CN113989532A - Intelligent identification method and device for rubber tree diseases and insect pests - Google Patents
Intelligent identification method and device for rubber tree diseases and insect pests Download PDFInfo
- Publication number
- CN113989532A CN113989532A CN202111235483.XA CN202111235483A CN113989532A CN 113989532 A CN113989532 A CN 113989532A CN 202111235483 A CN202111235483 A CN 202111235483A CN 113989532 A CN113989532 A CN 113989532A
- Authority
- CN
- China
- Prior art keywords
- rubber tree
- image acquisition
- pest
- result
- 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.)
- Pending
Links
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention discloses an intelligent identification method and device for rubber tree diseases and insect pests, which are used for obtaining expected growth characteristics according to basic information and growth environment information; acquiring an image of the first rubber tree by a first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain an actual growth characteristic, and comparing the actual growth characteristic with an expected growth characteristic to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result. The method solves the technical problems of untimely/inaccurate prevention and control, poor prevention and control effect and low ecological benefit caused by the lack of intelligent rubber tree pest identification in the rubber tree pest prevention and control process in the prior art.
Description
Technical Field
The invention relates to the field related to intelligent identification of rubber tree diseases and insect pests, in particular to an intelligent identification method and device for rubber tree diseases and insect pests.
Background
Natural rubber is a traditional prop industry with competitive advantages in agricultural production, and rubber tree pest is a prominent problem in rubber production. Therefore, the research and control of rubber tree diseases and insect pests have been paid attention by rubber planting countries, and great progress is made in the research, development and popularization of the control of some main diseases of rubber trees. However, the past production prevention and control do not comprehensively treat the rubber plant diseases and insect pests on the whole, most of the plant diseases and insect pests do not have prediction methods and prevention and control indexes, and the prevention and control are blindness, so that the situations of more medicine, high cost, poor prevention effect, low benefit, serious environmental pollution, low economic, social and ecological benefits and the like often occur.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the prior art, in the process of preventing and controlling the plant diseases and insect pests of the rubber trees, the intelligent identification of the plant diseases and insect pests of the rubber trees is lacked, so that the technical problems of untimely/inaccurate prevention and control, poor prevention and control effect and low ecological benefit are caused.
Disclosure of Invention
The embodiment of the application provides an intelligent identification method and device for rubber tree diseases and insect pests, and solves the technical problems that in the process of rubber tree disease and insect pest control in the prior art, the intelligent disease and insect pest identification of a rubber tree is lacked, the control is not timely/inaccurate, the control effect is poor, and the ecological benefit is low, so that the intelligent and accurate identification of the rubber tree diseases and insect pests based on images is achieved, the timely and accurate disease and insect pest control is performed, and the technical effects of improving the control effect and the ecological benefit are achieved.
In view of the above problems, the present application provides an intelligent identification method and apparatus for rubber tree diseases and insect pests.
In a first aspect, the application provides an intelligent identification method for rubber tree diseases and insect pests, wherein the method is applied to an intelligent identification system for the diseases and the pests, the system is in communication connection with a first image acquisition device, and the method comprises the following steps: obtaining basic information of a first rubber tree; obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information; acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
On the other hand, this application still provides a rubber tree plant diseases and insect pests's intelligent recognition device, the device includes: a first obtaining unit, configured to obtain basic information of a first rubber tree; a second obtaining unit, configured to obtain growth environment information of the first rubber tree, and obtain an expected growth characteristic of the first rubber tree according to the basic information and the growth environment information; the third obtaining unit is used for carrying out image acquisition on the first rubber tree through a first image acquisition device to obtain a first image acquisition result; a fourth obtaining unit, configured to perform image analysis according to the first image acquisition result to obtain an actual growth characteristic of the first rubber tree, and compare the actual growth characteristic with the expected growth characteristic to obtain a first influence parameter; the first construction unit is used for constructing a pest and disease characteristic comparison model of the rubber tree, inputting the first influence parameter and the first image acquisition result into the pest and disease characteristic comparison model and obtaining a first output result; and the fifth obtaining unit is used for identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
In a third aspect, the invention provides an intelligent identification device for rubber tree diseases and insect pests, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the steps of the method of the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the basic information of the first rubber tree is obtained; obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information; acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; according to first output result carries out the pest and disease damage discernment prevention and cure of first rubber tree is discerned through image acquisition and influence parameter to the pest and disease damage characteristic of rubber tree, considers the growth environment of rubber tree and the characteristic of pest and disease damage and compares comprehensively, and then reaches the accuracy and discerns the pest and disease damage, carries out timely accurate pest and disease damage prevention and cure, reaches the technological effect that improves prevention and cure effect, improvement ecological benefit.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart of an intelligent identification method for rubber tree diseases and insect pests according to an embodiment of the application;
FIG. 2 is a schematic flow chart of the intelligent identification method for rubber tree diseases and insect pests for obtaining expected growth characteristics according to the embodiment of the application;
FIG. 3 is a schematic flow chart of the method for intelligently identifying rubber tree diseases and insect pests according to the embodiment of the application for obtaining the first image acquisition result;
FIG. 4 is a schematic flow chart of a first preliminary examination sampling position distribution rule obtained by the intelligent rubber tree pest and disease identification method according to the embodiment of the application;
FIG. 5 is a schematic flow chart of the method for intelligently identifying rubber tree diseases and insect pests according to the embodiment of the application for obtaining the first influence parameter;
FIG. 6 is a schematic flow chart of a method for intelligently identifying rubber tree diseases and insect pests according to the embodiment of the present application, in which a disease and insect pest characteristic comparison model of a rubber tree is constructed;
FIG. 7 is a schematic view of a model parameter correction process of an intelligent identification method for rubber tree diseases and insect pests according to an embodiment of the present application;
FIG. 8 is a schematic structural diagram of an intelligent identification device for rubber tree diseases and insect pests according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a first constructing unit 15, a fifth obtaining unit 16, electronics 50, a processor 51, a memory 52, an input device 53, an output device 54.
