WO2021035858A1 - 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法 - Google Patents

叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法 Download PDF

Info

Publication number
WO2021035858A1
WO2021035858A1 PCT/CN2019/107983 CN2019107983W WO2021035858A1 WO 2021035858 A1 WO2021035858 A1 WO 2021035858A1 CN 2019107983 W CN2019107983 W CN 2019107983W WO 2021035858 A1 WO2021035858 A1 WO 2021035858A1
Authority
WO
WIPO (PCT)
Prior art keywords
leaf
chlorophyll
leaves
potassium
chlorophyll content
Prior art date
Application number
PCT/CN2019/107983
Other languages
English (en)
French (fr)
Inventor
石吉勇
邹小波
李志华
黄晓玮
郭志明
张文
张迪
李文亭
胡雪桃
孙悦
石海军
史永强
Original Assignee
江苏大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 江苏大学 filed Critical 江苏大学
Priority to GB2018070.9A priority Critical patent/GB2591565B/en
Priority to CH01498/20A priority patent/CH716708B1/de
Publication of WO2021035858A1 publication Critical patent/WO2021035858A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N31/00—Investigating or analysing non-biological materials by the use of the chemical methods specified in the subgroup; Apparatus specially adapted for such methods
    • G01N31/002—Determining nitrogen by transformation into ammonia, e.g. KJELDAHL method
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0098—Plants or trees
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30188—Vegetation; Agriculture

