CN111814866A - Disease and pest early warning method and device, computer equipment and storage medium - Google Patents
Disease and pest early warning method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111814866A CN111814866A CN202010634534.5A CN202010634534A CN111814866A CN 111814866 A CN111814866 A CN 111814866A CN 202010634534 A CN202010634534 A CN 202010634534A CN 111814866 A CN111814866 A CN 111814866A
- Authority
- CN
- China
- Prior art keywords
- plant
- pest
- data
- target picture
- characteristic 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
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 44
- 201000010099 disease Diseases 0.000 title claims abstract description 32
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 241000196324 Embryophyta Species 0.000 claims abstract description 96
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 230000008635 plant growth Effects 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 230000002776 aggregation Effects 0.000 claims abstract description 13
- 238000004220 aggregation Methods 0.000 claims abstract description 13
- 241000238631 Hexapoda Species 0.000 claims abstract description 9
- 230000004931 aggregating effect Effects 0.000 claims abstract description 7
- 230000012010 growth Effects 0.000 claims description 15
- 238000006116 polymerization reaction Methods 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 244000025254 Cannabis sativa Species 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 241000445816 Arundo formosana Species 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000234643 Festuca arundinacea Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 244000292693 Poa annua Species 0.000 description 1
- 244000197975 Solidago virgaurea Species 0.000 description 1
- 235000000914 Solidago virgaurea Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000009331 sowing Methods 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 238000002054 transplantation Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06V10/30—Noise filtering
Abstract
The invention discloses a pest and disease early warning method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining IoT sensing time sequence data to obtain IoT dimension characteristics; collecting a lawn picture, and preprocessing the lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying from the target picture according to the plant characteristics to obtain focus characteristics; acquiring plant growth state data, and aggregating the focus characteristics, IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregated characteristic data; performing first similarity calculation on the time-series multi-dimensional aggregation characteristic data and the historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result. According to the invention, the effective early warning of the outbreak of the lawn diseases and insect pests is realized by predicting the multi-dimensional time sequence data.
Description
Technical Field
The invention relates to the technical field of plant protection, in particular to a disease and pest early warning method and device, computer equipment and a storage medium.
Background
At present, most of the solutions commonly adopted in the field of plant protection are used for economic crops (such as rice, corn and the like), and the economic crops have great differences in the aspects of area (non-continuity), urban difference (environmental characteristics), plant complexity (shrub, arbor shielding and the like) and maintenance means (irrigation, disinfection) compared with the scenes of the community greening lawn, so that the solutions cannot be directly used for plant protection of the community greening lawn. Meanwhile, the traditional crop pest judgment model is only established after pest discovery, and then loss is reduced by prolonging the pest discovery time. In an actual scene, the disease and insect pest outbreak is a process of qualitative change caused by quantitative change, and the process has a universal time sequence characteristic rule.
In communities, the lawn pests and diseases are discovered mainly by greening maintenance personnel by utilizing plant protection knowledge learned by the personnel, and relevant medicaments are sprayed for prevention after identification, or the relevant medicaments are regularly sprayed to achieve prevention and treatment effects. However, the method depends heavily on the plant protection professional quality of the greening maintenance personnel, and in the actual business, high labor cost and resource waste are brought, and meanwhile, great economic loss can be caused due to untimely monitoring.
Disclosure of Invention
The embodiment of the invention provides a pest and disease early warning method, a pest and disease early warning device, computer equipment and a storage medium, and aims to early warn the outbreak of pests and diseases on a lawn.
In a first aspect, an embodiment of the present invention provides a pest and disease damage early warning method, including:
obtaining IoT sensing time sequence data, and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics;
collecting a lawn picture, and preprocessing the collected lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
acquiring plant growth state data, and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregated characteristic data;
performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
Further, the collecting the lawn picture and preprocessing the collected lawn picture to obtain a target picture includes:
and performing quality screening on the collected pictures, and selecting the pictures with the picture brightness, the definition and the angle reaching preset standards as target pictures.
Further, the identifying the plant species of the target picture by using an image identification algorithm includes:
and extracting the features of the target picture, inputting the extracted features into a neural network model for plant species analysis, performing vertical optimization through data labeling under lines, and matching from a plant database to obtain the plant species.