Detailed Description
The embodiment of the application provides an intelligent identification method and device for rubber tree diseases and insect pests, and solves the technical problems that in the process of rubber tree disease and insect pest control in the prior art, the intelligent disease and insect pest identification of a rubber tree is lacked, the control is not timely/inaccurate, the control effect is poor, and the ecological benefit is low, so that the intelligent and accurate identification of the rubber tree diseases and insect pests based on images is achieved, the timely and accurate disease and insect pest control is performed, and the technical effects of improving the control effect and the ecological benefit are achieved. Embodiments of the present application are described below with reference to the accompanying drawings. As can be known to those skilled in the art, with the development of technology and the emergence of new scenarios, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems.
The terms "first," "second," and the like in the description and in the claims of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely descriptive of the various embodiments of the application and how objects of the same nature can be distinguished. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Summary of the application
Natural rubber is a traditional prop industry with competitive advantages in agricultural production, and rubber tree pest is a prominent problem in rubber production. Therefore, the research and control of rubber tree diseases and insect pests have been paid attention by rubber planting countries, and great progress is made in the research, development and popularization of the control of some main diseases of rubber trees. However, the past production prevention and control do not comprehensively treat the rubber plant diseases and insect pests on the whole, most of the plant diseases and insect pests do not have prediction methods and prevention and control indexes, and the prevention and control are blindness, so that the situations of more medicine, high cost, poor prevention effect, low benefit, serious environmental pollution, low economic, social and ecological benefits and the like often occur.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an intelligent identification method for rubber tree diseases and insect pests, wherein the method is applied to an intelligent identification system for the diseases and the pests, the system is in communication connection with a first image acquisition device, and the method comprises the following steps: obtaining basic information of a first rubber tree; obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information; acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides an intelligent identification method for rubber tree diseases and insect pests, wherein the method is applied to an intelligent identification system for diseases and insect pests, the system is in communication connection with a first image acquisition device, and the method includes:
step S100: obtaining basic information of a first rubber tree;
step S200: obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information;
particularly, disease and pest intelligent recognition system is for carrying out rubber tree disease and pest intelligent recognition's system, disease and pest intelligent recognition system is the intelligent system who has information interaction including the model that carries out the disease and pest characteristic ratio, the continuous study of information processing ability, first image acquisition device is the device that can carry out image acquisition, according to the environment of gathering, the growth cycle of the rubber tree of collection, the difference of gathering the position, first image acquisition device can carry out image acquisition's equipment for unmanned aerial vehicle carries, just first image acquisition device with disease and pest intelligent recognition system communication connection, first image acquisition device can with disease and pest intelligent recognition system carries out real-time information interaction. And acquiring basic information of the first rubber tree through the pest and disease identification system, wherein the basic information comprises but is not limited to variety information, growth cycle information, variety quality information and the like of the first rubber tree. The method comprises the steps that growth environment information of a first rubber tree is obtained through the intelligent pest and disease identification system, the growth environment information comprises growth soil property information, nutrition history supply information and the like of the first rubber tree, the expected growth characteristics of the first rubber tree are obtained through evaluation of the expected growth characteristics of the first rubber tree through the basic information and the growth environment information, and for example, the expected growth characteristics can be size characteristics and rubber leaf characteristics of the rubber tree and can be latex yield characteristics of the rubber tree. The basic information of the first rubber tree and the growth environment information are obtained, a foundation is laid for accurate subsequent evaluation of the expected growth characteristics of the first rubber tree, and data support is provided for accurate subsequent pest and disease feature identification based on the evaluated expected growth characteristics.
