CN114140695B - Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing - Google Patents
Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing Download PDFInfo
- Publication number
- CN114140695B CN114140695B CN202111555635.4A CN202111555635A CN114140695B CN 114140695 B CN114140695 B CN 114140695B CN 202111555635 A CN202111555635 A CN 202111555635A CN 114140695 B CN114140695 B CN 114140695B
- Authority
- CN
- China
- Prior art keywords
- tea
- quality index
- tea tree
- nitrogen
- unmanned aerial
- 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.)
- Active
Links
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 title claims abstract description 156
- 229910052757 nitrogen Inorganic materials 0.000 title claims abstract description 78
- 235000009024 Ceanothus sanguineus Nutrition 0.000 title claims abstract description 66
- 240000003553 Leptospermum scoparium Species 0.000 title claims abstract description 66
- 235000015459 Lycium barbarum Nutrition 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000003745 diagnosis Methods 0.000 title claims abstract description 20
- 230000003595 spectral effect Effects 0.000 claims abstract description 23
- 150000001413 amino acids Chemical class 0.000 claims abstract description 22
- 150000008442 polyphenolic compounds Chemical class 0.000 claims abstract description 22
- 235000013824 polyphenols Nutrition 0.000 claims abstract description 22
- 238000001228 spectrum Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 238000010219 correlation analysis Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 11
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 241001122767 Theaceae Species 0.000 claims 4
- 244000269722 Thea sinensis Species 0.000 abstract description 40
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000007726 management method Methods 0.000 abstract description 7
- 235000016709 nutrition Nutrition 0.000 abstract description 5
- 230000035764 nutrition Effects 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 2
- 241000196324 Embryophyta Species 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 241000209140 Triticum Species 0.000 description 4
- 235000021307 Triticum Nutrition 0.000 description 4
- 239000000618 nitrogen fertilizer Substances 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical class C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 3
- 230000004720 fertilization Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002028 Biomass Substances 0.000 description 2
- 235000006468 Thea sinensis Nutrition 0.000 description 2
- 229930002875 chlorophyll Natural products 0.000 description 2
- 235000019804 chlorophyll Nutrition 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001420622 Meris Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 235000021049 nutrient content Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a prediction method and a system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing. The prediction method comprises the following steps: collecting a multispectral picture by using an unmanned aerial vehicle carrying a multispectral camera, and preprocessing to obtain spectral parameters; dividing a tea garden to be tested into areas, and obtaining ground parameters such as nitrogen content and quality index of tea trees; determining a region of interest, and performing correlation analysis on the spectral parameters and the ground parameters; constructing a regression prediction model of the ground parameters and selecting an optimal model; and constructing an estimated remote sensing monitoring image by using the spectrum parameters and the optimal model. The invention determines the nutrition of the tea tree young shoot nitrogen and tea polyphenol, amino acid and water extract in the picking period by digital image technology, and hyperspectral parameters and equation models, and can realize nondestructive and effective detection of main biochemical components of the tea tree, thereby providing important basis for tea garden management.
Description
Technical Field
The invention belongs to the field of unmanned aerial vehicle remote sensing, and particularly relates to a prediction method and a prediction system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing.
Background
In actual production, reasonable application of the nitrogenous fertilizer can ensure the quality and the high yield of tea trees, and improper application of the nitrogenous fertilizer can cause nitrogen stress, nitrogen loss and environmental pollution. Tea polyphenol and amino acid are taken as main metabolites of tea, the content of the tea polyphenol and the amino acid determines the quality of the tea, and the tea polyphenol and the amino acid are key biochemical components for measuring the taste of the tea. Traditional plant biochemical parameters and nitrogen content measurement are mainly performed by chemical diagnosis, but the methods cannot quickly and accurately acquire related information, and destructive sampling and destructive detection limit the application in actual production. In addition, in production, people can also diagnose whether plants lack certain elements through appearance by experience, and the method is simple, but lacks strict data support and has certain contingency. Therefore, the method for monitoring the nitrogen content of the tea trees and the content of tea polyphenol and amino acid in real time and accurately has important significance for monitoring the growth of the tea trees, regulating and controlling the dosage of nitrogenous fertilizer and evaluating the quality of the tea.
