CN114112991B - Nondestructive testing method and system for salt damage of protected melon - Google Patents
Nondestructive testing method and system for salt damage of protected melon Download PDFInfo
- Publication number
- CN114112991B CN114112991B CN202111549418.4A CN202111549418A CN114112991B CN 114112991 B CN114112991 B CN 114112991B CN 202111549418 A CN202111549418 A CN 202111549418A CN 114112991 B CN114112991 B CN 114112991B
- Authority
- CN
- China
- Prior art keywords
- melon
- sample
- image
- model
- salt damage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- FJJCIZWZNKZHII-UHFFFAOYSA-N [4,6-bis(cyanoamino)-1,3,5-triazin-2-yl]cyanamide Chemical compound N#CNC1=NC(NC#N)=NC(NC#N)=N1 FJJCIZWZNKZHII-UHFFFAOYSA-N 0.000 title claims abstract description 125
- 235000015510 Cucumis melo subsp melo Nutrition 0.000 title claims abstract description 124
- 150000003839 salts Chemical class 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000009659 non-destructive testing Methods 0.000 title claims abstract description 15
- 241000219112 Cucumis Species 0.000 title abstract 7
- 238000001228 spectrum Methods 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000011161 development Methods 0.000 claims abstract description 10
- 238000003556 assay Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 42
- 238000012549 training Methods 0.000 claims description 39
- 238000013527 convolutional neural network Methods 0.000 claims description 30
- 235000009847 Cucumis melo var cantalupensis Nutrition 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000018109 developmental process Effects 0.000 claims description 9
- 241000196324 Embryophyta Species 0.000 claims description 8
- 230000005078 fruit development Effects 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 229910052736 halogen Inorganic materials 0.000 claims description 6
- 150000002367 halogens Chemical class 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 244000241257 Cucumis melo Species 0.000 claims 41
- 230000001066 destructive effect Effects 0.000 claims 1
- 241000282414 Homo sapiens Species 0.000 abstract description 2
- 244000064895 Cucumis melo subsp melo Species 0.000 description 94
- 150000002500 ions Chemical class 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 description 2
- 241001608711 Melo Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- 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 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
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 relates to a nondestructive testing method and a nondestructive testing system for salt damage of a protected melon, which are characterized by acquiring image data of a melon sample to be tested; inputting the image data into an image identification model to obtain a first identification result; determining a hyperspectral assay model from the first discrimination result; inputting the spectrum data into a hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in a first identification result; and determining the salt damage value of the melon sample to be detected according to the second identification result. The invention combines the image identification model and the hyperspectral identification model to identify the sample to be detected, can obtain the full-band spectrum information of the sample to be detected, does not need complex sample pretreatment, and avoids the sample from being damaged by human beings. The invention can increase the information quantity of the acquired tested sample, thereby improving the accuracy of measuring the salt damage of the melon and improving the economical efficiency of detection.
Description
Technical Field
The invention relates to the technical field of crop detection, in particular to a nondestructive testing method and system for salt damage of a facility melon.
Background
Melon (culumis melo L) comprises 7 varieties of 2 subspecies. The muskmelon is 1 subspecies (ssp. Rimidus Fill) of muskmelon, the origin center of which is in the middle east, and is suitable for growing in high-temperature drought climates. At present, melon cultivation can be carried out by utilizing facilities such as a greenhouse from south to north in China.
At present, salt damage measurement of muskmelon is generally performed by using growth morphology indexes, such as plant height, leaf area, biological yield, chlorophyll content and the like of muskmelon, and the method often separates part of plant tissues from the muskmelon for measurement, so that the development process of the muskmelon is artificially damaged.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a nondestructive testing method and system for salt damage of a facility melon.
In order to achieve the above object, the present invention provides the following solutions:
a nondestructive testing method for salt damage of a protected melon comprises the following steps:
acquiring image data of a melon sample to be detected;
inputting the image data into an image identification model to obtain a first identification result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
determining a hyperspectral assay model from the first authentication result;
inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
and determining the salt damage value of the melon sample to be detected according to the second identification result.
Preferably, the acquiring the image data of the melon sample to be tested includes:
and acquiring the image data by using a digital single phase inverter.
