CN115406860A - Rapid yellow dragon disease detection device and method based on modeling comparison - Google Patents
Rapid yellow dragon disease detection device and method based on modeling comparison Download PDFInfo
- Publication number
- CN115406860A CN115406860A CN202211121387.7A CN202211121387A CN115406860A CN 115406860 A CN115406860 A CN 115406860A CN 202211121387 A CN202211121387 A CN 202211121387A CN 115406860 A CN115406860 A CN 115406860A
- Authority
- CN
- China
- Prior art keywords
- leaves
- model
- disease
- huanglongbing
- database
- 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.)
- Pending
Links
- 201000010099 disease Diseases 0.000 title claims abstract description 41
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 25
- 241001478315 Candidatus Liberibacter asiaticus Species 0.000 claims abstract description 26
- 210000003462 vein Anatomy 0.000 claims abstract description 18
- 238000003333 near-infrared imaging Methods 0.000 claims abstract description 17
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 15
- 239000000758 substrate Substances 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000003752 polymerase chain reaction Methods 0.000 claims description 10
- 238000001228 spectrum Methods 0.000 claims description 10
- 229920002472 Starch Polymers 0.000 claims description 9
- 229930002875 chlorophyll Natural products 0.000 claims description 9
- 235000019804 chlorophyll Nutrition 0.000 claims description 9
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound 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 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 235000019698 starch Nutrition 0.000 claims description 9
- 239000008107 starch Substances 0.000 claims description 9
- 235000000346 sugar Nutrition 0.000 claims description 9
- 230000003321 amplification Effects 0.000 claims description 6
- 238000012512 characterization method Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 4
- 239000004382 Amylase Substances 0.000 claims description 3
- 102000013142 Amylases Human genes 0.000 claims description 3
- 108010065511 Amylases Proteins 0.000 claims description 3
- 235000019418 amylase Nutrition 0.000 claims description 3
- 238000012569 chemometric method Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims description 3
- 230000002950 deficient Effects 0.000 claims description 3
- 238000009795 derivation Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000004128 high performance liquid chromatography Methods 0.000 claims description 3
- KBPHJBAIARWVSC-RGZFRNHPSA-N lutein Chemical compound C([C@H](O)CC=1C)C(C)(C)C=1\C=C\C(\C)=C\C=C\C(\C)=C\C=C\C=C(/C)\C=C\C=C(/C)\C=C\[C@H]1C(C)=C[C@H](O)CC1(C)C KBPHJBAIARWVSC-RGZFRNHPSA-N 0.000 claims description 3
- 229960005375 lutein Drugs 0.000 claims description 3
- ORAKUVXRZWMARG-WZLJTJAWSA-N lutein Natural products CC(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C1=C(C)CCCC1(C)C)C=CC=C(/C)C=CC2C(=CC(O)CC2(C)C)C ORAKUVXRZWMARG-WZLJTJAWSA-N 0.000 claims description 3
- 235000012680 lutein Nutrition 0.000 claims description 3
- 239000001656 lutein Substances 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- KBPHJBAIARWVSC-XQIHNALSSA-N trans-lutein Natural products CC(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C1=C(C)CC(O)CC1(C)C)C=CC=C(/C)C=CC2C(=CC(O)CC2(C)C)C KBPHJBAIARWVSC-XQIHNALSSA-N 0.000 claims description 3
- FJHBOVDFOQMZRV-XQIHNALSSA-N xanthophyll Natural products CC(=C/C=C/C=C(C)/C=C/C=C(C)/C=C/C1=C(C)CC(O)CC1(C)C)C=CC=C(/C)C=CC2C=C(C)C(O)CC2(C)C FJHBOVDFOQMZRV-XQIHNALSSA-N 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 244000276331 Citrus maxima Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000207199 Citrus Species 0.000 description 1
- 235000001759 Citrus maxima Nutrition 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000012408 PCR amplification Methods 0.000 description 1
- 241000589634 Xanthomonas Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000020971 citrus fruits Nutrition 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012031 short term test Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/04—Preparation or injection of sample to be analysed
- G01N30/06—Preparation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/86—Signal analysis
- G01N30/8696—Details of Software
Abstract
The invention discloses a device and a method for rapidly detecting huanglongbing based on modeling comparison, wherein the device comprises a computer, a shell, a substrate, a vein alignment line, a near-infrared imaging spectrometer and a camera, and the detection method comprises the following steps: the method comprises the following steps of firstly, collecting a sample; step two, modeling data; step three, perfecting a database; step four, model deployment; step five, detecting the blade; the Huanglongbing detection device designed by the invention has a simple structure, can automatically diagnose whether the blade has the Huanglongbing disease or not by collecting the near infrared spectrum data of the blade, and has the advantages of high efficiency, high accuracy and low cost.