Definitions

  • the invention belongs to the technical field of the diagnosis of crop nutrient element deficiency, and relates to a method for synchronously diagnosing the deficiency of nitrogen, potassium and magnesium in the leaf chlorophyll leaf surface distribution characteristics.
  • Nutrient elements are important components for the synthesis of various organic compounds in the leaves, and participate in various metabolisms during the growth and development of the leaves.
  • the deficiency of nutrient elements often leads to changes in the internal components and external morphology of the leaves.
  • Chlorophyll is one of the basic components of plant leaves. When crops are in a state of nutrient element deficiency, the synthesis and metabolism of chlorophyll and other pigments in the leaves will be hindered, which will lead to corresponding symptoms of nutrient deficiency in the leaves.
  • Nitrogen, potassium and magnesium are essential nutrients during the growth and development of cucumber plants.
  • Relevant studies have shown that the deficiency of nitrogen, potassium and magnesium leads to a decrease in the chlorophyll content of cucumber leaves and chlorophyll color. Therefore, the element deficiency based on chlorophyll content
  • the diagnosis method of deficiency can effectively distinguish the differences between nitrogen-deficient leaves and normal leaves, potassium-deficient leaves and normal leaves, and magnesium-deficient leaves and normal leaves.
  • Nutrient element physical and chemical analysis methods such as Kjeldahl method, atomic absorption spectrometry, etc. can accurately analyze the nitrogen, potassium and magnesium nutrient element content of cucumber leaves, and then realize the simultaneous diagnosis of cucumber leaf nitrogen, potassium and magnesium deficiency, but the nutrient element physical and chemical analysis
  • the diagnosis method requires destruction of the test sample, time-consuming, and complicated operation process.
  • the present invention proposes a synchronous diagnosis method of nitrogen, potassium and magnesium element deficiency based on the characteristics of leaf surface distribution of chlorophyll from the perspective of characterizing the chlorophyll content in the distribution characteristics of nitrogen, potassium and magnesium element deficiency leaves.
  • the method for synchronous diagnosis of nitrogen, potassium and magnesium element deficiency based on the characteristics of leaf chlorophyll distribution specifically includes the following steps:
  • the leaf surface is divided into large areas by the intersection point of the main leaf veins of the leaf and the main inflection point of the leaf contour line, and the divided large area is then divided into several small areas.
  • the method for dividing the large area includes: taking the intersection point of the main leaf veins of the leaf as the origin, the main inflection point a of the leaf contour line as the contour dividing point, and connecting the contour dividing point and the origin to obtain the large area dividing line segment, thereby dividing the cucumber
  • the leaf surface area is divided into a-3 large areas, where a is a positive integer.
  • the specific operation of the method for dividing the small area is as follows: determining n small area dividing points on the large area dividing line segment, and respectively connecting the small area dividing points of two adjacent large areas with lines to form the small area dividing line segment;
  • the a, m and n mentioned are all positive integers.
  • each line segment formed by dividing n small area dividing points on the large area dividing line segment has the same length.
  • the chlorophyll content and leaf surface distribution map of the leaves are sequentially detected; the preset parameters corresponding to all pixels in several small areas in the leaf chlorophyll leaf surface distribution map are sequentially extracted, and the independent variable array X is constructed.
  • the preset parameters include the mean value of the chlorophyll content, the variance of the chlorophyll content, the maximum value of the chlorophyll content, and the minimum value of the chlorophyll content.
  • the specific operation of the method for constructing the independent variable array X is as follows: using the mean value of the chlorophyll content, the variance of the chlorophyll content, the maximum value of the chlorophyll content, and the minimum value of the chlorophyll content corresponding to all the pixels in the m small areas in the chlorophyll leaf surface distribution map of j leaves The value constructs an independent variable array X with j rows ⁇ 4m columns; wherein the m and j are all positive integers.
  • the dependent variable array Y is used to record the nutrient status of nitrogen, potassium and magnesium of j leaves, including: using nutrient element physical and chemical analysis methods to sequentially detect the nutrient status of nitrogen, potassium and magnesium of j leaves, and construct j rows ⁇ 3 columns.
  • the first column of the dependent variable array Y is used to record the nutrient status of the nitrogen element, a value of 0 represents that the corresponding leaf nitrogen is normal, and a value of 1 represents the corresponding leaf nitrogen deficiency;
  • the dependent variable array Y The second column is used to record the nutritional status of potassium. When the value is 0, the corresponding leaf potassium is normal, and when the value is 1, the corresponding leaf potassium is deficient; the third column of the dependent variable array Y is used to record the magnesium nutrition If the value is 0, it means that the magnesium element of the corresponding leaf is normal, and when the value is 1, it means that the magnesium element of the corresponding leaf is deficient.
  • the preset parameters include the mean value of the chlorophyll content, the variance of the chlorophyll content, the maximum value of the chlorophyll content, and the minimum value of the chlorophyll content.