As a new remote sensing method, unmanned aerial vehicle remote sensing has the advantages of high flexibility, high speed, no damage, high resolution and the like, has the advantages of real-time performance and high flux, and can effectively make up for some defects of ground measurement. At present, people have developed a plurality of physicochemical parameter monitoring technologies by utilizing unmanned aerial vehicle remote sensing technology. For example, by acquiring crop canopy image data using an unmanned aerial vehicle, an aerial image diagnostic model of nitrogen nutrition status of winter wheat and summer corn is established. The unmanned aerial vehicle remote sensing data is analyzed by using a machine learning method, the above-ground biomass of rice, the nitrogen absorption of plants and the nitrogen nutrition index are measured, and scientific basis is provided for better detecting the crop growth and accurately managing the crops by using the remote sensing data. And acquiring hyperspectral images of wheat canopy by using the UAV, and establishing an inversion model of nitrogen concentration in the wheat blade so as to estimate the nitrogen concentration in the wheat blade at different growth stages. Among tea trees, only research has utilized unmanned aerial vehicles to classify tea tree varieties by means of hyperspectral features of tea tree canopy. However, research on estimating the nitrogen content, tea polyphenol and amino acid content in tea tree canopy leaves by using unmanned aerial vehicle multispectral remote sensing technology is rare.
Therefore, research and utilization of unmanned aerial vehicle to obtain multispectral data of tea tree canopy realizes nondestructive testing of tea tree leaf nitrogen content and tea polyphenol and amino acid content through establishing different models, and has important significance for improving tea garden nitrogen diagnosis and real-time monitoring of tea quality, and has important significance for improving nitrogen fertilizer utilization efficiency and improving fertilization technology.
Disclosure of Invention
In order to solve the problems, the invention provides a prediction method and a system for tea tree nitrogen diagnosis and quality index measurement based on unmanned aerial vehicle multispectral remote sensing. The remote sensing of the unmanned aerial vehicle is taken as a platform, multispectral information of the tea tree canopy is obtained by using a multispectral camera, and the diagnosis of nitrogen in the tea tree canopy and the determination of quality parameters are realized through digital image processing and machine learning technologies.
In order to achieve the aim of the invention, the invention is realized by adopting the following technical scheme:
The invention provides a prediction method for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing, which comprises the following steps:
S1: determining the space range of a test area, setting the flight path of the unmanned aerial vehicle, preprocessing a multispectral image acquired by the unmanned aerial vehicle, and acquiring spectral parameters;
s2: dividing the area of the tea garden to be tested, and measuring the nitrogen content and quality index of tea trees in each area;
s3: determining a region of interest; carrying out correlation analysis on spectral parameters in the region of interest and nitrogen content and quality indexes of the tea tree; selecting 4-8 spectrum parameters with highest relativity from each content index;
s4: repeating the steps S1-S3; constructing a regression prediction model of the nitrogen content and the quality index of the tea tree, and selecting an optimal model of each content index;
S5: and (3) constructing an estimated remote sensing monitoring image of the nitrogen content and the quality index of the tea tree by utilizing the spectral parameters selected in the step (S3) and combining the optimal model in the step (S4), namely realizing the information visualization of the nitrogen content and the quality index of the tea tree.
Further, the quality index includes tea polyphenol content and amino acid content.
Further, in the step S1, the flying height of the unmanned aerial vehicle is 20m-30m; the unmanned aerial vehicle is provided with a multispectral camera; the angle of view of the multispectral camera is 30, the exposure time is 5mm, and the ISO is 100.
Further, in the step S2, the tea garden to be tested is divided into square areas with a side length of 1 m.
Further, the specific steps of the step S3 are as follows:
(1) Determining a region of interest by using an environment visualization program, and extracting an average DN value of the region;
(2) In the interested area, 28 spectrum parameters are selected, and correlation analysis is carried out on the spectrum parameters and the nitrogen content and quality index of the tea tree respectively;
(3) In order to prevent the situation of excessive fitting of the model during modeling, 5 spectrum parameters with highest correlation are respectively selected from the nitrogen content and each quality index.