Preferably, the method for determining the image identification model comprises the following steps:
acquiring image data of a melon sample set, and dividing the image data of the melon sample set into an image training set and an image testing set according to the ratio of 7:3;
constructing a convolutional neural network;
inputting the convolutional neural network according to the image training set to train to obtain a trained convolutional neural network;
and inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
Preferably, the method for determining the hyperspectral identification model is as follows:
acquiring spectrum data of a melon sample set, and dividing the spectrum data of the melon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
constructing a target detection algorithm model based on machine learning;
inputting the target detection algorithm model pair according to the spectrum training set to train to obtain a trained target detection algorithm model;
and inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
Preferably, the obtaining spectral data of the melon sample set includes:
obtaining spectral data of a melon sample set by using a near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
Preferably, the determining the salt damage value of the melon sample to be tested according to the second identification result includes:
analyzing the second identification result to obtain a plurality of plant ion content information;
and determining the salt damage value according to the plant ion content information.
A facility melon salt damage nondestructive testing system comprising:
the acquisition module is used for acquiring image data and spectrum data of the melon sample to be detected;
the first authentication module is used for inputting the image data into an image authentication model to obtain a first authentication result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
the spectrum model determining module is used for determining a hyperspectral measurement model according to the first identification result;
the second identification module is used for inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
and the salt damage determination module is used for determining the salt damage value of the melon sample to be detected according to the second identification result.
Preferably, the acquiring module specifically includes:
the first acquisition unit is used for acquiring the image data by using a digital single phase inverter;
the second acquisition unit is used for acquiring spectrum data of the melon sample to be detected by using the near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
Preferably, the first authentication module specifically includes:
the first acquisition unit is used for acquiring image data of the muskmelon sample set and dividing the image data of the muskmelon sample set into an image training set and an image test set according to the ratio of 7:3;
the first construction unit is used for constructing a convolutional neural network;
the first training unit is used for inputting the convolutional neural network to train according to the image training set to obtain a trained convolutional neural network;
the first test unit is used for inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
Preferably, the spectrum model determining module specifically includes:
the second acquisition unit is used for acquiring the spectrum data of the muskmelon sample set and dividing the spectrum data of the muskmelon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
the second construction unit is used for constructing a target detection algorithm model based on machine learning;
the second training unit is used for inputting the target detection algorithm model pair for training according to the spectrum training set to obtain a trained target detection algorithm model;
and the second test unit is used for inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention combines the image identification model and the hyperspectral identification model to identify the sample to be detected. The image data is acquired by using a digital camera in an image identification mode, and full-band spectrum information of the sample to be detected can be obtained by using a spectrum technology in a hyperspectral identification mode, so that complex sample pretreatment is not needed, and the sample is prevented from being damaged by human beings. The invention can increase the information quantity of the acquired tested sample, thereby improving the accuracy of measuring the salt damage of the melon and improving the economical efficiency of detection.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for nondestructive determination of salt damage in a protected melon in an embodiment provided by the invention;
FIG. 2 is a block diagram of a system for nondestructive testing of salt damage in a protected melon in accordance with an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The terms "first," "second," "third," and "fourth" and the like in the description and in the claims of this application and in the drawings, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, inclusion of a list of steps, processes, methods, etc. is not limited to the listed steps but may alternatively include steps not listed or may alternatively include other steps inherent to such processes, methods, products, or apparatus.
The invention aims to provide a nondestructive measurement method and system for salt damage of a protected melon, which can increase the information quantity of an acquired measured sample, thereby improving the accuracy of measuring the salt damage of the melon and improving the detection economy.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Fig. 1 is a flowchart of a method for nondestructive measurement of salt damage of a protected melon in an embodiment of the present invention, and as shown in fig. 1, the present invention provides a method for nondestructive measurement of salt damage of a protected melon, including:
step 100: acquiring image data of a melon sample to be detected;
step 200: inputting the image data into an image identification model to obtain a first identification result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
step 300: determining a hyperspectral assay model from the first authentication result;
step 400: inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
step 500: and determining the salt damage value of the melon sample to be detected according to the second identification result.
Preferably, the acquiring the image data of the melon sample to be tested includes:
and acquiring the image data by using a digital single phase inverter.
Preferably, the method for determining the image identification model comprises the following steps:
acquiring image data of a melon sample set, and dividing the image data of the melon sample set into an image training set and an image testing set according to the ratio of 7:3;
constructing a convolutional neural network;
inputting the convolutional neural network according to the image training set to train to obtain a trained convolutional neural network;
and inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
Specifically, in this embodiment, the sample to be tested is melon in each development stage, including vine stage, flowering and fruit setting stage, fruit development stage and abnormal stage. Wherein the melon in abnormal stage is melon with extremely rapid or slow growth and development. The above melons form a melon sample set.
