GB2591565A - Method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on leaf surface - Google Patents

Method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on leaf surface Download PDF

Info

Publication number
GB2591565A
GB2591565A GB2018070.9A GB202018070A GB2591565A GB 2591565 A GB2591565 A GB 2591565A GB 202018070 A GB202018070 A GB 202018070A GB 2591565 A GB2591565 A GB 2591565A
Authority
GB
United Kingdom
Prior art keywords
leaf
potassium
nitrogen
leaves
chlorophyll
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
GB2018070.9A
Other versions
GB202018070D0 (en
GB2591565B (en
GB2591565A8 (en
Inventor
Shi Jiyong
Zou Xiaobo
Li Zhihua
Huang Xiaowei
Guo Zhiming
Zhang Wen
Zhang Di
Li Wenting
Hu Xuetao
Sun Yue
Shi Haijun
Shi Yongqiang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University
Original Assignee
Jiangsu University
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 Jiangsu University filed Critical Jiangsu University
Publication of GB202018070D0 publication Critical patent/GB202018070D0/en
Publication of GB2591565A publication Critical patent/GB2591565A/en
Publication of GB2591565A8 publication Critical patent/GB2591565A8/en
Application granted granted Critical
Publication of GB2591565B publication Critical patent/GB2591565B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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

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)
  • Molecular Biology (AREA)
  • Quality & Reliability (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

A method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency on the basis of distribution characteristics of leaf chlorophyll on the leaf surface: first, segmenting a leaf surface area of a leaf to be measured into a plurality of small areas; then, extracting regional distribution characteristics of chlorophyll, and extracting chlorophyll content mean values, chlorophyll content variances, chlorophyll content maximum values, and chlorophyll content minimum values corresponding to all pixel points in the small areas in a leaf chlorophyll leaf surface distribution diagram by using a hyperspectral image technology; constructing a nitrogen-potassium-magnesium deficiency diagnosis model on the basis; and diagnosing nitrogen, potassium and magnesium deficiency of said leaf according to the model. According to the method, the limitation that an element deficiency diagnosis method based on chlorophyll content cannot synchronously diagnose the deficiency of nitrogen, potassium and magnesium elements in cucumber leaves is overcome; the distribution characteristics of chlorophyll on the leaf surface can be rapidly extracted in a lossless mode, and the deficiency of nitrogen, potassium and magnesium elements in leaves can be efficiently diagnosed.

