CN109557003B - Pesticide deposition amount detection method and device and data acquisition combination device - Google Patents
Pesticide deposition amount detection method and device and data acquisition combination device Download PDFInfo
- Publication number
- CN109557003B CN109557003B CN201910060614.1A CN201910060614A CN109557003B CN 109557003 B CN109557003 B CN 109557003B CN 201910060614 A CN201910060614 A CN 201910060614A CN 109557003 B CN109557003 B CN 109557003B
- Authority
- CN
- China
- Prior art keywords
- characteristic wave
- pesticide
- deposition amount
- pesticide deposition
- characteristic
- 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
- 239000000575 pesticide Substances 0.000 title claims abstract description 142
- 230000008021 deposition Effects 0.000 title claims abstract description 107
- 238000001514 detection method Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000005507 spraying Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000001678 irradiating effect Effects 0.000 claims description 5
- 239000002131 composite material Substances 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 239000004973 liquid crystal related substance Substances 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000002310 reflectometry Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims 8
- 238000013480 data collection Methods 0.000 claims 1
- 238000001228 spectrum Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 4
- 102000004190 Enzymes Human genes 0.000 description 2
- 108090000790 Enzymes Proteins 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000000746 purification Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 230000001502 supplementing effect Effects 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 239000003905 agrochemical Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000000889 atomisation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004737 colorimetric analysis Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 244000037666 field crops Species 0.000 description 1
- 238000004817 gas chromatography Methods 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000361 pesticidal effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 1
- 229910052721 tungsten Inorganic materials 0.000 description 1
- 239000010937 tungsten Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/04—Investigating sedimentation of particle suspensions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Dispersion Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a pesticide deposition amount detection method and device and a data acquisition and combination device, and belongs to the technical field of pesticide deposition amount detection. A method for detecting the deposition amount of pesticides for targeted application, comprising the steps of: a. determining a characteristic wave band; b. customizing a characteristic wave light source and a characteristic wave band pass filter; c. collecting data corresponding to the concentration of the characteristic wave and the pesticide; d. acquiring a characteristic wave-pesticide deposition amount relation model; e. and detecting the pesticide deposition amount of crops on site. A characteristic wave data acquisition combination device comprises four image pick-up devices with the same structure. The pesticide deposition amount detection device for targeted pesticide application comprises the four camera devices and a control circuit, wherein the control circuit comprises a singlechip MCU and a starting switch. The method has the characteristics of convenience, rapidness, high detection efficiency and the like.
Description
Technical Field
The invention relates to the technical field of pesticide deposition detection.
Background
In the field pesticide spraying operation process, the unmanned aerial vehicle is adopted to spray the pesticide, the non-aerial line pesticide dosage is possibly smaller, or the pesticide is greatly influenced by weather (such as wind direction, wind speed, rainfall and the like), and the pesticide is sprayed from a pesticide liquid box to be transferred to target plant leaves in the whole process, so that the pesticide liquid needs to be subjected to a series of processes of atomization, flight, impact, rebound and the like. In the process, pesticide loss such as pesticide droplet drift, droplet evaporation, droplet loss and the like can be unavoidable; therefore, most pesticide droplets hardly reach the intended target blade, and the exertion of the pesticide effect is limited. The pesticide deposition amount is required to be detected, and then the pesticide supplementing adjustment is carried out in a targeted manner, under the existing pesticide application technical conditions, the canopy of crops is often used as a target for researching the pesticide deposition rate, and therefore the pesticide supplementing according to the deposition amount is an important means for carrying out targeted pesticide application.
The existing pesticide deposition amount detection method usually adopts methods such as an enzyme inhibition principle and a photoelectric colorimetric method, and the detection method adopting the enzyme inhibition principle needs to measure the pesticide deposition amount after picking and processing the crop leaves, is an off-line detection method, cannot realize real-time rapid nondestructive detection, and brings inconvenience to the detection of the pesticide deposition amount of field crops. The spectrum detection method generally comprises laboratory detection and field detection, wherein a darkroom is required to be built for laboratory detection, visible light interference is eliminated, and the leaves of crops to be detected are picked for detection, and the leaves are not required to be damaged, but real-time detection in the field cannot be achieved. The portable spectrometer is adopted for field detection, the external visible light has certain interference, and the spectrometer is expensive in cost and is not suitable for agricultural production practice.