Further, the spectral parameters with the highest correlation degree with the nitrogen content are EVI, MTVI2, OSAVI, SAVI, NLI, MCARI, MSR and RDVI; the spectral parameters with the highest correlation with the tea polyphenol content are RDVI, DVI, TCARI, RVI, NLI, OSAVI, SAVI and TVI; the spectral parameters with the highest correlation with amino acid content were OSAVI, SAVI, NLI, MTCI, EVI, NDVI, RDVI and MTVI.
Further, in the step S4, a regression prediction model of the nitrogen content and the quality index is constructed by adopting a machine learning method, and the specific steps are as follows:
(1) Dividing all data sets into 75% training sets and 25% testing sets, evaluating the performance of the model by determining a coefficient R 2, a Root Mean Square Error (RMSE) and a Normalized Root Mean Square Error (NRMSE), and selecting the optimal model;
(2) Fitting the measured value of the nitrogen content and the quality index of each tea tree with the spectrum parameter to construct a regression prediction model of the nitrogen content and the quality index of each tea tree;
(3) In order to evaluate the inversion accuracy of the regression prediction model, the measured values of each content index in the test set are compared with the estimated values of the regression prediction model to verify the stability of the regression prediction model.
Further, the method of machine learning includes PLSR, SVM, BP neural networks.
Further, when R 2, RMSE, and NRMSE of the regression prediction model were tested close to the training set, it was shown that the regression prediction model had good stability.
The invention also provides a prediction system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing, which comprises the following steps: unmanned plane;
The multispectral camera is carried on the unmanned aerial vehicle and is used for collecting multispectral images of the growth period of the tea tree;
the sensor is arranged on the multispectral camera and used for acquiring the nitrogen content and the quality index of the tea tree;
A processor that performs the following operations:
preprocessing a multispectral image acquired by the multispectral camera by using multispectral data inversion software therein to acquire spectral parameters; determining a region of interest using an environment visualization program therein; constructing a regression prediction model of tea tree nitrogen and quality indexes; and constructing an estimated remote sensing monitoring image of the nitrogen and the quality index of the tea tree.
Compared with the prior art, the invention has the advantages and beneficial effects that:
1. According to the method, through researching the nitrogen dynamic rules of the tea trees under the variable fertilization condition and the uniform fertilization condition, the time dynamics of the tea tree growth model and the remote sensing assimilation nitrogen are simulated, the tea tree nitrogen model and the remote sensing assimilation strategy are constructed, the model is applied to the regional scale, the time-space dynamics of the tea tree growth condition is detected through real-time and accurate adjustment of model initial parameters, and then the tea garden ground parameters (tea polyphenol and amino acid content) and the nitrogen content are estimated.
2. According to the invention, the multispectral camera carried by the unmanned aerial vehicle is utilized to acquire spectral information of the tea tree canopy, and plant biomass and leaf nitrogen nutrient content and tea polyphenol and amino acid content are synchronously measured. Based on a machine learning method, a regression prediction model is established, the relation between the tea tree canopy spectral information, plant nitrogen nutrition index and young sprout quality index is researched, and the digital image technology is determined to estimate young sprout nitrogen nutrition, tea polyphenol, amino acid, water extract, hyperspectral parameters and equation model of the tea tree in the picking period. The invention can realize nondestructive and effective detection of main biochemical components of tea trees, thereby providing important basis for tea garden management, and further optimizing a tea garden management method to improve tea garden management efficiency.
Drawings
FIG. 1 is a flow chart of a method for predicting tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing.
FIG. 2 shows the correlation coefficients of the spectral parameters with the nitrogen content (a), tea polyphenols (b) and amino acid (c) content.
FIG. 3 shows the results of stability of the model of the nitrogen content (a, d and g), tea polyphenols (b, e and h) and amino acids (c, f and j) content in the leaves.
