CN112967233A - Rubber tree anthracnose identification system - Google Patents
Rubber tree anthracnose identification system Download PDFInfo
- Publication number
- CN112967233A CN112967233A CN202110175520.6A CN202110175520A CN112967233A CN 112967233 A CN112967233 A CN 112967233A CN 202110175520 A CN202110175520 A CN 202110175520A CN 112967233 A CN112967233 A CN 112967233A
- Authority
- CN
- China
- Prior art keywords
- anthracnose
- rubber tree
- identification system
- data acquisition
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 244000043261 Hevea brasiliensis Species 0.000 title claims abstract description 107
- 230000005540 biological transmission Effects 0.000 claims abstract description 25
- 230000010365 information processing Effects 0.000 claims abstract description 24
- 238000005070 sampling Methods 0.000 claims description 18
- 241000193738 Bacillus anthracis Species 0.000 claims description 17
- 208000020282 anthrax disease Diseases 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 208000015181 infectious disease Diseases 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 5
- 239000000575 pesticide Substances 0.000 abstract description 8
- 238000005507 spraying Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract 1
- 201000010099 disease Diseases 0.000 description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 20
- 238000000034 method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003292 glue Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 206010017533 Fungal infection Diseases 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 208000024386 fungal infectious disease Diseases 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
Abstract
The application discloses rubber tree anthracnose identification system, including flight device, the last data acquisition device that is provided with data transmission device and sensitive wave band for rubber tree blade anthracnose hyperspectral characteristic of flight device, still include information processing apparatus, flight device is used for carrying on data acquisition device and gathers rubber tree blade image data in the rubber tree top, and information processing apparatus is used for carrying on rubber tree blade image data analysis and obtaining the classification and the outbreak degree information of anthracnose, information processing apparatus sets up in portable computer, and portable computer is used for carrying on data acquisition and shows the acquisition result. The rubber tree anthracnose identification system can timely find the situation before the outbreak of the rubber tree serious disaster area, guide pesticide spraying, effectively prevent the large-range spread of rubber tree anthracnose, avoid the problems of labor and time waste and subjective experience judgment, and is favorable for improving the yield and the quality of rubber.
Description
Technical Field
The invention belongs to the technical field of rubber tree disease identification, and particularly relates to a rubber tree anthracnose identification system.
Background
Rubber trees are important tropical agricultural crops and have important strategic value and economic value, however, global warming can cause the spread and the prevalence of rubber tree diseases, wherein anthracnose is one of main leaf diseases of the rubber trees, and the anthracnose can significantly influence the yield and the quality of rubber to cause serious economic loss, so that the prevention of the large-area spread of the anthracnose is necessary.
However, the traditional anthracnose investigation method is time-consuming and labor-consuming, rubber farmers need to walk through rubber forests to observe the health condition of rubber trees, but because the rubber trees grow too high and have limited human eyesight, crown tree leaves cannot be seen clearly, so that whether the rubber trees are infected with anthracnoses cannot be accurately judged, and meanwhile, the types of the leaf diseases of the rubber trees are various and can be judged only by the experienced rubber farmers, so that the method is easily influenced by subjective factors.
Disclosure of Invention
In order to solve the problems, the invention provides a rubber tree anthracnose recognition system which can timely find the situation before the outbreak of the rubber tree in a severe anthracnose area, guide pesticide spraying, effectively prevent the large-range spread of the rubber tree anthracnose, avoid the problems of labor waste and time waste and subjective experience judgment and be beneficial to the improvement of the yield and the quality of rubber.
The invention provides a rubber tree anthracnose identification system which comprises a flight device, wherein a data transmission device and a data acquisition device with sensitive wave bands having hyperspectral characteristics of rubber tree leaf anthracnose are arranged on the flight device, the flight device also comprises an information processing device for carrying out data interaction with the data acquisition device through the data transmission device, the flight device is used for carrying the data acquisition device to acquire rubber tree leaf image data above a rubber tree, the information processing device is used for analyzing the rubber tree leaf image data and obtaining classification and outbreak degree information of the anthracnose, the information processing device is arranged in a portable computer, and the portable computer is used for controlling the data acquisition device to acquire data and display an acquisition result based on a user instruction.