Disclosure of Invention
The invention aims to solve the technical problem of providing a pesticide deposition amount detection method, a pesticide deposition amount detection device and a data acquisition combination device, which can realize direct detection of pesticide deposition amount on site and have the characteristics of convenience, rapidness, high detection efficiency and the like.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for detecting the deposition amount of pesticides for targeted application, comprising the steps of:
a. The method comprises the steps of determining characteristic wave bands, configuring pesticide solutions with different concentrations, selecting a group of crop blades, spraying the pesticide solutions with different concentrations on each blade to form pesticide deposition amounts with different concentrations on each blade, so as to form characteristic wave band sampling samples, irradiating each blade in a darkroom environment by adopting a composite light source, collecting pesticide deposition amount reflectivity data and wavelength data taking the blade as a carrier by using a spectrometer, and determining four characteristic wave bands which can reflect characteristic waves with different pesticide deposition amounts most by using a principal component analysis method;
b. The method comprises the steps of customizing a characteristic wave light source and a characteristic wave band-pass filter, respectively customizing the characteristic wave light source and the characteristic wave band-pass filter corresponding to each characteristic wave band of four characteristic wave bands, wherein the four characteristic wave light sources and the four characteristic wave band-pass filters which are customized can only emit or pass light of the wavelength of the characteristic wave band corresponding to the four characteristic wave light sources and the four characteristic wave band-pass filters;
c. Collecting characteristic wave-pesticide concentration corresponding data, configuring pesticide solutions with different concentrations according to the detection range of pesticide deposition amounts of crop blades, selecting a group of crop blades, respectively spraying the pesticide solutions with different concentrations on each blade in the group of blades to form pesticide deposition amounts with different concentrations on each blade, enabling the pesticide deposition amounts of each crop blade in the group to integrally and discretely cover the detection range of the pesticide deposition amounts of the crop blades, thereby forming a characteristic wave-pesticide deposition amount concentration corresponding data acquisition sample, acquiring light reflection intensity data of four characteristic wave bands of each blade in the sample, wherein the light reflection intensity data acquisition method of the characteristic wave bands comprises the following steps: each blade carrying different pesticide deposition amounts is irradiated through four characteristic wave light sources respectively, and a camera is adopted to shoot through a characteristic wave band-pass filter corresponding to each characteristic wave light source, so that light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts of each concentration taking the blade as a carrier are acquired in an image information form;
d. C, acquiring a characteristic wave-pesticide deposition amount relation model, respectively introducing the pesticide deposition amounts of all concentrations and light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts obtained in the step c into a CNN convolutional neural network for deep learning training, and automatically generating a corresponding relation between the pesticide deposition amounts and the light reflection intensity data of the four characteristic wave bands by a system so as to obtain a characteristic wave-pesticide deposition amount relation model taking the light reflection intensity data of the four characteristic wave bands as input and the pesticide deposition amounts as output;
e. C, detecting the pesticide deposition amount of the crops on site, acquiring the light reflection intensity data of the crop leaves for four characteristic wave bands according to the light reflection intensity data acquisition method of the characteristic wave bands in the step c, and inputting the acquired light reflection intensity data of the four characteristic wave bands into a characteristic wave-pesticide deposition amount relation model so as to obtain the pesticide deposition amount of the crops taking the crop leaves with the light reflection intensity data of the four characteristic wave bands as samples.
The combination device comprises four image pick-up devices with the same structure, namely an image pick-up device I, an image pick-up device II, an image pick-up device III and an image pick-up device IV, wherein the image pick-up devices I, the image pick-up device II, the image pick-up device III and the image pick-up device IV respectively comprise a CCD camera, the characteristic wave light source and the characteristic wave band pass filter, the characteristic wave light source is arranged on the CCD camera and used for irradiating a view finding range of the CCD camera, the characteristic wave band pass filter is arranged at the front end of a lens of the CCD camera so that the CCD camera can collect light with characteristic wave band wavelengths transmitted by the characteristic wave band pass filter, and the characteristic wave light source of each image pick-up device corresponds to the characteristic wave band pass filter so that light reflection intensity data of four characteristic wave bands are collected by each image pick-up device respectively.