Description

METHOD FOR SYNCHRONOUSLY DIAGNOSING NITROGEN, POTASSIUM, AND MAGNESIUM DEFICIENCY BASED ON
CHLOROPHYLL DISTRIBUTION CHARACTERISTICS ON LEAF
SURFACE
Technical Field
The present invention relates to the technical field of nutrient deficiency diagnosis of crops, and in particular, to a method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on a leaf surface.
Background
Nutrients are important for synthesis of organic compounds in leaves, and take part in various types of metabolism during the growth and development of leaves. Nutrient deficiency usually leads to changes in internal components and external morphology of leaves.
Chlorophyll is one of the basic components of plant leaves. When crops are in a state of nutrient deficiency, the synthesis and metabolism of chlorophyll and other pigments in the leaves are hindered, which leads to corresponding nutrient deficiency symptoms in the leaves.
Nitrogen, potassium, and magnesium are essential macronutrients during the growth and development of cucumber plants. Relevant studies show that the deficiency of nitrogen, potassium, or magnesium leads to a decrease in the chlorophyll content of cucumber leaves and causes chlorosis. Therefore, element deficiency diagnosis methods based on the chlorophyll content can effectively distinguish between nitrogen-deficient leaves and normal leaves, potassium-deficient leaves and normal leaves, and magnesium-deficient leaves and normal leaves. However, they can hardly accurately distinguish between nitrogen-deficient, potassium-deficient, and magnesium-deficient leaves, and thereby, it is difficult to efficiently and synchronously diagnose the nitrogen, potassium, and magnesium deficiency in cucumber leaves. Methods of physicochemical analysis on nutrients, such as Kjeldahl method and atomic absorption spectrometry, can accurately analyze the nutrient content of nitrogen, potassium, and magnesium in cucumber leaves, and realize synchronous diagnosis of nitrogen, potassium, and magnesium deficiency in cucumber leaves. However, the diagnosis methods of physicochemical analysis on nutrients require destruction of test samples, and are time-consuming and complicated to operate.
Summary
From the perspective of chlorophyll content distribution characteristics on a leaf deficient in nitrogen, potassium, and magnesium, the present invention provides a method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll di stributi on characteristics on a leaf surface.
The method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on a leaf surface specifically comprises the following steps: Division of a leaf surface region: dividing the leaf surface into large regions by using an intersection point of main veins and main turning points on the contour line of the leaf and subdividing the large regions into several small regions.
The large regions are obtained by division using the following method, which comprises: taking the intersection point of main veins of the leaf as an origin and taking a main turning points on the contour line of the leaf as division points of the contour line, and connecting the division points of the contour line and the origin to obtain large-region division segments, thereby dividing the surface region of the cucumber leaf into a-3 large regions, where a is a positive integer.
The small regions are obtained by division using the following method, which comprises: determining ii small-region division points on each large-region division segment, and respectively connecting the small-region division points of every two adjacent large regions to form small-region division segments, so that the leaf surface region is divided into m=((f-3)(n+1)+2 small regions by the small-region division segments, the large-region division segments, and the external contour line, where a, m, 71 are positive integers.
The segments formed between the 71 small-region division points on each large-region division segment have the same length.
Extraction of regional distribution characteristics of chlorophyll: taking multiple leaves as training samples, sequentially detecting the chlorophyll content distribution patterns on the surfaces of the leaves, sequentially extracting preset parameters corresponding to all the pixels in several small regions in each of the chlorophyll distribution patterns on the surfaces of the leaves, and creating an independent variable array X. The preset parameters comprise mean value, variance, maximum value, and minimum value of the chlorophyll content.
Building of a nitrogen, potassium, and magnesium deficiency diagnosis model: sequentially detecting the nutritional status of nitrogen, potassium, and magnesium of the leaves, and creating a dependent variable array Y, and building a nitrogen, potassium, and magnesium deficiency diagnosis model Y=F(X) by using the independent variable array X and the dependent variable array Y corresponding to the leaves.
The independent variable array Xis specifically created by using the following method: creating an independent variable array X of j rowsx4m columns by using the mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the m small regions in each of the chlorophyll distribution patterns on the surfaces of the j leaves, where m,/ are positive integers.
The dependent variable array Y is used for recording the nutritional status of nitrogen, potassium, and magnesium of the j leaves, comprising: sequentially detecting the nutritional status of nitrogen, potassium, and magnesium of the j leaves by using a method of physicochemical analysis on nutrients, and creating a dependent variable array Y of j rowsx3 columns, where j is a positive integer The first column of the dependent variable array Y is used for recording the nutritional status of nitrogen, its value being 0 indicates normal content of nitrogen in the corresponding leaf, while its value being 1 indicates nitrogen deficiency in the corresponding leaf; the second column of the dependent variable array Y is used for recording the nutritional status of potassium, its value being 0 indicates normal content of potassium in the corresponding leaf, while its value being t indicates potassium deficiency in the corresponding leaf; the third column of the dependent variable array Y is used for recording the nutritional status of magnesium, its value being 0 indicates normal content of magnesium in the corresponding leaf, while its value being 1 indicates magnesium deficiency in the corresponding leaf Diagnosis of nitrogen, potassium, and magnesium deficiency of the leaves to be detected: dividing the surface region of each leaf to be detected into several small regions; sequentially extracting preset parameters corresponding to all the pixels in the small regions in the chlorophyll distribution pattern on the surface of each leaf to be detected, and creating an independent variable array X' of the leaves to be detected; substituting the independent variable array X' of the leaves to be detected into the nitrogen, potassium, and magnesium deficiency diagnosis model Y=F(X), and calculating the dependent variable array Y'=F(X) of the leaves to be detected The preset parameters comprise mean value, variance, maximum value, and minimum value of the chlorophyll content.
The present invention has the following beneficial effects.
