CN111460990A - Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method - Google Patents
Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method Download PDFInfo
- Publication number
- CN111460990A CN111460990A CN202010242607.6A CN202010242607A CN111460990A CN 111460990 A CN111460990 A CN 111460990A CN 202010242607 A CN202010242607 A CN 202010242607A CN 111460990 A CN111460990 A CN 111460990A
- Authority
- CN
- China
- Prior art keywords
- grassland
- pest
- insect
- module
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 509
- 241000238631 Hexapoda Species 0.000 title claims abstract description 282
- 238000012544 monitoring process Methods 0.000 title claims abstract description 249
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 38
- 230000000694 effects Effects 0.000 claims abstract description 21
- 238000004891 communication Methods 0.000 claims abstract description 10
- 238000013500 data storage Methods 0.000 claims abstract description 10
- 201000010099 disease Diseases 0.000 claims description 39
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 39
- 238000010586 diagram Methods 0.000 claims description 15
- 230000002708 enhancing effect Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012628 principal component regression Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 208000024891 symptom Diseases 0.000 claims description 3
- 230000037237 body shape Effects 0.000 claims description 2
- -1 iginal Species 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 241001465754 Metazoa Species 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 244000025254 Cannabis sativa Species 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000749 insecticidal effect Effects 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003898 horticulture Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Marine Sciences & Fisheries (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Agronomy & Crop Science (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
Abstract
The invention belongs to the technical field of grassland insect damage monitoring and early warning, and discloses a high and cold pastoral area grassland insect damage monitoring and early warning system and method based on big data, wherein the high and cold pastoral area grassland insect damage monitoring and early warning system based on the big data comprises: grassland monitoring module, grassland growth condition judging module, image processing module, central control module, insect pest identification judging module, insect pest estimation module, insect pest early warning module, deinsectization module, driving module, big data processing module, data storage module, wireless communication module, power module, terminal module, display module. According to the method, the contrast enhancement parameters are adjusted, the result grassland image is determined according to the adjusted contrast enhancement parameters, and the accuracy of the contrast enhancement parameters is improved, so that the grassland image enhancement effect is improved; and calculating the accuracy of the prediction model according to the acquired actual value and the prediction value, evaluating the prediction model and providing data support for the optimization of the prediction model.
Description
Technical Field
The invention belongs to the technical field of grassland insect damage monitoring and early warning, and particularly relates to a system and a method for monitoring and early warning grassland insect damage in an alpine pasturing area based on big data.
Background
The pasturing area is an area mainly produced by animal husbandry. It is relative to agricultural areas mainly based on planting production, forest areas mainly based on forestry production and fishing areas mainly based on fishery production. Is a breeding and production base for producing domestic animals and work animals. The pasturing areas in China are mainly distributed in the western and northwest marginal zones and belong to natural grasslands. The important characteristic of meadow agriculture should be highlighted in pastoral area, the effect among the full play grass industry meadow ecosystem, combine planting grass with raise livestock, raise the land, combine land and domestic animal, increase meadow ecosystem's variety, stability, fecundity, constantly outwards extend ecosystem simultaneously, become complicated gradually, the enlargement makes it more rich in elasticity, establish one and mainly rely on self-sustaining, low input, have the meadow ecosystem of vitality in the economy.
In a grassland ecosystem, insect pest measurement and report are the basis for controlling insect pests, the conventional insect pest survey is still a manual survey, insect pest symptoms and quantity are visually measured, survey data are recorded, the experience and the skill of professional technicians are mostly relied on, time and labor are wasted, the workload is high, the measurement and report personnel are very hard, the influence of human factors is large, and the requirement of modern measurement and report cannot be met.
Internationally, various pest early warning systems have been developed in the field of technically-intensive facility horticulture in Japan at the end of the 20 th century, so that manpower and material resources are saved, and the pest control effect is greatly improved; the expert system for pest and disease early warning developed by the Netherlands agricultural environmental engineering research institute combines an image processing technology and an expert system technology, and achieves a good effect in the aspect of application; in the greenhouse in the countries such as the United states, the United kingdom and the like, the intelligent control system is adopted, and meanwhile, the machine vision technology is combined to early warn the grade degree and range of the plant diseases and insect pests. As a plurality of insect spots are relatively similar, the insect spots are distinguished under a complex background, which is a main difficulty of the current insect pest early warning system, so that the current advanced greenhouse computer monitoring early warning system still depends on foreign technologies; meanwhile, the monitoring is influenced by unclear grassland images acquired by the conventional big-data alpine pastoral pest monitoring and early warning system, and the pests cannot be accurately predicted. Therefore, a high and cold pastoral area grassland insect pest monitoring and early warning system based on big data is urgently needed, and the defects of the prior art are overcome.
In summary, the problems and defects of the prior art are: (1) the existing method for manually investigating insect pests mostly depends on the experience and skill of professional technicians, wastes time and labor, has large workload, is very hard for measuring and reporting personnel, has large influence of human factors, and can not adapt to the requirement of modern measuring and reporting.
(2) Many insect spots are relatively similar, and the insect spots are distinguished under a complex background, which is a main difficulty of the current insect pest early warning system, and the current advanced greenhouse computer monitoring early warning system still depends on foreign technologies.
(3) The monitoring is influenced by unclear grassland images acquired by the conventional big-data alpine pastoral pest monitoring and early warning system; meanwhile, the insect damage cannot be accurately predicted.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a high and cold pastoral area grassland insect pest monitoring and early warning system and method based on big data.
The invention is realized in such a way that a method for monitoring and early warning grassland insect pests in alpine pasturing areas based on big data comprises the following steps:
the method comprises the steps that firstly, a high-definition camera is carried by a stepping motor to collect grassland images of the alpine pasturing area, and the growth vigor of the grassland is judged according to the collected grassland images of the alpine pasturing area through a judging program; and the grassland insect pest situation is monitored in real time, and insect pest monitoring original images of a plurality of sampling points of the grassland in the alpine pasturing area are obtained.
Step two, denoising the acquired grassland insect pest monitoring original image through an image processing program; a first grassland pest monitoring image is obtained through an image enhancement program, and the first grassland pest monitoring image is obtained after sharpening the original grassland pest monitoring image.
Step three, obtaining contrast enhancement parameters; and adjusting the contrast of the first grassland pest monitoring image obtained in the second step according to the contrast enhancement parameter to obtain a second grassland pest monitoring image.
And step four, determining whether the deviation between the gray grassland image of the second grassland pest monitoring image and the gray grassland image of the original grassland pest monitoring image meets a parameter adjusting condition.
And fifthly, when the deviation between the gray grassland image of the second grassland pest monitoring image and the gray grassland image of the original grassland pest monitoring image meets the parameter adjusting condition, adjusting the contrast enhancement parameter to obtain the adjusted contrast enhancement parameter.
Sixthly, determining a final grassland pest monitoring image according to the adjusted contrast enhancement parameter, wherein the result grassland pest monitoring image is a grassland image obtained by enhancing the grassland image of the original grassland pest monitoring image; and (4) carrying out segmentation processing on the processed grassland insect pest monitoring image, and extracting a characteristic diagram of the grassland insect pest.
