Dendrobium officinale polysaccharide estimation method and system based on hyperspectral imaging

Abstract

The embodiment of the invention provides a dendrobium officinale polysaccharide estimation method and system based on hyperspectral imaging, and belongs to the technical field of polysaccharide detection. The estimation method comprises the following steps: acquiring a dendrobium growth model at a dendrobium growth stage and corresponding chlorophyll content; obtaining the growth stage of the current dendrobium nobile; determining the corresponding chlorophyll content according to the current growth stage of the dendrobium and a dendrobium growth model; and inputting the chlorophyll content into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content. The chlorophyll content is adopted as an independent variable, and the optimization direction of model parameter gradient updating in the modeling process can be indicated. By using leaf hyperspectral image data and constructing a two-stage model of'hyperspectral inversion chlorophyll model-dendrobium growth model-polysaccharide content estimation model ', the problems of difficult parameter adjustment, poor model precision and the like of directly constructing a'hyperspectral inversion chlorophyll model-polysaccharide content estimation model' regression model are avoided, the applicability is high, and the method is suitable for popularization and application. The implementation is easy.

Description

Technical Field

[0001] The present invention relates to the technical field of polysaccharide detection, and in particular to a method and system for estimating polysaccharides of Dendrobium officinale based on hyperspectral imaging. Background Art

[0002] Plant physiological phenotype estimation is an important task in agricultural production and planting management. With the improvement of agricultural production automation, informatization and intelligence, plant physiological phenotype estimation technology has gradually become a research hotspot. The current main plant phenotype estimation technologies include space remote sensing, near-ground sensing, meteorological models, machine learning, etc. These technologies still have problems such as low modeling accuracy, poor universality, and low detection efficiency in practice. Plant physiological parameter estimation based on spectral data and machine learning is a type of method that has received widespread attention in recent years. This type of method obtains crop growth information by analyzing the spectral band data reflected or absorbed by organs such as plant leaves and rhizomes, thereby modeling and estimating the corresponding plant physiological phenotypes (such as chlorophyll content, vegetation index, etc.). However, the data obtained by existing plant physiological instruments such as spectrometers are mostly point data on a single leaf, lacking data on plant group leaves; the instrument operation is complex; the modeling algorithm corresponds to a single plant species, mostly leafy crops, which cannot meet the needs of large-scale plant spectral data acquisition and modeling accuracy in actual production.

[0003] As a high value-added economic crop, Dendrobium officinale's main component is dendrobium polysaccharide, and the polysaccharide content determines the quality of Dendrobium officinale. Therefore, there is an urgent need for a low-cost, simple, fast, and accurate method for estimating the polysaccharide content of Dendrobium officinale, which is not only suitable for large scientific research units, but also for individual planting production. The spectral imaging data of specific wavelengths and the polysaccharide content of Dendrobium officinale are used for algorithm modeling, which can reduce the cost of physiological phenotype detection and quickly and scientifically improve the estimation accuracy and efficiency. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for estimating the polysaccharide content of Dendrobium officinale based on hyperspectral imaging, which solves the problem of estimating the polysaccharide content of Dendrobium officinale in a low-cost, simple, fast and accurate manner.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for estimating polysaccharides of Dendrobium officinale based on hyperspectral imaging, and the method comprises:

[0006] Obtaining the growth stage of Dendrobium and the growth model of Dendrobium corresponding to the chlorophyll content;

[0007] Get the current growth stage of Dendrobium officinale;

[0008] Determining the corresponding chlorophyll content according to the current growth stage of the dendrobium and the growth model of the dendrobium;

[0009] The chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

[0010] Optionally, obtaining a growth model of Dendrobium officinale with a growth stage and a corresponding chlorophyll content includes:

[0011] Obtaining hyperspectral image data of Dendrobium leaves;

[0012] Construct a hyperspectral inversion chlorophyll model;

[0013] Inputting the hyperspectral image data into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the dendrobium leaves;

[0014] A dendrobium growth model is constructed according to the chlorophyll content and the dendrobium growth stage.