According to the present invention, from the perspective of chlorophyll content distribution characteristics on a leaf deficient in nitrogen, potassium, and magnesium, the surface region of a cucumber leaf is divided into several small regions, and the mean value, variance, maximum value, and minimum value of the chlorophyll content at all the pixels in each small region are sequentially extracted, thereby achieving accurate presentation of the chlorophyll distribution characteristics on the surface of the cucumber leaf; based on the extracted chlorophyll distribution characteristics on the leaf surface, a diagnosis model capable of synchronously diagnosing nitrogen, potassium, and magnesium deficiency in the cucumber leaf is built, and a method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on the chlorophyll distribution characteristics on the surface of the cucumber leaf is established. Therefore, the limitation that the element deficiency diagnosis methods based on the chlorophyll content cannot synchronously diagnose nitrogen, potassium, and magnesium deficiency in cucumber leaves is eliminated. By using the solution of the present invention and the built nitrogen, potassium, and magnesium deficiency diagnosis model, the chlorophyll distribution characteristics on the surfaces of the leaves can be rapidly and nondestructively extracted, thereby achieving efficient diagnosis of nitrogen, potassium, and magnesium deficiency in the leaves.
The hyperspectral imaging technology can obtain not only two-dimensional image information of a sample to be detected, but also spectral information corresponding to each pixel in the two-dimensional image. The content of components to be detected corresponding to each pixel can be sequentially analyzed by using the sensitivity of the spectral information of the pixel to the content of the components to be detected, thereby achieving visualized distribution of the content of the components to be detected in the sample space
Brief Description of the Drawings
FIG. I is a schematic view showing division of a surface region of a cucumber leaf; FIG. 2 is a chlorophyll content distribution pattern on the surface of a cucumber leaf, where a is a legend and b is a chlorophyll distribution pattern; and FIG. 3 is a chlorophyll content distribution pattern on the surface of a cucumber leaf after regional division.
Detailed Description of the Embodiments
In order to make the objectives, technical solutions, and advantages of the present invention clearer so that persons skilled in the art can better understand the technical solutions of the present invention, the technical solutions of the present invention will be described more clearly and completely below with reference to the accompanying drawings and specific embodiments of the present invention It is obvious that the embodiments to be described are only a part rather than all of the embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention Embodiment 1: a method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on a leaf surface The method specifically includes the following steps.
A leaf surface region is divided as follows An intersection point of main veins of a leaf is taken as an origin and a main turning points on the contour line of the leaf are taken as division points of the contour line, and the division points of the contour line and the origin are connected to obtain large-region division segments, thereby dividing the surface region of the cucumber leaf into a-3 large regions, ii small-region division points are determined on each large-region division segment, and the small-region division points of every two adjacent large regions are respectively connected to form small-region division segments, so that the leaf surface region is divided into in=(a-3)(n+1)+2 small regions by the small-region division segments, the large-region division segments, and the external contour line, where the segments formed between the /I small-region division points on each large-region division segment have the same length.
Regional distribution characteristics of chlorophyll are extracted as follows, j leaves are taken as training samples, and the chlorophyll content distribution patterns on the surfaces of the j leaves are sequentially detected by using a hyperspectral imaging technology; regions corresponding to the in small regions obtained by division on each of the chlorophyll content distribution patterns on the surfaces of the leaves are non-repeatedly numbered; and the mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the in small regions in each of the chlorophyll distribution patterns on the surfaces of the j leaves are sequentially extracted. The mean value of the chlorophyll content is calculated by extracting the chlorophyll content corresponding to each pixel in a single small region, and calculating the mean value corresponding to all the pixels in the small region; the variance of the chlorophyll content is calculated by extracting the chlorophyll content corresponding to each pixel in a single small region, and calculating the variance corresponding to all the pixels in the small region; and the maximum value and the minimum value of the chlorophyll content are calculated by extracting the chlorophyll content corresponding to each pixel in a single small region, and respectively making statistics on the maximum value and the minimum value corresponding to all the pixels in the small region. A nitrogen, potassium, and magnesium deficiency diagnosis model is built as follows. An independent variable array A' of j rowsx4m columns is created by using the mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the in small regions in each of the chlorophyll distribution patterns on the surfaces of the j leaves; the nutritional status of nitrogen, potassium, and magnesium of the j leaves is sequentially detected by using a method of physicochemical analysis on nutrients, and a dependent variable array Y of j rowsx3 columns is created for recording the nutritional status of nitrogen, potassium, and magnesium of the j leaves, and a nitrogen, potassium, and magnesium deficiency diagnosis model Y=F(A) is built by using the independent variable array A' and the dependent variable array Y corresponding to the j leaves in combination with the K-nearest neighbor recognition algorithm The first column of the dependent variable array Y is used for recording the nutritional status of nitrogen, its value being 0 indicates normal content of nitrogen in the corresponding leaf, while its value being 1 indicates nitrogen deficiency in the corresponding leaf; the second column of the dependent variable array Y is used for recording the nutritional status of potassium, its value being 0 indicates normal content of potassium in the corresponding leaf, while its value being I indicates potassium deficiency in the corresponding leaf; the third column of the dependent variable array Y is used for recording the nutritional status of magnesium, its value being 0 indicates normal content of magnesium in the corresponding leaf, while its value being 1 indicates magnesium deficiency in the corresponding leaf Nitrogen, potassium, and magnesium deficiency of leaves to be detected are diagnosed as follows. The surface region of each of q leaves to be detected is divided into nt small regions by using the small-region division segments, the large-region division segments, and the external contour line, the mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the in small regions in each of the chlorophyll distribution patterns on the surfaces of the q leaves to be detected are sequentially extracted, and an independent variable array X' of q rowsx4m columns of the leaves to be detected is created; and the independent variable array X' of the leaves to be detected is substituted into the nitrogen, potassium, and magnesium deficiency diagnosis model Y=I-1(X), and the dependent variable array Yr=F(X") of q rowsx3 columns of the leaves to be detected is calculated, where the nutritional status of nitrogen, potassium, and magnesium of the uth leaf to be detected depends on the value of Pt, on the it' row of the dependent variable array Y' of the leaves to be detected.