Inputting the insect pest original image of each sampling point into a 2D convolutional neural network for training to form a training set; and the central processing unit receives the pest and disease damage characteristic diagram by using an identification program, and inputs the pest and disease damage characteristic diagram into the 2D convolutional neural network to obtain the pest type corresponding to the image information.
Analyzing the insect pest image of each sampling point based on a pre-configured grassland insect pest damage symptom learning model or an insect body shape learning model to obtain the insect pest number in the insect pest image and generate an insect pest record.
And step nine, acquiring real-time pest and disease damage related data and historical pest and disease damage related data of the grassland area from the cloud server, and selecting a modeling factor of the pest and disease damage prediction model according to the contribution degree of the acquired pest and disease damage related data to pest and disease damage occurrence.
And step ten, constructing a disease and insect pest prediction model based on the neural network according to the modeling factors selected in the step nine, and training and optimizing the prediction model by using the collected historical disease and insect pest related data.
Step eleven, calling a pest prediction model through a pest prediction program to input real-time pest related data and historical pest related data, and predicting the pest grade of the grassland area according to the pest record.
Twelfth, an acousto-optic early warning device is used for early warning the abnormal insect damage condition of the grassland, and an insect killing device is used for killing the insect damage of the grassland in the alpine pasturing area; carry on camera and insecticidal device through step motor to provide the drive for severe cold pastoral area grassland pest monitoring early warning system.
Step thirteen, processing the collected grassland image data by using the cloud server to centralize big data resources; the method comprises the steps of storing and collecting grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and information of insect killing conditions in alpine pasturing areas through a cloud server.
Step fourteen, a wireless sensing network is communicated through a network interface to carry out wireless transmission of grassland insect pest monitoring and early warning data in the alpine pasturing area; the solar cell panel is used for providing electric energy for the grassland insect damage monitoring and early warning system in the alpine pasturing area; receiving grassland pest monitoring and early warning data through the mobile terminal, and performing remote control on the grassland pest monitoring and early warning system.
And fifteen, displaying and acquiring real-time data of the grassland image, the insect pest monitoring original image, the grassland growth judgment result, the insect pest identification result, the insect pest grade, the insect pest early warning information and the insect killing condition of the alpine pasturing area through an L ED high-definition display.
Further, in the third step, before the contrast of the first grassland pest monitoring image is adjusted according to the contrast enhancement parameter for the first time, the obtaining of the contrast enhancement parameter includes:
determining a second average gray value of the gray grassland pest monitoring image of the original grassland pest monitoring image, and acquiring a corresponding relation between a pre-stored average gray value and a contrast enhancement parameter;
when the second average gray value is not equal to the average gray value in the corresponding relationship, the second average gray value is greater than the ith average gray value in the corresponding relationship, and the second average gray value is less than the (i + 1) th average gray value in the corresponding relationship, inputting the ith average gray value, the ith contrast enhancement parameter corresponding to the ith average gray value, the (i + 1) th contrast enhancement parameter corresponding to the (i + 1) th average gray value, and the second average gray value into a preset formula to obtain the contrast enhancement parameter corresponding to the second average gray value; and i is a positive integer.
Further, in the fourth step, determining whether a deviation between the grayscale grassland pest monitoring image of the second grassland pest monitoring image and the grayscale grassland pest monitoring image of the original grassland pest monitoring image satisfies a parameter adjusting condition includes:
converting the original grassland pest monitoring image into a gray grassland pest monitoring image to obtain the gray grassland pest monitoring image of the original grassland pest monitoring image;
converting the second grassland pest monitoring image into a gray grassland pest monitoring image to obtain a gray grassland pest monitoring image of the second grassland pest monitoring image;
comparing the gray grassland pest monitoring image of the original grassland pest monitoring image with the gray grassland pest monitoring image of the second grassland pest monitoring image to obtain a difference grassland pest monitoring image;
determining whether the first average gray value of the difference grassland pest monitoring image is larger than a preset gray value and whether the value of the contrast enhancement parameter is larger than 1;
and when the first average gray value is greater than the preset gray value and the contrast enhancement parameter is greater than 1, determining that the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets the parameter adjusting condition.
Further, in the sixth step, determining a final grassland pest monitoring image according to the adjusted contrast enhancement parameter includes:
taking the adjusted contrast enhancement parameter as the contrast enhancement parameter, and executing the contrast enhancement parameter acquisition again; adjusting the contrast of the first grassland pest monitoring image according to the contrast enhancement parameter to obtain a second grassland pest monitoring image; determining whether the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets a parameter adjusting condition;
and when the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image does not meet the parameter adjusting condition, denoising the second grassland pest monitoring image to obtain a final grassland pest monitoring image, wherein the denoising is used for reducing noise introduced in the contrast adjusting process.
Further, in the eighth step, the insect pest record comprises insect pest species, insect pest number and corresponding collection movement time period; the cloud server is stored with a database of biological data, local meteorological data, grassland related data and historical pest and disease related data of various pest types; the grassland related data comprises grassland area meteorological data, grassland area soil data, grassland area geographic position data and grassland character data.
Further, in the ninth step, artificial interference or non-artificial interference is adopted to select modeling factors of the pest and disease prediction model; wherein, the manual interference adopts a stepwise regression Maic estimation algorithm, and the non-manual interference adopts a multiple regression algorithm, a steady regression algorithm, a ridge regression algorithm or a principal component regression algorithm;
the construction of the disease and pest prediction model comprises the following substeps:
(1) inputting a data sequence corresponding to the modeling factor of the selected plant disease and insect pest prediction model;
(2) carrying out feature extraction on the data sequence by using an encoder;
(3) decoding the feature using a decoder network;
(4) and outputting the prediction result by utilizing the softmx layer through a multilayer fully-connected network in the L STM neural network.
Further, in the twelfth step, the method for killing the grassland insect pests in the alpine pasturing area by the insect killing device comprises the following steps:
(I) acquiring the insect pest type of the easily-broken insect pest in the current grassland time period, and acquiring the activity time of each insect pest according to the climate information and the insect pest type;
(II) counting the probability of each insect pest fed back by all the insect killing devices, and screening out the insect pest type with the probability of more than 10%;
(III) comparing the pest type screened in the step (II) with the pest type obtained in the step (I), sending the existing pest type to the pest killing lamp, sending the non-existing pest type to a manager to confirm the activity time of the manager, and obtaining the climate information, the pest type and the activity time of each pest in the current time period again; and sending the pest type and the pest activity time to the pest killing lamp according to the pest activity time uploaded by the manager.
The invention also aims to provide a big-data-based grassland pest monitoring and early warning system for the alpine pasturing area, which applies the big-data-based grassland pest monitoring and early warning method for the alpine pasturing area, and the big-data-based grassland pest monitoring and early warning system for the alpine pasturing area comprises:
grassland monitoring module, grassland growth condition judging module, image processing module, central control module, insect pest identification judging module, insect pest estimation module, insect pest early warning module, deinsectization module, driving module, big data processing module, data storage module, wireless communication module, power module, terminal module, display module.