[0015] Optionally, a hyperspectral inversion chlorophyll model is constructed, including:

[0016] Constructing the hyperspectral inversion chlorophyll model according to the partial least squares regression method;

[0017] Dividing the hyperspectral image data into a training set and a validation set;

[0018] Using a training set to train the hyperspectral inversion chlorophyll model;

[0019] Using the validation set to estimate the performance index of the hyperspectral chlorophyll inversion model after training;

[0020] Determine whether the performance index of the hyperspectral inversion chlorophyll model meets the requirements;

[0021] When it is judged that the performance index of the hyperspectral inversion chlorophyll model meets the requirement, the hyperspectral inversion chlorophyll model is saved.

[0022] Optionally, dividing the hyperspectral image data into a training set and a validation set comprises:

[0023] Sorting the hyperspectral image data from low to high according to chlorophyll content;

[0024] Divide every four of the hyperspectral image data into one group;

[0025] The third hyperspectral image data in each group is used as a validation set, and the rest are used as training sets.

[0026] Optionally, the chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content, comprising:

[0027] On the basis of the long short-term memory network LSTM, the memory unit is simplified, and a reset gate and an update gate are set. The reset gate is used to control the influence weight of the historical state on the current candidate state, and the update gate is used to control the influence weight of the historical state and the current candidate state on the current hidden state;

[0028] Constructing the polysaccharide content estimation model according to the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate and outputting the polysaccharide content estimation value;

[0029] The loss function of the polysaccharide content estimation model is determined, the training loss of the polysaccharide content estimation model is determined according to the actual polysaccharide content and the polysaccharide content estimation value, and the parameter weights of the polysaccharide content estimation model are updated by back propagation.

[0030] Optionally, constructing the polysaccharide content estimation model and outputting the polysaccharide content estimation value according to the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate includes:

[0031] Pre-treating the chlorophyll content;

[0032] The chlorophyll content is input into the polysaccharide content estimation model, and the polysaccharide content estimation value is output.

[0033] On the other hand, the present invention provides a system for estimating polysaccharides of Dendrobium officinale based on hyperspectral imaging, the system comprising:

[0034] An image acquisition module, used to collect hyperspectral image data of Dendrobium leaves;

[0035] The processor is connected to the image acquisition module for obtaining the current content of dendrobium polysaccharides according to the hyperspectral image data.

[0036] Optionally, the processor is configured to execute:

[0037] Obtaining the growth stage of Dendrobium and the growth model of Dendrobium corresponding to the chlorophyll content;

[0038] Get the current growth stage of Dendrobium officinale;

[0039] Determining the corresponding chlorophyll content according to the current growth stage of the dendrobium and the growth model of the dendrobium;

[0040] The chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

[0041] Optionally, obtaining a growth model of Dendrobium officinale with a growth stage and a corresponding chlorophyll content includes:

[0042] Acquiring hyperspectral image data of the dendrobium leaves;

[0043] Construct a hyperspectral inversion chlorophyll model;

[0044] Inputting the hyperspectral image data into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the dendrobium leaves;

[0045] A dendrobium growth model is constructed according to the chlorophyll content and the dendrobium growth stage.

[0046] Through the above technical scheme, the present invention establishes a growth model of Dendrobium by tracking the entire growth cycle of Dendrobium, and then constructs a polysaccharide content estimation model according to the chlorophyll content and the polysaccharide content. The chlorophyll content of the Dendrobium leaf is used as an independent variable, which is conducive to indicating the optimization direction of the gradient update of the model parameter in the modeling process, and reduces the optimization difficulty of the model. And the hyperspectral image data of the leaf is used instead of the point data obtained by the conventional near-infrared spectrometer. Through the two-level model construction of "hyperspectral-chlorophyll time series-Dendrobium polysaccharide", the problems of difficult parameter adjustment and poor model accuracy of the direct construction of the "hyperspectral inversion chlorophyll model-polysaccharide content estimation model" regression model are avoided. The present invention solves the problem that it is difficult to simply, low-cost, accurately and efficiently obtain the content of Dendrobium polysaccharide in traditional estimation, has very important application value and social and economic benefits, can be widely used in agriculture, gardening and other fields, has strong applicability, simple and effective methods, and is easy to implement.