  • the cucumber leaf area is divided into several small areas, and the mean and variance of the chlorophyll content at all pixels in each small area are extracted one by one. , Maximum and minimum values, to achieve the accurate characterization of the chlorophyll distribution characteristics of cucumber leaves; based on the extracted chlorophyll leaf distribution characteristics, a diagnostic model that can simultaneously diagnose the deficiency of nitrogen, potassium and magnesium in cucumber leaves was constructed, and a model based on cucumber was established.
  • the synchronous diagnosis method of nitrogen, potassium and magnesium element deficiency based on the characteristics of leaf chlorophyll distribution overcomes the limitation that the element deficiency diagnosis method based on chlorophyll content cannot simultaneously diagnose the deficiency of nitrogen, potassium and magnesium element in cucumber leaves; with the help of the scheme and construction of the present invention
  • the N, K, and Mg deficiency diagnosis model can quickly and non-destructively extract the leaf surface distribution characteristics of chlorophyll, and realize the efficient diagnosis of leaf N, K, and Mg deficiency.
  • Hyperspectral imaging technology can not only obtain the two-dimensional image information of the sample to be tested, but also obtain the spectral information corresponding to each pixel in the two-dimensional image. Using the sensitivity of the spectral information of the pixel points to the content of the component to be measured, the content of the component to be measured corresponding to each pixel can be analyzed one by one, and the distribution of the content of the component to be measured in the sample space can be visualized.
  • Figure 1 is a schematic diagram of the segmentation of the leaf surface area of cucumber leaves
  • Figure 2 is the leaf surface distribution map of the chlorophyll content of cucumber leaves, where a is the legend and b is the chlorophyll distribution map;
  • Figure 3 is a leaf surface distribution diagram of chlorophyll content of cucumber leaves after region segmentation.
  • Example 1 A synchronous diagnosis method of nitrogen, potassium and magnesium element deficiency based on the characteristics of leaf chlorophyll distribution
  • Segmentation of leaf surface area Taking the intersection point of the main leaf veins of the leaf as the origin, the main inflection point a of the leaf contour line is used as the contour dividing point, and the large area dividing line segment is obtained by connecting the contour dividing point and the origin, so as to divide the cucumber leaf surface
  • Chlorophyll regional distribution feature extraction Using j leaves as training samples, hyperspectral image technology is used to sequentially detect the chlorophyll content leaf surface distribution map of j leaves; the m small areas after segmentation correspond to the chlorophyll content leaf surface distribution map Regions are numbered without repetition; extract the mean value of chlorophyll content, variance of chlorophyll content, maximum value of chlorophyll content, and minimum value of chlorophyll content corresponding to all pixels in m small areas in the chlorophyll leaf surface distribution map of j leaves in sequence.
  • the calculation method of the average value of chlorophyll content is to extract the chlorophyll content corresponding to each pixel in a single small area, and calculate the average value corresponding to all pixels in the small area;
  • the calculation method of the chlorophyll content variance is to extract each pixel in a single small area Corresponding chlorophyll content, and calculate the variance corresponding to all pixels in the small area;
  • the calculation method of the maximum and minimum chlorophyll content is to extract the chlorophyll content corresponding to each pixel in a single small area, and count all the pixels in the small area separately The maximum and minimum values corresponding to the points.
  • the first column of the dependent variable array Y is used to record the nutritional status of nitrogen elements, a value of 0 represents that the corresponding leaf nitrogen is normal, and a value of 1 represents the corresponding leaf nitrogen deficiency; the dependent variable array Y
  • the second column of is used to record the nutritional status of potassium. When the value is 0, the corresponding leaf potassium is normal, and when the value is 1, the corresponding leaf potassium is deficient; the third column of the dependent variable array Y is used to record magnesium Nutritional status, when the value is 0, the corresponding leaf magnesium is normal, and when the value is 1, it represents the magnesium deficiency of the corresponding leaf.
  • Diagnosis of N, K, and Mg deficiency of the tested leaves For q of the tested leaves, use the small area segmentation line, the large area segmentation line and the outer contour line to divide the leaf surface area of each test leaf into m small areas; extract q in turn The average value of the chlorophyll content, the variance of the chlorophyll content, the maximum value of the chlorophyll content, and the minimum value of the chlorophyll content corresponding to all the pixels in the m small areas in the leaf surface distribution map of the tested leaf.
  • the a, m, n, q, and j are all positive integers.
  • Example 2 Synchronous diagnosis of nitrogen, potassium and magnesium deficiency based on the distribution characteristics of chlorophyll of cucumber leaves
  • Chlorophyll regional distribution feature extraction S2. Chlorophyll regional distribution feature extraction:
  • the leaf surface distribution map K i corresponds to the maximum value of the chlorophyll content X_P 3 _i, the ith in the independent variable array X chlorophyll content in leaf lines 79 to 104 as the i-th piece of cucumber leaf chlorophyll content distribution K i corresponding to FIG minimum x_P 4 _i.
  • the second column of the dependent variable array Y is used to record the nutritional status of potassium, a value of 0 means that the potassium element of the corresponding leaf is normal, and a value of 1 means that the potassium element of the corresponding leaf is deficient; the third of the dependent variable array Y The column is used to record the nutritional status of magnesium. A value of 0 means that the magnesium element of the corresponding leaf is normal, and a value of 1 means that the magnesium element of the corresponding leaf is deficient.