The pesticide deposition amount detection device for targeted pesticide application comprises the four camera devices and a control circuit, wherein the control circuit comprises a singlechip MCU and a starting switch, switching value signals sent by the starting switch are transmitted to the singlechip MCU through I/O ports, the singlechip MCU sends time sequence control signals through the four I/O ports, the opening and closing of CCD cameras of the four camera devices are sequentially controlled, image signals collected by the four CCD cameras are respectively transmitted to the singlechip MCU through the respective I/O ports, and operation output signals of the singlechip MCU are transmitted to a display device through the I/O ports.
The invention is further improved in that:
the display device is a YM12232B type liquid crystal display.
The MCU is also connected with the zigbee wireless communication module through an I/O port so as to realize the wireless transmission of operation output signals of the MCU.
The beneficial effects of adopting above-mentioned technical scheme to produce lie in:
Advantage 1: at present, most of crop pesticide spraying deposition amount detection needs to pick blades and even crush the blades, and measurement is carried out in a laboratory, so that the efficiency is low. The invention can detect the deposition amount of the crop pesticide in the field, can realize nondestructive and real-time detection, has higher speed and timeliness, can transmit data in real time, can be used for a farmland pesticide spraying robot or a pesticide spraying operator to perform quick variable pesticide spraying, timely and accurately supplements the pesticide to the pesticide-lacking area, does not lack and exceed the pesticide-lacking area, and does not repeatedly spray the pesticide-lacking area. And the leaves are not required to be picked, crops are not damaged, and the nondestructive testing effect is realized.
Advantage 2: the traditional chemical detection method, chromatographic detection method and the like have more steps, and the steps of sample extraction, purification and the like consume a certain time, and the spectrum detection method adopted by the patent does not need the steps of sample extraction, purification and the like, and is accurate and efficient.
Advantage 3: in the prior spectrum detection method, a spectrometer is adopted for direct detection, the purchase and maintenance cost of the spectrometer is relatively high, the equipment capable of meeting the measurement requirement is more than hundreds of thousands yuan, the cost is relatively high, and the agricultural production practice is not facilitated. The equipment built by the method provided by the invention only needs to be built and combined by devices such as the characteristic wave light source, the characteristic wave band pass filter, the CCD camera, the control circuit and the like, the cost is about thousands yuan, and the cost is greatly reduced on the basis of meeting the measurement requirement, so that the spectrum measurement pesticide deposition amount has the possibility of popularizing and practicing to farmers in farmland production operation.
Advantage 4: in the prior method for measuring the deposition amount of pesticides by spectrum, spectrum equipment is used for collecting spectrum data information of crop leaves, and processing is carried out after the data information is derived to determine the deposition amount. The method and the device provided by the invention integrate data acquisition and analysis into the same control chip, build a mathematical model and then edit the mathematical model into the control chip, input the mathematical model after the device acquires the data, and automatically obtain deposition output data.
Advantage 5: the establishment of the corresponding relation model of the spectrum image information and the pesticide deposition amount is more efficient and accurate than the traditional method. According to the invention, a CNN (convolutional neural network) deep learning method is adopted, and spectral image information and pesticide deposition amount information are automatically trained and modeled, so that compared with the traditional neural network, support vector machine and other machine learning methods, the method has the advantages of higher dimension reduction efficiency and higher accuracy, greatly improves the accuracy of mathematical models, reduces the modeling difficulty and time of corresponding relations, and further ensures that the measurement result is more accurate.
The pesticide deposition amount detection device for targeted pesticide application can realize automatic completion of the output of the deposition amount calculation from photographing. The method has the characteristics of convenience, rapidness, high detection efficiency and the like.
Drawings
FIG. 1 is a flow chart of a method for detecting the deposition amount of an agricultural chemical in the present application;
FIG. 2 is a schematic structural diagram of each camera device of the characteristic wave data acquisition and combination device in the application;
FIG. 3 is a schematic structural view of a pesticide deposition amount detecting device for targeted application in the present application;
fig. 4 is a schematic diagram of the construction of a control circuit of the pesticide deposition amount detecting device for targeted application in the present application.
In the drawings: a CCD camera; 1-1. A lens of a CCD camera; 2. a characteristic wave light source; 3. a characteristic band pass filter;
Detailed Description
The invention will be described in further detail with reference to the drawings and the specific embodiments.