[0047] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0049] Figure 1 is a flow chart of an estimation method according to one embodiment of the invention;

[0050] Figure 2 is a flow chart of constructing a growth model of Dendrobium officinale according to one embodiment of the invention;

[0051] Figure 3 is a flow chart of constructing a hyperspectral inversion chlorophyll model according to one embodiment of the invention;

[0052] Figure 4 is a flow chart of partitioning data according to one embodiment of the invention;

[0053] Figure 5 is a flow chart of constructing a polysaccharide yield estimation model according to one embodiment of the invention;

[0054] Figure 6 is a flow chart for obtaining an estimated value of polysaccharide content according to one embodiment of the invention. DETAILED DESCRIPTION

[0055] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0056] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0057] Figure 1 is a flow chart of an estimation method according to an embodiment of the present invention, in which the estimation method comprises:

[0058] In step S1, a growth model of Dendrobium officinale with a growth stage and a corresponding chlorophyll content is obtained.

[0059] In step S2, the current growth stage of the Dendrobium officinale is obtained.

[0060] In step S3, the corresponding chlorophyll content is determined according to the current growth stage of the dendrobium and the growth model of the dendrobium.

[0061] In step S4, the chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

[0062] Compared with the prior art, the present invention tracks the entire growth cycle of Dendrobium officinale, establishes a growth model of Dendrobium officinale, and then constructs a polysaccharide content estimation model based on chlorophyll content and polysaccharide yield, and uses the chlorophyll content of Dendrobium officinale leaves as an independent variable, which is conducive to indicating the optimization direction of the gradient update of the model parameter in the modeling process, and reduces the optimization difficulty of the model. The present invention solves the problem that traditional estimation is difficult to obtain the polysaccharide content of Dendrobium officinale simply, at low cost, accurately and efficiently, has very important application value and social and economic benefits, can be widely used in agriculture, gardening and other fields, has strong applicability, and the method is simple and effective, and is easy to implement.

[0063] With the popularization of hyperspectral technology, researchers have found that hyperspectral reflectance data may contain a variety of physiological and biochemical information of plants, and hyperspectral reflectance data can be used to establish prediction methods and models for plant phenotypic traits. However, existing hyperspectral technology is mostly used for "point" measurement of plant leaves, which cannot meet the measurement requirements of the whole plant or canopy level. On the other hand, the plant physiological phenotype regression model based on the spectral reflectance data of point measurement is subject to limited point measurement data, and the modeling accuracy cannot meet the monitoring needs of actual production, making it difficult to apply. Hyperspectral imaging technology can obtain hyperspectral image data of the whole plant or canopy level of plants, which makes up for the shortcomings of conventional leaf "point" measurement and is suitable for fast, non-destructive and comprehensive growth observation of plants. However, the increase in the dimension of hyperspectral image data increases the difficulty of data mining. Using traditional machine learning algorithms to directly model the "hyperspectral image-polysaccharide content" regression model, the model parameters are difficult to adjust and converge. Therefore, in this embodiment, the present invention avoids the problems of difficult parameter adjustment and poor model accuracy of directly constructing the regression model of "hyperspectral inversion chlorophyll model-Dendrobium growth model-polysaccharide content estimation model" by constructing a two-level model of "hyperspectral inversion chlorophyll model-Dendrobium growth model-polysaccharide content estimation model". The specific steps for obtaining the growth stage of Dendrobium and the corresponding chlorophyll content of Dendrobium growth model can be various known to those skilled in the art. In one example of the present invention, Figure 2 As shown, this may include:

[0064] In step S11, hyperspectral image data of the dendrobium leaves are obtained, wherein the wavelength range of the obtained hyperspectral image data is 400-1000nm, and the aboveground part of the dendrobium, namely the stem and leaf imaging area, is extracted.

[0065] In step S12, a hyperspectral inversion chlorophyll model is constructed. In the process of constructing a hyperspectral inversion chlorophyll model, historical data is needed to train the hyperspectral inversion chlorophyll model. When collecting hyperspectral image data, a hyperspectral imager is used to measure the reflectance spectrum imaging data, and the spectrum acquisition range is 400-1000nm. Set the sampling time point and interval, use a hyperspectral imaging device, and regularly collect data from the aboveground part of the same part of Dendrobium for chlorophyll content detection. During a single sampling, multiple data are collected and averaged to improve accuracy. The specific preparation method includes:

[0066] The prepared leaves were placed on a light source imaging table to collect data. Before measurement, a standard diffuse reflectance whiteboard made of polytetrafluoroethylene was used for standard spectral calibration. Considering the uneven characteristics of the leaves, three hyperspectral images of fresh branches with leaves were repeatedly collected for each plant. After collecting the spectral data of all the fresh branches and leaves of the above samples, the leaves were collected and numbered and placed in a centrifuge tube. An appropriate amount of solvent such as ethanol or acetone was added to allow the chlorophyll to fully contact and dissolve with the solvent. The chlorophyll was mixed by oscillation and centrifuged to obtain a chlorophyll extract. Using an ultraviolet-visible spectrophotometer, the absorbance in the chlorophyll extract was measured at different wavelengths. According to the absorbance values ​​at specific wavelengths (663nm and 645nm), the chlorophyll content was calculated, and finally the hyperspectral image data and chlorophyll content of the leaves to be trained were obtained.