Step S300: acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result;
step S400: performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter;
specifically, the first rubber tree is subjected to image acquisition by the first image acquisition device, the positions of the image acquisition may be randomly distributed, or the first rubber tree is subjected to image acquisition according to the whole and then analyzed, and then image acquisition with a position with a side weight is performed on the first rubber tree according to the analysis result. And evaluating the actual growth characteristics of the first rubber tree based on the first image acquisition result, namely obtaining the actually presented growth characteristics of the first rubber tree according to the first image acquisition result. And comparing the characteristics through the actual growth characteristics and the expected growth characteristics, such as comparison of leaf states, color comparison, emulsion yield comparison and the like, and obtaining the first influence parameter according to the deviation value of the actual growth characteristics and the expected growth characteristics. And determining the first influence parameter by comparing the actual growth characteristic with the expected growth characteristic, and carrying out data support of growth matching dimensionality for judging whether the rubber tree is abnormal or not in the follow-up process, thereby tamping a foundation for carrying out accurate pest and disease damage evaluation.
Step S500: establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result;
step S600: and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
Specifically, the pest characteristic comparison model is a model for performing characteristic analysis comparison of images in machine learning, and the model performs image characteristic comparison of the first rubber tree by taking a first influence parameter as a parameter for weight analysis, taking an input first image acquisition result as detection data and taking a historical training data set as a basic parameter for comparison. The pest characteristic comparison model is obtained through training of multiple groups of training data, the training data of the model includes, but is not limited to, a first influence parameter, an image acquisition result and identification information for identifying the pest characteristic comparison result, the pest characteristic comparison model is supervised and learned through the identification information for identifying the pest characteristic comparison result, the pest characteristic comparison model after being supervised and learned is tested through test data, when the test result meets a preset detection standard, the training of the model is finished, the first influence parameter and the first image acquisition result are input into the pest characteristic comparison model, and a first output result is obtained. And identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result. According to the first output result, the matching degree of the first rubber tree and the characteristic matching of each pest and disease damage is determined, when the matching degree is higher than an expected threshold value, the first rubber tree is prevented and controlled according to the matched pest and disease damage, the pest and disease damage is accurately identified, timely and accurate pest and disease damage prevention and control is carried out, and the technical effects of improving the prevention and control effect and improving the ecological benefit are achieved.
Further, as shown in fig. 2, step S200 in the embodiment of the present application further includes:
step S210: obtaining variety information of the first rubber tree;
step S220: obtaining first growth cycle information of the first rubber tree according to the variety information;
step S230: taking the variety information and the first growth cycle information as the basic information;
step S240: and constructing a growth prediction model according to the basic information and the growth environment information, wherein the growth prediction model is a model constructed by using a large amount of rubber tree growth information as basic data and matching the basic information with the growth environment information through the basic data, and the expected growth characteristics of the first rubber tree are obtained according to the growth prediction model.
Specifically, the variety information of the first rubber tree refers to the planting material which is screened out through a series of rubber tree seed selection programs and reaches the test seed level or above. Generally, varieties include sexes and clones, and clones further include: the tree crown clone, the stem clone, the old clone and the like have different growth characteristics such as growth period, cold resistance, heat resistance, high latex yield and the like according to different varieties of rubber trees. Acquiring a growth cycle of the first rubber tree according to variety information of the first rubber tree, wherein the growth cycle is estimated growth cycle information of the first rubber tree obtained by performing comprehensive analysis processing according to historical planting information of the same variety of the first rubber tree, the variety information and the growth cycle information are used as basic information, and a growth prediction model of the first rubber tree is constructed by using basic information of the first rubber tree and the growth environment information, wherein the growth prediction model is a model for predicting growth characteristics of the first rubber tree, which is constructed by using a large amount of growth information of the same variety of the first rubber tree as basic data, and the growth characteristics of the first rubber tree are predicted based on the growth prediction model, such as size of a sapling stage, leaf characteristics of the first rubber tree, and leaf characteristics of a mature stage, Latex yield characteristics, etc. Through the construction of the growth prediction model, the obtained expected growth characteristics of the first rubber tree are more accurate, and a data basis is provided for the subsequent accurate identification of plant diseases and insect pests.
Further, as shown in fig. 3, the acquiring an image of the first rubber tree by the first image acquiring device to obtain a first image acquiring result, in step S300 of this embodiment of the present application, further includes:
step S310: obtaining a first initial detection sampling position distribution rule;
step S320: performing initial inspection image acquisition position distribution of the first rubber tree according to the first initial inspection sampling position distribution rule to obtain a first position distribution result;
step S330: acquiring images through the first image acquisition device based on the first position distribution result to obtain a first image acquisition set;
step S340: and marking the acquisition position of the first image acquisition set to obtain the first image acquisition result.