Referring to fig. 1, a pesticide deposition amount detection method for targeted application includes the steps of:
a. The method comprises the steps of determining characteristic wave bands, configuring pesticide solutions with different concentrations, selecting a group of crop blades, spraying the pesticide solutions with different concentrations on each blade to form pesticide deposition amounts with different concentrations on each blade, so as to form characteristic wave band sampling samples, irradiating each blade in a darkroom environment by adopting a composite light source, collecting pesticide deposition amount reflectivity data and wavelength data taking the blade as a carrier by using a spectrometer, and determining four characteristic wave bands which can reflect characteristic waves with different pesticide deposition amounts most by using a principal component analysis method;
b. The method comprises the steps of customizing a characteristic wave light source and a characteristic wave band-pass filter, respectively customizing the characteristic wave light source and the characteristic wave band-pass filter corresponding to each characteristic wave band of four characteristic wave bands, wherein the four characteristic wave light sources and the four characteristic wave band-pass filters which are customized can only emit or pass light of the wavelength of the characteristic wave band corresponding to the four characteristic wave light sources and the four characteristic wave band-pass filters;
c. Collecting characteristic wave-pesticide concentration corresponding data, configuring pesticide solutions with different concentrations according to the detection range of pesticide deposition amounts of crop blades, selecting a group of crop blades, respectively spraying the pesticide solutions with different concentrations on each blade in the group of blades to form pesticide deposition amounts with different concentrations on each blade, enabling the pesticide deposition amounts of each crop blade in the group to integrally and discretely cover the detection range of the pesticide deposition amounts of the crop blades, thereby forming a characteristic wave-pesticide deposition amount concentration corresponding data acquisition sample, acquiring light reflection intensity data of four characteristic wave bands of each blade in the sample, wherein the light reflection intensity data acquisition method of the characteristic wave bands comprises the following steps: each blade carrying different pesticide deposition amounts is irradiated through four characteristic wave light sources respectively, and a camera is adopted to shoot through a characteristic wave band-pass filter corresponding to each characteristic wave light source, so that light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts of each concentration taking the blade as a carrier are acquired in an image information form;
d. C, acquiring a characteristic wave-pesticide deposition amount relation model, respectively introducing the pesticide deposition amounts of all concentrations and light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts obtained in the step c into a CNN convolutional neural network for deep learning training, and automatically generating a corresponding relation between the pesticide deposition amounts and the light reflection intensity data of the four characteristic wave bands by a system so as to obtain a characteristic wave-pesticide deposition amount relation model taking the light reflection intensity data of the four characteristic wave bands as input and the pesticide deposition amounts as output;
e. C, detecting the pesticide deposition amount of the crops on site, acquiring the light reflection intensity data of the crop leaves for four characteristic wave bands according to the light reflection intensity data acquisition method of the characteristic wave bands in the step c, and inputting the acquired light reflection intensity data of the four characteristic wave bands into a characteristic wave-pesticide deposition amount relation model so as to obtain the pesticide deposition amount of the crops taking the crop leaves with the light reflection intensity data of the four characteristic wave bands as samples.
Referring to fig. 2, a combination device for collecting characteristic wave data includes four image pick-up devices with the same structure, which are respectively an image pick-up device I, an image pick-up device II, an image pick-up device III and an image pick-up device IV, each of which includes a CCD camera 1, the above-mentioned characteristic wave light source 2 (and the above-mentioned characteristic wave band pass filter 3, the characteristic wave light source 2 is disposed on the CCD camera 1 and is used for illuminating the view finding range of the CCD camera 1, the characteristic wave band pass filter 3 is disposed at the front end of the lens 1-1 of the CCD camera 1 so that the CCD camera 1 collects light with the wavelength of the characteristic wave band transmitted by the characteristic wave band pass filter 3, and the characteristic wave light source 2 of each image pick-up device corresponds to the characteristic wave band pass filter 3 so that light reflection intensity data of four characteristic wave bands are collected by each image pick-up device respectively.
The device is used for shooting each blade carrying different pesticide deposition amounts respectively, so that light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts of each concentration taking the blade as a carrier are collected in an image information form, and a characteristic wave-pesticide deposition amount relation model which takes the pesticide deposition amount as an output is generated for standby.