[0067] In step S13, the hyperspectral image data is input into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the Dendrobium leaves. The original plant physiological phenotype regression model based on the spectral reflectance data modeled by point measurement is subject to limited point measurement data and cannot reflect the overall level of the plant. Therefore, the modeling accuracy cannot meet the monitoring needs of actual production and is difficult to apply. Compared with the prior art, the key point of the present invention is to use the hyperspectral imaging data of the leaves instead of the point data obtained by the conventional near-infrared spectrometer. A hyperspectral inversion model for the chlorophyll content of Dendrobium leaves is established based on the hyperspectral imaging equipment. The acquisition is accurate and fast, which can effectively avoid the cumbersome process of traditional agricultural methods that requires a lot of manual operations, and improve the accuracy and efficiency of the estimation of Dendrobium polysaccharide yield.

[0068] In step S14, a growth model of Dendrobium officinale is constructed according to the chlorophyll content and the growth stage of Dendrobium officinale.

[0069] The PLSR (Partial Least Squares Regression) model is a statistical method for establishing a prediction model. It decomposes the independent variables and dependent variables into new latent variables and performs linear regression on these latent variables to establish a linear fitting prediction model. Specifically, the PLSR model consists of two parts: 1) the decomposition process, that is, decomposing the independent variables and dependent variables into new latent variables; 2) the regression process, the linear regression is performed on the latent variables to establish a prediction model. In the decomposition process, the PLSR model uses methods such as orthogonal partial least squares (OPLS) or non-orthogonal partial least squares (NPLS) to convert the original independent variable and dependent variable matrices into new latent variable matrices. In the regression process, the PLSR model reduces the dimension of a large number of potential related variables to avoid multicollinearity problems, uses the least squares method to perform linear regression on these latent variables, and determines the relationship between the variables based on the regression coefficients. The PLSR method has strong interpretability, low computing power requirements, and fast calculation speed. Based on the above statistical data, we use the PLSR algorithm to model the chlorophyll content of leaves and analyze and evaluate the performance of the model. The linear PLSR method is used to fit the data with the average spectral reflectance curve of the hyperspectral image data of each leaf sample as the input variable and the chlorophyll content as the output variable. Therefore, in this embodiment, the specific steps for constructing the hyperspectral inversion chlorophyll model can be various known to those skilled in the art. In one example of the present invention, Figure 3 As shown, this may include:

[0070] In step S121, a hyperspectral inversion chlorophyll model is constructed according to the partial least squares regression method.

[0071] In step S122 , the hyperspectral image data is divided into a training set and a validation set.

[0072] In step S123, the training set is used to train the hyperspectral inversion chlorophyll model.

[0073] In step S124, the validation set is used to estimate the performance index of the trained hyperspectral chlorophyll inversion model.

[0074] In step S125, it is determined whether the performance indicators of the hyperspectral inversion chlorophyll model meet the requirements. If it is determined that the performance indicators of the hyperspectral inversion chlorophyll model meet the requirements, step S126 is executed, otherwise step S123 is executed. Among them, the types of performance indicators can be a variety known to those skilled in the art. In one example of the present invention, the hyperspectral inversion chlorophyll model of the present invention uses the determination coefficient (R2), the root mean square error of prediction (RMSEP) and the relative analytical error (RPD) to evaluate and compare the prediction performance of the hyperspectral inversion chlorophyll model. Rc2 and Rp2 represent the determination coefficients of the calibration and prediction sets, respectively. The closer R2 is to 1 and the smaller the RMSEP is, the higher the accuracy of the model is. In addition, an RPD value less than 1.5 indicates that the model prediction performance is very poor; an RPD value between 1.5 and 2.0 indicates that the model prediction performance is poor and can only be roughly estimated; an RPD value between 2.0 and 2.5 indicates that an approximate quantitative prediction can be made; an RPD value between 2.5 and 3.0 indicates that the model prediction performance is good and quantitative analysis can be done; a PRD value above 3.0 is classified as an excellent quantitative prediction model and can achieve high-precision quantitative analysis. Specifically, it includes:

[0075] The coefficient of determination is calculated according to formula (1):

[0076]

[0077] According to formula (2), the root mean square error is calculated:

[0078]

[0079] The relative analysis error is calculated according to formula (3):

[0080]

[0081] in, is the i-th predicted chlorophyll content, is the average value of the actual measured chlorophyll content, y i is the chlorophyll content of the ith actual measurement, n is the number of sample data, SD p is the standard deviation of the prediction set, R 2 is the coefficient of determination, RMSEP is the root mean square error, and RPD is the relative analytical error.

[0082] In step S126, the hyperspectral inversion chlorophyll model is saved.

[0083] In order to avoid changing the original spectral information, we use the original spectral data for data analysis. The data is divided into a training set and a validation set at a ratio of 3:1. In order to reduce the data difference between the training set and the validation set, all the data are sorted from low to high according to the chlorophyll content, and then the third data is extracted from every four data items as the validation set data. Therefore, the step of dividing the hyperspectral image data into a training set and a validation set can be a variety of steps known to those skilled in the art. In one example of the present invention, Figure 4 As shown, including:

[0084] In S1221, the hyperspectral image data is sorted from low to high according to the chlorophyll content.

[0085] In S1222, every four hyperspectral image data are divided into one group.

[0086] In S1223, the third hyperspectral image data in each group is used as a validation set, and the rest are used as training sets.

[0087] In this embodiment, in order to solve the problem of gradient disappearance or explosion in traditional RNN and the problem of unsatisfactory memory effect when processing long sequence data, the present invention tracks the entire growth cycle of Dendrobium, establishes a Dendrobium growth model by detecting the chlorophyll content at different growth stages of Dendrobium, and establishes a polysaccharide yield estimation model based on the GRU algorithm. Specifically, Figure 5 As shown, including:

[0088] In step S41, the memory cell is simplified on the basis of the long short-term memory network LSTM, and a reset gate and an update gate are set. The reset gate is used to control the weight of the influence of the historical state on the current candidate state, and the update gate is used to control the weight of the influence of the historical state and the current candidate state on the current hidden state. GRU simplifies the memory cell structure (cell) on the basis of the recurrent neural network RNN, and introduces a gating mechanism to alleviate the gradient disappearance problem of traditional RNN and LSTM in long sequence learning. GRU controls the information flow through two main gating mechanisms: reset gate and update gate. GRU does not have a separate memory cell, but directly maintains long-term memory through hidden states. Among them, the reset gate controls how to use the past hidden state to calculate the candidate state at the current moment. If the value of the reset gate is 0, it means that the past hidden state is ignored and only the input at the current moment is considered. The update gate determines how much of the hidden state at the current moment comes from the hidden state at the previous moment and how much comes from the current candidate state. The update gate enables GRU to maintain control of historical information at each moment. When calculating the candidate hidden state, GRU will decide how to combine the current moment input and the hidden state at the previous moment based on the output of the reset gate. The final hidden state is obtained by weighted averaging the previous hidden state and the current candidate hidden state through the update gate. Specifically, it includes:

[0089] According to formula (4), the reset gate of the polysaccharide content estimation model is determined.

[0090] r t =Sigmoid(W r [h t-1 , x t ]+b r ), (4)

[0091] Among them, r t is the output of the reset gate at the current moment, W r is the weight matrix, b r is the bias term, h t-1 is the hidden state at the previous moment, x t is the input at the current moment;

[0092] According to formula (5), the update gate of the polysaccharide content estimation model is determined.

[0093] z t =Sigmoid(W z [h t-1 , x t ]+b z ), (5)

[0094] Among them, z t is the output of the update gate at the current moment, Wz is the weight matrix, b z is the bias term, h t-1 is the hidden state at the previous moment, x t is the input at the current moment;

[0095] According to formula (6), the candidate hidden states of the polysaccharide content estimation model are determined.

[0096]

[0097] in, is the candidate hidden state at the current moment, r t is the output of the reset gate at the current moment, b h is the bias term, h t-1 is the hidden state at the previous moment, x t is the input at the current moment, tanh is the hyperbolic tangent activation function;

[0098] According to formula (7), the final hidden state of the polysaccharide content estimation model is determined.

[0099]

[0100] Among them, h t is the hidden state at the current moment, z t Update the output of the gate for the current moment, is the candidate hidden state at the current moment, h t-1 is the hidden state at the previous moment, x t The input at the current moment.

[0101] In step S42, a polysaccharide content estimation model is constructed based on the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate, and the polysaccharide content estimation value is output. Specifically, smooth L1 loss is selected as the loss function, including:

[0102] Determine the loss function of the estimation model according to formula (8)

[0103]

[0104] Where x is the estimated value of polysaccharide content, is the actual polysaccharide content, and smoothL1loss is the loss function.

[0105] In step S43, the loss function of the polysaccharide content estimation model is determined, the training loss of the polysaccharide content estimation model is determined according to the actual polysaccharide content and the polysaccharide content estimation value, and the parameter weights of the polysaccharide content estimation model are updated by back propagation.

[0106] In this embodiment, the steps of constructing a polysaccharide content estimation model and outputting a polysaccharide content estimation value according to the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate can be various steps known to those skilled in the art. In one example of the present invention, Figure 6 As shown, this may include:

[0107] In step S421, the chlorophyll content is preprocessed, that is, the polysaccharide content of the dendrobium at different growth stages detected is normalized, including:

[0108] The chlorophyll content is normalized according to formula (9):

[0109]

[0110] Among them, x t is the chlorophyll content at time t, x′ t is the normalized chlorophyll content at time t, x max and x min are the maximum and minimum values ​​of chlorophyll content, respectively.

[0111] In step S422, the chlorophyll content is input into a polysaccharide content estimation model, and an estimated polysaccharide content value is output.

[0112] On the other hand, the present invention provides a system for estimating polysaccharides of Dendrobium officinale based on hyperspectral imaging, the system comprising an image acquisition module and a processor. The image acquisition module is used to collect hyperspectral image data of Dendrobium officinale leaves, and the processor is connected to the image acquisition module in communication to obtain the current polysaccharide content of Dendrobium officinale according to the hyperspectral image data.

[0113] In this embodiment, the processor is used to execute the following method, including:

[0114] In step S1, a growth model of Dendrobium officinale with a growth stage and a corresponding chlorophyll content is obtained.

[0115] In step S2, the current growth stage of the Dendrobium officinale is obtained.

[0116] In step S3, the corresponding chlorophyll content is determined according to the current growth stage of the dendrobium and the growth model of the dendrobium.

[0117] In step S4, the chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

[0118] Compared with the prior art, the present invention tracks the entire growth cycle of Dendrobium officinale, establishes a growth model of Dendrobium officinale, and then constructs a polysaccharide content estimation model based on chlorophyll content and polysaccharide yield, and uses the chlorophyll content of Dendrobium officinale leaves as an independent variable, which is conducive to indicating the optimization direction of the gradient update of the model parameter in the modeling process, and reduces the optimization difficulty of the model. The present invention solves the problem that traditional estimation is difficult to obtain the polysaccharide content of Dendrobium officinale simply, at low cost, accurately and efficiently, has very important application value and social and economic benefits, can be widely used in agriculture, gardening and other fields, has strong applicability, and the method is simple and effective, and is easy to implement.

[0119] With the popularization of hyperspectral technology, researchers have found that hyperspectral reflectance data may contain a variety of physiological and biochemical information of plants, and hyperspectral reflectance data can be used to establish prediction methods and models for plant phenotypic traits. However, existing hyperspectral technology is mostly used for "point" measurement of plant leaves, which cannot meet the measurement requirements of the whole plant or canopy level. On the other hand, the plant physiological phenotype regression model based on the spectral reflectance data of point measurement is subject to limited point measurement data, and the modeling accuracy cannot meet the monitoring needs of actual production, making it difficult to apply. Hyperspectral imaging technology can obtain hyperspectral image data of the whole plant or canopy level of plants, which makes up for the shortcomings of conventional leaf "point" measurement and is suitable for fast, non-destructive and comprehensive growth observation of plants. However, the increase in the dimension of hyperspectral image data increases the difficulty of data mining. Using traditional machine learning algorithms to directly model the "hyperspectral image-polysaccharide content" regression model, the model parameters are difficult to adjust and converge. Therefore, in this embodiment, the present invention avoids the problems of difficult parameter adjustment and poor model accuracy of directly constructing the regression model of "hyperspectral inversion chlorophyll model-Dendrobium growth model-polysaccharide content estimation model" by constructing a two-level model of "hyperspectral inversion chlorophyll model-Dendrobium growth model-polysaccharide content estimation model". The specific steps for obtaining the growth stage of Dendrobium and the corresponding chlorophyll content of Dendrobium growth model can be various known to those skilled in the art. In one example of the present invention, Figure 2 As shown, this may include:

[0120] In step S11, hyperspectral image data of the dendrobium leaves are obtained, wherein the wavelength range of the obtained hyperspectral image data is 400-1000nm, and the aboveground part of the dendrobium, namely the stem and leaf imaging area, is extracted.

[0121] In step S12, a hyperspectral inversion chlorophyll model is constructed. In the process of constructing a hyperspectral inversion chlorophyll model, historical data is needed to train the hyperspectral inversion chlorophyll model. When collecting hyperspectral image data, a hyperspectral imager is used to measure the reflectance spectrum imaging data, and the spectrum acquisition range is 400-1000nm. Set the sampling time point and interval, use a hyperspectral imaging device, and regularly collect data from the aboveground part of the same part of Dendrobium for chlorophyll content detection. During a single sampling, multiple data are collected and averaged to improve accuracy. The specific preparation method includes:

[0122] The prepared leaves were placed on a light source imaging table to collect data. Before measurement, a standard diffuse reflectance whiteboard made of polytetrafluoroethylene was used for standard spectral calibration. Considering the uneven characteristics of the leaves, three hyperspectral images of fresh branches with leaves were repeatedly collected for each plant. After collecting the spectral data of all the fresh branches and leaves of the above samples, the leaves were collected and numbered and placed in a centrifuge tube. An appropriate amount of solvent such as ethanol or acetone was added to allow the chlorophyll to fully contact and dissolve with the solvent. The chlorophyll was mixed by oscillation and centrifuged to obtain a chlorophyll extract. Using an ultraviolet-visible spectrophotometer, the absorbance in the chlorophyll extract was measured at different wavelengths. According to the absorbance values ​​at specific wavelengths (663nm and 645nm), the chlorophyll content was calculated, and finally the hyperspectral image data and chlorophyll content of the leaves to be trained were obtained.

[0123] In step S13, the hyperspectral image data is input into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the Dendrobium leaves. The original plant physiological phenotype regression model based on the spectral reflectance data modeled by point measurement is subject to limited point measurement data and cannot reflect the overall level of the plant. Therefore, the modeling accuracy cannot meet the monitoring needs of actual production and is difficult to apply. Compared with the prior art, the key point of the present invention is to use the hyperspectral imaging data of the leaves instead of the point data obtained by the conventional near-infrared spectrometer. A hyperspectral inversion model for the chlorophyll content of Dendrobium leaves is established based on the hyperspectral imaging equipment. The acquisition is accurate and fast, which can effectively avoid the cumbersome process of traditional agricultural methods that requires a lot of manual operations, and improve the accuracy and efficiency of the estimation of Dendrobium polysaccharide yield.

[0124] In step S14, a growth model of Dendrobium officinale is constructed according to the chlorophyll content and the growth stage of Dendrobium officinale.

[0125] Through the above technical scheme, the present invention establishes a growth model of Dendrobium by tracking the entire growth cycle of Dendrobium, and then constructs a polysaccharide content estimation model according to the chlorophyll content and the polysaccharide content. The chlorophyll content of the Dendrobium leaf is used as an independent variable, which is conducive to indicating the optimization direction of the gradient update of the model parameter in the modeling process, and reduces the optimization difficulty of the model. And the hyperspectral image data of the leaf is used instead of the point data obtained by the conventional near-infrared spectrometer. Through the two-level model construction of "hyperspectral-chlorophyll time series-Dendrobium polysaccharide", the problems of difficult parameter adjustment and poor model accuracy of the direct construction of the "hyperspectral inversion chlorophyll model-polysaccharide content estimation model" regression model are avoided. The present invention solves the problem that it is difficult to simply, low-cost, accurately and efficiently obtain the content of Dendrobium polysaccharide in traditional estimation, has very important application value and social and economic benefits, can be widely used in agriculture, gardening and other fields, has strong applicability, simple and effective methods, and is easy to implement.