Specifically, the first preliminary sampling position distribution rule is a distribution rule of image sampling positions of the first rubber tree, generally speaking, the first rubber tree is regarded as an organic whole, and the position distribution of image acquisition is performed on the first rubber tree according to a principle of random distribution sampling, so as to obtain the first position distribution result. According to the obtained first position distribution result, carrying out image acquisition based on the first image acquisition device to obtain a first image acquisition set, carrying out position identification on the first image acquisition set by using the image acquisition position points of all images in the first image acquisition set, and obtaining the first image acquisition result according to the first image acquisition set subjected to the position identification. Through the distribution and the position identification of the acquisition position, position and data support are provided for subsequent accurate assessment of the plant diseases and insect pests of the first rubber tree, and a foundation is laid for accurately identifying the plant diseases and insect pests and performing timely and accurate plant disease prevention and control.
Further, as shown in fig. 4, in the step S310 of obtaining the first preliminary sampling location distribution rule, the method further includes:
step S311: carrying out integral image acquisition on the first rubber tree to obtain a first sampling determination image;
step S312: performing image characteristic analysis on the first sampling determination image to obtain a first image characteristic analysis result;
step S313: judging whether a first side reacquisition area exists in the first image feature analysis result;
step S314: and when the first image feature analysis result has a first side reacquisition area, setting the first initial examination sampling position distribution rule based on the first side reacquisition area.
Specifically, before setting the first preliminary examination sample position distribution rule, the first image acquisition device acquires an entire image of the first rubber tree to obtain a first sample determination image, performs image feature analysis on the first image based on the first sample determination image to determine whether or not there is an abnormal region in the first rubber tree, determines a side weight acquisition region based on a result of the image feature analysis when there is an abnormality in the image feature analysis, performs side weight setting of the first preliminary examination sample position distribution rule based on the side weight acquisition region, and for example, when there is a first side weight region in the result of the image feature analysis, the preliminary plan is to perform 10-position point random distribution sampling on the first rubber tree, and then performs the side weight region, and dividing the first side weight area into 10 randomly distributed sampling points according to the size ratio of the side weight area, increasing sampling points according to the difference of the inner side weight of the area, and determining the sampling positions according to the side weight. The setting of the first preliminary sampling position distribution rule is finally determined according to the rule described by way of example. Through right the refinement of first preliminary examination sampling position distribution rule makes the image that first image acquisition device gathered can feed back more the characteristic of first rubber tree, and then provides better data support for follow-up accurate plant diseases and insect pests analysis that carries on.
Further, as shown in fig. 5, step S400 in the embodiment of the present application further includes:
step S410: obtaining latex yield information of the first rubber tree;
step S420: generating a latex yield change curve of the first rubber tree according to the latex yield information;
step S430: carrying out matching degree evaluation on the latex yield change curve and the growth environment information to obtain a first matching degree evaluation result;
step S440: and generating a first adjusting parameter according to the first matching degree evaluation result, and obtaining the first influence parameter based on the first adjusting parameter.
Specifically, latex yield information of the first rubber tree is obtained according to the basic information, wherein the latex yield information is historical latex yield information obtained according to the historical information of the first rubber tree, time-based statistics and analysis are carried out on the historical latex yield information, a variation curve of the latex yield of the first rubber tree along with time, namely the latex yield variation curve, is constructed according to the results of the statistics and analysis, growth environment information of the first rubber tree, namely season information, soil information, weather information, temperature information, humidity information, nutrition information and the like, is obtained, matching degree evaluation is carried out according to the growth environment information and the variation curve of the latex yield, namely whether the growth environment of the first rubber tree is matched with real-time latex yield variation of the first rubber tree or not is judged, and obtaining a first adjusting parameter according to the result of the matching degree evaluation, and adjusting the influence parameter of the growth characteristic evaluation based on the first adjusting parameter to obtain the final first influence parameter. Through further analysis of the matching degree of the latex output and the environment, the first influence parameter is more accurately determined, and a foundation is laid for accurate subsequent pest and disease identification.
Further, as shown in fig. 6, in the step S500 of constructing the pest characteristic comparison model of the rubber tree, the method further includes:
step S510: acquiring a rubber tree pest image set;
step S520: constructing a pest and disease feature set marked with position features based on the pest and disease image set to obtain a first construction result;
step S530: constructing a training data set based on the first construction result, the first influence parameter and identification information for identifying the pest and disease identification result;
step S540: and constructing the pest and disease damage characteristic comparison model based on the training data set.