FIG. 4 is a remote sensing profile of tea plant nitrogen, tea polyphenols and amino acid content, wherein (a) tea plant nitrogen estimates the raw image; (b) estimation of nitrogen; (c) raw image estimates of tea polyphenols and amino acids; (d) estimation of tea polyphenol content; (e) estimation of amino acid content.
Detailed Description
The technical scheme of the invention is further described in detail by combining the following specific examples.
Example 1
A prediction method for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing is shown in a flow chart in figure 1, and comprises the following steps:
step one, collecting multispectral images, which comprises the following specific steps:
(1) And determining the space range of the test area, and designing the flight path. A multispectral image of the growth period of the tea tree is acquired by using a four-rotor unmanned aerial vehicle (matrix 200V2, DJI, inc., china) to carry multispectral cameras (MS 600, yusense, inc., qingdao, china); the field angle of the camera was 30 and the flying height was 25m. The exposure time of the camera was set to 5mm and the iso was set to 100. Wherein the multispectral camera used was equipped with 6 bands of 450nm, 555nm, 660nm, 720nm, 750nm and 840nm, each channel using a 1.2mp high dynamic range global shutter CMOS detector. The terrestrial spatial resolution is 8.65 cm@h=120m. The pixels of the sensor are 120 ten thousand, and the resolution is 1280 x 960.
(2) The acquired unmanned aerial vehicle remote sensing images were pre-processed using Yusense map software (V1.0, yusense, inc., qingdao, china).
Step two, obtaining ground parameters:
Dividing the tea garden to be tested into square areas with side length of 1 meter, and measuring new quality parameters and nitrogen content of mature leaves in the areas. The statistical description of the measurement index is shown in table 1.
Table 1: statistical description of measurement indicators
Step three, selecting spectrum parameters, which comprises the following specific steps:
(1) A region of interest (ROI) is determined using the environment visualization program ENVI and the average DN value of the test points is extracted.
(2) According to the existing spectral variable research results, 22 vegetation indexes plus the original 6 channels are selected, 28 spectral parameters are added, and correlation analysis is carried out on the vegetation indexes and the ground parameters (figure 2).
(3) In order to prevent excessive spectrum parameters from being used in modeling to cause excessive fitting of the model, 5 spectrum parameters with higher correlation degree are selected for each biochemical parameter respectively for subsequent simulation research. Wherein the five spectral parameters with highest nitrogen content are EVI、MTVI2(Modified triangular vegetation index)、OSAVI(Optimization of soil-adjusted vegetation index)、SAVI(Soil-adjusted vegetation index)、RDVI(Renormalized difference vegetation index)、NLI(Nonlinear vegetation index)、MCARI(Modified chlorophyll absorption ratio index)、MSR(Modified simple ratio); and tea polyphenol content are RDVI、DVI、OSAVI、SAVI、TVI(Triangular vegetation index)、TCARI(Transformed chlorophyll absorption reflectance index)、RVI(Ratio vegetation index)、NLI; and amino acid content are OSAVI、SAVI、NLI(Nonlinear vegetation index)、RDVI(Renormalized difference vegetation index)、MTVI2(Modified triangular vegetation index)、MTCI(MERIS Terrestrial chlorophyll index)、EVI、NDVI.
Fourth, the regression model is established, which comprises the following specific steps:
(1) In order to ensure the effectiveness and reliability of the data, the steps are repeated to obtain multiple unmanned aerial vehicle multispectral images, new quality indexes of tea trees and mature leaf nitrogen content data.
(2) A regression prediction model is established by adopting a machine learning (PLSR, SVM, BPNN) method, and an optimal model is selected. Wherein PLSR integrates the advantages of multiple linear regression, principal component analysis, and typical correlation analysis; the SVM is a nonlinear mapping theory basis, so that the SVM has low robustness; the BPNN can realize nonlinear mapping and has self-learning capability and generalization capability.