Referring to fig. 3 to 4, a pesticide deposition amount detection device for targeted pesticide application comprises the four image pick-up devices and a control circuit, wherein the control circuit comprises a singlechip MCU and a start switch, switching value signals sent by the start switch are transmitted to the singlechip MCU through I/O ports, the singlechip MCU sends time sequence control signals through the four I/O ports, the on and off of CCD cameras of the four image pick-up devices are sequentially controlled, light reflection intensity data of four characteristic wave bands collected by the four CCD cameras in an image information form are respectively transmitted to the singlechip MCU through the respective I/O ports, and operation output signals of the singlechip MCU are transmitted to a display device through the I/O ports.
The display device is a YM12232B type liquid crystal display.
The MCU is also connected with the zigbee wireless communication module through an I/O port so as to realize the wireless transmission of operation output signals of the MCU.
The operation formula of the MCU in the control circuit of the device is based on a characteristic wave-pesticide deposition amount relation model, and the characteristic wave-pesticide deposition amount relation model is obtained by the pesticide deposition amount detection method for targeted application in the application, and is not described in detail herein.
According to the equipment and the using method of the equipment disclosed by the invention, a composite light source (marine optical Vivo halogen tungsten lamp) and a spectrometer (model: VNIR-SWIR spectrometer manufactured by CAMLIN company) are adopted in a darkroom environment to determine that wavelengths of four characteristic wave bands capable of reflecting characteristic waves of different pesticide deposition amounts are 650nm, 830nm, 1150nm and 1581nm respectively, the four characteristic wave light sources and the four corresponding characteristic wave bandpass filters are customized through a (forest photoelectric manufacturer), the light reflection intensity data of the four characteristic wave bands are acquired through a characteristic wave data acquisition and combination device (wherein the model 1 of the CCD camera is PCO 1600), the pesticide deposition amount of cotton crops is detected through a pesticide deposition amount detection device, the detection result is compared with the result detected through a gas chromatography detection method, and the prediction accuracy is obtained, and the comparison result is shown in the following table:
Claims (4)
1. A method for detecting the deposition amount of pesticides for targeted application, which is characterized by comprising the following steps: the method comprises the following steps:
a. The method comprises the steps of determining characteristic wave bands, configuring pesticide solutions with different concentrations, selecting a group of crop blades, spraying the pesticide solutions with different concentrations on each blade to form pesticide deposition amounts with different concentrations on each blade, so as to form characteristic wave band sampling samples, irradiating each blade in a darkroom environment by adopting a composite light source, collecting pesticide deposition amount reflectivity data and wavelength data taking the blade as a carrier by using a spectrometer, and determining four characteristic wave bands which can reflect characteristic waves with different pesticide deposition amounts most by using a principal component analysis method;
b. customizing a characteristic wave light source and a characteristic wave band-pass filter, respectively customizing the characteristic wave light source and the characteristic wave band-pass filter corresponding to each characteristic wave band of the four characteristic wave bands, wherein the four characteristic wave light sources and the four characteristic wave band-pass filters which are customized can only emit or pass the light of the wavelength of the characteristic wave band corresponding to the characteristic wave light source and the characteristic wave band-pass filter;
c. Collecting characteristic wave-pesticide concentration corresponding data, configuring pesticide solutions with different concentrations according to the detection range of pesticide deposition amounts of crop blades, selecting a group of crop blades, respectively spraying the pesticide solutions with different concentrations on each blade in the group of blades to form pesticide deposition amounts with different concentrations on each blade, enabling the pesticide deposition amounts of each crop blade in the group to integrally and discretely cover the detection range of the pesticide deposition amounts of the crop blades, thereby forming a characteristic wave-pesticide deposition amount concentration corresponding data acquisition sample, acquiring light reflection intensity data of four characteristic wave bands of each blade in the sample, wherein the light reflection intensity data acquisition method of the characteristic wave bands comprises the following steps: each blade carrying different pesticide deposition amounts is irradiated through four characteristic wave light sources respectively, and a camera is adopted to shoot through the characteristic wave band-pass filter corresponding to each characteristic wave light source, so that light reflection intensity data of four characteristic wave bands corresponding to the pesticide deposition amounts with each concentration taking the blade as a carrier are acquired in an image information form;