Further, the determining the plant characteristics according to the identified plant species and then identifying the focus characteristics from the target picture according to the plant characteristics includes:
filtering out image noise of the target picture by using a median filtering algorithm, and performing image enhancement processing on the target picture by using a gray level transformation algorithm and a high-low cap conversion algorithm;
separating the green position in the target picture through color space conversion to obtain a leaf focus;
and extracting the shape, color and texture characteristics of the leaf focus to obtain focus characteristics.
Further, the acquiring the plant growth state data includes:
establishing a lawn ruler every other preset area;
identifying the growth scale of the plant under the scale by an image object identification technology, averaging the growth scale, and taking the average as plant growth state data.
Further, the calculation of the first similarity of the time sequence multidimensional polymerization characteristic data and the historical pest characteristic data comprises the following steps:
and performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and the historical pest characteristic data by using a Mahalanobis distance algorithm.
Further, the method also comprises the following steps:
respectively calculating first similarity of time sequence multi-dimensional aggregation characteristic data of each day and the historical pest characteristic data within continuous preset days;
and carrying out weighted summation on the first similarity of each day to obtain a second similarity.
In a second aspect, an embodiment of the present invention provides a pest and disease early warning device, including:
the acquisition unit is used for acquiring IoT sensing time sequence data and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics;
the acquisition unit is used for acquiring the lawn picture and preprocessing the acquired lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
the aggregation unit is used for acquiring plant growth state data and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregation characteristic data;
the comparison unit is used for calculating the first similarity of the time sequence multi-dimensional polymerization characteristic data and the historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
In a third aspect, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program that is stored in the memory and is executable on the processor, and when the processor executes the computer program, the pest and disease warning method described above is implemented.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for early warning of plant diseases and insect pests is implemented.
The embodiment of the invention provides a pest and disease early warning method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining IoT sensing time sequence data, and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics; collecting a lawn picture, and preprocessing the collected lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics; acquiring plant growth state data, and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregated characteristic data; performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result. According to the embodiment of the invention, the similarity between the multi-dimensional time sequence data and the historical characteristic data is calculated, so that the effective early warning of the outbreak of the lawn diseases and insect pests is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a pest and disease damage early warning method provided by an embodiment of the invention;
fig. 2 is a schematic block diagram of a pest and disease early warning device provided by the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. 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.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1, fig. 1 is a schematic flow chart of a pest and disease damage warning method provided by an embodiment of the present invention, specifically including: steps S101 to S104.
S101, obtaining IoT sensing time sequence data, and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics;
s102, collecting a lawn picture, and preprocessing the collected lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
s103, acquiring plant growth state data, and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multi-dimensional aggregate characteristic data;
s104, performing first similarity calculation on the time sequence multi-dimensional aggregation characteristic data and historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
In this embodiment, IoT sensing time series data, plant disease and pest characteristic data (i.e., the lesion characteristic) and plant growth state data are aggregated into multidimensional characteristic data (i.e., the time series multidimensional aggregated characteristic data), a similarity between the time series multidimensional aggregated characteristic data and historical disease and pest characteristic data is calculated, and an early warning result is correspondingly output according to the similarity. According to the embodiment, the early warning of the occurrence of the lawn diseases and insect pests can be effectively realized, the time sequence characteristics are introduced, and the possibility of the occurrence of the lawn diseases and insect pests in a period of time is predicted according to the rule of the time sequence characteristics, so that the accuracy of the early warning is improved.
The IoT (The Internet of things) is to collect any object or process needing monitoring, connection and interaction in real time and collect various required information such as sound, light, heat, electricity, mechanics, chemistry, biology and location through various devices and technologies such as various information sensors, radio frequency identification technology, global positioning system, infrared sensor and laser scanner, and realize The ubiquitous connection of objects and people through various possible network accesses, and realize intelligent sensing, identification and management of objects and processes. In this embodiment, IoT environmental timing data is formed by collecting data (including soil temperature, soil humidity, soil EC value, PH value, ambient temperature, ambient humidity, ambient lighting, ambient wind, etc.).