(3) When modeling, all data sets were separated into 75% training and 25% test sets. The performance of the model was evaluated by determining the coefficients (R 2), root Mean Square Error (RMSE) and Normalized Root Mean Square Error (NRMSE). The larger R 2, the smaller the RMSE and NRMSE, which means the better the performance of the model. R 2, RMSE, and NRMSE are calculated by equations (1), (2), and (3):
Wherein n is the number of samples; the composition of xi, The measured value and the measured average value of the biochemical component sample are generated; yi,/>Is the predicted value and the predicted mean value of the sample.
(4) Fitting the measured value of each parameter with the spectrum parameter to establish a prediction model of the nitrogen content of tea trees, tea polyphenol and amino acid. Table 2 shows the established SVM, PLSR and BP neural network models.
Table 2: SVM, PLSR and BP neural network model
(5) To evaluate the inversion accuracy of each model, the measured values of each biochemical parameter in the test set were compared with the estimated values of the model, and the stability of the model of the nitrogen content, tea polyphenol and amino acid content in the leaf was verified (fig. 3). When the R 2, RMSE, and NRMSE of the test model were close to the training set, this model was shown to have good stability.
Step five, visualization processing:
And (3) constructing remote sensing monitoring images (figure 4) by using the optimal model obtained in the step (IV) according to the spectral parameters screened in the step (III).
The invention relates to a method for estimating ground parameters of a tea garden and optimizing management of the tea garden based on unmanned aerial vehicle remote sensing technology, wherein the traditional quality parameter measurement is dependent on manual means and experience judgment, so that misjudgment is easy to occur, and the detection efficiency is low. Therefore, the unmanned aerial vehicle remote sensing technology and the machine learning method are used for tea garden nitrogen management and quality index measurement to improve the tea garden management efficiency.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (8)
1. A prediction method for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing is characterized by comprising the following steps:
S1: determining the space range of a test area, setting the flight path of the unmanned aerial vehicle, preprocessing a multispectral image acquired by the unmanned aerial vehicle, and acquiring spectral parameters;
s2: dividing the area of the tea garden to be tested, and measuring the nitrogen content and quality index of tea trees in each area;
s3: determining a region of interest; carrying out correlation analysis on spectral parameters in the region of interest and nitrogen content and quality indexes of the tea tree; selecting 4-8 spectrum parameters with highest relativity from each content index;
The method comprises the following specific steps:
(1) Determining a region of interest by using an environment visualization program, and extracting an average DN value of the region;
(2) In the interested area, 28 spectrum parameters are selected, and correlation analysis is carried out on the spectrum parameters and the nitrogen content and quality index of the tea tree respectively;
(3) In order to prevent the situation of excessive fitting of the model during modeling, 5 spectrum parameters with highest correlation are respectively selected from the nitrogen content and each quality index;
s4: repeating the steps S1-S3; constructing a regression prediction model of the nitrogen content and the quality index of the tea tree, and selecting an optimal model of each content index;
the regression prediction model of nitrogen content and quality index is constructed by adopting a machine learning method, and the specific steps are as follows:
(1) Dividing all data sets into 75% training sets and 25% testing sets, evaluating the performance of the model by determining a coefficient R 2, a Root Mean Square Error (RMSE) and a Normalized Root Mean Square Error (NRMSE), and selecting the optimal model; the larger R 2, the smaller the RMSE and NRMSE, which means that the better the performance of the model, R 2, RMSE and NRMSE are calculated by the following formula:
，
，
，
Wherein n is the number of samples; the composition of xi, The measured value and the measured average value of the biochemical component sample are generated; yi,/>The predicted value and the predicted average value of the sample are obtained;
(2) Fitting the measured value of the nitrogen content and the quality index of each tea tree with the spectrum parameter to construct a regression prediction model of the nitrogen content and the quality index of each tea tree;
(3) In order to evaluate the inversion precision of the regression prediction model, comparing the measured value of each content index in a test set with the estimated value of the regression prediction model to verify the stability of the regression prediction model;
S5: and (3) constructing an estimated remote sensing monitoring image of the nitrogen content and the quality index of the tea tree by utilizing the spectral parameters selected in the step (S3) and combining the optimal model in the step (S4), namely realizing the information visualization of the nitrogen content and the quality index of the tea tree.