d. C, acquiring a characteristic wave-pesticide deposition amount relation model, respectively introducing the pesticide deposition amounts of all concentrations and the light reflection intensity data of the four characteristic wave bands corresponding to the pesticide deposition amounts obtained in the step c into a CNN convolutional neural network for deep learning training, and automatically generating a corresponding relation between the pesticide deposition amounts and the light reflection intensity data of the four characteristic wave bands by a system so as to obtain a characteristic wave-pesticide deposition amount relation model taking the light reflection intensity data of the four characteristic wave bands as input and the pesticide deposition amounts as output;
e. C, carrying out field detection on the pesticide deposition amount of crops, collecting the light reflection intensity data of the crop leaves for the four characteristic wave bands according to the light reflection intensity data collection method of the characteristic wave bands in the step c, and inputting the collected light reflection intensity data of the four characteristic wave bands into a characteristic wave-pesticide deposition amount relation model so as to obtain the crop pesticide deposition amount taking the crop leaves with the collected light reflection intensity data of the four characteristic wave bands as samples;
The combination device comprises four imaging devices with the same structure, namely an imaging device I, an imaging device II, an imaging device III and an imaging device IV, wherein the imaging devices comprise a CCD (charge coupled device) camera (1), a characteristic wave light source (2) and a characteristic wave band-pass filter (3), the characteristic wave light source (2) is arranged on the CCD camera (1) and is used for irradiating the view finding range of the CCD camera (1), the characteristic wave band-pass filter (3) is arranged at the front end of a lens (1-1) of the CCD camera (1) so that the CCD camera (1) can collect light with the wavelength of a characteristic wave band transmitted by the characteristic wave band-pass filter (3), and the characteristic wave light source (2) of each imaging device corresponds to the characteristic wave band-pass filter (3) so that light reflection intensity data of the four characteristic wave bands are collected by each imaging device respectively.
2. The pesticide deposition detection device for targeted pesticide application is applied to the pesticide deposition detection method for targeted pesticide application according to claim 1 and comprises a combination device and a control circuit, and is characterized in that the control circuit comprises a single chip microcomputer MCU and a starting switch, switching value signals sent by the starting switch are transmitted to the single chip microcomputer MCU through I/O ports, the single chip microcomputer MCU sends out time sequence control signals through four I/O ports, the starting and the closing of CCD cameras of the four cameras are sequentially controlled, image signals collected by the four CCD cameras are respectively transmitted to the single chip microcomputer MCU through the respective I/O ports, and operation output signals of the single chip microcomputer MCU are transmitted to a display device through the I/O ports.
3. A pesticide deposition amount detection apparatus for targeted application as set forth in claim 2 wherein: the display device is a YM12232B type liquid crystal display.
4. A pesticide deposition amount detection apparatus for targeted application as set forth in claim 2 or 3, wherein: the singlechip MCU is also connected with the zigbee wireless communication module through an I/O port so as to realize the wireless transmission of operation output signals of the singlechip MCU.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910060614.1A CN109557003B (en) | 2019-01-23 | 2019-01-23 | Pesticide deposition amount detection method and device and data acquisition combination device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910060614.1A CN109557003B (en) | 2019-01-23 | 2019-01-23 | Pesticide deposition amount detection method and device and data acquisition combination device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109557003A CN109557003A (en) | 2019-04-02 |
| CN109557003B true CN109557003B (en) | 2024-08-02 |
Family