In a specific application scenario, the early warning test is performed on the cool-season grass and the warm-season grass by using the pest and disease early warning method provided by the embodiment, for example, the early warning is performed on common lawn types (taiwan grass, paradise grass, hawaii grass, goldenrod grass and the like) and mixed-sowing lawns (grass glume cutting, poa annua, festuca arundinacea and the like) in the community.
In a specific embodiment, meteorological data is acquired, and the meteorological data, the focus feature, the IoT dimensional feature and the plant growth state data are aggregated to obtain time-series multidimensional aggregated feature data.
In this embodiment, the meteorological data and other data are aggregated, so that the final early warning accuracy can be improved. The meteorological data can comprise meteorological temperature, barometric pressure and the like, and can be acquired through a national meteorological website.
In an embodiment, the acquiring a lawn picture and preprocessing the acquired lawn picture to obtain a target picture includes:
and performing quality screening on the collected pictures, and selecting the pictures with the picture brightness, the definition and the angle reaching preset standards as target pictures.
In the embodiment, the pictures meeting the preset standard are selected from the collected pictures, and the pictures not meeting the preset standard are removed, so that the quality of the target picture is ensured, and the follow-up steps are facilitated.
In a specific embodiment, the collected pictures are screened according to the growth cycle of the plant, that is, the picture conforming to the growth cycle of the plant is selected as the target picture. For example, based on the city, month, ambient temperature and the gaussian distribution characteristics of the picture color, a picture conforming to the green turning state can be screened out for subsequent analysis (green turning means that the green of the plant changes from yellow to green after seedling transplantation or overwintering, and the lawn which is not green turning does not have analytical significance).
In an embodiment, the identifying the plant species of the target picture by using an image identification algorithm includes:
and extracting the features of the target picture, inputting the extracted features into a neural network model for plant species analysis, performing vertical optimization through data labeling under lines, and matching from a plant database to obtain the plant species.
In this embodiment, first, feature extraction is performed on the target picture, then, the extracted features are input into the neural network model, an analysis result is output by the neural network model, and finally, the analysis result is matched by using a plant database, so that a plant type corresponding to the target picture is determined.
Specifically, the target picture training data is preprocessed to obtain training set data, test set data and verification set data;
performing two-layer convolution-pooling on the training set data, namely inputting the training set data into a one-dimensional convolution layer and outputting a first characteristic matrix; inputting the first feature matrix into a 3 x 3 maximum pooling layer to perform dimension reduction processing on the first feature matrix; inputting the feature matrix subjected to dimensionality reduction into the next convolution layer again, outputting a second feature matrix with the same specification as the target picture, inputting the second feature matrix into a 3 x 3 maximum pooling layer, taking the output result of the maximum pooling layer as the input of a full connection layer, and outputting an analysis result through the full connection layer, thereby constructing a training model for plant species identification;
then, optimizing the model by using a gradient descent algorithm as an optimizer, a Softmax algorithm as a classifier and a square loss function (Least square method) as the optimizer, and performing multiple test optimization on the model by using test set data to finally obtain an optimized model;
the accuracy of the constructed model is verified by using a reduce _ mean method of Tensorflow (a symbolic mathematical system based on data flow programming) as an evaluation model;
and testing the constructed model by using the verification set data to verify the testing accuracy of the actual data.
The plant database in this embodiment is a pre-established plant database. Of course, in the process of identifying the plant species, the plant database may not match the identification result, that is, the plant database does not include such plant, so that such plant may be first included in the plant database, and then the plant characteristics of such plant may be determined.
In an embodiment, the determining a plant characteristic according to the identified plant species and then identifying a lesion characteristic from the target picture according to the plant characteristic includes:
filtering out image noise of the target picture by using a median filtering algorithm, and performing image enhancement processing on the target picture by using a gray level transformation algorithm and a high-low cap conversion algorithm;
separating the green position in the target picture through color space conversion to obtain a leaf focus;
and extracting the shape, color and texture characteristics of the leaf focus to obtain focus characteristics.
In this embodiment, after determining the plant features corresponding to the target picture, a series of processing (for example, noise filtering, gray level conversion, high-low cap conversion, and the like) is performed on the target picture, then focus image extraction is performed on the processed target picture, so as to obtain the leaf focus, and finally focus features are extracted from the leaf focus.
It should be noted that plant diseases and insect pests of grass plants are scattered in leaves of grass at an early stage, and most of the plant diseases and insect pests have yellow brown focus positions (rust is reddish brown) and green focus positions, so that the green focus positions can be separated through color space conversion to obtain the leaf focus. In addition, when the focus features are extracted, the form (area, shape), color (R, G, B, R/G, B/G), texture features (entropy, energy, inertia) of the leaf focus are mainly extracted.
In one embodiment, the acquiring the plant growth state data includes:
establishing a lawn ruler every other preset area;
identifying the growth scale of the plant under the scale by an image object identification technology, averaging the growth scale, and taking the average as plant growth state data.
In this embodiment, the growth states of the plants are greatly related to the environmental parameters, and the growth states of different regions of the same lawn are different. For lawn plants, the growth state of the plant can be determined by the height of the plant leaf. Therefore, in order to relatively accurately predict the plant growth state and acquire the plant growth state data, a lawn ruler (i.e., a reference ruler with scales) can be established on the lawn, for example, a ruler is established every 20 square meters, so that the whole lawn forms a grid, then the ruler and the growth scales of the plants under the ruler are read through an image object recognition technology, and finally, the average number of the read growth scales is taken as the plant growth state data. Further, plant growth status data were recorded by day.
In one embodiment, the performing a first similarity calculation on the time-series multidimensional polymerization characteristic data and the historical pest characteristic data includes:
and performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and the historical pest characteristic data by using a Mahalanobis distance algorithm.
In this embodiment, after the time series multidimensional polymerization characteristic data is obtained, a mahalanobis distance algorithm is used to calculate the similarity between the time series multidimensional polymerization characteristic data and the historical pest characteristic data. And after the similarity is obtained, comparing the similarity with a preset similarity threshold, and correspondingly outputting an early warning result according to the comparison result. For example, when the calculated similarity is greater than or equal to a preset similarity threshold, the probability of pest occurrence can be displayed in the sent early warning result; and when the calculated similarity is smaller than a preset similarity threshold, the probability of pest and disease damage occurrence displayed in the early warning result can be relatively low.
The mahalanobis distance represents the distance between a point and a distribution, and the mahalanobis distance algorithm is an effective method for calculating the similarity between two unknown sample sets, is not influenced by dimensions, has no relation between the mahalanobis distance between two points and the unit of measurement of the original data, and has the same mahalanobis distance between two points calculated from the normalized data and the centralized data (i.e., the difference between the original data and the mean value). Mahalanobis distance can also exclude interference with correlations between variables. The calculation formula is as follows:
in the formula, DM(x) Is the mahalanobis distance, x is the multivariate vector, μ is the mean of x, and Σ is the covariance matrix of x.
In one embodiment, the pest early warning method further comprises:
respectively calculating first similarity of time sequence multi-dimensional aggregation characteristic data of each day and the historical pest characteristic data within continuous preset days;
and carrying out weighted summation on the first similarity of each day to obtain a second similarity.
In this embodiment, the similarity of multiple days (i.e., the first similarity between the time series multidimensional aggregation characteristic data of each day and the historical pest characteristic data) is calculated, and the similarity of each day is weighted and summed, so that the finally obtained similarity (i.e., the second similarity) is more accurate. For example, the similarity is calculated by day for the past 7 days, and the similarities for each day in 7 days are weighted and summed to obtain the final similarity.
The embodiment may also compare the second similarity with a preset similarity threshold, and output an early warning result according to the comparison result. And, here, the greater the second similarity, the greater the probability of occurrence of a pest; the smaller the second similarity, the smaller the probability of occurrence of a pest.
In a specific application scenario, as shown in table 1, IOT soil sensing data and environmental data, meteorological data, plant growth status data, and plant disease and pest characteristics of the last 7 days are obtained, and as can be seen from table 1, when the temperature vector of the last 7 days is continuously 20 ° to 30 °, the plant (taiwan grass) is likely to generate brown spot, so that it can be used to warn whether the plant (taiwan grass) has a disease and pest.
TABLE 1
Fig. 2 is a schematic block diagram of a pest and disease damage early warning device 200 provided in an embodiment of the present invention, including:
an obtaining unit 201, configured to obtain IoT sensing timing sequence data, and perform preprocessing on the IoT sensing timing sequence data to obtain IoT dimensional characteristics;
the acquisition unit 202 is used for acquiring a lawn picture and preprocessing the acquired lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
the aggregation unit 203 is configured to obtain plant growth state data, and aggregate the focus features, IoT dimensional features, and plant growth state data to obtain time-series multidimensional aggregate feature data;
the comparison unit 204 is used for performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
In one embodiment, the acquisition unit 202 includes:
and the screening unit is used for screening the quality of the collected pictures and selecting the pictures with the brightness, the definition and the angle reaching the preset standards as target pictures.
In an embodiment, the acquisition unit 202 further comprises:
and the first feature extraction unit is used for extracting features of the target picture, inputting the extracted features into a neural network model for plant species analysis, performing vertical optimization through offline data labeling, and matching from a plant database to obtain plant species.
In an embodiment, the acquisition unit 202 further comprises:
the image processing unit is used for filtering the image noise of the target picture by using a median filtering algorithm and performing image enhancement processing on the target picture by using a gray level transformation algorithm and a high-low cap conversion algorithm;
the separation unit is used for separating the green position in the target picture through color space conversion to obtain a leaf focus;
and the second feature extraction unit is used for extracting the morphological, color and texture features of the leaf focus to obtain the focus features.
In one embodiment, the aggregation unit 203 includes:
the lawn scale establishing unit is used for establishing a lawn scale every other preset area;
and the identification unit is used for identifying the growth scale of the plant under the scale through an image object identification technology, averaging the growth scale and taking the average as plant growth state data.
In one embodiment, the comparing unit 204 comprises:
and performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and the historical pest characteristic data by using a Mahalanobis distance algorithm.
In one embodiment, the pest warning apparatus 200 further includes:
the calculation unit is used for respectively calculating first similarity between the time sequence multi-dimensional aggregation characteristic data of each day and the historical pest characteristic data within continuous preset days;
and the weighted summation unit is used for carrying out weighted summation on the first similarity of each day to obtain a second similarity.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps provided by the above embodiments can be implemented. The storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The embodiment of the present invention further provides a computer device, which may include a memory and a processor, where the memory stores a computer program, and the processor may implement the steps provided in the above embodiments when calling the computer program in the memory. Of course, the electronic device may also include various network interfaces, power supplies, and the like.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A pest and disease damage early warning method is characterized by comprising the following steps:
obtaining IoT sensing time sequence data, and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics;
collecting a lawn picture, and preprocessing the collected lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
acquiring plant growth state data, and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregated characteristic data;
performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
2. A pest early warning method according to claim 1, wherein the step of collecting lawn pictures and preprocessing the collected lawn pictures to obtain target pictures comprises:
and performing quality screening on the collected pictures, and selecting the pictures with the picture brightness, the definition and the angle reaching preset standards as target pictures.
3. A pest warning method according to claim 1, wherein the plant species identification of the target picture by using an image recognition algorithm comprises:
and extracting the features of the target picture, inputting the extracted features into a neural network model for plant species analysis, performing vertical optimization through data labeling under lines, and matching from a plant database to obtain the plant species.
4. A pest warning method according to claim 1, wherein the step of determining plant characteristics according to the identified plant species and then identifying focus characteristics from the target picture according to the plant characteristics comprises the steps of:
filtering out image noise of the target picture by using a median filtering algorithm, and performing image enhancement processing on the target picture by using a gray level transformation algorithm and a high-low cap conversion algorithm;
separating the green position in the target picture through color space conversion to obtain a leaf focus;
and extracting the shape, color and texture characteristics of the leaf focus to obtain focus characteristics.
5. A pest warning method according to claim 1 wherein the acquiring plant growth state data includes:
establishing a lawn ruler every other preset area;
identifying the growth scale of the plant under the scale by an image object identification technology, averaging the growth scale, and taking the average as plant growth state data.
6. A pest early warning method according to claim 1, wherein the first similarity calculation is performed on the time series multidimensional aggregate characteristic data and historical pest characteristic data, and comprises the following steps:
and performing first similarity calculation on the time sequence multidimensional polymerization characteristic data and the historical pest characteristic data by using a Mahalanobis distance algorithm.
7. A pest warning method according to claim 1 further comprising:
respectively calculating first similarity of time sequence multi-dimensional aggregation characteristic data of each day and the historical pest characteristic data within continuous preset days;
and carrying out weighted summation on the first similarity of each day to obtain a second similarity.
8. A plant disease and insect pest early warning device is characterized by comprising:
the acquisition unit is used for acquiring IoT sensing time sequence data and preprocessing the IoT sensing time sequence data to obtain IoT dimensional characteristics;
the acquisition unit is used for acquiring the lawn picture and preprocessing the acquired lawn picture to obtain a target picture; carrying out plant species identification on the target picture by using an image identification algorithm, determining plant characteristics according to the plant species obtained by identification, and then identifying focus characteristics from the target picture according to the plant characteristics;
the aggregation unit is used for acquiring plant growth state data and aggregating the focus characteristics, the IoT dimension characteristics and the plant growth state data to obtain time sequence multidimensional aggregation characteristic data;
the comparison unit is used for calculating the first similarity of the time sequence multi-dimensional polymerization characteristic data and the historical pest characteristic data; and comparing the calculation result with a preset similarity threshold value, and outputting an early warning result according to the comparison result.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the pest warning method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when executed by a processor, implements a pest warning method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010634534.5A CN111814866A (en) | 2020-07-02 | 2020-07-02 | Disease and pest early warning method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010634534.5A CN111814866A (en) | 2020-07-02 | 2020-07-02 | Disease and pest early warning method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111814866A true CN111814866A (en) | 2020-10-23 |
Family
ID=72856158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010634534.5A Pending CN111814866A (en) | 2020-07-02 | 2020-07-02 | Disease and pest early warning method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814866A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN116401417A (en) * | 2023-06-07 | 2023-07-07 | 深圳市中农网有限公司 | Hierarchical storage method based on massive agricultural product data |
| CN117290762A (en) * | 2023-10-11 | 2023-12-26 | 北京邮电大学 | Insect pest falling-in identification method, type identification method, device, insect trap and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006235669A (en) * | 2005-02-22 | 2006-09-07 | Mitsubishi Electric Corp | Feature similarity determining device and program |
| CN103514459A (en) * | 2013-10-11 | 2014-01-15 | 中国科学院合肥物质科学研究院 | Method and system for identifying crop diseases and pests based on Android mobile phone platform |
| CN107094492A (en) * | 2017-06-30 | 2017-08-29 | 合肥虎俊装饰工程有限公司 | A kind of garden management system based on Internet of Things |
| CN107506790A (en) * | 2017-08-07 | 2017-12-22 | 西京学院 | Greenhouse winter jujube plant disease prevention model based on agriculture Internet of Things and depth belief network |
| CN110147403A (en) * | 2019-05-23 | 2019-08-20 | 中国农业科学院农业信息研究所 | Agriculture big data fusion method, device, equipment and storage medium |
| CN110213376A (en) * | 2019-06-05 | 2019-09-06 | 黑龙江省七星农场 | A kind of information processing system and method for pest prevention |
| CN110516712A (en) * | 2019-08-01 | 2019-11-29 | 仲恺农业工程学院 | Insect pest image-recognizing method, insect pest monitoring method, device, equipment and medium |
| CN110622182A (en) * | 2018-09-04 | 2019-12-27 | 安徽中科智能感知产业技术研究院有限责任公司 | Wheat severe disease prediction method based on multiple time sequence attribute element depth characteristics |
-
2020
- 2020-07-02 CN CN202010634534.5A patent/CN111814866A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006235669A (en) * | 2005-02-22 | 2006-09-07 | Mitsubishi Electric Corp | Feature similarity determining device and program |