Specifically, the rubber tree pest image set is an image set acquired by subjecting the same kind of rubber trees to pest at different time and different degrees after suffering from the pest. The disease and pest image set of the rubber tree is obtained through big data, and further the disease and pest image set of the rubber tree is a disease and pest image set with position marks and time marks, for example, six-spotted spider mites mainly generate diseases and pests in the period from 4 late ten days to 5 months and from 10 late ten days to 11 months, mainly damage old leaves of the rubber tree, particularly serious damage to leaves in an aging period, and also damage tender leaves, and the positions are generally at the back of the leaves along two sides of a main vein and then are expanded into harmful. The pest is characterized by a yellowish white spot. And constructing a pest and disease damage characteristic set based on the time and position identification to obtain a first construction result. And taking the first construction result as a comparison characteristic, constructing a training data set according to the comparison characteristic, identification information for identifying the pest and disease identification result and the first influence parameter, and constructing the pest and disease characteristic comparison model based on the training data set. When the pest and disease feature comparison model is constructed, the first influence parameters and the first image acquisition result are input into the pest and disease feature comparison model, the pest and disease feature comparison model conducts traversal of pest and disease features through the rubber tree pest and disease image set, and the recognition result of the pest and disease is output based on the traversed matching degree, so that the pest and disease can be recognized accurately, timely and accurate pest and disease prevention and control can be conducted, and the technical effects of improving the prevention and control effect and ecological benefits can be achieved.
Further, as shown in fig. 7, step S700 in the embodiment of the present application further includes:
step S710: obtaining a first identification result according to the first output result;
step S720: inputting the first identification result into a prevention and control means list to obtain a first pest prevention and control means;
step S730: performing pest control on the first rubber tree based on the first pest control means, and performing control stage image acquisition on the first rubber tree through the image acquisition device to obtain a second image acquisition set;
step S740: and obtaining a first feedback parameter based on the second image acquisition set, and correcting the pest and disease damage characteristic comparison model through the first feedback parameter.
Specifically, according to the first output result, obtaining a pest and disease identification result of the first rubber tree, inputting a prevention and control means list based on the pest and disease identification result, wherein the prevention and control means list is an expert treatment list constructed according to the types, positions, degrees and time of different pests and diseases, performing prevention and control means matching of the first identification result based on the prevention and control means list to obtain a first pest and disease control means, performing pest and disease control on the first rubber tree based on the first pest and disease control means, performing prevention and control stage image acquisition on the first rubber tree through the image acquisition device in the prevention and control process to obtain a second image acquisition set, namely comparing the expected recovery stage and the actual recovery stage of the first rubber tree, and obtaining a first feedback parameter according to the comparison result, the first feedback parameter is a parameter of the effective degree of prevention and control of the first rubber tree according to the first pest prevention and control means, when the pest identification result is not matched with the actual pest of the first rubber tree, the first feedback parameter is greatly abnormal, real-time feedback correction is carried out on the pest characteristic comparison model based on the first feedback parameter, and therefore the technical effect that the pest judgment is more accurate through continuous learning of the pest characteristic comparison model is guaranteed.
To sum up, the intelligent identification method and device for the plant diseases and insect pests of the rubber trees provided by the embodiment of the application have the following technical effects:
1. the basic information of the first rubber tree is obtained; obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information; acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; according to first output result carries out the pest and disease damage discernment prevention and cure of first rubber tree is discerned through image acquisition and influence parameter to the pest and disease damage characteristic of rubber tree, considers the growth environment of rubber tree and the characteristic of pest and disease damage and compares comprehensively, and then reaches the accuracy and discerns the pest and disease damage, carries out timely accurate pest and disease damage prevention and cure, reaches the technological effect that improves prevention and cure effect, improvement ecological benefit.
2. Due to the adoption of the construction mode of the growth prediction model, the obtained expected growth characteristics of the first rubber tree are more accurate, and a data basis is provided for the subsequent accurate identification of plant diseases and insect pests.
3. Due to the adoption of the mode of distribution and position identification of the acquisition positions, position and data support is provided for the subsequent accurate assessment of the plant diseases and insect pests of the first rubber tree, and a foundation is laid for accurately identifying the plant diseases and insect pests and timely and accurately preventing and treating the plant diseases and insect pests.
Example two
Based on the same inventive concept as the intelligent identification method for rubber tree diseases and insect pests in the previous embodiment, the invention also provides an intelligent identification device for rubber tree diseases and insect pests, as shown in fig. 8, the device comprises:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain basic information of a first rubber tree;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain growth environment information of the first rubber tree, and obtain expected growth characteristics of the first rubber tree according to the basic information and the growth environment information;
a third obtaining unit 13, where the third obtaining unit 13 is configured to perform image acquisition on the first rubber tree through a first image acquisition device to obtain a first image acquisition result;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to perform image analysis according to the first image acquisition result to obtain an actual growth characteristic of the first rubber tree, and compare the actual growth characteristic with the expected growth characteristic to obtain a first influence parameter;
the first construction unit 15 is used for constructing a pest characteristic comparison model of the rubber tree, inputting the first influence parameter and the first image acquisition result into the pest characteristic comparison model, and obtaining a first output result;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to perform pest identification and control on the first rubber tree according to the first output result.