Herein, a, in, it, q,/ are all positive integers.
Embodiment 2: synchronous diagnosis of nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on the surfaces of cucumber leaves Division of the surface region of a cucumber leaf, extraction of regional distribution characteristics of chlorophyll, building of a nitrogen, potassium, and magnesium deficiency diagnosis model, and diagnosis of nitrogen, potassium, and magnesium deficiency of cucumber leaves to be detected are included.
Si: Division of the surface region of a cucumber leaf (I) An intersection point of main veins of a cucumber leaf is taken as an origin 0, and a region enclosed by a contour line of the cucumber leaf is taken as the surface region to be divided of the cucumber leaf. Nine main turning points A, B, C, D, E, F, G, H, I on the contour line of the cucumber leaf are sequentially selected as division points of the contour line, where the division point E on the contour line is the tip of the longest main vein of the cucumber leaf The division points of the contour line B, C, D, E, F, G, H are respectively connected to the point 0, to obtain large-region division segments BO, CO, DO, ED, 1,0, GO, HO, so that the surface region of the cucumber leaf is divided into eight large regions of OAB, OBC, OCD, ODE, OFF, OFG, OGH, OHI, as shown in FIG. 1.
(2) Three (that is, n=3) small-region division points B7, B2, 133 are determined on the large-region division segment BO, and the segments /113/, 81132, 8783, 1130 have the same length; three small-region division points Cr, C C3 are determined on the large-region division segment CO, and the segments CC7i, (71(72, C 2C 3, C30 have the same length; three small-region division points Di, D2, D3 are determined on the large-region division segment DO, and the segments DDi, D1D2, 1)21)3, D30 have the same length; three small-region division points El, E7, £3 are determined on the large-region division segment £0, and the segments E.Ei, E/E2, E2E3, E30 have the same length; three small-region division points F7, F2, F3 are determined on the large-region division segment FO, and the segments FPli, P1P2, F2F3, F30 have the same length; three small-region division points G, 02, G3 are determined on the large-region division segment GO, and the segments GGi, 0102, 0203, 030 have the same length; and three small-region division points Hz, H2, 113 are determined on the large-region division segment HO, and the segments Hit, H/H2, H2H3, H30 have the same length.
(3) The small-region division points Biei, B2C2, B3(73, (72D2, C3D3, D;EI, D2E2, D3E3, ET!, E2F2, E3F3, FIG!, F702, F303, GIH1, 02112, 03H3 are respectively connected to form small-region division segments. The surface region of the cucumber leaf is divided into 26 small regions by the small-region division segments, the large-region division segments, and the external contour line.
S2: Extraction of regional distribution characteristics of chlorophyll: (1) 60 cucumber leaves are grown by soilless cultivation as training samples, and chlorophyll content distribution patterns K1, K7, ..., K36, K60 on the surfaces of the 60 (that is, j=60) cucumber leaves are sequentially detected by using a hyperspectral imaging technology (JmSpector VJOP, Spectral Imaging Ltd, Oulu, Finland). The chlorophyll content distribution pattern on the surface of a single cucumber leaf is shown in FIG. 2, where the grayscale value of each pixel in the chlorophyll distribution pattern represents the chlorophyll content at the pixel, a smaller graysca1e value of a pixel indicates a lower chlorophyll content corresponding to the pixel, and a greater grayscaIe value of a pixel indicates a higher chlorophyll content corresponding to the pixel. The corresponding relationship between the grayscale values of the pixels and the chlorophyll content is shown in the legend a of FIG. 2.
(2) Regions corresponding to the 26 small regions on the chlorophyll content distribution pattern on the leaf surface are non-repeatedly numbered. The chlorophyll content distribution on the surface of the cucumber leaf after region division is shown in FIG. 3, where the serial numbers corresponding to the 26 small regions are the Arabic numerals in brackets in the small regions in FIG. 3.
(3) The mean values of the chlorophyll content X Pi /, X Pi 2, ..., X PI 59, X P, 60 corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns K1, K2, ..., K59, K60 on the surfaces of the 60 cucumber leaves are sequentially extracted.
The mean values of the chlorophyll content corresponding to the chlorophyll content distribution pattern K, on the surface of the cucumber leaf are X Pi /IX 11/ /, X P i 2, ..., X P1 i 25, X P3 i 26], and X Pi v is the mean value of the chlorophyll content corresponding to all the pixels in the IP small region of the ith cucumber leaf, where iE I, 2., 59, 60), ,E {1, 2, . 25, 26).
(4) The variances of the chlorophyll content X P2 1, X P2 2, ..., X P2 59, X P2 60 corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns K1, K2, ..., K59, K60 on the surfaces of the 60 cucumber leaves are sequentially extracted. The variances of the chlorophyll content corresponding to the chlorophyll content distribution pattern K, on the surface of the cucumber leaf are X P2 i=[X P2 i I, X P2 i 2, ..., X P2 i 25, X P2 26], and X P2 l' is the variance of the chlorophyll content corresponding to all the pixels in the vth small region of the cucumber leaf, where iE t 1, 2, ..., 59, 60), v E {1, 2_ 25, 26).
(5) The maximum values of the chlorophyll content X P3 1, X P3 2, ..., X P3 59, X P3 60 corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns K1, K2, , K59, K60 on the surfaces of the 60 cucumber leaves are sequentially extracted. The maximum values of the chlorophyll content corresponding to the chlorophyll content distribution pattern K, on the surface of the Ph cucumber leaf are X PS i=[X P3 i 1, X P3 i 2, ..., X P3 I 25,X P3 i 26], and X P3 i V is the maximum value of the chlorophyll content corresponding to all the pixels in the vth small region of the cucumber leaf, where iE 1, 2, 59, 60), v Ell, 2, . , 25, 26).
(6) The minimum values of the chlorophyll content X P4 1, X P4 2, . , X P4 59, X P4 60 corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns KI, K2, ..., K59, K60 on the surfaces of the 60 cucumber leaves are sequentially extracted. The minimum values of the chlorophyll content corresponding to the chlorophyll content distribution pattern K, on the surface of the ith cucumber leaf are X P4 /[X i J,XPj i 2, ..., X P4 1 25,X P4 i 26], and X P4 i v is the minimum value of the chlorophyll content corresponding to all the pixels in the vth small region of the cucumber leaf, where iE (1, 2, 59, 60), vE II, 2, ..., 25, 26).