Description
Technical Field
The invention relates to the technical field of pest control, in particular to a device and a method for quickly detecting huanglongbing based on modeling comparison.
Background
The yellow shoot disease of citrus is also called yellow shoot disease, yellow blight and green fruit disease, and the main control method of the yellow shoot disease comprises the steps of firstly, carrying out strict quarantine to prevent the spread of diseased seedlings; secondly, establishing a disease-free nursery stock base and selecting disease-free nursery stocks; thirdly, the diseased plant is eradicated as soon as possible. However, the effective implementation of these methods depends on a set of accurate and effective detection technology, the existing diagnosis of huanglongbing mainly adopts the PCR technology, and whether the leaves have huanglongbing can be obtained by detecting whether the sample has an amplification band, which has the advantages of high accuracy and high sensitivity, but also has the problems of long time consumption, high cost and tedious operation, so that the requirement of large-scale detection cannot be met.
Disclosure of Invention
The invention aims to provide a device and a method for rapidly detecting huanglongbing based on modeling comparison, which aim to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides a yellow dragon disease short-term test device based on modeling contrast, includes the computer, one side of computer is provided with the casing, fixedly connected with base plate in the casing, and the upper surface of base plate is provided with the vein alignment line, and the top of vein alignment line is provided with near-infrared imaging spectrometer, and near-infrared imaging spectrometer fixed connection in the casing, fixedly connected with camera on the both sides outer wall of near-infrared imaging spectrometer, and near-infrared imaging spectrometer and camera all establish electric connection with the computer.
A method for rapidly detecting Huanglongbing disease based on modeling comparison comprises the steps of firstly, collecting a sample; step two, modeling data; step three, perfecting a database; step four, model deployment; step five, detecting the blades;
wherein in the first step, the method specifically comprises the following steps:
1.1 collecting and shooting 10000 photos of old, medium, tender, normal, lack and sick leaves in a test field, wherein the photos of the leaves comprise the front and back sides of the leaves;
1.2 numbering each leaf and carrying out characterization processing on the shot picture;
wherein in the second step, the method specifically comprises the following steps:
2.1 removing veins from the leaves numbered in the step 1.2, collecting the near infrared spectrum of each leaf by using a near infrared spectrometer, and establishing a qualitative discrimination model of the leaves by using TQ Analyst software;
2.2 detecting whether an amplified band appears in the vein part taken out in the step 2.1 by using a PCR (polymerase chain reaction) amplification instrument, so as to obtain whether the leaf has the yellow dragon disease;
2.3 classifying 10000 processed pictures and spectrograms by combining PCR detection results, training by using a deep learning model, preliminarily establishing a database, and associating the database with a qualitative discrimination model;
the third step specifically comprises the following steps:
3.1 carrying infrared equipment by using an unmanned aerial vehicle, and screening normal, deficiency and Huanglongbing leaves by combining a database;
3.2 determining the contents of chlorophyll, starch, soluble sugar, lutein and amylase of the leaves screened in the step 3.1 by adopting a high performance liquid chromatography, classifying, numbering and photographing the leaves by taking a tree as a standard, performing characteristic treatment on the photographed picture, analyzing and determining each index data range of the leaves of the huanglongbing disease, screening out the pictures of the leaves in the latent period, and inputting the pictures into a database;
in the fourth step, the database and the qualitative judgment model which are trained successfully are deployed to a computer, and the spectrometer and the camera are electrically connected with the computer;
in the fifth step, firstly, the leaf to be detected is placed on the substrate, so that the vein is superposed with the vein alignment line, then infrared spectrum acquisition is carried out through the near infrared imaging spectrometer and the camera, the acquired near infrared spectrum data is input into the qualitative discrimination model, the qualitative discrimination model is combined with the database, qualitative discrimination of old, medium, tender, normal, lack, diseased and latent leaf is realized, and the detection result is displayed on the computer.
Preferably, in step 1.2, the photo characterization processing adopts one of a HOG feature extraction algorithm, a LBP feature extraction algorithm, or a Haar feature extraction algorithm.
Preferably, in step 2.1, the near infrared spectrum needs to be subjected to multivariate scattering correction and second-order derivation and smoothing preprocessing to eliminate the influence of noise and baseline drift.