ID=65873815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910060614.1A Active CN109557003B (en) | 2019-01-23 | 2019-01-23 | Pesticide deposition amount detection method and device and data acquisition combination device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109557003B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110057764B (en) * | 2019-04-25 | 2021-09-14 | 浙江省农业科学院 | Pesticide application safety management warning device and method |
| CN110100596B (en) * | 2019-06-03 | 2023-08-29 | 河北农业大学 | Crop light supplementing and sterilizing method and device and data acquisition device |
| CN112730275B (en) * | 2021-02-04 | 2023-06-30 | 华东理工大学 | Microscopic spectrum imaging system, pesticide detection system and method thereof |
| CN113008742B (en) * | 2021-02-23 | 2022-08-19 | 中国农业大学 | Method and system for detecting deposition amount of fog drops |
| CN113252522B (en) * | 2021-05-12 | 2022-03-15 | 中国农业大学 | Hyperspectral scanning-based device for measuring deposition amount of fog drops on plant leaves |
| CN113589846B (en) * | 2021-08-27 | 2022-05-17 | 河北农业大学 | System and method for droplet control under wind field monitoring based on unmanned aerial vehicle pesticide spraying |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN209525221U (en) * | 2019-01-23 | 2019-10-22 | 河北农业大学 | Pesticide deposit amount characteristic wave data acquisition and pesticide deposit amount detection device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3436093B2 (en) * | 1996-08-01 | 2003-08-11 | 株式会社サタケ | Leaf component measuring device |
| US20050221504A1 (en) * | 2004-04-01 | 2005-10-06 | Petruno Patrick T | Optoelectronic rapid diagnostic test system |
| CN101592659B (en) * | 2009-02-09 | 2012-08-08 | 马义才 | System and method for quantitative detection of test strips on basis of continuous fluorescent-substance markers |
| WO2015195746A1 (en) * | 2014-06-18 | 2015-12-23 | Innopix, Inc. | Spectral imaging system for remote and noninvasive detection of target substances using spectral filter arrays and image capture arrays |
| CN204405523U (en) * | 2015-03-11 | 2015-06-17 | 中国科学院地理科学与资源研究所 | A kind of crop nitrogen nutrition diagnostic equipment |
-
2019
- 2019-01-23 CN CN201910060614.1A patent/CN109557003B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN209525221U (en) * | 2019-01-23 | 2019-10-22 | 河北农业大学 | Pesticide deposit amount characteristic wave data acquisition and pesticide deposit amount detection device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109557003A (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109557003B (en) | Pesticide deposition amount detection method and device and data acquisition combination device | |
| CN104483285B (en) | Automatic vehicle-mounted soil nutrient detection and sampling device based on near infrared spectrum technology | |
| CN110260789B (en) | System and method for monitoring phenotype of field high-throughput crops | |
| CN108693119B (en) | Intelligent pest and disease damage investigation and printing system based on unmanned aerial vehicle hyperspectral remote sensing | |
| CN103439265B (en) | Real-time monitoring method for growth characters of tea trees in intensive cultivation | |
| CN101936882B (en) | Nondestructive testing method and device for nitrogen and water of crops | |
| CN101915738B (en) | Method and device for rapidly detecting nutritional information of tea tree based on hyperspectral imaging technique | |
| CN107807125B (en) | Plant information calculation system and method based on unmanned aerial vehicle-mounted multispectral sensor | |
| US20100111369A1 (en) | Portable Intelligent Fluorescence and Transmittance Imaging Spectroscopy System | |
| JP6390054B2 (en) | Monitoring system | |
| CN103048266B (en) | Automatic recognizing method and device for nitrogen phosphorus and potassium stress of protected tomatoes | |
| CN103439264B (en) | A kind of fertility of the tea tree live body based on tuning on-line characteristic harvester | |
| WO2021181371A1 (en) | Systems and methods for monitoring plants in plant growing areas | |
| CN103018196A (en) | Fast detection method for rape water demand information | |
| CN110346305B (en) | Method and device for measuring nitrogen content of plant leaves | |
| US20180373937A1 (en) | Methods and systems for automated micro farming | |
| CN209525221U (en) | Pesticide deposit amount characteristic wave data acquisition and pesticide deposit amount detection device | |
| CN107727542A (en) | A kind of device for fast detecting and detection method that droplet is sprayed suitable for unmanned plane | |
| CN113342036A (en) | Accurate management and control system and method for crops | |
| CN103674855A (en) | Optical path system used for monitoring crop growth information | |
| CN114460080A (en) | Rice disease and pest intelligent monitoring system | |
| CN112816441B (en) | Method and device for detecting growth condition of facility horticultural crop | |
| CN102798614A (en) | Soil total potassium content detection apparatus and method | |
| CN210775225U (en) | Fruit maturity detection and picking device based on Raman spectrum | |
| CN106404680A (en) | Device and method for field quick on-site detection of citrus huanglongbing |
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 |