The grassland monitoring module is connected with the central control module and used for acquiring grassland images of alpine pasturing areas through a high-definition camera, monitoring insect pest conditions of the grasslands in real time and acquiring insect pest monitoring original images;
the grassland growth condition judging module is connected with the central control module and used for judging the growth condition of the grassland according to the collected grassland images of the alpine pasturing area through a judging program;
the image processing module is connected with the central control module and used for denoising, enhancing and segmenting the acquired grassland insect pest monitoring original image through an image processing program and extracting a grassland insect pest characteristic diagram;
the central control module is connected with the grassland monitoring module, the grassland growth condition judging module, the image processing module, the insect pest identifying and judging module, the insect pest estimating module, the insect pest early warning module, the deinsectization module, the driving module, the big data processing module, the data storage module, the wireless communication module, the power supply module, the terminal module and the display module and is used for controlling the normal operation of each module of the grassland insect pest monitoring and early warning system in the alpine pastoral area through the central processing unit;
the insect pest identification and judgment module is connected with the central control module and used for identifying and judging insect pests according to the extracted grassland insect pest characteristic diagram through an identification program and generating insect pest records;
the insect pest estimation module is connected with the central control module and used for estimating the insect pest grade according to the insect pest record through an insect pest estimation program;
the insect pest early warning module is connected with the central control module and is used for early warning the abnormal insect pest condition of the grassland through the acousto-optic early warning device;
the insect killing module is connected with the central control module and is used for killing grassland insect pests in the alpine pasturing area through the insect killing device;
the driving module is connected with the central control module, is used for carrying the camera and the insect killing device through the stepping motor and provides driving for the grassland insect pest monitoring and early warning system in the alpine pasturing area;
the big data processing module is connected with the central control module and used for processing the acquired grassland image data by centralizing big data resources through the cloud server;
the data storage module is connected with the central control module and used for storing and acquiring grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and information of insect killing conditions in the alpine pasturing area through the cloud server;
the wireless communication module is connected with the central control module and used for communicating a wireless sensing network through a network interface to perform wireless transmission of grassland insect pest monitoring and early warning data in the alpine pasturing area;
the power supply module is connected with the central control module and used for providing electric energy for the grassland insect pest monitoring and early warning system in the alpine pasturing area through the solar cell panel;
the terminal module is connected with the central control module and used for receiving grassland insect pest monitoring and early warning data through the mobile terminal and performing remote control on the grassland insect pest monitoring and early warning system;
the display module is connected with the central control module and used for displaying and collecting real-time data of alpine pastoral area grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and insect killing conditions through an L ED high-definition display.
Another object of the present invention is to provide a computer program product stored on a computer readable medium, which includes a computer readable program for providing a user input interface to implement the big data based grassland pest monitoring and warning method in alpine pasturing area when the computer program product is executed on an electronic device.
Another object of the present invention is to provide a computer-readable storage medium storing instructions, which when executed on a computer, cause the computer to execute the big data based grassland pest monitoring and early warning method for alpine pasturing area.
The method has the advantages that the grassland insect pest images in the alpine pasturing area are collected in real time through the high-definition camera, the insect pest images are identified and detected into corresponding insect pest types and quantities, the insect pest images are uploaded to the central processing unit in real time, the manual investigation link is replaced, the workload and labor intensity of the surveyor can be greatly reduced, the occurrence rule of the insect pest can be remarkably improved, the occurrence rule of the insect pest can be analyzed and researched more scientifically, the method adjusts the contrast of the first grassland image according to the contrast enhancement parameter through the image enhancement module, after the second grassland image is obtained, whether the deviation between the gray grassland image of the second grassland image and the gray grassland image of the original grassland image meets the adjustment condition needs to be detected, if the adjustment condition is met, the deviation between the gray grassland image of the second grassland image and the gray grassland image of the original grassland image is larger, the value of the contrast enhancement parameter is inaccurate, the comparison enhancement parameter is determined through adjusting the contrast enhancement parameter, the comparison result image of the original grassland image and the gray grassland image of the original land image of the original grassland image can be improved, the prediction model is obtained, the prediction of the grassland image, the prediction of the grassland is improved, the prediction of the prediction model, the prediction of the grassland is improved, the prediction of the grassland by adjusting contrast enhancement parameter, the prediction of the grassland, the prediction model, the prediction of the STM is provided by the neural network, the prediction model, the prediction.
Meanwhile, when insect pest identification is carried out, the central processing unit is firstly adopted to obtain climate information of the current time period, pests which move in the current time period and pest moving time period are obtained, then the image information of the grassland in the range where the pest is located is obtained through the pest killing device, the pest condition corresponding to pest spots existing in the image is analyzed, misjudgment is avoided by counting the scale of the occurrence of the pest, the pest trapping and killing are carried out through the scale of the occurrence of the pest, the pest trapping and killing can be carried out at the initial stage of the outbreak of the pest, and the large-scale outbreak of the pest is avoided; and then the insect pest activity time and the preferred trapping wavelength of the insect pest are combined to carry out accurate trapping and killing on the insect pest, so that the trapping and killing efficiency is improved.
Drawings
Fig. 1 is a flow chart of a method for monitoring and early warning grassland insect pests in alpine pasturing areas based on big data according to an embodiment of the invention.
FIG. 2 is a block diagram of a big-data-based grassland pest monitoring and early warning system in an alpine pastoral area according to an embodiment of the present invention;
in the figure: 1. a grassland monitoring module; 2. a grassland growth condition judging module; 3. an image processing module; 4. a central control module; 5. a pest identification and judgment module; 6. a pest estimation module; 7. an insect pest early warning module; 8. a disinsection module; 9. a drive module; 10. a big data processing module; 11. a data storage module; 12. a wireless communication module; 13. a power supply module; 14. a terminal module; 15. and a display module.
Fig. 3 is a flowchart of a method for enhancing the acquired grassland pest monitoring original image by the image processing program according to the embodiment of the present invention.
Fig. 4 is a flowchart of a method for estimating pest grade according to pest records through a pest estimation program according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for killing grassland insect pests in alpine pasturing areas by using an insect killing device according to an embodiment of the present invention.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for monitoring and early warning grassland insect pests in alpine pasturing areas based on big data provided by the embodiment of the invention comprises the following steps:
s101, collecting grassland images of alpine pasturing areas through a high-definition camera, monitoring the conditions of grassland insect pests in real time, and acquiring insect pest monitoring original images. And judging the growth vigor of the grassland according to the collected grassland images of the alpine pasturing area through a judgment program.
And S102, denoising, enhancing and segmenting the obtained grassland insect pest monitoring original image through an image processing program, and extracting a grassland insect pest characteristic diagram. And controlling the normal operation of the grassland insect pest monitoring and early warning system in the alpine pasturing area through the central processing unit.
S103, identifying and judging the pests according to the extracted grassland pest characteristic diagram through an identification program, and generating pest records. And (4) estimating the pest grade according to the pest record through a pest estimation program. And early warning is carried out on the abnormal insect pest condition of the grassland through an acousto-optic early warning device.
And S104, killing the grassland insect pests in the alpine pasturing area through the insect killing device. Carry on camera and insecticidal device through step motor to provide the drive for severe cold pastoral area grassland pest monitoring early warning system. And processing the acquired grassland image data by centralizing large data resources through the cloud server.
S105, storing and acquiring the grassland image, the insect pest monitoring original image, the grassland growth judgment result, the insect pest identification result, the insect pest grade, the insect pest early warning information and the information of the insect killing condition in the alpine pasturing area through the cloud server.
And S106, the wireless sensing network is connected through the network interface to perform wireless transmission of the grassland insect pest monitoring and early warning data in the alpine pasturing area. The solar cell panel is used for providing electric energy for the grassland insect damage monitoring and early warning system in the alpine pasturing area.
And S107, receiving the grassland insect pest monitoring and early warning data through the mobile terminal, and remotely controlling the grassland insect pest monitoring and early warning system, and displaying and collecting real-time data of grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and insect killing conditions in the alpine pasturing area through an L ED high-definition display.
As shown in fig. 2, the system for monitoring and warning grassland insect pests in alpine pasturing areas based on big data provided by the embodiment of the invention comprises: grassland monitoring module 1, grassland growth condition judging module 2, image processing module 3, central control module 4, insect pest identification judging module 5, insect pest estimation module 6, insect pest early warning module 7, deinsectization module 8, driving module 9, big data processing module 10, data storage module 11, wireless communication module 12, power module 13, terminal module 14 and display module 15.
Grassland monitoring module 1 is connected with central control module 4 for gather high and cold pastoral area grassland image through high definition camera, carry out real-time supervision to the grassland pest circumstances, and acquire the original image of pest monitoring.
And the grassland growth condition judging module 2 is connected with the central control module 4 and used for judging the grassland growth condition according to the collected grassland images of the alpine pasturing area through a judging program.
And the image processing module 3 is connected with the central control module 4 and is used for denoising, enhancing and segmenting the obtained grassland insect pest monitoring original image through an image processing program and extracting a grassland insect pest characteristic diagram.
Central control module 4, with grassland monitoring module 1, grassland growth condition judge module 2, image processing module 3, insect pest discernment judge module 5, the insect pest is estimated module 6, insect pest early warning module 7, deinsectization module 8, drive module 9, big data processing module 10, data storage module 11, wireless communication module 12, power module 13, terminal module 14, display module 15 connect for through the normal operating of each module of central processing unit control alpine pastoral area grassland insect pest monitoring and early warning system.
And the pest identification and judgment module 5 is connected with the central control module 4 and used for identifying and judging the pests according to the extracted grassland pest characteristic diagram through an identification program and generating pest records.
And the insect pest estimation module 6 is connected with the central control module 4 and is used for estimating the insect pest grade according to the insect pest record through an insect pest estimation program.
And the pest early warning module 7 is connected with the central control module 4 and is used for early warning the abnormal pest situation of the grassland through the acousto-optic early warning device.
And the pest killing module 8 is connected with the central control module 4 and used for killing the grassland pests in the alpine pasturing area through the pest killing device.
And the driving module 9 is connected with the central control module 4 and used for carrying the camera and the insect killing device through the stepping motor and providing driving for the grassland insect pest monitoring and early warning system in the alpine pasturing area.
And the big data processing module 10 is connected with the central control module 4 and is used for processing the acquired grassland image data by centralizing big data resources through the cloud server.
The data storage module 11 is connected with the central control module 4 and used for storing and collecting information of grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and insect killing conditions of alpine pasturing areas through the cloud server.
And the wireless communication module 12 is connected with the central control module 4 and used for connecting a wireless sensing network through a network interface to perform wireless transmission of grassland pest monitoring and early warning data in the alpine pasturing area.
And the power module 13 is connected with the central control module 4 and used for providing electric energy for the grassland insect pest monitoring and early warning system in the alpine pasturing area through a solar cell panel.
And the terminal module 14 is connected with the central control module 4 and used for receiving the grassland insect pest monitoring and early warning data through the mobile terminal and performing remote control on the grassland insect pest monitoring and early warning system.
As shown in fig. 3, the method for enhancing the obtained grassland pest monitoring original image through the image processing program according to the embodiment of the present invention includes:
s201, acquiring a first grassland image through an image enhancement program, wherein the first grassland image is obtained by sharpening an original grassland image.
S202, contrast enhancement parameters are obtained. And adjusting the contrast of the first grassland image according to the contrast enhancement parameter to obtain a second grassland image.
S203, determining whether the deviation between the gray-scale grassland image of the second grassland image and the gray-scale grassland image of the original grassland image meets a parameter adjusting condition.
And S204, when the deviation between the gray-scale grassland image of the second grassland image and the gray-scale grassland image of the original grassland image meets the parameter adjusting condition, adjusting the contrast enhancement parameter to obtain the adjusted contrast enhancement parameter.
S205, determining a result grassland image according to the adjusted contrast enhancement parameter, wherein the result grassland image is obtained by performing grassland image enhancement processing on the original grassland image.
Before the contrast of the first grassland pest monitoring image is adjusted according to the contrast enhancement parameter for the first time, the obtaining of the contrast enhancement parameter comprises the following steps:
and determining a second average gray value of the gray grassland pest monitoring image of the original grassland pest monitoring image, and acquiring a corresponding relation between the pre-stored average gray value and the contrast enhancement parameter.
When the second average gray value is not equal to the average gray value in the corresponding relationship, the second average gray value is greater than the ith average gray value in the corresponding relationship, and the second average gray value is less than the (i + 1) th average gray value in the corresponding relationship, inputting the ith average gray value, the ith contrast enhancement parameter corresponding to the ith average gray value, the (i + 1) th contrast enhancement parameter corresponding to the (i + 1) th average gray value, and the second average gray value into a preset formula to obtain the contrast enhancement parameter corresponding to the second average gray value. And i is a positive integer.
The embodiment of the invention provides a method for determining whether the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets the parameter adjusting condition, which comprises the following steps:
and converting the original grassland pest monitoring image into a gray grassland pest monitoring image to obtain the gray grassland pest monitoring image of the original grassland pest monitoring image.
And converting the second grassland pest monitoring image into a gray grassland pest monitoring image to obtain the gray grassland pest monitoring image of the second grassland pest monitoring image.
And comparing the gray grassland pest monitoring image of the original grassland pest monitoring image with the gray grassland pest monitoring image of the second grassland pest monitoring image to obtain a difference grassland pest monitoring image.
And determining whether the first average gray value of the difference grassland pest monitoring image is greater than a preset gray value and whether the value of the contrast enhancement parameter is greater than 1.
And when the first average gray value is greater than the preset gray value and the contrast enhancement parameter is greater than 1, determining that the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets the parameter adjusting condition.
The method for determining the final grassland pest monitoring image according to the adjusted contrast enhancement parameters provided by the embodiment of the invention comprises the following steps:
and taking the adjusted contrast enhancement parameter as the contrast enhancement parameter, and executing the contrast enhancement parameter acquisition again. And adjusting the contrast of the first grassland pest monitoring image according to the contrast enhancement parameter to obtain a second grassland pest monitoring image. And determining whether the deviation between the gray grassland insect pest monitoring image of the second grassland insect pest monitoring image and the gray grassland image of the original grassland insect pest monitoring image meets a parameter adjusting condition.
And when the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image does not meet the parameter adjusting condition, denoising the second grassland pest monitoring image to obtain a final grassland pest monitoring image, wherein the denoising is used for reducing noise introduced in the contrast adjusting process.
As shown in fig. 4, a method for estimating pest grade according to pest records through a pest estimation program according to an embodiment of the present invention includes:
s301, collecting real-time disease and insect pest related data and historical disease and insect pest related data of the grassland area through collecting equipment.
And S302, selecting a modeling factor of the disease and insect pest prediction model according to the contribution degree of the collected disease and insect pest related data to the disease and insect pest occurrence.
And S303, constructing a disease and pest prediction model based on the neural network according to the selected modeling factors, and training and optimizing the prediction model by using the collected historical disease and pest related data.
And S304, calling a disease and insect prediction model to input real-time disease and insect pest related data and historical disease and insect pest related data to predict disease and insect pest data in the grassland area, and verifying the accuracy of the predicted data.
The insect pest record provided by the embodiment of the invention comprises insect pest species, insect pest number and corresponding collection movement time period. The cloud server stores biological data of various insect pest types, local meteorological data, grassland related data and historical pest related data. The grassland related data comprises grassland area meteorological data, grassland area soil data, grassland area geographic position data and grassland character data.
The selection of the modeling factors of the pest and disease prediction model is carried out by adopting artificial interference or non-artificial interference, wherein the artificial interference adopts a stepwise regression Maic estimation algorithm, and the non-artificial interference adopts a multiple regression algorithm, a steady regression algorithm, a ridge regression algorithm or a principal component regression algorithm.
The construction of the disease and pest prediction model provided by the embodiment of the invention comprises the following substeps:
(1) and inputting a data sequence corresponding to the modeling factor of the selected pest and disease prediction model.
(2) And performing feature extraction on the data sequence by using an encoder.
(3) The features are decoded using a decoder network.
(4) And outputting the prediction result by utilizing the softmx layer through a multilayer fully-connected network in the L STM neural network.
As shown in fig. 5, a method for killing grassland insect pests in alpine pasturing areas by using an insect killing device according to an embodiment of the present invention includes:
s401, acquiring the insect pest type of the easily-broken insect pest in the current grassland period, and acquiring the activity time of each insect pest according to the climate information and the insect pest type.
S402, counting the probability of each insect pest fed back by all the insect killing devices, and screening out the insect pest types with the probability of more than 10%.
And S403, comparing the pest type screened in the S402 with the pest type obtained in the S401, sending the existing pest type to the pest killing lamp, sending the non-existing pest type to a manager to confirm the activity time of the manager, and sending the pest type and the activity time of the pest type to the pest killing lamp according to the pest activity time uploaded by the manager.
According to the embodiment of the invention, when all screened pest types do not exist in the previously acquired pest types, the climate information of the current time period is acquired again, and then the pest types and the activity time of each pest are acquired again.
The computer instructions may be stored on or transmitted from one computer-readable storage medium to another computer-readable storage medium, e.g., from one website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DS L) or wireless (e.g., infrared, wireless, microwave, etc.) means to another website site, computer, server, or data center via a solid state storage medium, such as a solid state Disk, or the like, (e.g., a solid state Disk, a magnetic storage medium, such as a DVD, a SSD, etc.), or any combination thereof.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. The alpine pastoral area grassland insect pest monitoring and early warning method based on big data is characterized by comprising the following steps of:
the method comprises the steps that firstly, a high-definition camera is carried by a stepping motor to collect grassland images of the alpine pasturing area, and the growth vigor of the grassland is judged according to the collected grassland images of the alpine pasturing area through a judging program; monitoring the insect pest situation of the grassland in real time to obtain insect pest monitoring original images of a plurality of sampling points of the grassland in the alpine pasturing area;
step two, denoising the acquired grassland insect pest monitoring original image through an image processing program; acquiring a first grassland pest monitoring image through an image enhancement program, wherein the first grassland pest monitoring image is obtained by sharpening the original grassland pest monitoring image;
step three, obtaining contrast enhancement parameters; adjusting the contrast of the first grassland pest monitoring image obtained in the second step according to the contrast enhancement parameter to obtain a second grassland pest monitoring image;
determining whether the deviation between the gray grassland image of the second grassland pest monitoring image and the gray grassland image of the original grassland pest monitoring image meets a parameter adjusting condition;
step five, when the deviation between the gray grassland image of the second grassland pest monitoring image and the gray grassland image of the original grassland pest monitoring image meets the parameter adjusting condition, adjusting the contrast enhancement parameter to obtain an adjusted contrast enhancement parameter;
sixthly, determining a final grassland pest monitoring image according to the adjusted contrast enhancement parameter, wherein the result grassland pest monitoring image is a grassland image obtained by enhancing the grassland image of the original grassland pest monitoring image; carrying out segmentation processing on the processed grassland insect pest monitoring image, and extracting a grassland insect pest characteristic diagram;
inputting the insect pest original image of each sampling point into a 2D convolutional neural network for training to form a training set; the central processing unit receives the pest characteristic diagram by using an identification program, and inputs the pest characteristic diagram into a 2D convolutional neural network to obtain a pest type corresponding to the image information;
analyzing the insect pest image of each sampling point based on a pre-configured grassland insect pest damage symptom learning model or insect body shape learning model to obtain the insect pest number in the insect pest image and generate an insect pest record;
step nine, acquiring real-time pest and disease damage related data and historical pest and disease damage related data of the grassland area from a cloud server, and selecting a modeling factor of a pest and disease damage prediction model according to the contribution degree of the acquired pest and disease damage related data to pest and disease damage occurrence;
step ten, constructing a disease and insect pest prediction model based on a neural network according to the modeling factors selected in the step nine, and training and optimizing the prediction model by using collected historical disease and insect pest related data;
step eleven, calling a pest prediction model through a pest prediction program to input real-time pest related data and historical pest related data, and predicting the pest grade of the grassland area according to the pest record;
twelfth, an acousto-optic early warning device is used for early warning the abnormal insect damage condition of the grassland, and an insect killing device is used for killing the insect damage of the grassland in the alpine pasturing area; the camera and the insect killing device are carried by the stepping motor, and the driving is provided for the grassland insect pest monitoring and early warning system in the alpine pasturing area;
step thirteen, processing the collected grassland image data by using the cloud server to centralize big data resources; storing and acquiring grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and information of insect killing conditions in alpine pasturing areas through a cloud server;
step fourteen, a wireless sensing network is communicated through a network interface to carry out wireless transmission of grassland insect pest monitoring and early warning data in the alpine pasturing area; the solar cell panel is used for providing electric energy for the grassland insect damage monitoring and early warning system in the alpine pasturing area; receiving grassland pest monitoring and early warning data through a mobile terminal, and performing remote control on a grassland pest monitoring and early warning system;
and fifteen, displaying and acquiring real-time data of the grassland image, the insect pest monitoring original image, the grassland growth judgment result, the insect pest identification result, the insect pest grade, the insect pest early warning information and the insect killing condition of the alpine pasturing area through an L ED high-definition display.
2. The big-data-based grassland pest monitoring and early warning method for the alpine pasturing area according to claim 1, wherein in step three, before the contrast of the first grassland pest monitoring image is adjusted for the first time according to the contrast enhancement parameter, the obtaining of the contrast enhancement parameter comprises:
determining a second average gray value of the gray grassland pest monitoring image of the original grassland pest monitoring image, and acquiring a corresponding relation between a pre-stored average gray value and a contrast enhancement parameter;
when the second average gray value is not equal to the average gray value in the corresponding relationship, the second average gray value is greater than the ith average gray value in the corresponding relationship, and the second average gray value is less than the (i + 1) th average gray value in the corresponding relationship, inputting the ith average gray value, the ith contrast enhancement parameter corresponding to the ith average gray value, the (i + 1) th contrast enhancement parameter corresponding to the (i + 1) th average gray value, and the second average gray value into a preset formula to obtain the contrast enhancement parameter corresponding to the second average gray value; and i is a positive integer.
3. The big-data-based grassland pest monitoring and early warning method for the alpine pasturing area according to claim 1, wherein in step four, the step of determining whether the deviation between the gray-scale grassland pest monitoring image of the second grassland pest monitoring image and the gray-scale grassland pest monitoring image of the original grassland pest monitoring image meets a parameter adjusting condition comprises the steps of:
converting the original grassland pest monitoring image into a gray grassland pest monitoring image to obtain the gray grassland pest monitoring image of the original grassland pest monitoring image;
converting the second grassland pest monitoring image into a gray grassland pest monitoring image to obtain a gray grassland pest monitoring image of the second grassland pest monitoring image;
comparing the gray grassland pest monitoring image of the original grassland pest monitoring image with the gray grassland pest monitoring image of the second grassland pest monitoring image to obtain a difference grassland pest monitoring image;
determining whether the first average gray value of the difference grassland pest monitoring image is larger than a preset gray value and whether the value of the contrast enhancement parameter is larger than 1;
and when the first average gray value is greater than the preset gray value and the contrast enhancement parameter is greater than 1, determining that the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets the parameter adjusting condition.
4. The method for monitoring and warning grassland insect pests in the alpine pasturing area based on big data as claimed in claim 1, wherein in step six, the determining the final grassland insect pest monitoring image according to the adjusted contrast enhancement parameter comprises:
taking the adjusted contrast enhancement parameter as the contrast enhancement parameter, and executing the contrast enhancement parameter acquisition again; adjusting the contrast of the first grassland pest monitoring image according to the contrast enhancement parameter to obtain a second grassland pest monitoring image; determining whether the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image meets a parameter adjusting condition;
and when the deviation between the gray grassland pest monitoring image of the second grassland pest monitoring image and the gray grassland pest monitoring image of the original grassland pest monitoring image does not meet the parameter adjusting condition, denoising the second grassland pest monitoring image to obtain a final grassland pest monitoring image, wherein the denoising is used for reducing noise introduced in the contrast adjusting process.
5. The method for monitoring and early warning grassland pests in the alpine pasturing area based on the big data as claimed in claim 1, wherein in the eighth step, the pest records comprise pest types, pest numbers and corresponding collecting movement periods; the cloud server is stored with a database of biological data, local meteorological data, grassland related data and historical pest and disease related data of various pest types; the grassland related data comprises grassland area meteorological data, grassland area soil data, grassland area geographic position data and grassland character data.
6. The method for monitoring and early warning grassland pests in the alpine pasturing area based on the big data as claimed in claim 1, wherein in the ninth step, the selection of the pest prediction model modeling factors is performed by adopting manual interference or non-manual interference; wherein, the manual interference adopts a stepwise regression Maic estimation algorithm, and the non-manual interference adopts a multiple regression algorithm, a steady regression algorithm, a ridge regression algorithm or a principal component regression algorithm;
the construction of the disease and pest prediction model comprises the following substeps:
(1) inputting a data sequence corresponding to the modeling factor of the selected plant disease and insect pest prediction model;
(2) carrying out feature extraction on the data sequence by using an encoder;
(3) decoding the feature using a decoder network;
(4) and outputting the prediction result by utilizing the softmx layer through a multilayer fully-connected network in the L STM neural network.
7. The method for monitoring and early warning grassland insect pests in alpine pasturing areas based on big data as claimed in claim 1, wherein in the twelfth step, the method for killing the grassland insect pests in the alpine pasturing areas through the insect killing device comprises:
(I) acquiring the insect pest type of the easily-broken insect pest in the current grassland time period, and acquiring the activity time of each insect pest according to the climate information and the insect pest type;
(II) counting the probability of each insect pest fed back by all the insect killing devices, and screening out the insect pest type with the probability of more than 10%;
(III) comparing the pest type screened in the step (II) with the pest type obtained in the step (I), sending the existing pest type to the pest killing lamp, sending the non-existing pest type to a manager to confirm the activity time of the manager, and obtaining the climate information, the pest type and the activity time of each pest in the current time period again; and sending the pest type and the pest activity time to the pest killing lamp according to the pest activity time uploaded by the manager.
8. The high-cold pastoral area grassland insect pest monitoring and early warning system based on the big data and applying the high-cold pastoral area grassland insect pest monitoring and early warning method based on the big data of any one of claims 1 to 7 is characterized by comprising the following steps:
the grassland monitoring module is connected with the central control module and used for acquiring grassland images of alpine pasturing areas through a high-definition camera, monitoring insect pest conditions of the grasslands in real time and acquiring insect pest monitoring original images;
the grassland growth condition judging module is connected with the central control module and used for judging the growth condition of the grassland according to the collected grassland images of the alpine pasturing area through a judging program;
the image processing module is connected with the central control module and used for denoising, enhancing and segmenting the acquired grassland insect pest monitoring original image through an image processing program and extracting a grassland insect pest characteristic diagram;
the central control module is connected with the grassland monitoring module, the grassland growth condition judging module, the image processing module, the insect pest identifying and judging module, the insect pest estimating module, the insect pest early warning module, the deinsectization module, the driving module, the big data processing module, the data storage module, the wireless communication module, the power supply module, the terminal module and the display module and is used for controlling the normal operation of each module of the grassland insect pest monitoring and early warning system in the alpine pastoral area through the central processing unit;
the insect pest identification and judgment module is connected with the central control module and used for identifying and judging insect pests according to the extracted grassland insect pest characteristic diagram through an identification program and generating insect pest records;
the insect pest estimation module is connected with the central control module and used for estimating the insect pest grade according to the insect pest record through an insect pest estimation program;
the insect pest early warning module is connected with the central control module and is used for early warning the abnormal insect pest condition of the grassland through the acousto-optic early warning device;
the insect killing module is connected with the central control module and is used for killing grassland insect pests in the alpine pasturing area through the insect killing device;
the driving module is connected with the central control module, is used for carrying the camera and the insect killing device through the stepping motor and provides driving for the grassland insect pest monitoring and early warning system in the alpine pasturing area;
the big data processing module is connected with the central control module and used for processing the acquired grassland image data by centralizing big data resources through the cloud server;
the data storage module is connected with the central control module and used for storing and acquiring grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and information of insect killing conditions in the alpine pasturing area through the cloud server;
the wireless communication module is connected with the central control module and used for communicating a wireless sensing network through a network interface to perform wireless transmission of grassland insect pest monitoring and early warning data in the alpine pasturing area;
the power supply module is connected with the central control module and used for providing electric energy for the grassland insect pest monitoring and early warning system in the alpine pasturing area through the solar cell panel;
the terminal module is connected with the central control module and used for receiving grassland insect pest monitoring and early warning data through the mobile terminal and performing remote control on the grassland insect pest monitoring and early warning system;
the display module is connected with the central control module and used for displaying and collecting real-time data of alpine pastoral area grassland images, insect pest monitoring original images, grassland growth judgment results, insect pest identification results, insect pest grades, insect pest early warning information and insect killing conditions through an L ED high-definition display.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the big data based grassland pest monitoring and warning method of any one of claims 2 to 8 when executed on an electronic device.
10. A computer-readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the big-data-based grassland pest monitoring and early warning method according to any one of claims 2 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010242607.6A CN111460990B (en) | 2020-03-31 | 2020-03-31 | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010242607.6A CN111460990B (en) | 2020-03-31 | 2020-03-31 | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111460990A true CN111460990A (en) | 2020-07-28 |
| CN111460990B CN111460990B (en) | 2023-04-07 |
Family
ID=71682362
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010242607.6A Active CN111460990B (en) | 2020-03-31 | 2020-03-31 | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111460990B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985445A (en) * | 2020-09-02 | 2020-11-24 | 青海省草原总站 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
| CN112001290A (en) * | 2020-08-18 | 2020-11-27 | 南京工程学院 | Rice planthopper migration flight path prediction method based on YOLO algorithm |
| CN112325946A (en) * | 2020-11-12 | 2021-02-05 | 延安大学 | Grassland ecological monitoring system based on Internet of things |
| CN112950399A (en) * | 2021-03-10 | 2021-06-11 | 中国热带农业科学院热带作物品种资源研究所 | Non-pollution prevention and control system and method for planting Shanlan rice |
| CN113191302A (en) * | 2021-05-14 | 2021-07-30 | 成都鸿钰网络科技有限公司 | Method and system for monitoring grassland ecology |
| CN113610327A (en) * | 2021-09-13 | 2021-11-05 | 贵州春芯科技有限公司 | Pepper disease prediction method and device, electronic device and storage medium |
| CN114170513A (en) * | 2021-12-08 | 2022-03-11 | 广东省农业科学院植物保护研究所 | Spodoptera frugiperda pest situation monitoring method and system and storage medium |
| CN116258373A (en) * | 2023-03-15 | 2023-06-13 | 杭州盈禾嘉田科技有限公司 | Disease and pest detection, prediction and early warning system and method based on big data |
| CN116384594A (en) * | 2023-06-05 | 2023-07-04 | 四川凯普顿信息技术股份有限公司 | Crop pest early warning method, system, terminal and medium based on big data analysis |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2641729A1 (en) * | 1976-09-16 | 1978-03-30 | Max Planck Gesellschaft | PROCEDURE FOR THE EARLY DETECTION, LOCALIZATION AND CONTROL OF STORAGE ROOM POLLUTION AND DEVICE FOR CARRYING OUT THE PROCEDURE |
| CN2105840U (en) * | 1990-11-26 | 1992-06-03 | 内蒙古农牧学院 | Suction catcher for locust on grassland |
| JP2000293622A (en) * | 1999-04-09 | 2000-10-20 | Canon Inc | Method and device for image processing and storage medium |
| DE102006002037A1 (en) * | 2006-01-16 | 2007-07-19 | Siemens Ag | Method for processing diagnostic image data |
| CN103598169A (en) * | 2013-11-15 | 2014-02-26 | 华南农业大学 | Visual sensor based remote drosophila monitoring system and monitoring method thereof |
| CN104381231A (en) * | 2014-11-06 | 2015-03-04 | 浙江大学 | Image-based field insect pest situation monitoring device |
| CN104635694A (en) * | 2015-01-08 | 2015-05-20 | 沈阳远大智能高科农业有限公司 | Intelligent agricultural early warning system |
| CN105844285A (en) * | 2016-02-25 | 2016-08-10 | 中国农业大学 | Cucumber disease identification method and apparatus based on image information |
| CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
| CN107711762A (en) * | 2017-10-19 | 2018-02-23 | 上海中信信息发展股份有限公司 | Intelligent Insect infestation monitoring method and intelligent Insect infestation monitoring device |
| CN107864935A (en) * | 2017-09-30 | 2018-04-03 | 常州金禾新能源科技有限公司 | New formula trapping lamp of getting lost |
| CN107926887A (en) * | 2017-10-31 | 2018-04-20 | 四川农业大学 | Diseases and pests of agronomic crop precisely identifies and intelligence control system |
| CN108009936A (en) * | 2017-10-31 | 2018-05-08 | 四川农业大学 | Pest and disease monitoring system based on internet of things |
| CN108230309A (en) * | 2017-12-29 | 2018-06-29 | 成都东谷利农农业科技有限公司 | Field pest and disease monitoring system and method |
| CN108535452A (en) * | 2018-05-07 | 2018-09-14 | 内蒙古蒙草生态环境（集团）股份有限公司 | A kind of grassland desertification stage division and its application |
| CN207941485U (en) * | 2018-01-04 | 2018-10-09 | 青海省草原总站 | A kind of grassland poison bait granulator |
| CN109032093A (en) * | 2018-08-14 | 2018-12-18 | 荆州农业科学院 | A kind of rice pest monitoring system |
| CN110363103A (en) * | 2019-06-24 | 2019-10-22 | 仲恺农业工程学院 | Identifying pest method, apparatus, computer equipment and storage medium |
| CN110837926A (en) * | 2019-11-04 | 2020-02-25 | 四川省烟草公司广元市公司 | Tobacco main pest and disease damage prediction method based on big data |
-
2020
- 2020-03-31 CN CN202010242607.6A patent/CN111460990B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE2641729A1 (en) * | 1976-09-16 | 1978-03-30 | Max Planck Gesellschaft | PROCEDURE FOR THE EARLY DETECTION, LOCALIZATION AND CONTROL OF STORAGE ROOM POLLUTION AND DEVICE FOR CARRYING OUT THE PROCEDURE |
| CN2105840U (en) * | 1990-11-26 | 1992-06-03 | 内蒙古农牧学院 | Suction catcher for locust on grassland |
| JP2000293622A (en) * | 1999-04-09 | 2000-10-20 | Canon Inc | Method and device for image processing and storage medium |
| DE102006002037A1 (en) * | 2006-01-16 | 2007-07-19 | Siemens Ag | Method for processing diagnostic image data |
| CN103598169A (en) * | 2013-11-15 | 2014-02-26 | 华南农业大学 | Visual sensor based remote drosophila monitoring system and monitoring method thereof |
| CN104381231A (en) * | 2014-11-06 | 2015-03-04 | 浙江大学 | Image-based field insect pest situation monitoring device |
| CN104635694A (en) * | 2015-01-08 | 2015-05-20 | 沈阳远大智能高科农业有限公司 | Intelligent agricultural early warning system |
| CN105844285A (en) * | 2016-02-25 | 2016-08-10 | 中国农业大学 | Cucumber disease identification method and apparatus based on image information |
| CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
| CN107864935A (en) * | 2017-09-30 | 2018-04-03 | 常州金禾新能源科技有限公司 | New formula trapping lamp of getting lost |
| CN107711762A (en) * | 2017-10-19 | 2018-02-23 | 上海中信信息发展股份有限公司 | Intelligent Insect infestation monitoring method and intelligent Insect infestation monitoring device |