Optionally, a digital single-phase inverter is used for acquiring color images of melons in the vine stretching period, the flowering and fruit setting period, the fruit development period and the abnormal period, wherein 50 color images are respectively acquired in each period, and the total number of the color images is 200. The 200 color pictures were taken as image data of a melon sample set.
Preferably, the method for determining the hyperspectral identification model is as follows:
acquiring spectrum data of a melon sample set, and dividing the spectrum data of the melon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
constructing a target detection algorithm model based on machine learning;
inputting the target detection algorithm model pair according to the spectrum training set to train to obtain a trained target detection algorithm model;
and inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
Preferably, the obtaining spectral data of the melon sample set includes:
obtaining spectral data of a melon sample set by using a near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
Specifically, the near infrared hyperspectral meter is fixed in the camera bellows to avoid interference of ambient light, the resolution of the near infrared hyperspectral meter is 5nm, and the integration time is 6.4ms. Before collection, melon groups in each period are sequentially arranged, and various hyperspectral data are obtained.
As an alternative embodiment, each set of melon data trains an initial algorithmic model separately.
Preferably, the determining the salt damage value of the melon sample to be tested according to the second identification result includes:
analyzing the second identification result to obtain a plurality of plant ion content information;
and determining the salt damage value according to the plant ion content information.
Salt damage determination is carried out on melon samples in unknown growth periods by the method, and the classification result and the salt damage determination result are completely consistent with the real melon salt damage influence values. Therefore, the invention can provide a novel detection method for salt damage detection in the standard melon market.
Fig. 2 is a block diagram of a nondestructive measurement system for salt damage of a protected melon according to an embodiment of the present invention, and as shown in fig. 2, the present embodiment further provides a nondestructive measurement system for salt damage of a protected melon, including:
the acquisition module is used for acquiring image data and spectrum data of the melon sample to be detected;
the first authentication module is used for inputting the image data into an image authentication model to obtain a first authentication result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
the spectrum model determining module is used for determining a hyperspectral measurement model according to the first identification result;
the second identification module is used for inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
and the salt damage determination module is used for determining the salt damage value of the melon sample to be detected according to the second identification result.
Preferably, the acquiring module specifically includes:
the first acquisition unit is used for acquiring the image data by using a digital single phase inverter;
the second acquisition unit is used for acquiring spectrum data of the melon sample to be detected by using the near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
Preferably, the first authentication module specifically includes:
the first acquisition unit is used for acquiring image data of the muskmelon sample set and dividing the image data of the muskmelon sample set into an image training set and an image test set according to the ratio of 7:3;
the first construction unit is used for constructing a convolutional neural network;
the first training unit is used for inputting the convolutional neural network to train according to the image training set to obtain a trained convolutional neural network;
the first test unit is used for inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
Preferably, the spectrum model determining module specifically includes:
the second acquisition unit is used for acquiring the spectrum data of the muskmelon sample set and dividing the spectrum data of the muskmelon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
the second construction unit is used for constructing a target detection algorithm model based on machine learning;
the second training unit is used for inputting the target detection algorithm model pair for training according to the spectrum training set to obtain a trained target detection algorithm model;
and the second test unit is used for inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
The beneficial effects of the invention are as follows:
(1) The invention can obtain the full-band spectrum information of the sample to be detected and improve the extracted information quantity.
(2) The invention can greatly shorten the measurement time, does not depend on the measurement experience of measurement personnel, does not need a large amount of reagents, does not need complex early sample preparation, does not need to destroy the tissue structure of the melon, and saves a large amount of manpower, material resources and financial resources.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (10)
1. A method for the nondestructive determination of salt damage of a protected melon, comprising the steps of:
acquiring image data and spectrum data of a melon sample to be detected;
inputting the image data into an image identification model to obtain a first identification result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
determining a hyperspectral assay model from the first authentication result;
inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
and determining the salt damage value of the melon sample to be detected according to the second identification result.
2. The method for non-destructive testing of salt damage in a protected melon according to claim 1, wherein said obtaining image data of a sample of melon to be tested comprises:
and acquiring the image data by using a digital single phase inverter.