Further, the apparatus further comprises:
a sixth obtaining unit, configured to obtain variety information of the first rubber tree;
a seventh obtaining unit, configured to obtain first growth cycle information of the first rubber tree according to the variety information;
an eighth obtaining unit configured to take the item information and the first growth cycle information as the basic information;
a ninth obtaining unit, configured to construct a growth prediction model according to the basic information and the growth environment information, where the growth prediction model is a model constructed by using a large amount of rubber tree growth information as basic data and matching the basic information and the growth environment information with the basic data, and obtain expected growth characteristics of the first rubber tree according to the growth prediction model.
Further, the apparatus further comprises:
a tenth obtaining unit, configured to obtain a first preliminary sample position distribution rule;
an eleventh obtaining unit, configured to perform initial inspection image acquisition position distribution on the first rubber tree according to the first initial inspection sampling position distribution rule, to obtain a first position distribution result;
a twelfth obtaining unit, configured to perform image acquisition by the first image acquisition device based on the first position distribution result, to obtain a first image acquisition set;
a thirteenth obtaining unit, configured to perform acquisition position labeling on the first image acquisition set, and obtain the first image acquisition result.
Further, the apparatus further comprises:
a fourteenth obtaining unit, configured to perform overall image acquisition on the first rubber tree to obtain a first sampling determination image;
a fifteenth obtaining unit, configured to perform image feature analysis on the first sample determination image to obtain a first image feature analysis result;
the first judging unit is used for judging whether the first image feature analysis result has a first side reacquisition area or not;
and the first setting unit is used for setting the distribution rule of the first primary detection sampling position based on a first side reacquisition area when the first image feature analysis result has the first side reacquisition area.
Further, the apparatus further comprises:
a sixteenth obtaining unit, configured to obtain latex yield information of the first rubber tree;
a seventeenth obtaining unit configured to generate a latex yield variation curve of the first rubber tree according to the latex yield information;
an eighteenth obtaining unit, configured to perform matching degree evaluation on the latex yield variation curve and the growth environment information to obtain a first matching degree evaluation result;
a nineteenth obtaining unit, configured to generate a first adjustment parameter according to the first matching degree evaluation result, and obtain the first influence parameter based on the first adjustment parameter.
Further, the apparatus further comprises:
a twentieth obtaining unit, configured to obtain a rubber tree pest image set;
a twenty-first obtaining unit, configured to construct, based on the pest image set, a pest feature set identified with a location feature, and obtain a first construction result;
the second construction unit is used for constructing a training data set based on the first construction result, the first influence parameter and identification information for identifying the pest and disease identification result;
and the third construction unit is used for constructing the pest and disease damage characteristic comparison model based on the training data set.
Further, the apparatus further comprises:
a twenty-second obtaining unit, configured to obtain a first recognition result according to the first output result;
a twenty-third obtaining unit, configured to input the first identification result into a control means list, and obtain a first pest control means;
a twenty-fourth obtaining unit, configured to perform pest control on the first rubber tree based on the first pest control means, perform control-stage image acquisition on the first rubber tree by using the image acquisition device, and obtain a second image acquisition set;
and the twenty-fifth obtaining unit is used for obtaining a first feedback parameter based on the second image acquisition set and correcting the pest and disease damage characteristic comparison model through the first feedback parameter.
Various changes and specific examples of the intelligent identification method for rubber tree diseases and insect pests in the first embodiment of fig. 1 are also applicable to the intelligent identification device for rubber tree diseases and insect pests of the present embodiment, and through the detailed description of the intelligent identification method for rubber tree diseases and insect pests, those skilled in the art can clearly know the implementation method of the intelligent identification device for rubber tree diseases and insect pests in the present embodiment, so for the brevity of the description, detailed description is not repeated here.
Exemplary electronic device
The electronic apparatus of the embodiment of the present application is described below with reference to fig. 9.
Fig. 9 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the intelligent identification method for rubber tree diseases and insect pests in the foregoing embodiments, the present invention further provides an intelligent identification device for rubber tree diseases and insect pests, and hereinafter, an electronic device according to an embodiment of the present application is described with reference to fig. 9. The electronic device may be a removable device itself or a stand-alone device independent thereof, on which a computer program is stored which, when being executed by a processor, carries out the steps of any of the methods as described hereinbefore.
As shown in fig. 9, the electronic device 50 includes one or more processors 51 and a memory 52.
The processor 51 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 50 to perform desired functions.
The memory 52 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 51 to implement the methods of the various embodiments of the application described above and/or other desired functions.