| CN103514459A (en) * | 2013-10-11 | 2014-01-15 | 中国科学院合肥物质科学研究院 | Method and system for identifying crop diseases and pests based on Android mobile phone platform |
| CN107094492A (en) * | 2017-06-30 | 2017-08-29 | 合肥虎俊装饰工程有限公司 | A kind of garden management system based on Internet of Things |
| CN107506790A (en) * | 2017-08-07 | 2017-12-22 | 西京学院 | Greenhouse winter jujube plant disease prevention model based on agriculture Internet of Things and depth belief network |
| CN110622182A (en) * | 2018-09-04 | 2019-12-27 | 安徽中科智能感知产业技术研究院有限责任公司 | Wheat severe disease prediction method based on multiple time sequence attribute element depth characteristics |
| CN110147403A (en) * | 2019-05-23 | 2019-08-20 | 中国农业科学院农业信息研究所 | Agriculture big data fusion method, device, equipment and storage medium |
| CN110213376A (en) * | 2019-06-05 | 2019-09-06 | 黑龙江省七星农场 | A kind of information processing system and method for pest prevention |
| CN110516712A (en) * | 2019-08-01 | 2019-11-29 | 仲恺农业工程学院 | Insect pest image-recognizing method, insect pest monitoring method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 李翠玲 等: "基于高光谱的番茄叶片斑潜蝇虫害检测", 光谱学与光谱分析, vol. 38, no. 01, pages 253 - 257 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN116401417A (en) * | 2023-06-07 | 2023-07-07 | 深圳市中农网有限公司 | Hierarchical storage method based on massive agricultural product data |
| CN116401417B (en) * | 2023-06-07 | 2023-09-05 | 深圳市中农网有限公司 | Hierarchical storage method based on massive agricultural product data |
| CN117290762A (en) * | 2023-10-11 | 2023-12-26 | 北京邮电大学 | Insect pest falling-in identification method, type identification method, device, insect trap and system |
| CN117290762B (en) * | 2023-10-11 | 2024-04-02 | 北京邮电大学 | Insect pest falling-in identification method, type identification method, device, insect trap and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814866A (en) | Disease and pest early warning method and device, computer equipment and storage medium | |
| CN111767802B (en) | Method and device for detecting abnormal state of object | |
| CN113221765B (en) | Vegetation phenological period extraction method based on digital camera image effective pixels | |
| US20140099000A1 (en) | Device and method for detecting plantation rows | |
| CN110427798B (en) | Intelligent green vegetable identification and leaf environment change prediction method | |
| Prakash et al. | A study of image processing in agriculture | |
| JP2021509212A (en) | Disease prediction and control methods and their systems | |
| CN116227758B (en) | Agricultural product maturity prediction method and system based on remote sensing technology and deep learning | |
| CN116543316B (en) | Method for identifying turf in paddy field by utilizing multi-time-phase high-resolution satellite image | |
| CN117114913A (en) | Intelligent agricultural data acquisition system based on big data | |
| Shahrin et al. | Agricultural analysis and crop yield prediction of habiganj using multispectral bands of satellite imagery with machine learning | |
| Poornam et al. | Image based Plant leaf disease detection using Deep learning | |
| DB et al. | Classification of oil palm female inflorescences anthesis stages using machine learning approaches | |
| CN114973024A (en) | Method and system for monitoring and evaluating comprehensive evaluation index of mechanical cotton picking and defoliating effect | |
| CN109960972B (en) | Agricultural and forestry crop identification method based on middle-high resolution time sequence remote sensing data | |
| Dubey | Automatic recognition of fruits and vegetables and detection of fruit diseases | |
| Zhang et al. | Automatic non-destructive multiple lettuce traits prediction based on DeepLabV3+ | |
| CN116739868B (en) | Afforestation management system and method based on artificial intelligence | |
| CN113127464A (en) | Agricultural big data environment feature processing method and device and electronic equipment | |
| Sitokonstantinou et al. | A sentinel based agriculture monitoring scheme for the control of the cap and food security | |
| CN116757707A (en) | Crop fruit growth tracing method and system | |
| CN113537645A (en) | Soybean yield prediction method based on machine learning fusion satellite and weather data | |
| Al-Shammari et al. | Mapping cotton fields using phenology-based metrics derived from a time series of Landsat imagery. | |
| Nandhini et al. | Identification and classification of leaf diseases in turmeric plants | |
| CN113762773B (en) | Associated positioning decomposition method and system for disaster monitoring and forecasting |
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 |