3. The method for nondestructively determining salt damage of a protected melon according to claim 1, wherein the method for determining the image identification model is as follows:
acquiring image data of a melon sample set, and dividing the image data of the melon sample set into an image training set and an image testing set according to the ratio of 7:3;
constructing a convolutional neural network;
inputting the convolutional neural network according to the image training set to train to obtain a trained convolutional neural network;
and inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
4. The method for nondestructively determining salt damage of a protected melon according to claim 1, wherein the method for determining the hyperspectral identification model is as follows:
acquiring spectrum data of a melon sample set, and dividing the spectrum data of the melon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
constructing a target detection algorithm model based on machine learning;
inputting the target detection algorithm model pair according to the spectrum training set to train to obtain a trained target detection algorithm model;
and inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
5. The method for non-destructive testing of salt damage in a protected melon of claim 4, wherein said obtaining spectral data of a sample set of melon comprises:
obtaining spectral data of a melon sample set by using a near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
6. The method for non-destructive determination of salt damage of a protected melon according to claim 1, wherein said determining a salt damage value of said melon sample to be tested based on said second identification result comprises:
analyzing the second identification result to obtain a plurality of plant ion content information;
and determining the salt damage value according to the plant ion content information.
7. A system for the non-destructive testing of salt damage in a protected melon, comprising:
the acquisition module is used for acquiring image data and spectrum data of the melon sample to be detected;
the first authentication module is used for inputting the image data into an image authentication model to obtain a first authentication result; the image identification model is obtained by training a convolutional neural network by adopting image data of melon sample sets in each growth period; the first identification result comprises melon information in a vine stretching period, melon information in a flower setting period, melon information in a fruit development period or melon information in an abnormal period;
the spectrum model determining module is used for determining a hyperspectral measurement model according to the first identification result;
the second identification module is used for inputting the spectrum data into the hyperspectral identification model to obtain a second identification result; the hyperspectral identification model is constructed based on a target detection algorithm by adopting a melon sample set of a development period corresponding to melon information in the first identification result;
and the salt damage determination module is used for determining the salt damage value of the melon sample to be detected according to the second identification result.
8. The system for the nondestructive testing of salt damage in a protected melon of claim 7, wherein the acquisition module comprises:
the first acquisition unit is used for acquiring the image data by using a digital single phase inverter;
the second acquisition unit is used for acquiring spectrum data of the melon sample to be detected by using the near infrared hyperspectral instrument; the near infrared hyperspectral instrument adopts a halogen lamp to provide illumination, and is fixed in a camera bellows.
9. The system for the non-destructive testing of the salt damage of a protected melon according to claim 7, wherein said first identification module comprises:
the first acquisition unit is used for acquiring image data of the muskmelon sample set and dividing the image data of the muskmelon sample set into an image training set and an image test set according to the ratio of 7:3;
the first construction unit is used for constructing a convolutional neural network;
the first training unit is used for inputting the convolutional neural network to train according to the image training set to obtain a trained convolutional neural network;
the first test unit is used for inputting the image test set into the trained convolutional neural network for testing to obtain the image identification model.