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Pathology (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Wood Science & Technology (AREA)
  • Botany (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Molecular Biology (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

一种叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法；首先将待测叶片叶面区域分割，将叶片分割为若干个小区域；然后对叶绿素区域分布特征提取，用高光谱图像技术提取叶片叶绿素叶面分布图中小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值和叶绿素含量最小值；基于此构建氮钾镁亏缺诊断模型；依据模型对待测叶片氮钾镁亏缺诊断。该方法克服了基于叶绿素含量的元素亏缺诊断方法无法同步诊断黄瓜叶片氮钾镁元素亏缺的局限性；可以快速、无损的提取叶绿素叶面分布特征，实现叶片氮钾镁元素亏缺的高效诊断。

Description

叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法 技术领域
本发明属于一种作物营养元素亏缺诊断技术领域，涉及一种叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法。
背景技术
营养元素是叶片合成各种有机化合物的重要成分，参与叶片生长发育过程中的多种代谢，营养元素亏缺往往导致叶片的内部组分和外部形态发生变化。叶绿素是植物叶片的基本组成物质之一，当作物处于营养元素亏缺状态时，叶片中叶绿素等色素的合成与代谢产生障碍，进而导致叶片出现相应的缺素症状。
氮钾镁元素是黄瓜植株生长、发育过程中所必需的大量营养元素，相关研究表明氮钾镁元素亏缺均导致黄瓜叶片叶绿素含量降低并引起叶片颜色褪绿，因此，基于叶绿素含量的元素亏缺诊断方法可以有效区分缺氮叶片与正常叶片、缺钾叶片与正常叶片、缺镁叶片与正常叶片之间的差异，但是难以准确判断缺氮、缺钾与缺镁叶片之间的差异，导致难以高效同步诊断黄瓜叶片氮钾镁元素亏缺。营养元素理化分析方法如凯氏定氮法、原子吸收光谱法等可以精确的分析黄瓜叶片的氮钾镁营养元素含量，进而实现黄瓜叶片氮钾镁元素亏缺的同步诊断，但是营养元素理化分析诊断方法需要破坏检测样本、耗时长、操作过程复杂。
发明内容
本发明从表征叶绿素含量在氮钾镁元素亏缺叶片分布特征的角度出发，提出了一种基于叶片叶绿素叶面分布特征的氮钾镁元素亏缺同步诊断方法。
所述一种基于叶片叶绿素叶面分布特征的氮钾镁元素亏缺同步诊断方法，具体包括如下步骤：
叶片叶面区域分割：
以叶片主叶脉交汇点、叶片轮廓线的主要拐点将叶面分割为大区域，将分割的大区域再分割为若干个小区域。
其中所述大区域的分割方法包括：以叶片主叶脉交汇点为原点，叶片轮廓线的主要拐点a作为轮廓线分割点，以轮廓线分割点和原点连线得到大区域分割线段，从而将黄瓜叶片叶面区域分割为a-3个大区域，其中所述的a为正整数。
其中所述小区域的分割方法具体操作如下：在大区域分割线段上确定n个小区域分割点，分别用线条将相邻两个大区域的各个小区域分割点相连形成小区域分割线段；小区域分割线段、大区域分割线段与外轮廓线将叶片叶面区域分割为m＝(a-3)(n+1)+2个小区域；
其中所述的a、m、n均为正整数。
其中，所述大区域分割线段上n个小区域分割点分割形成的各个线段长度相等。
叶绿素区域分布特征提取：
利用多片叶片作为训练样本，依次检测叶片的叶绿素含量叶面分布图；依次提取叶片叶绿素叶面分布图中若干个小区域中所有像素点对应的预设的参数，构建自变量数组X。
所述预设的参数包括叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值和叶绿素含量最小值。
氮钾镁亏缺诊断模型构建：
依次检测叶片的氮钾镁元素营养状况，构建因变量数组Y；利用叶片对应的自变量数组X、因变量数组Y，建立氮钾镁亏缺诊断模型Y＝F(X)。
其中，所述自变量数组X构建方法具体操作如下：利用j片叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值构建j行×4m列的自变量数组X；其中，所述的m、j均为正整数。
其中所述因变量数组Y用于记录j片叶片的氮钾镁元素营养状况，包括：利用营养元素理化分析方法依次检测j片叶片的氮钾镁元素营养状况，构建j行×3列的因变量数组Y；其中，所述的j为正整数。
其中，所述因变量数组Y的第1列用于记录氮元素营养状况，取值为0时代表对应叶片氮元素正常，取值为1时代表对应叶片氮元素亏缺；因变量数组Y的第2列用于记录钾元素营养状况，取值为0时代表对应叶片钾元素正常，取值为1时代表对应叶片钾元素亏缺；因变量数组Y的第3列用于记录镁元素营养状况，取值为0时代表对应叶片镁元素正常，取值为1时代表对应叶片镁元素亏缺。
待测叶片氮钾镁亏缺诊断：
将待测叶片叶面区域分割为若干个小区域；依次提取待测叶片叶绿素叶面分布图中若干个小区域中所有像素点对应的预设的参数构建待测叶片自变量数组X’；待测叶片自变量数组X’代入氮钾镁亏缺诊断模型Y＝F(X)，计算待测叶片因变量数组Y’＝F(X’)。
所述预设的参数包括叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值和叶绿素含量最小值。
本发明的有益效果：
本发明从表征叶绿素含量在氮钾镁元素亏缺叶片分布特征的角度出发，将黄瓜叶片叶面区域分割为若干个小区域，通过逐一提取每个小区域所有像素点处叶绿素含量的均值、方差、 最大值以及最小值，实现了黄瓜叶片叶绿素叶面分布特征的精确表征；基于提取的叶绿素叶面分布特征，构建了可同步诊断黄瓜叶片氮钾镁元素亏缺的诊断模型，建立了基于黄瓜叶片叶绿素叶面分布特征的氮钾镁元素亏缺同步诊断方法，克服了基于叶绿素含量的元素亏缺诊断方法无法同步诊断黄瓜叶片氮钾镁元素亏缺的局限性；借助本发明方案以及构建的氮钾镁元素亏缺诊断模型，可以快速、无损的提取叶绿素叶面分布特征，实现叶片氮钾镁元素亏缺的高效诊断。
高光谱图像技术既可获取待测样本的二维图像信息，又可获取二维图像中每个像素点对应的光谱信息。利用像素点光谱信息对待测组分含量的敏感性，可逐一解析每个像素点对应的待测组分含量，进而实现待测组分含量在样本空间中的分布可视化。
附图说明
图1为黄瓜叶片叶面区域分割示意图；
图2为黄瓜叶片叶绿素含量叶面分布图，其中a为图例、b为叶绿素分布图；
图3为经过区域分割的黄瓜叶片叶绿素含量叶面分布图。
具体的实施方案
为了使本发明的目的、技术方案和优势更加清楚，使本领域技术人员更好的理解本发明的技术方案，下面将结合本发明的附图和具体实施例对本发明的技术方案更加清楚、完成的描述。显然，所描述的实施例是本发明的一部分实施方式，而不是全部，基于本发明的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施方式，都属于本发明保护的范围。