In one example, the electronic device 50 may further include: an input device 53 and an output device 54, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The embodiment of the invention provides an intelligent identification method for rubber tree diseases and insect pests, wherein the method is applied to an intelligent identification system for the diseases and the pests, the system is in communication connection with a first image acquisition device, and the method comprises the following steps: obtaining basic information of a first rubber tree; obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information; acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result; performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter; establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result; and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result. The problem of among the prior art in carrying out rubber tree pest control process, the existence lacks the intelligent plant diseases and insect pests discernment that carries on the rubber tree, leads to and then to lead to the prevention and cure untimely/inaccurate, the prevention and cure effect is poor, ecological benefits is low technical problem is solved, reach and carry out the intelligence of rubber tree pest and insect pests, accurate discernment based on the image, and then carry out timely accurate pest control, reach the technological effect that improves prevention and cure effect, improves ecological benefits.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present application can be implemented by software plus necessary general-purpose hardware, and certainly can also be implemented by special-purpose hardware including special-purpose integrated circuits, special-purpose CPUs, special-purpose memories, special-purpose components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present application, the implementation of a software program is more preferable. Based on such understanding, the technical solutions of the present application may be substantially embodied in the form of a software product, which is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk of a computer, and includes several instructions for causing a computer device to execute the method according to the embodiments of the present application.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on or transmitted from a computer-readable storage medium to another computer-readable storage medium, which may be magnetic (e.g., floppy disks, hard disks, tapes), optical (e.g., DVDs), or semiconductor (e.g., Solid State Disks (SSDs)), among others.
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Additionally, the terms "system" and "network" are often used interchangeably herein. The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that in the embodiment of the present application, "B corresponding to a" means that B is associated with a, from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may be determined from a and/or other information.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In short, the above description is only a preferred embodiment of the present disclosure, and is not intended to limit the scope of the present disclosure. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (9)
1. An intelligent identification method for rubber tree diseases and insect pests is applied to an intelligent identification system for the diseases and the pests, wherein the system is in communication connection with a first image acquisition device, and the method comprises the following steps:
obtaining basic information of a first rubber tree;
obtaining growth environment information of the first rubber tree, and obtaining expected growth characteristics of the first rubber tree according to the basic information and the growth environment information;
acquiring an image of the first rubber tree through the first image acquisition device to obtain a first image acquisition result;
performing image analysis according to the first image acquisition result to obtain actual growth characteristics of the first rubber tree, and comparing the actual growth characteristics with the expected growth characteristics to obtain a first influence parameter;
establishing a pest and disease feature comparison model of the rubber tree, and inputting the first influence parameter and the first image acquisition result into the pest and disease feature comparison model to obtain a first output result;
and identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
2. The method of claim 1, wherein the method further comprises:
obtaining variety information of the first rubber tree;
obtaining first growth cycle information of the first rubber tree according to the variety information;
taking the variety information and the first growth cycle information as the basic information;
and constructing a growth prediction model according to the basic information and the growth environment information, wherein the growth prediction model is a model constructed by using a large amount of rubber tree growth information as basic data and matching the basic information with the growth environment information through the basic data, and the expected growth characteristics of the first rubber tree are obtained according to the growth prediction model.
3. The method of claim 1, wherein said image capturing the first rubber tree by the first image capturing device to obtain a first image capturing result further comprises:
obtaining a first initial detection sampling position distribution rule;
performing initial inspection image acquisition position distribution of the first rubber tree according to the first initial inspection sampling position distribution rule to obtain a first position distribution result;
acquiring images through the first image acquisition device based on the first position distribution result to obtain a first image acquisition set;
and marking the acquisition position of the first image acquisition set to obtain the first image acquisition result.
4. The method of claim 3, wherein the obtaining the first preliminary sample location distribution rule further comprises:
carrying out integral image acquisition on the first rubber tree to obtain a first sampling determination image;
performing image characteristic analysis on the first sampling determination image to obtain a first image characteristic analysis result;
judging whether a first side reacquisition area exists in the first image feature analysis result;
and when the first image feature analysis result has a first side reacquisition area, setting the first initial examination sampling position distribution rule based on the first side reacquisition area.
5. The method of claim 1, wherein the method further comprises:
obtaining latex yield information of the first rubber tree;
generating a latex yield change curve of the first rubber tree according to the latex yield information;
carrying out matching degree evaluation on the latex yield change curve and the growth environment information to obtain a first matching degree evaluation result;
and generating a first adjusting parameter according to the first matching degree evaluation result, and obtaining the first influence parameter based on the first adjusting parameter.
6. The method of claim 3, wherein the constructing of the pest characteristic alignment model of the rubber tree further comprises:
acquiring a rubber tree pest image set;
constructing a pest and disease feature set marked with position features based on the pest and disease image set to obtain a first construction result;
constructing a training data set based on the first construction result, the first influence parameter and identification information for identifying the pest and disease identification result;
and constructing the pest and disease damage characteristic comparison model based on the training data set.
7. The method of claim 1, wherein the method further comprises:
obtaining a first identification result according to the first output result;
inputting the first identification result into a prevention and control means list to obtain a first pest prevention and control means;
performing pest control on the first rubber tree based on the first pest control means, and performing control stage image acquisition on the first rubber tree through the image acquisition device to obtain a second image acquisition set;
and obtaining a first feedback parameter based on the second image acquisition set, and correcting the pest and disease damage characteristic comparison model through the first feedback parameter.