Preferably, in the step 2.1, establishing a qualitative discrimination model of the blade specifically includes:
2.1.1 selecting 6000 parts of samples from 10000 parts of samples as a training set, 2000 parts of samples as a verification set and 2000 parts of samples as a test set; wherein the training set comprises six types of leaves including 500 old leaves, 500 middle leaves, 500 tender leaves, 500 normal leaves, 500 plain leaves and 3500 diseased leaves;
2.1.2 running TQ analysis software;
2.1.3 setting model parameters, specifically comprising a chemometric method and description information used for setting the model; setting an optical path correction method; setting component information to be analyzed by the model; setting the spectrum and category information of a model standard sample, namely a training set; setting a spectrum processing method; setting a spectrum area used by the model;
2.1.4 after step 2.1.2 is completed, the model can be established and stored;
2.1.5 using the verification set to check the prediction capability of the model, continuously adjusting the model according to the condition, selecting the best model, and recording each item setting of the best model;
2.1.6 training a new model by using the data of the training set and the verification set as a final model, and finally evaluating the final model by using the test set so as to obtain the optimal qualitative judgment model.
Preferably, in step 2.2, if an amplified band appears in the detection result, the leaf blade is judged to have yellow dragon disease.
Preferably, in step 2.3, in 10000 photos and spectra, the ratio of the training set to the validation set to the test set is 3.
Preferably, in the step 3.2, the average value of chlorophyll content of normal leaves is highest, and the content of chlorophyll-deficient leaves is lowest; the mean value of the soluble sugar and the starch content of the leaves with the huanglongbing disease is higher than that of the normal leaves, and the mean value of the soluble sugar and the starch content of the leaves with the latent period is between that of the leaves with the huanglongbing disease and the normal leaves.
Preferably, in the fifth step, the resolution of the camera is 1344 × 1024 pixels, the spectral resolution is 2.8nm, and the exposure time is 10ms.
Compared with the prior art, the invention has the beneficial effects that: the Huanglongbing detection device designed by the invention has a simple structure, can automatically diagnose whether the blade has the Huanglongbing disease or not by collecting the near infrared spectrum data of the blade, and has the advantages of high efficiency, high accuracy and low cost.
Drawings
FIG. 1 is a schematic view of the overall three-dimensional cut-away structure of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is a schematic diagram of a qualitative judgment model of shaddock leaf tablets;
FIG. 4 is a TQ Analyst software interface diagram;
in the figure: 1. a computer; 2. a housing; 3. a substrate; 4. aligning veins; 5. a near-infrared imaging spectrometer; 6. a camera is provided.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention: the utility model provides a yellow dragon disease quick detection device based on modeling contrast, including computer 1, one side of computer 1 is provided with casing 2, fixedly connected with base plate 3 in the casing 2, the upper surface of base plate 3 is provided with vein alignment line 4, the top of vein alignment line 4 is provided with near-infrared imaging spectrometer 5, and near-infrared imaging spectrometer 5 fixed connection is in casing 2, fixedly connected with camera 6 on near-infrared imaging spectrometer 5's the both sides outer wall, and near-infrared imaging spectrometer 5 and camera 6 all establish electric connection with computer 1.
Referring to fig. 2-4, an embodiment of the present invention: a method for rapidly detecting Huanglongbing disease based on modeling comparison comprises the steps of firstly, collecting a sample; step two, modeling data; step three, perfecting a database; step four, model deployment; step five, detecting the blades;
wherein in the first step, the method specifically comprises the following steps:
1.1 collecting and shooting 10000 photos of old, medium, tender, normal, lack and sick pomelo leaves in a test field, wherein the photos of the leaves comprise the front and back sides of the leaves, and the wavelength range of the leaves is 400-2500nm;
1.2, numbering each leaf, and performing characterization processing on the shot picture; wherein, the photo characterization processing adopts one of an HOG feature extraction algorithm, an LBP feature extraction algorithm or a Haar feature extraction algorithm;
wherein in the second step, the method specifically comprises the following steps:
2.1 after the leaves numbered in the step 1.2 are subjected to pulse removal, a near infrared spectrometer is used for collecting the near infrared spectrum of each leaf, and a qualitative discrimination model of the leaves is established for six types of leaves in the interval of 9881.46-4119.21 by utilizing TQ Analyst software; wherein the near infrared spectrum needs to be subjected to multivariate scattering correction, second-order derivation and smoothing pretreatment to eliminate
The effects of noise and baseline drift;
the establishment of the qualitative discrimination model of the blade specifically comprises the following steps:
2.1.1 selecting 6000 parts of samples from 10000 parts of samples as a training set, 2000 parts of samples as a verification set and 2000 parts of samples as a test set; wherein the training set comprises six types of 500 old, 500 medium, 500 tender, 500 normal, 500 plain and 3500 diseased leaves;
2.1.2 running TQ analysis software;
2.1.3 setting model parameters, specifically comprising a chemometric method and description information used for setting the model; setting an optical path correction method; setting component information to be analyzed by the model; setting the spectrum and category information of a model standard sample, namely a training set; setting a spectrum processing method; setting a spectrum area used by the model;
2.1.4 after completing step 2.1.2, a model can be established and saved;
2.1.5 using the verification set to check the prediction capability of the model, continuously adjusting the model according to the situation, selecting the best model, and recording each item setting of the best model;
2.1.6 training a new model by using the data of the training set and the verification set as a final model, and finally evaluating the final model by using the test set so as to obtain the optimal qualitative judgment model.