实施例1：一种基于叶片叶绿素叶面分布特征的氮钾镁元素亏缺同步诊断方法
具体包括如下步骤：
叶片叶面区域分割：以叶片主叶脉交汇点为原点，叶片轮廓线的主要拐点a个作为轮廓线分割点，以轮廓线分割点和原点连线得到大区域分割线段，从而将黄瓜叶片叶面区域分割为a-3个大区域；在大区域分割线段上确定n个小区域分割点，分别用线条将相邻两个大区域的各个小区域分割点相连形成小区域分割线段；小区域分割线段、大区域分割线段与外轮廓线将叶片叶面区域分割为m＝(a-3)(n+1)+2个小区域；其中所述大区域分割线段上n个小区域分割点分割形成的各个线段长度相等。
叶绿素区域分布特征提取：利用j片叶片作为训练样本，用高光谱图像技术依次检测j片叶片的叶绿素含量叶面分布图；将分割后的m个小区域在叶绿素含量叶面分布图上对应的区域用数字进行无重复编号；依次提取j片叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值和叶绿素含量最小值。其中 叶绿素含量均值的计算方式为提取单个小区域中各个像素点对应的叶绿素含量，并计算该小区域中所有像素点对应的平均值；叶绿素含量方差的计算方式为提取单个小区域中各个像素点对应的叶绿素含量，并计算该小区域中所有像素点对应的方差；叶绿素含量最大值及最小值的计算方式为提取单个小区域中各个像素点对应的叶绿素含量，分别统计该小区域中所有像素点对应的最大值和最小值。
氮钾镁亏缺诊断模型构建：利用j片叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值构建j行×4m列的自变量数组X；利用营养元素理化分析方法依次检测j片叶片的氮钾镁元素营养状况，构建j行×3列的因变量数组Y用于记录j片叶片的氮钾镁元素营养状况；利用j片叶片对应的自变量数组X、因变量数组Y，结合K-近邻模式识别算法建立氮钾镁亏缺诊断模型Y＝F(X)。
其中，所述的因变量数组Y的第1列用于记录氮元素营养状况，取值为0时代表对应叶片氮元素正常，取值为1时代表对应叶片氮元素亏缺；因变量数组Y的第2列用于记录钾元素营养状况，取值为0时代表对应叶片钾元素正常，取值为1时代表对应叶片钾元素亏缺；因变量数组Y的第3列用于记录镁元素营养状况，取值为0时代表对应叶片镁元素正常，取值为1时代表对应叶片镁元素亏缺。
待测叶片氮钾镁亏缺诊断：对q片待测叶片，利用小区域分割线段、大区域分割线段与外轮廓线将每一片待测叶片叶面区域分割为m个小区域；依次提取q片待测叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值构建q行×4m列的待测叶片自变量数组X’；待测叶片自变量数组X’代入氮钾镁亏缺诊断模型Y＝F(X)，计算q行×3列待测叶片因变量数组Y’＝F(X’)，其中第u片待测叶片的氮钾镁元素营养状况由待测叶片因变量数组Y’的第u行取值Y’ u决定。
其中，所述的a、m、n、q、j均为正整数。
实施例2：基于黄瓜叶片叶绿素叶面分布特征的氮钾镁元素亏缺同步诊断
包含黄瓜叶片叶面区域分割、叶绿素区域分布特征提取、氮钾镁亏缺诊断模型构建、待测黄瓜叶片氮钾镁亏缺诊断四个步骤。
S1.黄瓜叶片叶面区域分割：
(1)以黄瓜叶片主叶脉交汇点为O点，以黄瓜叶片轮廓线形成的封闭区域为黄瓜叶片叶面待分割区域，依次选择黄瓜叶片轮廓线的九个主要拐点A、B、C、D、E、F、G、H、I作为轮廓线分割点，其中轮廓线分割点E为黄瓜叶片最长主叶脉末端处的叶尖；用线条分别以轮廓线分割点B、C、D、E、F、G、H为起点，以O点为终点作连线，得到大区域分割线段 BO、CO、DO、EO、FO、GO、HO；从而将黄瓜叶片叶面区域分割为OAB、OBC、OCD、ODE、OEF、OFG、OGH、OHI八个大区域，如图1所示。
(2)在大区域分割线段BO上确定3(即n＝3)个小区域分割点B 1、B 2、B 3，使得线段BB 1、B 1B 2、B 2B 3、B 3O长度相等；在大区域分割线段CO上确定3个小区域分割点C 1、C 2、C 3，使得线段CC 1、C 1C 2、C 2C 3、C 3O长度相等；在大区域分割线段DO上确定3个小区域分割点D 1、D 2、D 3，使得线段DD 1、D 1D 2、D 2D 3、D 3O长度相等；在大区域分割线段EO上确定3个小区域分割点E 1、E 2、E 3，使得线段EE 1、E 1E 2、E 2E 3、E 3O长度相等；在大区域分割线段FO上确定3个小区域分割点F 1、F 2、F 3，使得线段FF 1、F 1F 2、F 2F 3、F 3O长度相等；在大区域分割线段GO上确定3个小区域分割点G 1、G 2、G 3，使得线段GG 1、G 1G 2、G 2G 3、G 3O长度相等；在大区域分割线段HO上确定3个小区域分割点H 1、H 2、H 3，使得线段HH 1、H 1H 2、H 2H 3、H 3O长度相等。
(3)分别用线条将小区域分割点B 1C 1、B 2C 2、B 3C 3，C 1D 1、C 2D 2、C 3D 3，D 1E 1、D 2E 2、D 3E 3，E 1F 1、E 2F 2、E 3F 3，F 1G 1、F 2G 2、F 3G 3，G 1H 1、G 2H 2、G 3H 3相连而形成小区域分割线段；小区域分割线段、大区域分割线段与外轮廓线将黄瓜叶片叶面区域分割为26个小区域；
S2.叶绿素区域分布特征提取：
(1)利用无土栽培方式培育60片黄瓜叶片作为训练样本，用高光谱图像技术(ImSpector V10E,Spectral Imaging Ltd.,Oulu,Finland)依次检测60(即j＝60)片黄瓜叶片的叶绿素含量叶面分布图K 1，K 2，……，K 59，K 60；其中单片黄瓜叶片的叶绿素含量叶面分布图如图2所示，其中叶绿素分布图中像素点的灰度值代表了该像素点处的叶绿素含量值，像素点的灰度值越低，该像素点对应的叶绿素含量越低；像素点的灰度值越高，该像素点对应的叶绿素含量越高；像素点灰度值与叶绿素含量值的对应关系如图2中图例a所示。
(2)将26个小区域在叶绿素含量叶面分布图上对应的区域进行无重复编号，经过区域分割的黄瓜叶片叶绿素含量叶面分布如图3所示，其中26个小区域对应的编号为图3中各小区域内括号中的阿拉伯数字。
(3)依次提取60片黄瓜叶片叶绿素叶面分布图K 1，K 2，……，K 59，K 60中26个小区域中所有像素点对应的叶绿素含量均值X_P 1_1，X_P 1_2，……，X_P 1_59，X_P 1_60，其中第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量均值X_P 1_i＝[X_P 1_i_1，X_P 1_i_2，……，X_P 1_i_25，X_P 1_i_26]，X_P 1_i_v为第i片黄瓜叶片内第v个小区域内所有像素点对应的叶绿素含量均值，且i∈{1，2，……，59，60}，v∈{1，2，……，25，26}。
(4)依次提取60片黄瓜叶片叶绿素叶面分布图K 1，K 2，……，K 59，K 60中26个小区域中所有像素点对应的叶绿素含量方差X_P 2_1，X_P 2_2，……，X_P 2_59，X_P 2_60，其中 第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量方差X_P 2_i＝[X_P 2_i_1，X_P 2_i_2，……，X_P 2_i_25，X_P 2_i_26]，X_P 2_i_v为第i片黄瓜叶片内第v个小区域内所有像素点对应的叶绿素含量方差，且i∈{1，2，……，59，60}，v∈{1，2，……，25，26}。
(5)依次提取60片黄瓜叶片叶绿素叶面分布图K 1，K 2，……，K 59，K 60中26个小区域中所有像素点对应的叶绿素含量最大值X_P 3_1，X_P 3_2，……，X_P 3_59，X_P 3_60，其中第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量最大值X_P 3_i＝[X_P 3_i_1，X_P 3_i_2，……，X_P 3_i_25，X_P 3_i_26]，X_P 3_i_v为第i片黄瓜叶片内第v个小区域内所有像素点对应的叶绿素含量最大值，且i∈{1，2，……，59，60}，v∈{1，2，……，25，26}。
(6)依次提取60片黄瓜叶片叶绿素叶面分布图K 1，K 2，……，K 59，K 60中26个小区域中所有像素点对应的叶绿素含量最小值X_P 4_1，X_P 4_2，……，X_P 4_59，X_P 4_60，其中第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量最小值X_P 4_i＝[X_P 4_i_1，X_P 4_i_2，……，X_P 4_i_25，X_P 4_i_26]，X_P 4_i_v为第i片黄瓜叶片内第v个小区域内所有像素点对应的叶绿素含量最小值，且i∈{1，2，……，59，60}，v∈{1，2，……，25，26}。
S3.氮钾镁亏缺诊断模型构建：
(1)依次利用60片黄瓜叶片叶绿素叶面分布图K 1，K 2，……，K 59，K 60中26个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值[X_P 1_1，X_P 2_1，X_P 3_1，X_P 4_1]，[X_P 1_2，X_P 2_2，X_P 3_2，X_P 4_2]，……，[X_P 1_59，X_P 2_59，X_P 3_59，X_P 4_59]，[X_P 1_60，X_P 2_60，X_P 3_60，X_P 4_60]构建60行×[26个小区域×4个参数(叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值)]行，即60行×104列的自变量数组X；其中自变量数组X中第i行第1列到26列为第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量均值X_P 1_i，自变量数组X中第i行第27列到52列为第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量方差X_P 2_i，自变量数组X中第i行第53列到78列为第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量最大值X_P 3_i，自变量数组X中第i行第79列到104列为第i片黄瓜叶片的叶绿素含量叶面分布图K i对应的叶绿素含量最小值X_P 4_i。
(2)利用营养元素理化分析方法(原子吸收光谱法、凯氏定氮法)依次检测60片黄瓜叶片的氮钾镁元素营养状况，构建60行×3列的因变量数组Y用于记录60片黄瓜叶片的氮钾镁元素营养状况，因变量数组Y的第1列用于记录氮元素营养状况，取值为0时代表对应叶片氮元素正常，取值为1时代表对应叶片氮元素亏缺；因变量数组Y的第2列用于记录钾元素营养状况，取值为0时代表对应叶片钾元素正常，取值为1时代表对应叶片钾元素亏缺；因变量数组Y的第3列用于记录镁元素营养状况，取值为0时代表对应叶片镁元素正常，取 值为1时代表对应叶片镁元素亏缺。
如第i片黄瓜叶片为氮钾镁元素均亏缺时，因变量数组Y的第i行Y i＝[1 1 1]；当第i片黄瓜叶片为氮钾元素亏缺而镁元素正常时，因变量数组Y的第i行Y i＝[1 1 0]；当第i片黄瓜叶片为氮镁元素亏缺而钾元素正常时，因变量数组Y的第i行Y i＝[1 0 1]；当第i片黄瓜叶片为钾镁元素亏缺而氮元素正常时，因变量数组Y的第i行Y i＝[0 1 1]；当第i片黄瓜叶片为氮元素亏缺而钾镁元素正常时，Y i＝[1 0 0]；当第i片黄瓜叶片为钾元素亏缺而氮镁元素正常时，因变量数组Y的第i行Y i＝[0 1 0]；当第i片黄瓜叶片为镁元素亏缺而氮钾元素正常时，因变量数组Y的第i行Y i＝[0 0 1]；当第i片黄瓜叶片为氮钾镁元素均正常时，因变量数组Y的第i行Y i＝[0 0 0]。
(3)利用60片黄瓜叶片对应的自变量数组X、因变量数组Y，结合K-近邻模式识别算法建立氮钾镁亏缺诊断模型Y＝F(X)。
实施例3：待测黄瓜叶片氮钾镁亏缺诊断
(1)按照实施例2步骤S1描述的方法，对10(即q＝10)片待测黄瓜叶片，利用小区域分割线段、大区域分割线段与外轮廓线将每一片待测黄瓜叶片叶面区域分割为26个小区域；
(2)按照实施例2步骤S2及S3描述的方法，依次提取10片待测黄瓜叶片叶绿素叶面分布图中26个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值[X’_P 1_1，X’_P 2_1，X’_P 3_1，X’_P 4_1]，[X’_P 1_2，X’_P 2_2，X’_P 3_2，X’_P 4_2]，……，[X’_P 1_9，X’_P 2_9，X’_P 3_9，X’_P 4_9]，[X’_P 1_10，X’_P 2_10，X’_P 3_10，X’_P 4_10]构建10行×104列的待测叶片自变量数组X’；其中第u片待测黄瓜叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值为[X’_P 1_u，X’_P 2_u，X’_P 3_u，X’_P 4_u]，其中u＝1，2，……，9，10。
(3)待测叶片自变量数组X’代入氮钾镁亏缺诊断模型Y＝F(X)，计算10行×3列待测叶片因变量数组Y’＝F(X’)，其中第u片待测叶片的氮钾镁元素营养状况由待测叶片因变量数组Y’的第u行取值Y’ u决定；若Y’ u的第1列取值为0时代表第u片待测叶片氮元素正常，Y’ u的第1列取值为1时代表第u片待测叶片氮元素亏缺；若Y’ u的第2列取值为0时代表第u片待测叶片钾元素正常，Y’ u的第2列取值为1时代表第u片待测叶片钾元素亏缺；若Y’ u的第3列取值为0时代表第u片待测叶片镁元素正常，Y’ u的第3列取值为1时代表第u片待测叶片镁元素亏缺。
表1.待测叶片氮钾镁元素亏缺同步诊断结果
Figure PCTCN2019107983-appb-000001