2. The method for predicting nitrogen diagnosis and quality index determination of tea tree based on multispectral remote sensing of unmanned aerial vehicle according to claim 1, wherein the quality index comprises tea polyphenol content and amino acid content.
3. The method for predicting nitrogen diagnosis and quality index measurement of tea tree based on multispectral remote sensing of unmanned aerial vehicle according to claim 1, wherein the flying height of unmanned aerial vehicle in step S1 is 20m-30m; the unmanned aerial vehicle is provided with a multispectral camera; the angle of view of the multispectral camera is 30, the exposure time is 5mm, and the ISO is 100.
4. The prediction method for tea tree nitrogen diagnosis and quality index measurement based on unmanned aerial vehicle multispectral remote sensing according to claim 1, wherein in step S2, the tea garden to be tested is divided into square areas with side length of 1 m.
5. The method for predicting nitrogen diagnosis and quality index measurement of tea trees based on multispectral remote sensing of unmanned aerial vehicle according to claim 1, wherein the spectral parameters with the highest correlation degree with the nitrogen content are EVI, MTVI2, OSAVI, SAVI, NLI, MCARI, MSR and RDVI; the spectral parameters with the highest correlation with the tea polyphenol content are RDVI, DVI, TCARI, RVI, NLI, OSAVI, SAVI and TVI; the spectral parameters with the highest correlation with amino acid content were OSAVI, SAVI, NLI, MTCI, EVI, NDVI, RDVI and MTVI.
6. The method for predicting nitrogen diagnosis and quality indicator determination of tea trees based on unmanned aerial vehicle multispectral remote sensing according to claim 1, wherein the machine learning method comprises PLSR, SVM, BP neural networks.
7. The method for predicting nitrogen diagnosis and quality indicator determination of tea trees based on unmanned aerial vehicle multispectral remote sensing according to claim 1, wherein when the R 2, RMSE and NRMSE of the regression prediction model are tested to be close to a training set, the regression prediction model is shown to have good stability.
8. A prediction system of a prediction method for tea tree nitrogen diagnosis and quality index measurement based on unmanned aerial vehicle multispectral remote sensing as claimed in claim 1, comprising: unmanned plane;
The multispectral camera is carried on the unmanned aerial vehicle and is used for collecting multispectral images of the growth period of the tea tree;
the sensor is arranged on the multispectral camera and used for acquiring the nitrogen content and the quality index of the tea tree;
A processor that performs the following operations:
preprocessing a multispectral image acquired by the multispectral camera by using multispectral data inversion software therein to acquire spectral parameters; determining a region of interest using an environment visualization program therein; constructing a regression prediction model of tea tree nitrogen and quality indexes; and constructing an estimated remote sensing monitoring image of the nitrogen and the quality index of the tea tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555635.4A CN114140695B (en) | 2021-12-17 | 2021-12-17 | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111555635.4A CN114140695B (en) | 2021-12-17 | 2021-12-17 | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114140695A CN114140695A (en) | 2022-03-04 |
| CN114140695B true CN114140695B (en) | 2024-04-26 |
Family
ID=80382939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111555635.4A Active CN114140695B (en) | 2021-12-17 | 2021-12-17 | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114140695B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115144342B (en) * | 2022-06-21 | 2024-05-28 | 河海大学 | Unmanned aerial vehicle multispectral citrus blade nitrogen content estimation method based on semi-supervised learning |
| CN117195609B (en) * | 2023-11-08 | 2024-01-26 | 吉林大学 | Quantitative diagnosis method for nitrogen nutrient deficiency of regional corn plants |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059427A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Method for quickly non-destructive measurement for nitrogen content of tea using multiple spectrum imaging technology |
| 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 |
| CN111161362A (en) * | 2020-01-15 | 2020-05-15 | 昆山小茶智能科技有限公司 | Tea tree growth state spectral image identification method |