2.2 detecting whether an amplification strip appears in the leaf part taken out in the step 2.1 by using a PCR (polymerase chain reaction) amplification instrument, and if the amplification strip appears in the detection result, judging that the leaf has yellow dragon disease;
2.3 classifying 10000 processed pictures and spectrograms by combining PCR detection results, training by using a deep learning model, preliminarily establishing a database, and associating the database with a qualitative judgment model; wherein, in 10000 photos and spectrograms, the proportion of a training set, a verification set and a test set is 3;
the third step specifically comprises the following steps:
3.1 carrying infrared equipment by using an unmanned aerial vehicle, and screening normal, deficiency and Huanglongbing leaves by combining a database;
3.2 determining the contents of chlorophyll, starch, soluble sugar, lutein and amylase of the leaves screened in the step 3.1 by adopting a high performance liquid chromatography, classifying, numbering and photographing the leaves by taking a tree as a standard, performing characteristic treatment on the photographed picture, analyzing and determining each index data range of the leaves of the huanglongbing disease, screening out the pictures of the leaves in the latent period, and inputting the pictures into a database; wherein the average chlorophyll content of normal leaves is highest, and the chlorophyll content of the normal leaves is lowest; the mean value of the soluble sugar and starch contents of the leaves with the huanglongbing disease is higher than that of the normal leaves, and the mean value of the soluble sugar and starch contents of the leaves with the latent period is between that of the leaves with the huanglongbing disease and the normal leaves;
in the fourth step, the database and the qualitative judgment model which are trained successfully are deployed to the computer 1, and the spectrometer 5 and the camera 6 are electrically connected with the computer 1;
in the fifth step, firstly, the blade to be detected is placed on the substrate 3, the vein is overlapped with the vein alignment line 4, then infrared spectrum collection is carried out through the near infrared imaging spectrometer 5 and the camera 6, collected near infrared spectrum data are input into the qualitative judgment model, the qualitative judgment model is combined with the database to realize qualitative judgment of old, middle, tender, normal, lack, sick and latent blades, and a detection result is displayed on the computer 1, wherein the resolution of the camera 6 is 1344 multiplied by 1024 pixels, the spectral resolution is 2.8nm, and the exposure time is 10ms.
Based on the above, the method has the advantages that firstly, a qualitative judgment model is established based on collected leaf spectral data, so that whether the leaf is normal or yellowed can be judged, then, a PCR amplification instrument is adopted to detect whether the leaf has the yellow dragon disease, a leaf yellow dragon disease detection database is preliminarily established, the qualitative judgment model is associated with the database, namely, whether the yellowed leaf is deficient or has the yellow dragon disease can be judged, then, the content of the leaf components is measured, the leaf in the latent period of the yellow dragon disease is determined, and after the picture of the leaf is recorded into the database, a perfect database can be obtained, so that whether the normal leaf is the leaf in the latent period of the yellow dragon disease can be judged, and finally, the qualitative judgment model and the database are deployed to a detection device; when the method is used for detecting the xanthomonas disease of the blade, the detection result can be obtained only by using the detection device to collect the near infrared spectrum data of the blade to be detected, so that the method has the advantages of accuracy, rapidness, high efficiency and no damage, and is suitable for large-batch blade detection.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (9)
1. The utility model provides a yellow dragon disease rapid detection device based on modeling contrast, includes computer (1), its characterized in that: one side of computer (1) is provided with casing (2), fixedly connected with base plate (3) in casing (2), the upper surface of base plate (3) is provided with vein alignment line (4), the top of vein alignment line (4) is provided with near-infrared imaging spectrometer (5), and near-infrared imaging spectrometer (5) fixed connection is in casing (2), fixedly connected with camera (6) on the both sides outer wall of near-infrared imaging spectrometer (5), and near-infrared imaging spectrometer (5) and camera (6) all establish electric connection with computer (1).