Preferably, in the rubber tree anthracnose identification system, the portable computer further has a GIS information management device connected to the data acquisition device through the data transmission device, and historical distribution data and anthracnose severity data of the rubber tree anthracnose disaster area are stored in the GIS information management device and are used for assisting in determining the sequence of rubber forest acquisition places of the data acquisition device.
Preferably, in the above rubber tree anthracnose identification system, the data acquisition device comprises a lens with a wavelength ranging from 530nm to 700nm and a portable spectrometer.
Preferably, in the rubber tree anthracnose identification system, the flight device is an unmanned aerial vehicle with a GPS module at the top, and the data transmission device is a 4G transmission module.
Preferably, in the rubber tree anthracnose identification system, the portable computer is a notebook computer.
Preferably, in the rubber tree anthracnose identification system, the data acquisition device is arranged at the bottom of the flight device, and the data transmission device is arranged inside the flight device.
Preferably, in the above rubber tree anthracnose recognition system, the information processing apparatus includes:
a dividing means for dividing an entire region of each leaf from image data of the rubber tree leaf;
the anthracnose blade determining component is used for classifying and identifying each blade by utilizing a convolutional neural network to identify the anthracnose blade;
the anthracnose grading component is used for grading the identified anthracnose leaves by utilizing a clustering algorithm K-means;
the anthracnose outbreak degree determining component is used for determining the anthracnose outbreak degree according to the proportion of infected anthracnose leaves to total leaves;
the anthrax disease grade determining component is used for determining the anthrax disease grade according to the highest anthrax blade infection level and the anthrax outbreak degree.
Preferably, in the rubber tree anthracnose identification system, the anthracnose classification component specifically classifies anthracnose according to the proportion of anthracnose pixels in a single blade to total pixels, the anthracnose pixels account for the first stage of the total pixels of the blade below 1/16, the anthracnose pixels account for the second stage of the total pixels of the blade between 1/16 and 1/4, the anthracnose pixels account for the third stage of the total pixels of the blade above 1/4, and the highest level of infection degree of the single blade in the acquisition area is the anthracnose level of the blade in the acquisition area.
Preferably, in the above rubber tree anthracnose identification system, the anthracnose outbreak degree determining means is specifically configured to determine that the number of infected anthracnose leaves is less than one fiftieth of the total number of leaves as a small-range outbreak, the number of infected anthracnose leaves is between one fiftieth and one tenth as a medium-range outbreak, and the number of infected anthracnose leaves is more than one tenth as a large-range outbreak.
Preferably, in the rubber tree anthracnose identification system, the overlapping area between two adjacent sampling points of the data acquisition device is 30% to 50%.
According to the description, the rubber tree anthracnose identification system provided by the invention comprises a flight device, wherein the flight device is provided with a data transmission device and a data acquisition device with sensitive wave band being the hyperspectral characteristic of rubber tree leaf anthracnose, and further comprises an information processing device for performing data interaction with the data acquisition device through the data transmission device, the flight device is used for carrying the data acquisition device to acquire rubber tree leaf image data above a rubber tree, the information processing device is used for analyzing the rubber tree leaf image data and obtaining the grading and outbreak degree information of the anthracnose, the information processing device is arranged in a portable computer, and the portable computer is used for controlling the data acquisition device to perform data acquisition and displaying the acquisition result based on a user instruction, so that the situation can be found in time before the outbreak of the severe anthracnose area, the pesticide is guided to be sprayed, the large-range spread of the rubber tree anthracnose is effectively prevented, the problems that labor and time are wasted and subjective experience judgment is relied on in manual work are avoided, and the improvement of the yield and the quality of rubber is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of a rubber tree anthracnose identification system provided by the present invention;
FIG. 2 is a schematic diagram of one embodiment of a rubber tree anthracnose identification system;
FIG. 3 is a schematic diagram of another embodiment of a rubber tree anthracnose identification system.
Detailed Description
The core of the invention is to provide a rubber tree anthracnose recognition system, which can timely find the situation before the outbreak of the rubber tree in a severe anthracnose area, guide pesticide spraying, effectively prevent the large-range spread of the rubber tree anthracnose, avoid the problems of labor and time waste and subjective experience judgment, and be beneficial to the improvement of the yield and the quality of rubber.
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.
The embodiment of the rubber tree anthracnose recognition system provided by the invention is shown in fig. 1, fig. 1 is a schematic diagram of the embodiment of the rubber tree anthracnose recognition system provided by the invention, the system comprises a flying device 1 which is a mobile carrier matched with the rubber tree blade data acquisition, and as the flying device can fly, the flying device can fly directly to the air above the rubber tree with the height of 20-30 meters to acquire more accurate information of the rubber tree blades, the flying device is generally operated by a remote controller, and a matched tablet computer can be used for watching an aerial photography interface and displaying a feedback result, the flying device 1 is provided with a data transmission device 101 and a data acquisition device 102 with sensitive wave bands of hyperspectral characteristics of the rubber tree blades, the types of the data transmission devices are not limited, and can be 4G communication or 5G communication and the like, the data acquisition device can be a device which is screened and verified and is only used for identifying the spectrum of the anthracnose of the rubber tree leaves, namely, the wave band range of a lens adopted in the data acquisition device is the sensitive wave band range of the anthracnose of the rubber tree leaves, so that the interference of irrelevant data is avoided, the sensitive wave band can be focused on in this way, the data volume is reduced, and the rapid diagnosis and identification of the anthracnose of the rubber tree are achieved, the data acquisition device also comprises an information processing device 2 which performs data interaction with the data acquisition device 102 through a data transmission device 101, the flight device 1 is used for carrying the data acquisition device 102 to acquire the image data of the rubber tree leaves above the rubber tree, the information processing device 2 is used for analyzing the image data of the rubber tree leaves and obtaining the grading and outbreak degree information of the anthracnose, the information processing device 2 is arranged in a portable computer 3, and can generate suggestions in the aspects of a pesticide spraying scheme and the, and the portable computer 3 is used for controlling the data acquisition device 102 to acquire data and displaying the acquisition result based on the user instruction.
By utilizing the system, the traditional mode of consuming a large amount of manual observation of rubber forest conditions side by side and artificially and subjectively assuming the types of the rubber tree leaf diseases is avoided, the problems that artificial judgment easily causes inaccurate disease identification and is not beneficial to timely prevention and control of the rubber forest are solved, the disease types and the disease degrees of the rubber tree anthracnose can be quickly identified, the large-range spread of the anthracnose can be timely prevented, the important effect on the prevention of the rubber forest diseases and the guarantee of the rubber yield is played, the operation is simple, the system is more convenient and intelligent, the anthracnose can be identified in the field in real time, and the guidance in the aspects of pesticide spraying and the like is carried out.
According to the description, in the embodiment of the rubber tree anthracnose identification system provided by the invention, the system comprises a flight device, wherein the flight device is provided with a data transmission device and a data acquisition device with sensitive wave bands having hyperspectral characteristics of rubber tree leaf anthracnose, and further comprises an information processing device for performing data interaction with the data acquisition device through the data transmission device, the flight device is used for carrying the data acquisition device to acquire rubber tree leaf image data above a rubber tree, the information processing device is used for analyzing the rubber tree leaf image data and obtaining classification and outbreak degree information of the anthracnose, the information processing device is arranged in a portable computer, and the portable computer is used for controlling the data acquisition device to perform data acquisition and displaying acquisition results based on user instructions, so that the situation can be timely found before the outbreak of the severe anthrax area, the pesticide is guided to be sprayed, the large-range spread of the rubber tree anthracnose is effectively prevented, the problems that labor and time are wasted and subjective experience judgment is relied on in manual work are avoided, and the improvement of the yield and the quality of rubber is facilitated.
In a specific embodiment of the above rubber tree anthracnose identification system, referring to fig. 2, fig. 2 is a schematic diagram of a specific embodiment of the rubber tree anthracnose identification system, the portable computer 3 further has a GIS information management device 4 connected to the data acquisition device 102 through the data transmission device 101, and the GIS information management device 4 stores therein rubber tree anthracnose disaster area history distribution data and anthracnose severity data for assisting in determining the sequence of the collection of the rubber forest sites of the data acquisition device 102.
It should be noted that, based on the GIS information management device, the sequence of data acquisition in rubber forest region can be distinguished, taking Hainan province as an example, some places have high topography, some places have low temperature or large wind power in winter, the survival rate and the propagation degree of the anthracnose mycosis can be influenced, the GIS information management device can be added to know which places have serious anthracnose all the year round, and which local anthrax outbreaks are earlier, the detection can be carried out in advance, the detection sequence is arranged according to the predicted outbreak sequence or the serious condition of the past year, the method has the advantages that the method can monitor and mainly inspect the glue forest with serious historical disasters in advance, namely, the GIS information management device can determine the sequence of the glue forest anthracnose prevention, and early-stage identification is carried out on the important areas, so that the anthracnose identification effect is better.
In another embodiment of the above rubber tree anthracnose identification system, referring to fig. 3, fig. 3 is a schematic diagram of another embodiment of the rubber tree anthracnose identification system, the data acquisition device 102 can comprise a lens 1021 with a wavelength range of 530nm to 700nm and a portable spectrometer 1022, specifically, the spectral monitoring is a quick and effective crop monitoring method, the operation is simple, the operation is easy, the crop disease identification and monitoring sensitive area is mainly positioned in visible light and near infrared wave bands, the sensitive wave band is different for different diseases and crop species, but the existing spectrometer realizes full-wavelength monitoring, therefore, the redundant data volume is huge, the data processing time is long, the embodiment is combined with the optical lens with the specific spectral band to monitor the rubber tree anthracnose, the data volume can be greatly reduced, and the data processing is convenient. Of course, lenses with other wavelength ranges may be selected according to actual needs, and are not limited herein.
In another embodiment of the above rubber tree anthracnose identification system, the flying device is an unmanned aerial vehicle with a GPS module on top, and the data transmission device is a 4G transmission module. Specifically, the GPS module can be used for marking the longitude and latitude and autonomous navigation of the sampling point, so that the transmitted data information can contain the longitude and latitude information, and the shooting and analysis of the outbreak area of the rubber tree anthracnose are more convenient.
The portable computer adopted in the embodiment is preferably a notebook computer, visual result display can be carried out, a disease grade area map can be fed back, after collected data are processed, a disease grade area map is fed back, different colors represent different grades, disease distribution can be clearly known, meanwhile, the disease distribution also needs to be watched by the notebook computer during aerial photography, the data collection device is preferably arranged at the bottom of the flight device, and the data transmission device is preferably arranged in the flight device.
In a preferred embodiment of the above rubber tree anthracnose identification system, the information processing device may include: the segmentation component is used for segmenting the complete area of each blade from the image data of the rubber tree blade, wherein the data is preprocessed firstly, and the blade is identified from the data; the anthracnose blade determining component is used for classifying each blade by utilizing a convolutional neural network and identifying anthracnose blades, namely finding out diseased blades from a stack of single blades by utilizing the convolutional neural network and identifying which are anthracnose blades and which are normal blades; the anthracnose grading component is used for grading the identified anthracnose leaves by utilizing a clustering algorithm K-means; the anthracnose outbreak degree determining component is used for determining the anthracnose outbreak degree according to the proportion of infected anthracnose leaves to total leaves; the anthrax disease grade determining component is used for determining the anthrax disease grade according to the highest anthrax blade infection level and the anthrax outbreak degree, and can feed back a disease control scheme.
The specific processing procedure of the information processing device is as follows: the method comprises the steps of firstly carrying out position marking on data transmitted to an information processing device according to a GPS, simultaneously carrying out denoising and smoothing on the data, carrying out classification and identification on leaves and anthracnose leaves by adopting a built CNN model, identifying the anthracnose, grading the identified anthracnose leaves by using a clustering algorithm K-means, judging the outbreak degree according to the proportion of the anthracnose infected leaves to the total leaves, determining the anthracnose disease grade by the highest grade in the anthracnose leaf grades and the outbreak degree together, and finally feeding back a result and a pesticide spraying scheme. It should be noted that, the CNN model training data is rubber tree data in the same area in the previous database, and because the types of anthracnose and rubber tree in different areas are different, which area of the CNN model is called is determined according to the GPS location information, so that anthracnose can be better identified.
In another specific embodiment, the anthracnose classification component may specifically classify anthracnose according to a proportion of anthracnose pixels in a single blade to total pixels, the anthracnose pixels occupying the first stage of the total pixels of the blade below 1/16, the anthracnose pixels occupying the second stage of the total pixels of the blade between 1/16 and 1/4, the anthracnose pixels occupying the third stage of the total pixels of the blade above 1/4, and the highest level of infection degree of the single blade in the acquisition area is the anthracnose level of the blade in the acquisition area. Of course, other modes can be selected for classification according to actual needs, and no limitation is made here.
In addition, the anthrax outbreak degree determining component can be specifically used for determining that the number of the anthrax infected leaves accounts for less than one fiftieth of the total number of the leaves to be a small-range outbreak, the number of the anthrax infected leaves accounts for between one fiftieth and one tenth of the total number of the leaves to be a medium-range outbreak, and the number of the anthrax infected leaves accounts for more than one tenth of. Of course, other modes can be selected for classification according to actual needs, and the classification is not limited herein.
For example, when the grade of the anthracnose leaves contains three levels and the outbreak degree is small-range outbreak, the grade of the anthracnose disease is three levels and the small-range outbreak, and the application method and the application frequency are determined according to different anthracnose disease grades.
In the preferred embodiment of the above rubber tree anthracnose identification system, the overlapping area between two adjacent sampling points of the data acquisition device may be 30% to 50%, and this overlapping is favorable for the accuracy of sampling, and will not miss any detail, and of course, this ratio may also be adjusted according to the actual needs, and this is not limited here.
The application of the above scheme is explained in detail below with two examples:
the first example is as follows:
by utilizing the rubber tree anthracnose identification system, firstly, areas with serious anthracnose in the whole year of the rubber forest in all parts of Hainan province and the easily-propagated outbreak time of the anthracnose are marked according to a database of a GIS information management device, and data are acquired according to the disease severity and the propagation time in sequence. Before data acquisition, a plantation area of the rubber forest needs to be surveyed in advance, and a set of autonomous flight routes of the unmanned aerial vehicle is worked out according to the planting positions of the same kind of rubber trees and the overall growth height rule of the rubber trees. According to the sparsity of the rubber tree, the flying height of the unmanned aerial vehicle is set to be 80 meters, the unmanned aerial vehicle reaches a designated point according to a set flying route after taking off, the unmanned aerial vehicle hovers above the rubber tree to be tested, the spectrometer collects data, after the point is collected, the unmanned aerial vehicle continues flying to the next sampling point for sampling, and the image overlapping area of the previous sampling point and the next sampling point is 50%. The autonomous flight path can be sampled by a zigzag or diagonal sampling method, the number of sampling points can be set manually according to whether the sampling area can be fully covered, the acquired data are transmitted to a computer through a wireless transmission device, the data are processed by an information processing device, and the result is output to a portable computer.
The second example:
the processing flow of the system is as follows: firstly, preprocessing the acquired data, wherein the preprocessing comprises eliminating the overlapping area of a previous sampling point and a next sampling point and carrying out data standardization processing, after the preprocessing is finished, the data of each sampling point is respectively processed, if a plurality of sampling points exist, a measured rubber forest area is divided into a plurality of small areas, then rubber tree blade identification is carried out on the data of each sampling point, specifically, a sampling Gabor filter can be used for identification, the Gabor filter can effectively extract local image textures or edges existing in the image, all rubber tree blades are identified, each blade is divided, each divided blade is independently input into a built CNN model for classification, two types of anthracnose blades and normal blades are identified, cluster analysis is carried out on the anthracnose blades, and the grade of the anthracnose blades is evaluated according to the proportion of the anthracnose pixels to the total blade pixels, the anthracnose pixel points occupying the leaf total pixel points below 1/16 are in the first stage, the anthracnose pixel points occupying the leaf total pixel points between 1/16 and 1/4 are in the second stage, the anthracnose pixel points occupying the leaf total pixel points are in the third stage above 1/4, and the highest grade of infection degree of a single leaf in a certain area is the anthracnose grade of the anthracnose leaf in the area. And then calculating the outbreak degree, wherein the outbreak degree is calculated according to the proportion of the number of the infected anthrax leaves to the total number of the leaves, when the number of the infected anthrax leaves is less than one fiftieth of the total number of the leaves, the small-range outbreak is determined, the medium-range outbreak is between the fiftieth and one tenth of the total number of the leaves, the large-range outbreak is over one tenth of the infected anthrax leaves, the anthrax disease grade is determined by the highest grade and the outbreak degree of the anthrax leaves in the grade, when the anthrax leaves contain three grades, and the outbreak degree is the small-range outbreak, the anthrax disease grade is three-grade small-range outbreak, and the.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The rubber tree anthracnose identification system is characterized by comprising a flying device, wherein the flying device is provided with a data transmission device and a data acquisition device with sensitive wave bands having hyperspectral characteristics of rubber tree leaf anthracnose, and further comprises an information processing device for performing data interaction with the data acquisition device through the data transmission device, the flying device is used for carrying the data acquisition device to acquire rubber tree leaf image data above a rubber tree, the information processing device is used for analyzing the rubber tree leaf image data and obtaining classification and outbreak degree information of the anthracnose, the information processing device is arranged in a portable computer, and the portable computer is used for controlling the data acquisition device to perform data acquisition and displaying acquisition results based on user instructions.
2. The rubber tree anthracnose identification system of claim 1, wherein the portable computer further comprises a GIS information management device connected with the data acquisition device through the data transmission device, and historical distribution data and anthracnose severity data of rubber tree anthracnose disaster areas are stored in the GIS information management device and used for assisting in determining the sequence of the rubber tree anthracnose collection locations of the data acquisition device.
3. The rubber tree anthracnose identification system of claim 1, wherein the data acquisition device comprises a lens and a portable spectrometer having a wavelength range of 530nm to 700 nm.
4. The rubber tree anthracnose identification system of claim 1, wherein the flight device is an unmanned aerial vehicle with a GPS module on top, and the data transmission device is a 4G transmission module.
5. The rubber tree anthracnose identification system of claim 4, wherein the portable computer is a laptop computer.
6. The rubber tree anthracnose identification system of claim 1, wherein the data acquisition device is disposed at the bottom of the flying device, and the data transmission device is disposed inside the flying device.
7. The rubber tree anthracnose identification system of claim 1, wherein the information processing device comprises:
a dividing means for dividing an entire region of each leaf from the rubber tree leaf image data;
the anthracnose blade determining component is used for classifying each blade by utilizing a convolutional neural network and identifying the anthracnose blade;
the anthracnose grading component is used for grading the identified anthracnose leaves by utilizing a clustering algorithm K-means;
the anthracnose outbreak degree determining component is used for determining the anthracnose outbreak degree according to the proportion of infected anthracnose leaves to total leaves;
the anthrax disease grade determining component is used for determining the anthrax disease grade according to the highest anthrax blade infection level and the anthrax outbreak degree.
8. The rubber tree anthracnose identification system of claim 7, wherein the anthracnose classification component specifically classifies anthracnose according to the proportion of anthracnose pixels in a single blade to total pixels, the anthracnose pixels account for the first level below 1/16 of the total pixels of the blade, the anthracnose pixels account for the second level between 1/16 and 1/4 of the total pixels of the blade, the anthracnose pixels account for the third level above 1/4 of the total pixels of the blade, and the highest level of infection of the single blade in the collection area is taken as the anthracnose level of the blade in the collection area.
9. The rubber tree anthracnose identification system of claim 7, wherein the anthracnose outbreak degree determining means is specifically configured to determine that a small-range outbreak is present when the number of infected anthracnose leaves is less than one fiftieth of the total number of leaves, a medium-range outbreak is present between one fiftieth and one tenth, and a large-range outbreak is present above one tenth.
10. The rubber tree anthracnose identification system of any one of claims 1-9, wherein the overlap area between two adjacent sampling points of the data acquisition device is 30% to 50%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110175520.6A CN112967233A (en) | 2021-02-07 | 2021-02-07 | Rubber tree anthracnose identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110175520.6A CN112967233A (en) | 2021-02-07 | 2021-02-07 | Rubber tree anthracnose identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112967233A true CN112967233A (en) | 2021-06-15 |
Family
ID=76284351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110175520.6A Pending CN112967233A (en) | 2021-02-07 | 2021-02-07 | Rubber tree anthracnose identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112967233A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693119A (en) * | 2018-04-20 | 2018-10-23 | 北京麦飞科技有限公司 | Pest and disease damage based on unmanned plane high-spectrum remote-sensing intelligently examines the system of beating |
| CN110376202A (en) * | 2019-06-13 | 2019-10-25 | 浙江水利水电学院 | Tea tree anthracnose scab recognition methods based on imaging hyperspectral technique |
| CN110580495A (en) * | 2019-06-21 | 2019-12-17 | 南京农业大学 | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear |
-
2021
- 2021-02-07 CN CN202110175520.6A patent/CN112967233A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108693119A (en) * | 2018-04-20 | 2018-10-23 | 北京麦飞科技有限公司 | Pest and disease damage based on unmanned plane high-spectrum remote-sensing intelligently examines the system of beating |
| CN110376202A (en) * | 2019-06-13 | 2019-10-25 | 浙江水利水电学院 | Tea tree anthracnose scab recognition methods based on imaging hyperspectral technique |
| CN110580495A (en) * | 2019-06-21 | 2019-12-17 | 南京农业大学 | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Orchard management with small unmanned aerial vehicles: A survey of sensing and analysis approaches | |
| CN111582055B (en) | Unmanned aerial vehicle aviation pesticide application route generation method and system | |
| Di Gennaro et al. | A low-cost and unsupervised image recognition methodology for yield estimation in a vineyard | |
| US20220107298A1 (en) | Systems and methods for crop health monitoring, assessment and prediction | |
| CN108693119B (en) | Intelligent pest and disease damage investigation and printing system based on unmanned aerial vehicle hyperspectral remote sensing | |
| Amarasingam et al. | A review of UAV platforms, sensors, and applications for monitoring of sugarcane crops | |
| Zhou et al. | Strawberry maturity classification from UAV and near-ground imaging using deep learning | |
| US11631166B2 (en) | Crop yield prediction method and system based on low-altitude remote sensing information from unmanned aerial vehicle | |
| CN106971167B (en) | Crop growth analysis method and system based on unmanned aerial vehicle platform | |
| WO2015006675A2 (en) | Method for automatic phenotype measurement and selection | |
| CN113468964B (en) | Hyperspectrum-based agricultural disease and pest monitoring method and device | |
| CN114863369B (en) | Method, device, equipment and medium for monitoring corn lodging by laser radar | |
| CN117589767B (en) | Tobacco leaf harvesting time determining method, electronic equipment and storage medium | |
| Zhang et al. | Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: a triennial study in an apple orchard | |
| CN117575835A (en) | Tea garden growth monitoring system and method based on unmanned aerial vehicle aerial photography | |
| CN116503740A (en) | Unmanned aerial vehicle vision system capable of accurately identifying crop types | |
| CN112967233A (en) | Rubber tree anthracnose identification system | |
| CN114694041A (en) | Hyperspectral identification method for cotton phytotoxicity and spider mite insect damage | |
| CN114782843A (en) | Crop yield prediction method and system based on unmanned aerial vehicle multispectral image fusion | |
| Mohapatra et al. | Eco-smart pest management in rice farming: prospects and challenges | |
| Papić et al. | On Olive Groves Analysis using UAVs | |
| Narmilan et al. | Detection of White Leaf Disease in Sugarcane Using Machine Learning Techniques over UAV Multispectral Images. Drones 2022, 6, 230 | |
| Stephen et al. | Detection and analysis of weed impact on sugar beet crop using drone imagery | |
| CN113468990B (en) | Model training method and device, electronic equipment and storage medium | |
| Ouyang | The Applications of UAV and Ground Digital Imagery Analysis for Monitoring Grapevine Canopy in Vineyard |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210615 |
|
| RJ01 | Rejection of invention patent application after publication |