10. The system for the nondestructive testing of salt damage in a protected melon of claim 7, wherein the spectral model determination module specifically comprises:
the second acquisition unit is used for acquiring the spectrum data of the muskmelon sample set and dividing the spectrum data of the muskmelon sample set into a spectrum training set and a spectrum test set according to the ratio of 7:3;
the second construction unit is used for constructing a target detection algorithm model based on machine learning;
the second training unit is used for inputting the target detection algorithm model pair for training according to the spectrum training set to obtain a trained target detection algorithm model;
and the second test unit is used for inputting the spectrum test set into the trained target detection algorithm model for testing to obtain the hyperspectral identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111549418.4A CN114112991B (en) | 2021-12-17 | 2021-12-17 | Nondestructive testing method and system for salt damage of protected melon |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111549418.4A CN114112991B (en) | 2021-12-17 | 2021-12-17 | Nondestructive testing method and system for salt damage of protected melon |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114112991A CN114112991A (en) | 2022-03-01 |
| CN114112991B true CN114112991B (en) | 2024-01-26 |
Family
ID=80365842
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111549418.4A Active CN114112991B (en) | 2021-12-17 | 2021-12-17 | Nondestructive testing method and system for salt damage of protected melon |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114112991B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175525A (en) * | 2019-04-28 | 2019-08-27 | 浙江大学 | A kind of salt tolerant okra kind rapid screening method |
| CN110907393A (en) * | 2019-11-22 | 2020-03-24 | 黑龙江八一农垦大学 | Method and device for detecting saline-alkali stress degree of plants |
| CN112634212A (en) * | 2020-12-14 | 2021-04-09 | 江西省林业科学院 | Hyperspectral unmanned aerial vehicle-based disease latent tree detection method and system |
| CN112884058A (en) * | 2021-03-09 | 2021-06-01 | 天津中医药大学 | Fritillaria variety identification method and system based on image and hyperspectrum combination |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10943173B2 (en) * | 2017-05-12 | 2021-03-09 | Harris Lee Cohen | Computer-implemented methods, computer readable medium and systems for generating a satellite data model for a precision agriculture platform |
-
2021
- 2021-12-17 CN CN202111549418.4A patent/CN114112991B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175525A (en) * | 2019-04-28 | 2019-08-27 | 浙江大学 | A kind of salt tolerant okra kind rapid screening method |
| CN110907393A (en) * | 2019-11-22 | 2020-03-24 | 黑龙江八一农垦大学 | Method and device for detecting saline-alkali stress degree of plants |
| CN112634212A (en) * | 2020-12-14 | 2021-04-09 | 江西省林业科学院 | Hyperspectral unmanned aerial vehicle-based disease latent tree detection method and system |
| CN112884058A (en) * | 2021-03-09 | 2021-06-01 | 天津中医药大学 | Fritillaria variety identification method and system based on image and hyperspectrum combination |
Non-Patent Citations (1)
| Title |
|---|
| 盐胁迫对作物生长的影响与监测技术研究;刘映雪 等;中国农机化学报;第42卷(第06期);第208-214页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114112991A (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
| CN104931470B (en) | A kind of pesticide residue detection device and detection method based on fluorescent high spectral technology | |
| CN112634212B (en) | Disease latent tree detection method and system based on hyperspectral unmanned aerial vehicle | |
| CN110781889B (en) | Deep learning-based nondestructive testing method for total sugar content in blueberry fruits | |
| CN101210876A (en) | Rice nutrient information measuring method based on visible/near infrared multispectral imaging | |
| CN102323267A (en) | System and method used for rapidly evaluating freshness of raw meat products | |
| CN113948220B (en) | Anthrax pathogen infection stage detection method with pre-analysis capability | |
| CN105548124A (en) | Method and device for detecting citrus canker | |
| CN106092990A (en) | A kind of three-dimensional fluorescence spectrum discrimination method of lycium barbarum | |
| CN105158186A (en) | Method for detecting black core of white radish based on hyperspectral image | |
| CN111751376A (en) | Rice nitrogen nutrition estimation method based on canopy image feature derivation | |
| CN111199192A (en) | Method for detecting integral maturity of field red globe grapes by adopting parallel line sampling | |
| CN115063653A (en) | Method and system for measuring dominant chromaticness of built environment based on image brain sensitive data | |
| CN110632068A (en) | Method for measuring processing resistance of tobacco leaves | |
| CN110826552A (en) | Grape nondestructive automatic detection device and method based on deep learning | |
| CN101059427A (en) | Method for quickly non-destructive measurement for nitrogen content of tea using multiple spectrum imaging technology | |
| CN110020604A (en) | A kind of quality of vegetable detection method and system | |
| CN104255118A (en) | Rapid lossless testing method based on near infrared spectroscopy technology for paddy rice seed germination percentage | |
| CN101936894A (en) | Near infrared spectrum and microscopic adipose cell data fusion-based pork freshness non-destructive testing technology | |
| CN109164069B (en) | Identification method for leaf surface disease grade of fruit tree | |
| CN102788796B (en) | Nutrient diagnosis device and nutrient diagnosis method for nitrogen of crops based on multi-information integration of high spectral images and fluorescent images | |
| CN114112991B (en) | Nondestructive testing method and system for salt damage of protected melon | |
| CN112884058A (en) | Fritillaria variety identification method and system based on image and hyperspectrum combination | |
| CN112651173A (en) | Agricultural product quality nondestructive testing method based on cross-domain spectral information and generalizable system | |
| Zhou et al. | Hyperspectral imaging technology for detection of moisture content of tomato leaves |
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 |