8. The utility model provides an intelligent recognition device of rubber tree plant diseases and insect pests, wherein, the device includes:
a first obtaining unit, configured to obtain basic information of a first rubber tree;
a second obtaining unit, configured to obtain growth environment information of the first rubber tree, and obtain an expected growth characteristic of the first rubber tree according to the basic information and the growth environment information;
the third obtaining unit is used for carrying out image acquisition on the first rubber tree through a first image acquisition device to obtain a first image acquisition result;
a fourth obtaining unit, configured to perform image analysis according to the first image acquisition result to obtain an actual growth characteristic of the first rubber tree, and compare the actual growth characteristic with the expected growth characteristic to obtain a first influence parameter;
the first construction unit is used for constructing a pest and disease characteristic comparison model of the rubber tree, inputting the first influence parameter and the first image acquisition result into the pest and disease characteristic comparison model and obtaining a first output result;
and the fifth obtaining unit is used for identifying and preventing the plant diseases and insect pests of the first rubber tree according to the first output result.
9. An intelligent identification device for rubber tree pests, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111235483.XA CN113989532A (en) | 2021-10-22 | 2021-10-22 | Intelligent identification method and device for rubber tree diseases and insect pests |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111235483.XA CN113989532A (en) | 2021-10-22 | 2021-10-22 | Intelligent identification method and device for rubber tree diseases and insect pests |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113989532A true CN113989532A (en) | 2022-01-28 |
Family
ID=79740580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111235483.XA Pending CN113989532A (en) | 2021-10-22 | 2021-10-22 | Intelligent identification method and device for rubber tree diseases and insect pests |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113989532A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082475A (en) * | 2022-08-22 | 2022-09-20 | 张家港大裕橡胶制品有限公司 | Pollution detection method and system in rubber glove production process |
| CN117746306A (en) * | 2023-12-12 | 2024-03-22 | 日照朝力信息科技有限公司 | Forest pest identification method and system based on image processing |
-
2021
- 2021-10-22 CN CN202111235483.XA patent/CN113989532A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082475A (en) * | 2022-08-22 | 2022-09-20 | 张家港大裕橡胶制品有限公司 | Pollution detection method and system in rubber glove production process |
| CN117746306A (en) * | 2023-12-12 | 2024-03-22 | 日照朝力信息科技有限公司 | Forest pest identification method and system based on image processing |
| CN117746306B (en) * | 2023-12-12 | 2024-06-04 | 日照朝力信息科技有限公司 | Forest pest identification method and system based on image processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sabzi et al. | A fast and accurate expert system for weed identification in potato crops using metaheuristic algorithms | |
| Ramesh et al. | Application of machine learning in detection of blast disease in South Indian rice crops | |
| CN113989532A (en) | Intelligent identification method and device for rubber tree diseases and insect pests | |
| Liu et al. | Towards automated yield estimation in viticulture | |
| CN111582554A (en) | Crop growth prediction method and system | |
| CN108090628A (en) | A kind of grain feelings security detection and analysis method based on PSO-LSSVM algorithms | |
| Sharma et al. | Image processing based automated identification of late blight disease from leaf images of potato crops | |
| CN113778110B (en) | Intelligent agricultural machine control method and system based on machine learning | |
| CN105891420A (en) | Method for intelligently analyzing plant growth states by means of big data | |
| CN116046687A (en) | Crop growth process monitoring method, device and medium | |
| CN117652267A (en) | Monitoring management method and system for landscaping maintenance | |
| CN109034450B (en) | Method for establishing potato late blight forecasting model in north China based on meteorological conditions | |
| CN105869061A (en) | Method for analyzing plant growth state through computer | |
| Gómez-Zamanillo et al. | Damage assessment of soybean and redroot amaranth plants in greenhouse through biomass estimation and deep learning-based symptom classification | |
| Akbar et al. | Wheat disease detection for yield management using IoT and deep learning techniques | |
| CN117152609A (en) | Crop appearance characteristic detecting system | |
| CN115039549B (en) | Crop planting and fertilizing information processing method and system | |
| CN110544237A (en) | Oil tea pest model training method and recognition method based on image analysis | |
| Duru et al. | Standing herbage mass: An integrated indicator of management practices for examining how fertility and defoliation regime shape the functional structure of species-rich grasslands | |
| CN113762773B (en) | Associated positioning decomposition method and system for disaster monitoring and forecasting | |
| Wang et al. | Automatically diagnosing leaf scorching and disease symptoms in trees/shrubs by using RGB image computation with a common statistical algorithm | |
| Anil et al. | Disease Detection and Diagnosis on the Leaves using Image Processing | |
| Rahman et al. | Influence of Membership Function and Degree on Sorghum Growth Prediction Models in Machine Learning. | |
| CN116542403B (en) | Crop yield prediction method, device, electronic equipment and readable storage medium | |
| Nath et al. | Design of intelligent system in agriculture using data mining |
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 |