| CN112179853A (en) * | 2020-09-29 | 2021-01-05 | 山东农业大学 | Fruit tree canopy nitrogen content remote sensing inversion method and system based on image shadow removal |
| CN112834442A (en) * | 2021-01-04 | 2021-05-25 | 四川大学 | Multispectral data-based large-area-scale crop growth real-time monitoring method |
-
2021
- 2021-12-17 CN CN202111555635.4A patent/CN114140695B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059427A (en) * | 2007-05-29 | 2007-10-24 | 浙江大学 | Method for quickly non-destructive measurement for nitrogen content of tea using multiple spectrum imaging technology |
| 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 |
| CN111161362A (en) * | 2020-01-15 | 2020-05-15 | 昆山小茶智能科技有限公司 | Tea tree growth state spectral image identification method |
| CN112179853A (en) * | 2020-09-29 | 2021-01-05 | 山东农业大学 | Fruit tree canopy nitrogen content remote sensing inversion method and system based on image shadow removal |
| CN112834442A (en) * | 2021-01-04 | 2021-05-25 | 四川大学 | Multispectral data-based large-area-scale crop growth real-time monitoring method |
Non-Patent Citations (1)
| Title |
|---|
| 基于无人机多光谱影像的夏玉米叶片氮含量遥感估测;魏鹏飞;徐新刚;李中元;杨贵军;李振海;冯海宽;陈帼;范玲玲;王玉龙;刘帅兵;;农业工程学报;20190423(第08期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114140695A (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11029251B2 (en) | Method for estimating aboveground biomass of rice based on multi-spectral images of unmanned aerial vehicle | |
| Qiao et al. | UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages | |
| CN110222475B (en) | Method for inverting moisture content of winter wheat plants based on multispectral remote sensing of unmanned aerial vehicle | |
| CN106372592B (en) | A kind of winter wheat planting area calculation method based on winter wheat area index | |
| CN112903600B (en) | Rice nitrogen fertilizer recommendation method based on multispectral image of fixed-wing unmanned aerial vehicle | |
| CN101692037B (en) | Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component | |
| CN114140695B (en) | Prediction method and system for tea tree nitrogen diagnosis and quality index determination based on unmanned aerial vehicle multispectral remote sensing | |
| CN111241912A (en) | Multi-vegetation index rice yield estimation method based on machine learning algorithm | |
| CN112345458A (en) | Wheat yield estimation method based on multispectral image of unmanned aerial vehicle | |
| CN113221765B (en) | Vegetation phenological period extraction method based on digital camera image effective pixels | |
| Shu et al. | Improving the estimation accuracy of SPAD values for maize leaves by removing UAV hyperspectral image backgrounds | |
| CN109827957B (en) | Rice leaf SPAD value estimation method and system based on computer vision | |
| CN113252583B (en) | Method for calculating alpine hay coverage based on hay vegetation index | |
| CN116403048B (en) | Crop growth estimation model construction method based on multi-mode data fusion | |
| WO2023197496A1 (en) | Comprehensive evaluation indicator monitoring and evaluation method and system for machine-harvested cotton defoliation effects | |
| Liu et al. | Estimating wheat fractional vegetation cover using a density peak k-means algorithm based on hyperspectral image data | |
| CN114219795A (en) | Hyperspectral imaging system-based tea tree drought induction component and drought degree assessment prediction method and system | |
| CN112418073A (en) | Wheat plant nitrogen content estimation method based on unmanned aerial vehicle image fusion characteristics | |
| Liang et al. | CanopyCAM–an edge-computing sensing unit for continuous measurement of canopy cover percentage of dry edible beans | |
| CN107818565B (en) | Method for investigating quantity of wheat seedlings in one-to-three-leaf period of wheat | |
| CN111191543A (en) | Rape yield estimation method | |
| CN116229288A (en) | Urban river TSM concentration inversion method based on unmanned aerial vehicle multispectral image | |
| CN112504972B (en) | Method for rapidly monitoring nitrogen content of tobacco | |
| Fernando Sánchez-Sastre et al. | Assessment of RGB Vegetation Indices to Estimate Chlorophyll Content in Sugar Beet Leaves in the Final Cultivation Stage. | |
| CN115019205B (en) | Rape flowering phase SPAD and LAI estimation method based on unmanned aerial vehicle multispectral image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |