CN110779875A - Method for detecting moisture content of winter wheat ear based on hyperspectral technology - Google Patents
Method for detecting moisture content of winter wheat ear based on hyperspectral technology Download PDFInfo
- Publication number
- CN110779875A CN110779875A CN201911059362.7A CN201911059362A CN110779875A CN 110779875 A CN110779875 A CN 110779875A CN 201911059362 A CN201911059362 A CN 201911059362A CN 110779875 A CN110779875 A CN 110779875A
- Authority
- CN
- China
- Prior art keywords
- winter wheat
- moisture content
- model
- wheat ear
- data
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for detecting moisture content of winter wheat ear based on hyperspectral technology, which comprises the steps of processing collected moisture data of the winter wheat ear, screening a characteristic wave band sensitive to the moisture content of the winter wheat ear, constructing an estimation model of the moisture content of the winter wheat ear by adopting a partial least square method, and adopting a decision coefficient R
2And performing model precision detection on the measured data and the root mean square error RMSE pair, and finally inputting the sensitive spectrum data of the target to be detected into the model in the third step to obtain the moisture content information of the winter wheat ear. The model constructed by the method can meet the requirement of detection precision of the moisture content of the winter wheat ear, and the detection precision, robustness and universality of the moisture content of the winter wheat ear are improved.
Description
Technical Field
The invention relates to the technical field of wheat moisture content detection, in particular to a method for detecting moisture content of winter wheat ear based on a hyperspectral technology.
Background
Winter wheat is grown in a slightly warm place, and is generally sown in the middle and last ten months of 9 months to the last ten months of 10 months, and matured in the middle and last months of 5 months to 6 months in the next year. Such as winter wheat in north and south China. The winter wheat is one of the main grain crops in China, the demand for grain production is gradually expanded along with the economic and social development of China, the growth and development conditions of the winter wheat are dynamically estimated, the yield of the winter wheat can be mastered in time, and the growth and development of the winter wheat ear is the key of yield formation, so that the development of the detection on the physiological parameters of the winter wheat ear has important significance.
The research and application of the Chinese agricultural remote sensing technology go through several stages from the technology introduction at the end of the 20 th century at 70 years, the key technology in the middle and later periods of the 80 th year to the 90 th year, and the rapid development and business application at present in the middle and later periods of the 90 th year. In the past 20 years, the research and application of Chinese agricultural remote sensing technology are greatly developed from depth and breadth, and remarkable progress is made. At present, remote sensing is widely applied to all links of agricultural production by virtue of the advantages of rapidness, simplicity, convenience, macroscopicity, no damage, objectivity and the like. The rapid acquisition and analysis of the farmland crop information is the premise and the basis for developing precise agricultural practice, is a key for breaking through the bottleneck restricting the application and development of the modern agriculture in China, and has obvious advantages in the agricultural field information acquisition in the remote sensing technology. Agricultural remote sensing information acquisition is the basis of agricultural remote sensing application. Chinese agricultural remote sensing information acquisition depends on foreign remote sensing data, and is carried out by massive application of autonomous domestic satellite remote sensing data, aerial remote sensing, unmanned aerial vehicles and ground near-distance remote sensing, so that a technical system for 'sky-ground-network' integrated agricultural remote sensing information collaborative comprehensive acquisition is formed.
Important basic information for measuring the health level of the winter wheat in the later growth and development period when the moisture content of the winter wheat ear is supplied in balance is also important basic data for evaluating the yield of the winter wheat, however, no technology for detecting the moisture content of the winter wheat ear exists at present, so that how to quickly and accurately detect the moisture content of the winter wheat ear is a problem which needs to be solved urgently. The invention provides a detection method for rapidly, nondestructively and accurately detecting the moisture content of the winter wheat ear by utilizing a hyperspectral technology, so that the growth and development information of the winter wheat ear can be effectively obtained, and a necessary basic technical support is provided for the yield estimation of the winter wheat.
Disclosure of Invention
Based on the technical problems, the invention aims to provide a method for detecting the moisture content of winter wheat ears based on a hyperspectral technology.
The detection method comprises the following steps:
carrying out field inspection on the spot, determining and carrying out collection and data processing of winter wheat samples and spectral data, then putting winter wheat ears into a baking oven in a laboratory, drying the winter wheat ears to constant weight, weighing the dry weight of the ears, and obtaining the water content of the wheat ears by adopting a conventional calculation method; screening 2/3 samples as training samples and 1/3 samples as verification samples by adopting a random sampling method;
secondly, based on the training sample, performing smooth denoising processing on the spectral data, processing and analyzing the spectral data by using a wavelet algorithm, performing correlation analysis on the spectral data and the water content of the winter wheat ear, and screening a characteristic wave band sensitive to the water content of the winter wheat ear;
step three, according to the sensitive characteristic wave band screened in the step two, an estimation model of the moisture content of the winter wheat ear is constructed by adopting a partial least square method, and a determination coefficient R is adopted
2Carrying out model precision detection on the model and the root mean square error RMSE pair so as to determine the feasibility of the test model;
and step four, finally inputting the sensitive spectrum data of the target to be detected into the model in the step three, and obtaining the moisture content information of the winter wheat ear.
Preferably, the spectral data in the step one is obtained by using a surface feature spectrometer.
Preferably, the spectral data is obtained by performing a winter wheat spectral measurement method in the field, and collecting winter wheat canopy spectral data in the field by using a ground feature spectrometer with a wave band coverage range of 350-2500 nm and an output spectral resolution of 1nm, wherein 10 pieces of spectral data are measured for each sample, and the average of the spectral data is taken as a final spectrum. Wherein the feature spectrometer uses a field portable feature spectrometer manufactured by ASD corporation of America for measurement.
Further preferably, the collected canopy spectral data is subjected to data processing, and the data processing comprises three parts of spectral smoothing, wavelet analysis and correlation analysis. The spectral digital signal collected by the photon detection system of the ground object spectrometer mainly comprises a detector response signal to the ground object and system noise. The detector is a valuable signal for the ground object response signal, needs to be reserved, and needs to be removed for system noise. In addition, background noise and spectral noise in the surface feature spectral curve also need to be eliminated, and spectral smoothing is adopted for noise elimination. Then, the smoothed spectrum is subjected to wavelet transform.
The spectral data obtained after the collected data are processed also needs to be verified, 1/3 samples are randomly screened from all samples to verify the processed data, and the accuracy of the data is further enhanced.
The spectrum smoothing process in the data processing: the spectrum digital signal collected by the photoelectric detection system of the ground object spectrometer is divided into two parts: the detector responds to the ground object response signal and the system noise. The system noise is mainly generated when each component of the detection system works, and besides, the ground object spectral curve also comprises background noise and spectral noise. The existence of noise brings great interference to the analysis, detection and discrimination of the ground object spectrum. To eliminate these interferences, the useful information needed is extracted from the surface feature spectrum, and a smoothing preprocessing is needed to perform on many "glitch" noises existing in the spectrum. Common smoothing methods are: moving average, Savitaky-Golay (SG) convolution smoothing, median filtering, Gaussian (GS) filtering, low-pass filtering, and wavelet de-noising. Different methods have different effects, and the principle for evaluating the superiority and inferiority of the smoothing method is as follows: the spectral curve is as smooth as possible under the principle that the characteristic value of the spectrum is kept to the maximum extent, and the sensitivity of the smoothed spectral curve to the moisture content of the winter wheat ear is better. After comparing several methods according to the self concept and principle of spectral denoising, the invention adopts a Hamming window low-pass filter with the length of 9 to smooth the spectral data through comparison analysis in the test.
The wavelet transform can decompose functions or signals on multiple scales through operations such as expansion, translation and the like, well overcomes the defect that the Fourier transform cannot simultaneously analyze a time domain and a frequency domain, is applied to numerous fields such as forest type identification, plant stress identification, geography, pest and disease information extraction, remote sensing image processing and the like, and is mainly applied to the field of vegetation physical and chemical parameter inversion by the continuous wavelet technology. The wavelet transformation can extract characteristic information which is most sensitive to vegetation physical and chemical parameters from spectral reflectivity data of hyperspectral remote sensing. The continuous wavelet transformation can obtain wavelet capability coefficients obtained by decomposing hyperspectral data on multiple scales at different positions, and can better extract some sensitive spectral characteristic information for quantitative inversion of moisture of winter wheat through correlation analysis. The continuous wavelet transform method decomposes the spectral reflectivity into wavelet energy coefficients with different scales by using a mother wavelet function, and adopts the following wavelet bases:
when a > 1, the compensation of ψ (λ/α) is larger than the wavelength range of ψ (λ), the wavelength range of ψ (λ/α) becomes larger than the increasing amplitude of the wavelength range of ψ (λ), when the wavelet transformation reflects relatively coarsely on the wavelength and reflects relatively finely on the frequency, which exactly corresponds to the low-frequency case, with a value of α < 1, the wavelength range of ψ (λ/α) is smaller than the wavelength range of ψ (λ), when the value of α is gradually reduced, the amplitude of ψ (λ/α) decreases than the wavelength range of ψ (λ) becomes smaller, when the wavelet transformation reflects relatively coarsely on the frequency and reflects relatively finely on the wavelength, these are the relative advantages of the method for finding the water content and the reason for the inversion of the water content of the wheat leaf.
(2) The hyperspectral data processing is carried out by adopting a wavelet technology denoising principle, wherein wavelet analysis is carried out by adopting localization and is mainly based on the detailed analysis of functions on time frequency and space frequency, so that relevant information is effectively extracted, and the problem which cannot be solved by Fourier transform is solved. The method comprises the steps of transforming a hyperspectral data signal by Continuous Wavelet Transform (CWT), selecting a threshold value to select the threshold value of a Wavelet coefficient obtained by transformation, and then reconstructing the signal according to the coefficient selected by the threshold value to obtain a denoised signal. The wavelet analysis principle is as follows:
the following tolerance conditions are satisfied in the function ψ (x):
let ψ (x) be a permissive wavelet and define its integral transform as follows:
the integral transform is f (x) an integral continuous wavelet transform with ψ (x) as the mother wavelet, where α is a scale factor representing the frequency dependent scaling and b is a time shift factor.
(4) The fourier transform has the problem that the time and frequency domain information of the signal cannot be localized simultaneously, so the short time fourier transform uses the signal divided into many small time intervals, each time interval being analyzed by the fourier transform in order to determine the frequency at which the time interval exists. In the step, a data processing program based on Harr wavelet base is compiled by using MATLAB language to complete the processing of the winter wheat canopy spectrum data, and correlation analysis is carried out on the winter wheat canopy spectrum data and the actually measured winter wheat leaf water data, and characteristic wave bands are screened and extracted. Wherein the Harr wavelet is a set of functions consisting of a set of piecewise constant functions. This set of functions is defined over a half-open interval [0,1), the value of each piecewise constant function is 1 in a small range and 0 elsewhere, taking the image as an example and using vector space in linear algebra to describe the haar-basis function. Wherein the Haar wavelets used are defined as follows:
and (3) correlation analysis: the correlation analysis and the regression analysis have close relation in practical application. In regression analysis, however, the functional form of the dependence of one random variable Y on another (or a group of) random variables X is heavily studied. While in correlation analysis the variables in question are in the same place, the analysis focuses on a myriad of correlation features between random variables. The correlation coefficient is calculated according to a product difference method, and the correlation degree between the two variables is reflected by multiplying the two dispersion differences on the basis of the dispersion difference between the two variables and the respective average value; the linear single correlation coefficient is heavily studied. The correlation coefficient, or linear correlation coefficient, generally denoted by the letter R, is used to measure the linear relationship between two variables: the calculation method is as follows:
wherein Cov (X, Y) is the covariance of X and Y, Var [ X ] is the variance of X, and Var [ Y ] is the variance of Y. The study focuses on the analysis of linear correlation by calculating the correlation coefficient R between variables to analyze the correlation between the two.
Preferably, the third step is to use the partial least square method as a modeling method to perform regression modeling, and the method can also be used for performing hyperspectral data dimensionality reduction, and is very practical in hyperspectral analysis. The kernel of the partial least square method is a linear algorithm, the partial least square algorithm is combined with non-linear algorithms such as machine learning and the like when a non-linear model is simply called, and the partial least square method is used for extracting score factors to achieve dimensionality reduction processing on hyperspectral data, so that the stability and adaptability of the model can be greatly enhanced. The method comprises the following specific steps:
(1) regression by partial least squares: modeling by a partial least square method and simultaneously considering dependent variable and independent variable principal component extraction, wherein the partial least square method simultaneously considers independent variable (x) principal component, dependent variable (y) principal component and dependent variable interpretation degree;
(2) in the partial least square algorithm, the number of principal components put into modeling needs to be determined, namely whether the prediction function of the model is improved after a new principal component is added is judged, the model precision judging method is cross validation, and the formula is shown as follows:
wherein: PRESS (h) is the sum of the squares of the prediction errors, SS is the sum of the squares of the errors, h is the number of components,
before the calculation of each step of modeling is finished, cross validation of effectiveness is carried out, if the validation is carried out in the h step
Stopping extracting the principal component when the model precision meets the requirement, otherwise, continuing to extract the principal component;
(3) the method adopts the partial least square method to construct model precision verification, and researches and adopts a random sampling method to divide winter wheat samples into a building module group and a verification group, wherein the building module group accounts for 2/3 of the total sample number, and the rest is the verification group. The accuracy of the constructed diagnosis model adopts regression evaluation indexes: determining the coefficient R
2Co-evaluating with the root mean square error RMSE to determine the coefficient R
2The specific calculation method is as follows:
the root mean square error RMSE is calculated as follows:
wherein the SOM
iAs actual value, SOMP
iIn order to predict the value of the target,
is the average of the actual values.
Compared with the prior art, the invention has the following beneficial effects: (1) the method has the advantages of high detection precision of the moisture content of the winter wheat ear, simplicity, convenience and rapidness, realizes rapid, nondestructive and real-time detection of the moisture content of the winter wheat ear, and can provide basic technical support for the estimation of the yield of the winter wheat.
(2) The method can effectively make up for the deficiency of obtaining the moisture content information of the winter wheat ear, has higher detection precision, and can meet the requirements of agricultural informatization, and the nondestructive detection method of the method better meets the practical application.
At present, research on winter wheat ear water content diagnosis technology is developed, technical support is provided for accurate detection of winter wheat ear water content, the technology is favorable for developing later-stage water and fertilizer management of winter wheat, and the technology has important practical significance for guaranteeing grain yield and quality in China
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for detecting moisture content of winter wheat ears based on a hyperspectral technology according to the invention;
FIG. 2 shows a correlation coefficient R between a wavelet coefficient and the moisture content of winter wheat ears in the embodiment of the present invention
2A matrix;
fig. 3 is a scatter diagram of the measured value of the moisture content of the winter wheat ear and the predicted value of the model in the embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following examples and figures.
Aiming at the problems of few researches on detecting the moisture content of the winter wheat ear and low precision in the prior art, the invention provides the method for detecting the moisture content of the winter wheat ear based on the wavelet technology, and the constructed model can meet the requirement on the detection precision of the moisture content of the winter wheat ear and improve the detection precision, robustness and universality of the moisture content of the winter wheat ear. The technical scheme adopted for solving the technical problems is as follows: a method for detecting moisture content of winter wheat ears based on a hyperspectral technology comprises the following steps:
carrying out field inspection on the spot, determining and collecting a winter wheat sample and spectral data, then putting winter wheat ears into a baking oven in a laboratory, drying the winter wheat ears to constant weight, weighing the dry weight of the ears, and obtaining the water content of the wheat ears by adopting a conventional calculation method; screening 2/3 samples as training samples and 1/3 samples as verification samples by adopting a random sampling method;
secondly, based on the training sample, performing smooth denoising processing on the spectral data, processing and analyzing the spectral data by using a wavelet algorithm, performing correlation analysis on the spectral data and the water content of the winter wheat ear, and screening a characteristic wave band sensitive to the water content of the winter wheat ear;
and step three, constructing an estimation model of the moisture content of the winter wheat ear by adopting a partial least square method according to the sensitive characteristic wave band screened in the step two, and performing model precision detection by adopting a decision coefficient (R2) and a Root Mean Square Error (RMSE) pair so as to determine the feasibility of the inspection model.
The specific steps of model construction are as follows:
(1) regression by partial least squares: modeling by a partial least square method and simultaneously considering dependent variable and independent variable principal component extraction, wherein the partial least square method simultaneously considers independent variable (x) principal component, dependent variable (y) principal component and dependent variable interpretation degree;
(2) in the partial least square algorithm, the number of principal components put into modeling needs to be determined, namely whether the prediction function of the model is improved after a new principal component is added is judged, the model precision judging method is cross validation, and the formula is shown as follows:
wherein: PRESS (h) is the sum of the squares of the prediction errors, SS is the sum of the squares of the errors, h is the number of components,
before the calculation of each step of modeling is finished, cross validation of effectiveness is carried out, if the validation is carried out in the h step
Stopping extracting the principal component when the model precision meets the requirement, otherwise, continuing to extract the principal component;
(3) the method adopts the partial least square method to construct model precision verification, and researches and adopts a random sampling method to divide winter wheat samples into a building module group and a verification group, wherein the building module group accounts for 2/3 of the total sample number, and the rest is the verification group. The accuracy of the constructed diagnosis model adopts regression evaluation indexes: determining the coefficient R
2Co-evaluating with the root mean square error RMSE to determine the coefficient R
2The specific calculation method is as follows:
the root mean square error RMSE is calculated as follows:
wherein the SOM
iAs actual value, SOMP
iIn order to predict the value of the target,
is the average of the actual values.
And step four, acquiring the winter wheat canopy spectrum data by using the process in the step one, then processing and analyzing by using the spectrum data processing method in the step two, and finally inputting the sensitive spectrum data of the target to be detected into the model in the step three to obtain the winter wheat ear moisture content information.
In the embodiment, winter wheat in Anping county, Hebei province is selected as an experimental object, the method of the first step is adopted to obtain the winter wheat canopy spectrum data and the winter wheat ear moisture content data, a random sampling method is adopted to screen 2/3 samples as training samples, and 1/3 samples are experimental samples; then processing and analyzing the winter wheat canopy spectrum data by adopting the method in the second step, carrying out correlation analysis on the winter wheat canopy spectrum data and the winter wheat ear water content data (the correlation coefficient is shown in figure 2), and extracting a characteristic wave band sensitive to the winter wheat ear water content; adopting the extracted wave bands in the third step, constructing a winter wheat ear water content diagnosis model by using a partial least squares algorithm, wherein the model result is shown in table 1, analyzing the model diagnosis result to obtain an optimal model which is a model constructed based on H6 and has a coefficient R
2The rms error RMSE reached 0.947 and 2.121, respectively, and the scatter plot is shown in fig. 3. The technical method can be applied to the detection of the water content of the winter wheat ear.
TABLE 1 estimation model of water content of winter wheat ear based on wavelet technique
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (6)
1. A method for detecting moisture content of winter wheat ear based on hyperspectral technology is characterized by comprising the following steps:
carrying out field inspection on the spot, determining and carrying out collection and data processing of winter wheat samples and spectral data, then putting winter wheat ears into a baking oven in a laboratory, drying the winter wheat ears to constant weight, weighing the dry weight of the ears, and obtaining the water content of the wheat ears by adopting a conventional calculation method; screening 2/3 samples as training samples and 1/3 samples as verification samples by adopting a random sampling method;
secondly, based on the training sample, performing smooth denoising processing on the spectral data, processing and analyzing the spectral data by using a wavelet algorithm, performing correlation analysis on the spectral data and the water content of the winter wheat ear, and screening a characteristic wave band sensitive to the water content of the winter wheat ear;
step three, according to the sensitive characteristic wave band screened in the step two, an estimation model of the moisture content of the winter wheat ear is constructed by adopting a partial least square method, and a determination coefficient R is adopted
2Carrying out model precision detection on the model and the root mean square error RMSE pair so as to determine the feasibility of the test model;
and step four, inputting the sensitive spectrum data of the target to be detected into the model in the step three, and obtaining the moisture content information of the winter wheat ear.
2. The method for detecting moisture content of winter wheat ears based on the hyperspectral technology as claimed in claim 1, wherein the spectral data in the step one is obtained by using a surface feature spectrometer.
3. The method for detecting the moisture content of the winter wheat ear based on the hyperspectral technology as claimed in claim 2, wherein the spectral data is obtained by performing a winter wheat spectral measurement method in the field, and collecting winter wheat canopy spectral data in the field by using a surface feature spectrometer with a wave band coverage range of 350-2500 nm and an output spectral resolution of 1nm, wherein 10 pieces of spectral data are determined for each sample, and the average is taken as a final spectrum.
4. The method for detecting moisture content of winter wheat ears based on the hyperspectral technique as claimed in claim 3, wherein the collected canopy spectral data is subjected to data processing, and the data processing comprises three parts of spectral smoothing, wavelet analysis and correlation analysis.
5. The method for detecting moisture content of winter wheat ears based on the hyperspectral technique as claimed in claim 4, characterized by further comprising the step of randomly screening 1/3 samples from all samples to verify the processed data.
6. The method for detecting moisture content of winter wheat ears based on the hyperspectral technology as claimed in claim 1, wherein the concrete steps of the third step are as follows:
(1) regression by partial least squares: modeling by a partial least square method and simultaneously considering dependent variable and independent variable principal component extraction, wherein the partial least square method simultaneously considers independent variable (x) principal component, dependent variable (y) principal component and dependent variable interpretation degree;
(2) in the partial least square algorithm, the number of principal components put into modeling needs to be determined, namely whether the prediction function of the model is improved after a new principal component is added is judged, the model precision judging method is cross validation, and the formula is shown as follows:
wherein: PRESS (h) is the sum of the squares of the prediction errors, SS is the sum of the squares of the errors, h is the number of components,
before the calculation of each step of modeling is finished, cross validation of effectiveness is carried out, if the validation is carried out in the h step
Stopping extracting the principal component when the model precision meets the requirement, otherwise, continuing to extract the principal component;