Claims (8)

  1. 一种叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法，其特征在于，包括如下步骤：
    叶片叶面区域分割：以叶片主叶脉交汇点、叶片轮廓线的主要拐点将叶面分割为大区域，将分割的大区域再分割为若干个小区域；
    叶绿素区域分布特征提取：利用多片叶片作为训练样本，依次检测叶片的叶绿素含量叶面分布图；依次提取叶片叶绿素叶面分布图中若干个小区域中所有像素点对应的预设的参数，构建自变量数组X；
    氮钾镁亏缺诊断模型构建：依次检测叶片的氮钾镁元素营养状况，构建因变量数组Y；利用叶片对应的自变量数组X、因变量数组Y，建立氮钾镁亏缺诊断模型Y＝F(X)；
    待测叶片氮钾镁亏缺诊断：将待测叶片叶面区域分割为若干个小区域；依次提取待测叶片叶绿素叶面分布图中若干个小区域中所有像素点对应的预设的参数构建待测叶片自变量数组X’；待测叶片自变量数组X’代入氮钾镁亏缺诊断模型Y＝F(X)，计算待测叶片因变量数组Y’＝F(X’)。
  2. 根据权利要求1所述的方法，其特征在于，所述大区域的分割方法包括：
    以叶片主叶脉交汇点为原点，叶片轮廓线的主要拐点a作为轮廓线分割点，以轮廓线分割点和原点连线得到大区域分割线段，从而将黄瓜叶片叶面区域分割为a-3个大区域，其中所述的a为正整数。
  3. 根据权利要求2所述的方法，其特征在于，所述小区域的分割方法包括：
    在大区域分割线段上确定n个小区域分割点，分别用线条将相邻两个大区域的各个小区域分割点相连形成小区域分割线段；小区域分割线段、大区域分割线段与外轮廓线将叶片叶面区域分割为m＝(a-3)(n+1)+2个小区域；
    其中所述的a、m、n均为正整数。
  4. 根据权利要求3所述的方法，其特征在于，所述大区域分割线段上n个小区域分割点分割形成的各个线段长度相等。
  5. 根据权利要求1所述的方法，其特征在于，所述预设的参数包括叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值。
  6. 根据权利要求1所述的方法，其特征在于，
    所述自变量数组X构建方法具体操作如下：利用j片叶片叶绿素叶面分布图中m个小区域中所有像素点对应的叶绿素含量均值、叶绿素含量方差、叶绿素含量最大值、叶绿素含量最小值构建j行×4m列的自变量数组X；其中，所述的m、j均为正整数。
  7. 根据权利要求1所述方法，其特征在于，所述因变量数组Y用于记录j片叶片的氮钾镁元 素营养状况，包括：
    利用营养元素理化分析方法依次检测j片叶片的氮钾镁元素营养状况，构建j行×3列的因变量数组Y；其中，所述的j为正整数。
  8. 根据权利要求7所述的方法，其特征在于，所述因变量数组Y的第1列用于记录氮元素营养状况，取值为0时代表对应叶片氮元素正常，取值为1时代表对应叶片氮元素亏缺；因变量数组Y的第2列用于记录钾元素营养状况，取值为0时代表对应叶片钾元素正常，取值为1时代表对应叶片钾元素亏缺；因变量数组Y的第3列用于记录镁元素营养状况，取值为0时代表对应叶片镁元素正常，取值为1时代表对应叶片镁元素亏缺。
PCT/CN2019/107983 2019-08-26 2019-09-26 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法 WO2021035858A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GB2018070.9A GB2591565B (en) 2019-08-26 2019-09-26 Method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on leaf surface
CH01498/20A CH716708B1 (de) 2019-08-26 2019-09-26 Methode zur Diagnose von Stickstoff, Kalium und Magnesiummangel in Pflanzen basierend auf den Verteilungseigenschaften von Blattchlorophyll auf der Blattoberfläche.

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910789336.3 2019-08-26
CN201910789336.3A CN110631995B (zh) 2019-08-26 2019-08-26 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法

Publications (1)

Publication Number Publication Date
WO2021035858A1 true WO2021035858A1 (zh) 2021-03-04

Family

ID=68969067

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/107983 WO2021035858A1 (zh) 2019-08-26 2019-09-26 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法

Country Status (4)

Country Link
CN (1) CN110631995B (zh)
CH (1) CH716708B1 (zh)
GB (1) GB2591565B (zh)
WO (1) WO2021035858A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114486761A (zh) * 2022-01-24 2022-05-13 云南省热带作物科学研究所 一种橡胶树叶片镁含量快速估算方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110631995B (zh) * 2019-08-26 2021-09-10 江苏大学 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法
CN111398198A (zh) * 2020-04-29 2020-07-10 中国农业大学 一种小麦籽粒微量元素快速无损检测方法

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865926A (zh) * 2006-04-30 2006-11-22 武汉大学 便携式植物叶片色素检测仪
CN101382488A (zh) * 2008-10-14 2009-03-11 江苏吟春碧芽茶叶研究所有限公司 利用可见-近红外漫反射光谱技术检测茶鲜叶氮含量的方法
CN101692037A (zh) * 2009-09-08 2010-04-07 江苏大学 高光谱图像和独立分量分析植物叶面叶绿素分布的方法
CN101915738A (zh) * 2010-06-23 2010-12-15 江苏大学 基于高光谱成像技术的茶树营养信息快速探测方法及装置
US20120123681A1 (en) * 2008-12-15 2012-05-17 Empresa Brasilera De Pesquisa Agropecuaria - Embrapa Method, apparatus and system for diagnosis of stress and disease in higher plants
CN103868891A (zh) * 2014-03-12 2014-06-18 中国农业科学院油料作物研究所 一种油菜叶片氮素营养快速诊断及推荐追氮的方法
CN105486669A (zh) * 2016-01-12 2016-04-13 丽水学院 一种植物必需营养元素亏缺的叶绿素荧光诊断方法
CN105675821A (zh) * 2016-02-21 2016-06-15 南京农业大学 一种作物氮素营养无损诊断的图像评价指标的建立方法
CN110631995A (zh) * 2019-08-26 2019-12-31 江苏大学 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
UA32191U (uk) * 2007-12-13 2008-05-12 Yuriev Inst Of Plant Science O Спосіб обліку ураженості зернових та зернобобових культур листовими хворобами
CN110148146B (zh) * 2019-05-24 2021-03-02 重庆大学 一种利用合成数据的植物叶片分割方法及系统