2. A method for rapidly detecting Huanglongbing disease based on modeling comparison comprises the steps of firstly, collecting a sample; step two, modeling data; step three, perfecting a database; step four, deploying the model; step five, detecting the blade; the method is characterized in that:
wherein in the first step, the method specifically comprises the following steps:
1.1 collecting and shooting 10000 photos of old, medium, tender, normal, lack and sick leaves in a test field, wherein the photos of the leaves comprise the front and back sides of the leaves;
1.2, numbering each leaf, and performing characterization processing on the shot picture;
wherein in the second step, the method specifically comprises the following steps:
2.1 removing veins from the leaves numbered in the step 1.2, collecting the near infrared spectrum of each leaf by using a near infrared spectrometer, and establishing a qualitative discrimination model of the leaves by using TQ Analyst software;
2.2 detecting whether an amplified band appears in the vein part taken out in the step 2.1 by using a PCR (polymerase chain reaction) amplification instrument, so as to obtain whether the leaf has the yellow dragon disease;
2.3 classifying 10000 processed pictures and spectrograms by combining PCR detection results, training by using a deep learning model, preliminarily establishing a database, and associating the database with a qualitative discrimination model;
the third step specifically comprises the following steps:
3.1 carrying infrared equipment by using an unmanned aerial vehicle, and screening normal, deficiency and Huanglongbing leaves by combining a database;
3.2 determining the contents of chlorophyll, starch, soluble sugar, lutein and amylase of the leaves screened in the step 3.1 by adopting a high performance liquid chromatography, classifying, numbering and photographing the leaves by taking a tree as a standard, performing characteristic treatment on the photographed picture, analyzing and determining each index data range of the leaves of the huanglongbing disease, screening out the pictures of the leaves in the latent period, and recording the pictures into a database; in the fourth step, the successfully trained database and the qualitative judgment model are deployed to the computer (1), and the spectrometer (5) and the camera (6) are electrically connected with the computer (1);
in the fifth step, the leaves to be detected are firstly placed on the substrate (3) to enable the veins to coincide with the vein alignment lines (4), then infrared spectrum collection is carried out through the near-infrared imaging spectrometer (5) and the camera (6), collected near-infrared spectrum data are input into the qualitative discrimination model, the qualitative discrimination model is combined with the database to realize qualitative discrimination of old, medium, tender, normal, lack of elements, diseased and latent period leaves, and the detection result is displayed on the computer (1).
3. The Huanglong disease rapid detection method based on modeling comparison as claimed in claim 2, characterized in that: in the step 1.2, the photo characterization processing adopts one of an HOG feature extraction algorithm, an LBP feature extraction algorithm or a Haar feature extraction algorithm.
4. The Huanglong disease rapid detection method based on modeling comparison as claimed in claim 2, characterized in that: in step 2.1, the near infrared spectrum needs to be subjected to multivariate scattering correction, second-order derivation and smoothing preprocessing so as to eliminate the influence of noise and baseline drift.
5. The Huanglong disease rapid detection method based on modeling comparison as claimed in claim 2, characterized in that: in the step 2.1, establishing a qualitative discrimination model of the blade specifically includes:
2.1.1 selecting 6000 parts of samples from 10000 parts of samples as a training set, 2000 parts of samples as a verification set and 2000 parts of samples as a test set; wherein the training set comprises six types of 500 old, 500 medium, 500 tender, 500 normal, 500 plain and 3500 diseased leaves;
2.1.2 running TQ analysis software;
2.1.3 setting model parameters, specifically comprising a chemometric method and description information used for setting the model; setting an optical path correction method; setting component information to be analyzed by the model; setting the spectrum and category information of a model standard sample, namely a training set; setting a spectrum processing method; setting a spectrum area used by the model;
2.1.4 after completing step 2.1.2, a model can be established and saved;
2.1.5 using the verification set to check the prediction capability of the model, continuously adjusting the model according to the situation, selecting the best model, and recording each item setting of the best model;
2.1.6 training a new model by using the data of the training set and the verification set as a final model, and finally evaluating the final model by using the test set so as to obtain the optimal qualitative judgment model.
6. The Huanglong disease rapid detection method based on modeling comparison as claimed in claim 2, characterized in that: in the step 2.2, if the detection result shows an amplified band, the leaf is judged to have yellow dragon disease.
7. The Huanglongbing rapid detection method based on modeling comparison as claimed in claim 2, wherein: in step 2.3, in 10000 photos and spectrograms, the proportion of the training set, the verification set and the test set is 3.
8. The Huanglongbing rapid detection method based on modeling comparison as claimed in claim 2, wherein: in the step 3.2, the average value of chlorophyll content of normal leaves is highest, and the chlorophyll-deficient leaves are lowest; the mean value of the soluble sugar and the starch content of the leaves with the huanglongbing disease is higher than that of the normal leaves, and the mean value of the soluble sugar and the starch content of the leaves with the latent period is between that of the leaves with the huanglongbing disease and the normal leaves.
9. The Huanglong disease rapid detection method based on modeling comparison as claimed in claim 2, characterized in that: in the fifth step, the resolution of the camera (6) is 1344 multiplied by 1024 pixels, the spectral resolution is 2.8nm, and the exposure time is 10ms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211121387.7A CN115406860A (en) | 2022-09-15 | 2022-09-15 | Rapid yellow dragon disease detection device and method based on modeling comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211121387.7A CN115406860A (en) | 2022-09-15 | 2022-09-15 | Rapid yellow dragon disease detection device and method based on modeling comparison |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115406860A true CN115406860A (en) | 2022-11-29 |
Family
ID=84165967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211121387.7A Pending CN115406860A (en) | 2022-09-15 | 2022-09-15 | Rapid yellow dragon disease detection device and method based on modeling comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115406860A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117470804A (en) * | 2023-11-03 | 2024-01-30 | 北京翼新数智科技有限公司 | Carbohydrate product near-infrared detection method and system based on AI algorithm |
-
2022
- 2022-09-15 CN CN202211121387.7A patent/CN115406860A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117470804A (en) * | 2023-11-03 | 2024-01-30 | 北京翼新数智科技有限公司 | Carbohydrate product near-infrared detection method and system based on AI algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bock et al. | From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy | |
| US11842483B2 (en) | Systems for cell shape estimation | |
| Bock et al. | Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging | |
| Yu et al. | Identification of crack features in fresh jujube using Vis/NIR hyperspectral imaging combined with image processing | |
| CN107665492B (en) | Colorectal panoramic digital pathological image tissue segmentation method based on depth network | |
| CN104990892B (en) | The spectrum picture Undamaged determination method for establishing model and seeds idenmtification method of seed | |
| US11721427B2 (en) | Computational pathology approach for retrospective analysis of tissue-based companion diagnostic driven clinical trial studies | |
| Guzmán et al. | Infrared machine vision system for the automatic detection of olive fruit quality | |
| CN110376202B (en) | Tea tree anthracnose lesion identification method based on imaging hyperspectral technology | |
| CN103472031A (en) | Navel orange sugar degree detection method based on hyper-spectral imaging technology | |
| CN102788794A (en) | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion | |
| Yao et al. | Hyperspectral image classification and development of fluorescence index for single corn kernels infected with Aspergillus flavus | |
| CN107679569A (en) | Raman spectrum substance automatic identifying method based on adaptive hypergraph algorithm | |
| CN114993965B (en) | Automatic pollution source identification method and system | |
| CN115406860A (en) | Rapid yellow dragon disease detection device and method based on modeling comparison | |
| CN107563427A (en) | The method and corresponding use that copyright for oil painting is identified | |
| CN109598284A (en) | A kind of hyperspectral image classification method based on large-spacing distribution and space characteristics | |
| CN114663821A (en) | Real-time nondestructive detection method for product quality based on video hyperspectral imaging technology | |
| CN109682821A (en) | A kind of citrus detection method of surface flaw based on multiple dimensioned Gaussian function | |
| WO2007004868A1 (en) | Method and apparatus for image characterization | |
| Peterson et al. | Identifying apple surface defects using principal components analysis and artificial neural networks | |
| WO2023098187A1 (en) | Processing method, processing apparatus, and processing system | |
| CN113751345B (en) | Pineapple nondestructive testing and grading device and method | |
| CN114689539A (en) | Soybean seed pathological change particle identification method and system based on near-infrared hyperspectral image | |
| KR102522202B1 (en) | Apparatus and method of predicting blood glucose level using near-infrared spectroscopy data |
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 |