(3) model accuracy verification constructed by partial least square method is adopted, and winter wheat samples are researched by adopting random sampling methodThe method comprises building modules and verification groups, wherein the building modules account for 2/3 of the total sample number, and the rest are verification groups. The accuracy of the constructed diagnosis model adopts regression evaluation indexes: determining the coefficient R
2Co-evaluating with the root mean square error RMSE to determine the coefficient R
2The specific calculation method is as follows:
the root mean square error RMSE is calculated as follows:
wherein the SOM
iAs actual value, SOMP
iIn order to predict the value of the target,
is the average of the actual values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911059362.7A CN110779875B (en) | 2019-11-01 | 2019-11-01 | Method for detecting moisture content of winter wheat ear based on hyperspectral technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911059362.7A CN110779875B (en) | 2019-11-01 | 2019-11-01 | Method for detecting moisture content of winter wheat ear based on hyperspectral technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110779875A true CN110779875A (en) | 2020-02-11 |
| CN110779875B CN110779875B (en) | 2022-03-01 |
Family
ID=69388272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911059362.7A Active CN110779875B (en) | 2019-11-01 | 2019-11-01 | Method for detecting moisture content of winter wheat ear based on hyperspectral technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110779875B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113128765A (en) * | 2021-04-20 | 2021-07-16 | 南京理工大学 | Accurate regulation and control technology based on crop monitoring model and internet of things data |
| CN113516025A (en) * | 2021-04-26 | 2021-10-19 | 山东深蓝智谱数字科技有限公司 | Hyperspectral image processing method, device and medium based on model construction |
| CN113553914A (en) * | 2021-06-30 | 2021-10-26 | 核工业北京地质研究院 | Abnormal target detection method for CASI (computer aided design) hyperspectral data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426153A (en) * | 2011-11-21 | 2012-04-25 | 南京农业大学 | Wheat plant moisture monitoring method based on canopy high spectral index |
| CN103592255A (en) * | 2013-11-22 | 2014-02-19 | 山东东阿阿胶股份有限公司 | Soft method for measuring total protein content of donkey-hide gelatin skin solution on basis of near infrared spectrum technology |
| CN105548234A (en) * | 2015-12-08 | 2016-05-04 | 大连工业大学 | Method for nondestructive detection of water and fat contents of yellow croaker |
| CN108480405A (en) * | 2018-04-16 | 2018-09-04 | 东北大学 | A kind of cold rolled sheet shape regulation and control efficiency coefficient acquisition methods based on data-driven |
| CN108664719A (en) * | 2018-04-26 | 2018-10-16 | 新乡医学院 | Application of the improved partial least-squares regression method in microbiological culture media optimization |
| CN110082300A (en) * | 2019-05-20 | 2019-08-02 | 中国水利水电科学研究院 | Canopy of winter wheat moisture content monitoring model method for building up based on spectral parameter |
| CN110222475A (en) * | 2019-07-03 | 2019-09-10 | 中国水利水电科学研究院 | A method of based on unmanned plane multispectral remote sensing inverting winter wheat plant moisture content |
-
2019
- 2019-11-01 CN CN201911059362.7A patent/CN110779875B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426153A (en) * | 2011-11-21 | 2012-04-25 | 南京农业大学 | Wheat plant moisture monitoring method based on canopy high spectral index |
| CN103592255A (en) * | 2013-11-22 | 2014-02-19 | 山东东阿阿胶股份有限公司 | Soft method for measuring total protein content of donkey-hide gelatin skin solution on basis of near infrared spectrum technology |
| CN105548234A (en) * | 2015-12-08 | 2016-05-04 | 大连工业大学 | Method for nondestructive detection of water and fat contents of yellow croaker |
| CN108480405A (en) * | 2018-04-16 | 2018-09-04 | 东北大学 | A kind of cold rolled sheet shape regulation and control efficiency coefficient acquisition methods based on data-driven |
| CN108664719A (en) * | 2018-04-26 | 2018-10-16 | 新乡医学院 | Application of the improved partial least-squares regression method in microbiological culture media optimization |
| CN110082300A (en) * | 2019-05-20 | 2019-08-02 | 中国水利水电科学研究院 | Canopy of winter wheat moisture content monitoring model method for building up based on spectral parameter |
| CN110222475A (en) * | 2019-07-03 | 2019-09-10 | 中国水利水电科学研究院 | A method of based on unmanned plane multispectral remote sensing inverting winter wheat plant moisture content |
Non-Patent Citations (5)
| Title |
|---|
| XIAOHE GU ET AL: ""Hyperspectral inversion of soil organic matter content in cultivated land based on wavelet transform"", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
| 刘冰 等: ""基于连续小波阈值去噪算法的目标检测研究"", 《图形图像》 * |
| 束美艳 等: ""表征冬小麦倒伏强度敏感冠层结构参数筛选及光谱诊断模型"", 《农业工程学报》 * |
| 林鹏达 等: ""基于CWT的黑土有机质含量野外高光谱反演模型"", 《水土保持研究》 * |
| 王延仓 等: ""基于小波变换与偏最小二乘耦合模型估测北方潮土有机质含量"", 《光谱学与光谱分析》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113128765A (en) * | 2021-04-20 | 2021-07-16 | 南京理工大学 | Accurate regulation and control technology based on crop monitoring model and internet of things data |
| CN113516025A (en) * | 2021-04-26 | 2021-10-19 | 山东深蓝智谱数字科技有限公司 | Hyperspectral image processing method, device and medium based on model construction |
| CN113516025B (en) * | 2021-04-26 | 2022-03-08 | 山东深蓝智谱数字科技有限公司 | Hyperspectral image processing method, device and medium based on model construction |
| CN113553914A (en) * | 2021-06-30 | 2021-10-26 | 核工业北京地质研究院 | Abnormal target detection method for CASI (computer aided design) hyperspectral data |
| CN113553914B (en) * | 2021-06-30 | 2024-03-19 | 核工业北京地质研究院 | CASI hyperspectral data abnormal target detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110779875B (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bao et al. | Vis-SWIR spectral prediction model for soil organic matter with different grouping strategies | |
| CN110779875B (en) | Method for detecting moisture content of winter wheat ear based on hyperspectral technology | |
| Lee et al. | Estimating chemical properties of Florida soils using spectral reflectance | |
| Ba et al. | Application of Vis-NIR spectroscopy for determination the content of organic matter in saline-alkali soils | |
| CN110907393B (en) | Method and device for detecting saline-alkali stress degree of plants | |
| CN105181643A (en) | Near-infrared inspection method for rice quality and application thereof | |
| Song et al. | Chlorophyll content estimation based on cascade spectral optimizations of interval and wavelength characteristics | |
| CN110531054B (en) | Soil organic carbon prediction uncertainty estimation method based on Bootstrap sampling | |
| CN103278473B (en) | The mensuration of pipering and moisture and method for evaluating quality in white pepper | |
| Hong et al. | Fusion of visible-to-near-infrared and mid-infrared spectroscopy to estimate soil organic carbon | |
| Zhang et al. | Allocate soil individuals to soil classes with topsoil spectral characteristics and decision trees | |
| CN110333195A (en) | Water content in plant leaf detection method and device | |
| CN106708782A (en) | Regional pest detection diagnosis judging method based on wavelet analysis | |
| CN113155747B (en) | Method for constructing fractional order differential spectral index and monitoring wheat stripe rust thereof | |
| CN113111799B (en) | Cultivated land soil fertility level monitoring method based on ensemble empirical mode decomposition | |
| CN109211829A (en) | A method of moisture content in the near infrared spectroscopy measurement rice based on SiPLS | |
| CN108827909B (en) | Rapid soil classification method based on visible near infrared spectrum and multi-target fusion | |
| CN113514410A (en) | Real-time quantitative monitoring method for vertical distribution of nitrogen utilization rate of summer corn in whole growth period based on canopy hyperspectral technology | |
| CN112129709A (en) | Apple tree canopy scale nitrogen content diagnosis method | |
| Tan et al. | Reducing the moisture effect and improving the prediction of soil organic matter with VIS-NIR spectroscopy in black soil area | |
| CN105608296A (en) | Leaf potassium concentration reversing method based on litchi canopy spectrum | |
| Liu et al. | Estimation of chlorophyll content in maize canopy using wavelet denoising and SVR method | |
| CN110231302A (en) | A kind of method of the odd sub- seed crude fat content of quick measurement | |
| CN113267458A (en) | Method for establishing quantitative prediction model of soluble protein content of sweet potatoes | |
| CN116148210A (en) | Fruit quality detection method and device |
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 |