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865926A (zh) * 2006-04-30 2006-11-22 武汉大学 便携式植物叶片色素检测仪
CN101382488A (zh) * 2008-10-14 2009-03-11 江苏吟春碧芽茶叶研究所有限公司 利用可见-近红外漫反射光谱技术检测茶鲜叶氮含量的方法
US20120123681A1 (en) * 2008-12-15 2012-05-17 Empresa Brasilera De Pesquisa Agropecuaria - Embrapa Method, apparatus and system for diagnosis of stress and disease in higher plants
CN101692037A (zh) * 2009-09-08 2010-04-07 江苏大学 高光谱图像和独立分量分析植物叶面叶绿素分布的方法
CN101915738A (zh) * 2010-06-23 2010-12-15 江苏大学 基于高光谱成像技术的茶树营养信息快速探测方法及装置
CN103868891A (zh) * 2014-03-12 2014-06-18 中国农业科学院油料作物研究所 一种油菜叶片氮素营养快速诊断及推荐追氮的方法
CN105486669A (zh) * 2016-01-12 2016-04-13 丽水学院 一种植物必需营养元素亏缺的叶绿素荧光诊断方法
CN105675821A (zh) * 2016-02-21 2016-06-15 南京农业大学 一种作物氮素营养无损诊断的图像评价指标的建立方法
CN110631995A (zh) * 2019-08-26 2019-12-31 江苏大学 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
SHI JIYONG , LI WENTING ,GUO ZHIMING ,HUANG XIAOWEI , LI ZHIHUA ,ZOU XIAOBO: "Nondestructive Diagnostics of Nitrogen and Potassium Deficiencies Based on Chlorophyll Distribution Features of Cucumber Leaves", TRANSACTION OF THE CHINESE SOCIETY FOR AGRICULTURAL MACHINERY, vol. 50, no. 8, 22 May 2019 (2019-05-22), pages 264 - 269, XP055786095, ISSN: 1000-1298, DOI: 10.6041/j.issn.1000-1298.2019.08.029 *
SHI JIYONG , LI WENTING . HU XUETAO , HUANG XIAWEI , LI ZHIHAU , GUO ZHIMING , ZOU XIAOBO: "Diagnosis of Nitrogen and Magnesium Deficiencies Based on Chlorophyll Distribution Features of Cucumber Leaf", TRANSACTIONS OF THE CHINESE SOCIETY OF AGRICULTURAL ENGINEERING, vol. 35, no. 13, 8 July 2019 (2019-07-08), pages 170 - 176, XP055786085, ISSN: 1002-6819, DOI: 10.11975/j.issn.1002-6819.2019.13.019 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114486761A (zh) * 2022-01-24 2022-05-13 云南省热带作物科学研究所 一种橡胶树叶片镁含量快速估算方法
CN114486761B (zh) * 2022-01-24 2024-04-12 云南省热带作物科学研究所 一种橡胶树叶片镁含量快速估算方法

Also Published As

Publication number Publication date
CN110631995A (zh) 2019-12-31
GB2591565A (en) 2021-08-04
GB2591565B (en) 2022-10-12
GB202018070D0 (en) 2020-12-30
GB2591565A8 (en) 2021-08-11
CN110631995B (zh) 2021-09-10
CH716708B1 (de) 2022-05-13

Similar Documents

Publication Publication Date Title
WO2021035858A1 (zh) 叶片叶绿素叶面分布特征同步诊断氮钾镁元素亏缺的方法
CN102495005B (zh) 高光谱图像技术诊断作物水分亏缺的方法
CN105224960B (zh) 基于聚类算法的玉米种子高光谱图像分类识别模型更新方法
Tu et al. A non-destructive and highly efficient model for detecting the genuineness of maize variety'JINGKE 968′ using machine vision combined with deep learning
Huang et al. Rice panicle length measuring system based on dual-camera imaging
CN104680524A (zh) 一种叶类蔬菜病害诊断方法
Shu et al. Improving the estimation accuracy of SPAD values for maize leaves by removing UAV hyperspectral image backgrounds
CN110265119A (zh) 骨龄评估与身高预测模型、其系统及其预测方法
US11461899B1 (en) Method for detecting infection stage of anthracnose pathogenic with pre-analysis capacity
CN103940748A (zh) 基于高光谱技术的柑橘冠层含氮量预测与可视化的方法
CN105067532A (zh) 一种鉴别油菜菌核病和灰霉病早期病斑的方法
Qiu et al. Field estimation of maize plant height at jointing stage using an RGB-D camera
Yang et al. A synthetic datasets based instance segmentation network for High-throughput soybean pods phenotype investigation
CN110610438B (zh) 一种农作物冠层叶柄夹角计算方法及系统
González et al. MyROOT 2.0: An automatic tool for high throughput and accurate primary root length measurement
CN116229265A (zh) 一种自动无损提取大豆植株表型的方法
Shi et al. Characterization of invisible symptoms caused by early phosphorus deficiency in cucumber plants using near-infrared hyperspectral imaging technology
Zhou et al. Development of an automated plant phenotyping system for evaluation of salt tolerance in soybean
Tu et al. AIseed: An automated image analysis software for high-throughput phenotyping and quality non-destructive testing of individual plant seeds
Wang et al. Combining vegetation, color, and texture indices with hyperspectral parameters using machine-learning methods to estimate nitrogen concentration in rice stems and leaves
CN105046229B (zh) 一种农作物行的识别方法及装置
CN111562273A (zh) 基于高光谱的鱼水射流除鳞轻微损伤可视化方法
He et al. A binocular stereovision system for transplant growth variables analysis
CN111932551B (zh) 一种水稻插秧机的漏插率检测方法
Zhong-zhi et al. Counting ear rows in maize using image process method

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 202018070

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20190926

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19943063

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19943063

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19943063

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27/10/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19943063

Country of ref document: EP

Kind code of ref document: A1