,其中受到广泛青睐的 就是双株高产技术。因此,本文将对双株高产技术的应用优势进行阐述,并探讨其在玉米种植 中的应用要点,希望可以为相关工作者的研究提供一些帮助。     

基于单目视觉和激光扫描技术的油菜植株模型重建及株型参数测量

分别采用单目视觉和激光扫描技术对2个油菜品种中双6号和华油杂62号的植株进行三维重建,并在重建模型上完成了对株高、叶柄长、叶片长度和叶片面积等4个株型参数的测量。结果表明:使用单目视觉和激光扫描技术的重建结果均能真实地表现油菜植株的整体形态,叶片间无遮挡的中双6号油菜植株效果更好,测量误差在2.00%以内;形态复杂叶片间部分遮挡的华油杂62号油菜植株测量误差在3.00%以内。模型重建试验表明,利用单目视觉和激光扫描技术能够完成复杂植株的模型重建,并实现部分株型参数的测量,可以为作物的遗传育种提供数据支持。     

Stimulation of 24,25-dihydroxyvitamin D3 production by 1,25-dihydroxyvitamin D3

Vitamin D-deficient rats produce [(3)H]1,25-dihydroxyvitamin D(3) from [(3)H]25-hydroxyvitamin D(3) regardless of dietary content of calcium or phosphate. A daily dose of 130 picomoles of 1,25-dihydroxyvitamin D(3) for a period of 5 days reduces production of [(3)H]1,25-dihydroxyvitamin D(3) to essentially zero and stimulates production of [(3)H]24,25-dihydroxyvitamin D(3). A daily dose of 325 picomoles of 25-hydroxyvitamin D(3) has a similar but less dramatic effect. On the other hand, 650 picomoles daily of 24,25-dihydroxyvitamin D(3) given to vitamin D-deficient rats had no effect. Thus it appears that 1,25-dihydroxyvitamin D(3) is an important factor in the regulation of kidney metabolism of 25-hydroxyvitamin D(3).     

玉米生长三维显示模型研究初探

动态显示玉米的生长、发育和产量形成过程,有利栽培管理。本研究主要目的是建立一个基于生长模拟模型的可视化系统,从而反映玉米生长、发育和产量形成的实时动态。有关玉米生长、发育和产量形成的基本算法与品种、环境和生产水平密切相关,其主要来自于现有文献和研究数据。基于生长模型的逐日输出,耦合玉米种子、根、茎、叶和穗等的形态建成和生长规则,从而建立了玉米形态变化的数学模型。通过计算机图形学、Visual C 和OpenGL,本文建立了基于生长模拟模型和三维动画技术的玉米可视化模型系统,其能基本反映玉米生长、发育和产量形成规律,并具有结构简单、界面友好和图像真实等优点。     

动物性食品理化检验学课程的教学改革探讨

针对动物性食品理化检验学教学过程中存在的问题进行探讨,着重论述了该课程在教学内容、教学方法及考核方式上应采取的改革措施,以充分提高学生学习本课程的兴趣和效果。     

面向犁体优化设计的三维CAD系统

研究开发了参数化犁体ＣＡＤ三维（３Ｄ）图形系统（ＰＳＣＡＤ），以辅助犁体优化设计，将３Ｄ概念引入ＣＡＤ，开发３Ｄ绘图与实体造型的三维图像模拟技术，保证了犁体研究与优化过程的直观和透明。该系统采用达到二阶参数连续的犁体曲面，样板曲线通用数学模型和参数造型，较传统建模方法光顺性有大幅度提高，可满足任意复杂及不同型式犁体的设计要求。