[0126] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0127] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for estimating polysaccharides of Dendrobium officinale based on hyperspectral imaging, characterized in that: The estimation method includes: Obtaining the growth stage of Dendrobium and the growth model of Dendrobium corresponding to the chlorophyll content; Get the current growth stage of Dendrobium officinale; Determining the corresponding chlorophyll content according to the current growth stage of the dendrobium and the growth model of the dendrobium; The chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

2. The estimation method according to claim 1, characterized in that: The growth model of Dendrobium officinale to obtain the growth stage of Dendrobium officinale and the corresponding chlorophyll content includes: Acquire hyperspectral image data of Dendrobium leaves; Construct a hyperspectral inversion chlorophyll model; Inputting the hyperspectral image data into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the dendrobium leaves; A dendrobium growth model is constructed according to the chlorophyll content and the dendrobium growth stage.

3. The estimation method according to claim 2, characterized in that: Construct a hyperspectral inversion chlorophyll model, including: Constructing the hyperspectral inversion chlorophyll model according to the partial least squares regression method; Dividing the hyperspectral image data into a training set and a validation set; Using a training set to train the hyperspectral inversion chlorophyll model; Using the validation set to estimate the performance index of the hyperspectral chlorophyll inversion model after training; Determine whether the performance index of the hyperspectral inversion chlorophyll model meets the requirements; When it is judged that the performance index of the hyperspectral inversion chlorophyll model meets the requirement, the hyperspectral inversion chlorophyll model is saved.

4. The estimation method according to claim 3, characterized in that: The hyperspectral image data is divided into a training set and a validation set, including: Sorting the hyperspectral image data from low to high according to chlorophyll content; Divide every four of the hyperspectral image data into one group; The third hyperspectral image data in each group is used as a validation set, and the rest are used as training sets.

5. The estimation method according to claim 1, characterized in that: Inputting the chlorophyll content into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content, comprising: On the basis of the long short-term memory network LSTM, the memory unit is simplified, and a reset gate and an update gate are set. The reset gate is used to control the influence weight of the historical state on the current candidate state, and the update gate is used to control the influence weight of the historical state and the current candidate state on the current hidden state; Constructing the polysaccharide content estimation model according to the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate and outputting the polysaccharide content estimation value; The loss function of the polysaccharide content estimation model is determined, the training loss of the polysaccharide content estimation model is determined according to the actual polysaccharide content and the polysaccharide content estimation value, and the parameter weights of the polysaccharide content estimation model are updated by back propagation.

6. The method according to claim 5, characterized in that The polysaccharide content estimation model is constructed according to the chlorophyll content, the actual polysaccharide content, the reset gate and the update gate, and the polysaccharide content estimation value is output, including: Pre-treating the chlorophyll content; The chlorophyll content is input into the polysaccharide content estimation model, and the polysaccharide content estimation value is output.

7. A Dendrobium officinale polysaccharide estimation system based on hyperspectral imaging, characterized in that: The system comprises: An image acquisition module, used to collect hyperspectral image data of Dendrobium leaves; The processor is connected to the image acquisition module for obtaining the current content of dendrobium polysaccharides according to the hyperspectral image data.

8. The system according to claim 7, characterized in that The processor is configured to execute: Obtaining the growth stage of Dendrobium and the growth model of Dendrobium corresponding to the chlorophyll content; Get the current growth stage of Dendrobium officinale; Determining the corresponding chlorophyll content according to the current growth stage of the dendrobium and the growth model of the dendrobium; The chlorophyll content is input into a polysaccharide content estimation model to obtain the dendrobium polysaccharide content.

9. The system according to claim 8, characterized in that The growth model of Dendrobium officinale to obtain the growth stage of Dendrobium officinale and the corresponding chlorophyll content includes: Acquiring hyperspectral image data of the dendrobium leaves; Construct a hyperspectral inversion chlorophyll model; Inputting the hyperspectral image data into the hyperspectral inversion chlorophyll model to obtain the chlorophyll content of the dendrobium leaves; A dendrobium growth model is constructed according to the chlorophyll content and the dendrobium growth stage.

Images