53: Building of a nitrogen, potassium, and magnesium deficiency diagnosis model: (1) An independent variable array X of 60 rowsx[26 small regionsx4 parameters (mean value, variance, maximum value, and minimum value of the chlorophyll content)] rows, that is, rowsx104 columns is created by sequentially using the mean values, variances, maximum values, and minimum values of the chlorophyll content [X /, X P2 1, X P 1, X P4 1], [X Pi 2, X P2 2, X P3 2, X P4 2].....X Pi 59, X P2 59, X P3 59, X P4 59], [X Pi 60, X P2 60, X PS 60, X P4 60] corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns K1, K2, ..., K59, K60 on the surfaces of the 60 cucumber leaves. The 1" column to the 26th column on the ith row in the independent variable array Xis the mean value of the chlorophyll content X Pi i corresponding to the chlorophyll content distribution pattern K, on the surface of the ith cucumber leaf, the 27th column to the 52th column on the ith row in the independent variable array Xis the variance of the chlorophyll content X P2 corresponding to the chlorophyll content distribution pattern K, on the surface of the ith cucumber leaf, the 53111 column to the 78111 column on the 1th row in the independent variable array X is the maximum value of the chlorophyll content X P3 i corresponding to the chlorophyll content distribution pattern K, on the surface of the ith cucumber leaf, and the 79th column to the 104th column on the ith row in the independent variable array Xis the minimum value of the chlorophyll content X P4 i corresponding to the chlorophyll content distribution pattern K1 on the surface of the ith cucumber leaf.
(2) The nutritional status of nitrogen, potassium, and magnesium of 60 cucumber leaves is sequentially detected by using a method of physicochemical analysis on nutrients (atomic absorption spectrometry or Kjeldahl method), and a dependent variable array Y of 60 rowsx3 columns is created for recording the nutritional status of nitrogen, potassium, and magnesium of the 60 cucumber leaves. The first column of the dependent variable array Y is used for recording the nutritional status of nitrogen, its value being 0 indicates normal content of nitrogen in the corresponding leaf, while its value being 1 indicates nitrogen deficiency in the corresponding leaf; the second column of the dependent variable array Y is used for recording the nutritional status of potassium, its value being 0 indicates normal content of potassium in the corresponding leaf, while its value being 1 indicates potassium deficiency in the corresponding leaf; the third column of the dependent variable array Y is used for recording the nutritional status of magnesium, its value being 0 indicates normal content of magnesium in the corresponding leaf, while its value being 1 indicates magnesium deficiency in the corresponding leaf If the ill' cucumber leaf is deficient in nitrogen, potassium, and magnesium, the ith row of the dependent variable array Y is Y,11 1 1]; if the ith cucumber leaf is deficient in nitrogen and potassium and has normal content of magnesium, the ith row of the dependent variable array Y is Y,=[1 1 0]; if the ith cucumber leaf is deficient in nitrogen and magnesium and has normal content of potassium, the is" row of the dependent variable array Y is Y1=[1 0 1]; if the is" cucumber leaf is deficient in potassium and magnesium and has normal content of nitrogen, the ?I' row of the dependent variable array /7 is)7,10 1 1]; if the Pi cucumber leaf is deficient in nitrogen and has normal content of potassium and magnesium, Y,=[1 0 0]; if the ith cucumber leaf is deficient in potassium and has normal content of nitrogen and magnesium, the ith row of the dependent variable array Y is Y,=[0 1 0]; if the 1111 cucumber leaf is deficient in magnesium and has normal content of nitrogen and potassium, the ith row of the dependent variable array Y is Ye=[0 0 1]; if the /6 cucumber leaf has normal content of nitrogen, potassium, and magnesium, the itt row of the dependent variable array Y is Y/=[0 0 0].
(3) A nitrogen, potassium, and magnesium deficiency diagnosis model Y1(X) is built by using the independent variable array X and the dependent variable array Y corresponding to the 60 cucumber leaves in combination with the K-nearest neighbor recognition algorithm.
Embodiment 3: Diagnosis of nitrogen, potassium, and magnesium deficiency of cucumber leaves to be detected (1) According to the method described in Step Si of Embodiment 2, the surface region of each of 10 (that is, g=10) cucumber leaves to be detected is divided into 26 small regions by using the small-region division segments, the large-region division segments, and the external contour line.
(2) According to the methods described in Steps S2 and S3 of Embodiment 2, the mean values, variances, maximum values, and minimum values of the chlorophyll content [X' Pi 1, X' P2 1, X' P3 1, X' P4 1], [X' P1 2, ' P2 2, X' P3 2, X' P4 2], ..., [X' PI 9, X' P2 9, X' P3 9, X' P4 91, [X' P7 10, ..)C P2 10, X' P3 10, X' P4 10] corresponding to all the pixels in the 26 small regions in each of the chlorophyll distribution patterns on the surfaces of the 10 cucumber leaves to be detected are sequentially extracted, and an independent variable array A" of 10 rowsx 104 columns of the leaves to be detected is created. The mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the in small regions in the chlorophyll distribution pattern on the surface of the nth cucumber leave to be detected are [X' P1 it, X' P2 ii, X' /33 II, X' P4 id, where u=1, 2, ..., 9, 10.
(3) The independent variable array X' of the leaves to be detected is substituted into the nitrogen, potassium, and magnesium deficiency diagnosis model Y=F(X), and the dependent variable array Yr=F(X) of 10 rowsx3 columns of the leaves to be detected is calculated. The nutritional status of nitrogen, potassium, and magnesium of the nth leaf to be detected depends on the value of Y'i, on the thhu row of the dependent variable array I" of the leaves to be detected The value of the first column of Y'7, being 0 indicates normal content of nitrogen in the nth leaf to be detected, while its value being 1 indicates nitrogen deficiency in the:ill' leaf to be detected, the value of the second column of YU being 0 indicates normal content of potassium in the leaf to be detected, while its value being 1 indicates potassium deficiency in the uth leaf to be detected; the value of the third column of Y',, being 0 indicates normal content of magnesium in the atth leaf to be detected, while its value being 1 indicates magnesium deficiency in the nill leaf to be detected.
Table 1 Results of synchronous diagnosis of nitrogen, potassium, and magnesium deficiency in leaves to be detected Leaf No. Diagnosis results of this solution Diagnosis results of a standard method of physicochemical analysis on nutrients Nitrogen Potassium Magnesium Nitrogen Potassium Magnesium 1 0 0 0 0 0 0 2 0 0 0 0 0 0 3 1 0 0 1 0 0 4 0 1 0 0 1 0 0 0 1 0 0 1 6 1 1 0 1 1 0 7 1 0 1 1 0 1 8 0 1 1 0 1 1 9 1 1 1 1 1 1 1 1 1 1 1 1 The 100% accuracy of diagnosis of this solution

Claims (8)

  1. Claims What is claimed is: 1. A method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on a leaf surface, characterized by comprising the following steps: division of a leaf surface region: dividing the leaf surface into large regions by using an intersection point of main veins and main turning points on the contour line of the leaf, and subdividing the large regions into several small regions, extraction of regional distribution characteristics of chlorophyll: taking multiple leaves as training samples, sequentially detecting the chlorophyll content distribution patterns on the surfaces of the leaves, sequentially extracting preset parameters corresponding to all the pixels in several small regions in each of the chlorophyll distribution patterns on the surfaces of the leaves, and creating an independent variable array X; building of a nitrogen, potassium, and magnesium deficiency diagnosis model: sequentially detecting the nutritional status of nitrogen, potassium, and magnesium of the leaves, and creating a dependent variable array Y; and building a nitrogen, potassium, and magnesium deficiency diagnosis model Y=I-;(X) by using the independent variable array X and the dependent variable array Y corresponding to the leaves; diagnosis of nitrogen, potassium, and magnesium deficiency of the leaves to be detected: dividing the surface region of each leaf to be detected into several small regions; sequentially extracting preset parameters corresponding to all the pixels in the small regions in the chlorophyll distribution pattern on the surface of each leaf to be detected, and creating an independent variable array X' of the leaves to be detected; substituting the independent variable array X' of the leaves to be detected into the nitrogen, potassium, and magnesium deficiency diagnosis model Y=E(X), and calculating the dependent variable array Y'=/?(X) of the leaves to be detected.
  2. 2. The method according to claim 1, characterized in that the large regions are obtained by division using the following method, which comprises: taking the intersection point of main veins of a leaf as an origin and taking a main turning points on the contour line of the leaf as division points of the contour line, and connecting the division points of the contour line and the origin to obtain large-region division segments, thereby dividing the surface region of the cucumber leaf into a-3 large regions, where a is a positive integer.
  3. 3. The method according to claim 2, characterized in that the small regions are obtained by division using the following method, which comprises: determining ii small-region division points on each large-region division segment, and respectively connecting the small-region division points of every two adjacent large regions to form small-region division segments, so that the leaf surface region is divided into ni=(a-3)(n+1)+2 small regions by the small-region division segments, the large-region division segments, and the external contour line, where a, in, n are positive integers.
  4. 4. The method according to claim 3, characterized in that the segments formed between the n small-region division points on each large-region division segment have the same length.
  5. 5. The method according to claim 1, characterized in that the preset parameters comprise mean value, variance, maximum value, and minimum value of the chlorophyll content.
  6. 6. The method according to claim 1, characterized in that the independent variable array Xis specifically created by using the following method: creating an independent variable array X of j rowsx4m columns by using the mean values, variances, maximum values, and minimum values of the chlorophyll content corresponding to all the pixels in the in small regions in each of the chlorophyll distribution patterns on the surfaces of the j leaves, where rn,j are positive integers.
  7. 7. The method according to claim 1, characterized in that the dependent variable array Y is used for recording the nutritional status of nitrogen, potassium, and magnesium of the j leaves, comprising: sequentially detecting the nutritional status of nitrogen, potassium, and magnesium of the j leaves by using a method of physicochemical analysis on nutrients, and creating a dependent variable array Y of/ rows x3 columns, where/ is a positive integer.
  8. 8. The method according to claim 7, characterized in that the first column of the dependent variable array Y is used for recording the nutritional status of nitrogen, its value being 0 indicates normal content of nitrogen in the corresponding leaf while its value being 1 indicates nitrogen deficiency in the corresponding leaf; the second column of the dependent variable array Y is used for recording the nutritional status of potassium, its value being 0 indicates normal content of potassium in the corresponding leaf, while its value being 1 indicates potassium deficiency in the corresponding leaf, the third column of the dependent variable array V is used for recording the nutritional status of magnesium, its value being 0 indicates normal content of magnesium in the corresponding leaf while its value being 1 indicates magnesium deficiency in the corresponding leaf.
GB2018070.9A 2019-08-26 2019-09-26 Method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on leaf surface Expired - Fee Related GB2591565B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910789336.3A CN110631995B (en) 2019-08-26 2019-08-26 Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency by leaf chlorophyll and leaf surface distribution characteristics
PCT/CN2019/107983 WO2021035858A1 (en) 2019-08-26 2019-09-26 Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency on the basis of distribution characteristics of leaf chlorophyll on leaf surface

Publications (4)

Publication Number Publication Date
GB202018070D0 GB202018070D0 (en) 2020-12-30
GB2591565A true GB2591565A (en) 2021-08-04
GB2591565A8 GB2591565A8 (en) 2021-08-11
GB2591565B GB2591565B (en) 2022-10-12

Family

ID=68969067

Family Applications (1)

Application Number Title Priority Date Filing Date
GB2018070.9A Expired - Fee Related 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

Country Status (4)

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

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110631995B (en) * 2019-08-26 2021-09-10 江苏大学 Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency by leaf chlorophyll and leaf surface distribution characteristics
CN111398198A (en) * 2020-04-29 2020-07-10 中国农业大学 Rapid nondestructive testing method for wheat grain trace elements
CN114486761B (en) * 2022-01-24 2024-04-12 云南省热带作物科学研究所 Rapid estimation method for magnesium content of rubber tree blade

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865926A (en) * 2006-04-30 2006-11-22 武汉大学 Portable detector for pigment in plant leaf
CN101382488A (en) * 2008-10-14 2009-03-11 江苏吟春碧芽茶叶研究所有限公司 Method for detecting nitrogen content in fresh tea by visible light-near infrared diffuse reflection spectrum technology
CN101692037A (en) * 2009-09-08 2010-04-07 江苏大学 Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component
CN101915738A (en) * 2010-06-23 2010-12-15 江苏大学 Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique
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 (en) * 2014-03-12 2014-06-18 中国农业科学院油料作物研究所 Method for rapidly diagnosing nitrogen nutrition in oilseed rape leaves and recommending application of nitrogen
CN105486669A (en) * 2016-01-12 2016-04-13 丽水学院 Chlorophyll fluorescence diagnostic method for deficiency of indispensable plant nutritive elements
CN105675821A (en) * 2016-02-21 2016-06-15 南京农业大学 Image evaluation index establishing method for nondestructive diagnosis of crop nitrogen nutrition
CN110631995A (en) * 2019-08-26 2019-12-31 江苏大学 Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency by leaf chlorophyll and leaf surface distribution characteristics

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
UA32191U (en) * 2007-12-13 2008-05-12 Yuriev Inst Of Plant Science O Method for recording affection of cereals and grain legumes with leaf diseases
CN110148146B (en) * 2019-05-24 2021-03-02 重庆大学 Plant leaf segmentation method and system by utilizing synthetic data

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1865926A (en) * 2006-04-30 2006-11-22 武汉大学 Portable detector for pigment in plant leaf
CN101382488A (en) * 2008-10-14 2009-03-11 江苏吟春碧芽茶叶研究所有限公司 Method for detecting nitrogen content in fresh tea by visible light-near infrared diffuse reflection spectrum technology
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 (en) * 2009-09-08 2010-04-07 江苏大学 Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component
CN101915738A (en) * 2010-06-23 2010-12-15 江苏大学 Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique
CN103868891A (en) * 2014-03-12 2014-06-18 中国农业科学院油料作物研究所 Method for rapidly diagnosing nitrogen nutrition in oilseed rape leaves and recommending application of nitrogen
CN105486669A (en) * 2016-01-12 2016-04-13 丽水学院 Chlorophyll fluorescence diagnostic method for deficiency of indispensable plant nutritive elements
CN105675821A (en) * 2016-02-21 2016-06-15 南京农业大学 Image evaluation index establishing method for nondestructive diagnosis of crop nitrogen nutrition
CN110631995A (en) * 2019-08-26 2019-12-31 江苏大学 Method for synchronously diagnosing nitrogen, potassium and magnesium element deficiency by leaf chlorophyll and leaf surface distribution characteristics

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, (20190522), vol. 50, no. 8, d *
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, (20190708), vol. 35, no. 13, doi *

Also Published As

Publication number Publication date
GB202018070D0 (en) 2020-12-30
CN110631995B (en) 2021-09-10
CH716708B1 (en) 2022-05-13
GB2591565B (en) 2022-10-12
WO2021035858A1 (en) 2021-03-04
CN110631995A (en) 2019-12-31
GB2591565A8 (en) 2021-08-11

Similar Documents

Publication Publication Date Title
GB2591565A (en) Method for synchronously diagnosing nitrogen, potassium, and magnesium deficiency based on chlorophyll distribution characteristics on leaf surface
Fiorani et al. Imaging plants dynamics in heterogenic environments
CN102495005B (en) Method for diagnosing crop water deficit through hyperspectral image technology
CN100416590C (en) Method for automatically identifying field weeds in crop seeding-stage using site and grain characteristic
Guo et al. Integrating spectral and textural information for identifying the tasseling date of summer maize using UAV based RGB images
US6397162B1 (en) System, device and method for estimating evapo-transpiration in plants
Aasen et al. PhenoCams for field phenotyping: using very high temporal resolution digital repeated photography to investigate interactions of growth, phenology, and harvest traits
CN109711102B (en) Method for rapidly evaluating crop disaster loss
CN101692037B (en) Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component
CN100536653C (en) Crop water-requesting information determination based on computer vision
Fernandez-Ordoñez et al. Maize crop yield estimation with remote sensing and empirical models
CN104614321A (en) Real-time crop growth condition monitoring method based on spectrum images
KR102095539B1 (en) Method for measuring growth amount by image analyzing ginseng
KR101822410B1 (en) Apparatus for diagnosing growth state of crop organ using crop organ image
CN107314990B (en) Spring corn remote sensing identification method
CN103971199B (en) A kind of remote sensing ranking method of a wide range of Grain Growth Situation
CN109827957B (en) Rice leaf SPAD value estimation method and system based on computer vision
CN109410232A (en) Based on conventional low resolution camera to the extracting method of Leaf color character value
CN113948220A (en) Anthrax pathogen infection stage detection method with pre-analysis capability
CN114708490A (en) Rice planting extraction and multiple cropping index monitoring method, system, terminal and storage medium
Singh et al. Biospeckle-based sensor for characterization of charcoal rot (Macrophomina Phaseolina (Tassi) Goid) disease in soybean (Glycine Max (L.) Merr.) crop
CN107437262B (en) Crop planting area early warning method and system
Zhang et al. Impact of spectral interval on wavelet features for detecting wheat yellow rust with hyperspectral data
AU2021103520A4 (en) A system for monitoring health condition of a crop and a method there of
CN111932551B (en) Missing transplanting rate detection method of rice transplanter

Legal Events

Date Code Title Description
PCNP Patent ceased through non-payment of renewal fee

Effective date: 20230926