| CN107926887A (en) * | 2017-10-31 | 2018-04-20 | 四川农业大学 | Diseases and pests of agronomic crop precisely identifies and intelligence control system |
| CN108009936A (en) * | 2017-10-31 | 2018-05-08 | 四川农业大学 | Pest and disease monitoring system based on internet of things |
| CN108230309A (en) * | 2017-12-29 | 2018-06-29 | 成都东谷利农农业科技有限公司 | Field pest and disease monitoring system and method |
| CN207941485U (en) * | 2018-01-04 | 2018-10-09 | 青海省草原总站 | A kind of grassland poison bait granulator |
| CN108535452A (en) * | 2018-05-07 | 2018-09-14 | 内蒙古蒙草生态环境（集团）股份有限公司 | A kind of grassland desertification stage division and its application |
| CN109032093A (en) * | 2018-08-14 | 2018-12-18 | 荆州农业科学院 | A kind of rice pest monitoring system |
| CN110363103A (en) * | 2019-06-24 | 2019-10-22 | 仲恺农业工程学院 | Identifying pest method, apparatus, computer equipment and storage medium |
| CN110837926A (en) * | 2019-11-04 | 2020-02-25 | 四川省烟草公司广元市公司 | Tobacco main pest and disease damage prediction method based on big data |
Non-Patent Citations (3)
| Title |
|---|
| 宋琨等: "一种基于机器视觉的农田害虫活体动态图像特征获取系统", 《电子质量》 * |
| 王磊等: "神经网络算法在茶叶防害虫识别中的应用", 《福建茶叶》 * |
| 索南扎西;: "天然草场鼠虫害防治形势与对策建议" * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112001290B (en) * | 2020-08-18 | 2023-10-27 | 南京工程学院 | Rice planthopper migration path prediction method based on YOLO algorithm |
| CN112001290A (en) * | 2020-08-18 | 2020-11-27 | 南京工程学院 | Rice planthopper migration flight path prediction method based on YOLO algorithm |
| CN111985445A (en) * | 2020-09-02 | 2020-11-24 | 青海省草原总站 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
| CN111985445B (en) * | 2020-09-02 | 2023-05-30 | 青海省草原总站 | Grassland insect pest monitoring system and method based on unmanned aerial vehicle multispectral remote sensing |
| CN112325946A (en) * | 2020-11-12 | 2021-02-05 | 延安大学 | Grassland ecological monitoring system based on Internet of things |
| CN112950399A (en) * | 2021-03-10 | 2021-06-11 | 中国热带农业科学院热带作物品种资源研究所 | Non-pollution prevention and control system and method for planting Shanlan rice |
| CN113191302A (en) * | 2021-05-14 | 2021-07-30 | 成都鸿钰网络科技有限公司 | Method and system for monitoring grassland ecology |
| CN113191302B (en) * | 2021-05-14 | 2022-11-01 | 成都鸿钰网络科技有限公司 | Method and system for monitoring grassland ecology |
| CN113610327A (en) * | 2021-09-13 | 2021-11-05 | 贵州春芯科技有限公司 | Pepper disease prediction method and device, electronic device and storage medium |
| CN114170513A (en) * | 2021-12-08 | 2022-03-11 | 广东省农业科学院植物保护研究所 | Spodoptera frugiperda pest situation monitoring method and system and storage medium |
| CN116258373A (en) * | 2023-03-15 | 2023-06-13 | 杭州盈禾嘉田科技有限公司 | Disease and pest detection, prediction and early warning system and method based on big data |
| CN116258373B (en) * | 2023-03-15 | 2024-02-09 | 杭州盈禾嘉田科技有限公司 | Disease and pest detection, prediction and early warning system and method based on big data |
| CN116384594A (en) * | 2023-06-05 | 2023-07-04 | 四川凯普顿信息技术股份有限公司 | Crop pest early warning method, system, terminal and medium based on big data analysis |
| CN116384594B (en) * | 2023-06-05 | 2023-08-01 | 四川凯普顿信息技术股份有限公司 | Crop pest early warning method, system, terminal and medium based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111460990B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460990B (en) | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method | |
| CN111767802B (en) | Method and device for detecting abnormal state of object | |
| CN114972843B (en) | Agricultural pest diagnosis and early warning system based on big data | |
| EP3482630A1 (en) | Method, system and computer program for performing a pest forecast | |
| Victorino et al. | Yield components detection and image-based indicators for non-invasive grapevine yield prediction at different phenological phases | |
| WO2023116454A1 (en) | Method and apparatus for identifying area having potential high risk of locust plagues, and device and storage medium | |
| CN117036088A (en) | Data acquisition and analysis method for identifying growth situation of greening plants by AI | |
| CN113273449A (en) | Digital twin body construction method for precise monitoring of sunlight greenhouse | |
| Carlos et al. | Monitoring system of environmental variables for a strawberry crop using IoT tools | |
| CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
| CN111967441A (en) | Crop disease analysis method based on deep learning | |
| CN112836623A (en) | Facility tomato farming decision auxiliary method and device | |
| KR102309568B1 (en) | Prediction system for collecting growth information of crop | |
| CN117575169A (en) | Intelligent agriculture management system based on data processing | |
| Hacking et al. | Vineyard yield estimation using 2-D proximal sensing: A multitemporal approach | |
| CN113435825B (en) | Intelligent management method, system and storage medium based on soil-borne disease control | |
| CN116975789B (en) | Intelligent farmland field analysis method, system and medium based on big data | |
| Scalisi et al. | Detecting, mapping and digitising canopy geometry, fruit number and peel colour in pear trees with different architecture | |
| KR20210059070A (en) | Cultivation monitoring system for crops and cultivation monitoring method for crops thereof | |
| La Madrid et al. | Real-Time Water Quality Monitoring System with Predictor for Tilapia Pond | |
| CN116046687A (en) | Crop growth process monitoring method, device and medium | |
| CN113408334B (en) | Crayfish full-chain data acquisition and intelligent detection method and device | |
| CN112042483B (en) | Three-dimensional cultivation method, system and device for new Chinese medicinal material variety | |
| FAISAL | A pest monitoring system for agriculture using deep learning | |
| CN211908856U (en) | Plant data acquisition system based on Internet of things |
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 |