Big data-based white moth identification processing method and system, and medium
By acquiring and analyzing the image feature data of white moths, calculating the high-incidity prediction index and loop-inducing contrast index, the problem of insufficient prediction of white moths in the existing technology is solved, and more accurate white moth identification and early warning is achieved, supporting scientific Governance strategy.
Patent Information
- Application Number
- CN202411136815.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-19
AI Technical Summary
The existing white moth recognition technology lacks the technology to use historical data for high-incidence prediction and environmental analysis, which leads to ineffective white moth management.
By obtaining the image feature data of the white moth in the current time period of the area to be identified and multiple same historical time periods, combining the image feature data of the preset sub-region, the high incidence prediction index of the white moth and the ring-inducing contrast index are calculated, and the white moth is performed High-incidence area warning.
It improves the accuracy and reliability of white moth identification and prediction, can target the identification of high-incidence areas, and supports scientific white moth management plans.
Smart Images

Figure CN119091162A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image recognition and big data technology, and in particular to a method, system and medium for white moth identification and processing based on big data. Background Art
[0002] In recent years, with global warming, the white moth epidemic has continued to expand southward. The white moth is a pest with strong reproductive capacity and rapid spread. Its life cycle includes four stages: egg, larva, pupa and adult. The larval stage is long and the appetite is amazing. Especially the larvae after the fifth instar can eat a large number of leaves in a short time, causing serious damage to crops and forests.
[0003] The current white moth identification technology is mainly based on the observation of the growth status of white moths and the monitoring of white moths in areas where white moths have been found. However, these valuable experiences have not been well utilized to carry out further white moth identification and control. There is insufficient research on the impact of white moth growth environment. There is a lack of technology that can predict the high incidence of white moths based on historical high incidence data of white moths and analyze and process the corresponding high incidence environment.
[0004] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention
[0005] The purpose of the present application is to provide a method, system and medium for identifying and processing white moths based on big data. The method can obtain the image feature data of white moths in the current time period of the area to be identified in multiple same historical time periods and the image feature data of multiple preset sub-areas, compare and obtain image feature comparison similarity data, obtain historical white moth outbreak rate data of multiple preset sub-areas, and process them in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index, compare them with a preset threshold, obtain a white moth suspected high incidence sub-area, obtain the current environmental change data of the white moth suspected high incidence sub-area, process them with the average data of multiple historical environmental change data, obtain a white moth ring change induced contrast index, further compare the threshold with the preset white moth ring change induced threshold, and mark the area as a white moth high incidence prediction area if it meets the threshold, issue a white moth high incidence warning for the sub-area, and provide strong support for the white moth control plan; thereby, the identification and prediction of the high incidence of white moths in the region can be achieved through image recognition and data processing.
[0006] The present application provides a method for identifying and processing white moths based on big data, comprising the following steps:
[0007] Obtaining a pest monitoring image set of the current time period of the area to be identified in multiple same historical time periods and extracting multiple pest image feature data, and then classifying them to obtain multiple types of pest image feature data sets;
[0008] Processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images;
[0009] Acquire image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and perform image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region;
[0010] Acquire the historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods, and process the data in combination with the corresponding image feature comparison similarity data to obtain the white moth high incidence prediction index corresponding to each sub-area;
[0011] Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a suspected white moth high incidence sub-area;
[0012] Obtain multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compare and process the current environmental change data with the average data of multiple historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth;
[0013] A threshold comparison is performed based on the white moth ring change induction contrast index and the preset white moth ring change induction threshold, and the suspected high-incidence sub-area of white moth that meets the threshold comparison requirements is marked as a white moth high-incidence prediction area, and a high-incidence warning of white moth in the sub-area is issued.
[0014] Among them, in the big data-based white moth identification and processing method described in the present application, it is characterized in that the acquisition of pest monitoring image sets in multiple historical time periods in the same time period as the current time period of the area to be identified and the extraction of multiple pest image feature data are performed, and then the classification is performed to obtain multiple types of pest image feature data sets, specifically:
[0015] Acquire a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified;
[0016] Extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images;
[0017] Classification processing is performed according to the pest image feature data corresponding to the multiple historical pest monitoring images to obtain multiple types of pest image feature data sets.
[0018] Among them, in a big data-based white moth identification and processing method described in the present application, it is characterized in that the image feature data of multiple preset sub-areas in the current time period of the area to be identified are obtained, and image feature similarity comparison is performed with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-area, specifically:
[0019] Acquire image feature data of a plurality of preset sub-areas in the current time period of the area to be identified, including contour size identification data, texture pattern data, color distribution data, and structure space relationship data;
[0020] The image feature data of the preset sub-region is compared with the image feature data of the white moth to obtain image feature comparison similarity data corresponding to each sub-region.
[0021] Among them, in the big data-based white moth identification and processing method described in the present application, it is characterized in that the historical white moth outbreak rate data of the multiple preset sub-areas in the multiple same historical time periods are obtained, and the white moth high incidence prediction index corresponding to each sub-area is obtained by combining the corresponding image feature comparison similarity data for processing, specifically:
[0022] Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods;
[0023] The historical white moth outbreak rate data is combined with the corresponding image feature comparison similarity data and processed through a preset high incidence prediction model to obtain a white moth high incidence prediction index corresponding to each sub-region.
[0024] Among them, in the big data-based white moth identification and processing method described in the present application, it is characterized in that the white moth high incidence prediction index corresponding to each sub-area is compared with a preset prediction index threshold to obtain a suspected high incidence sub-area of white moth, specifically:
[0025] Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a prediction index deviation rate;
[0026] Determining whether the prediction index deviation rate is greater than a preset prediction index deviation rate threshold;
[0027] If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-region is not a high-incidence sub-region of white moth;
[0028] If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-region is a suspected high-incidence sub-region of white moth.
[0029] Among them, in the big data-based white moth identification and processing method described in the present application, it is characterized in that a plurality of historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth are obtained, and the current environmental change data are compared with the average data of the plurality of historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth, specifically:
[0030] Obtain multiple historical environmental change data for the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data, and historical precipitation accumulation data;
[0031] Obtaining the current environmental change data of each suspected high-incidence sub-area of white moth in the current time period, including temperature and humidity fluctuation rate data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data;
[0032] By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained;
[0033] The calculation formula of the contrast index induced by the white moth ring change is:
[0034]
[0035] Among them, E φ is the contrast index induced by the white moth ring change, e bn is the current environmental change data, e hn is the average data of multiple historical environmental change data, κ1, κ z , μ1, μ2 are preset characteristic coefficients.
[0036] Among them, in the big data-based white moth identification and processing method described in the present application, it is characterized in that the threshold comparison is performed based on the white moth ring change induction contrast index and the preset white moth ring change induction threshold, and the suspected high-incidence sub-region of white moths that meets the threshold comparison requirements is marked as a white moth high-incidence prediction area, and a high-incidence warning of white moths in the sub-region is performed, specifically:
[0037] The contrast index deviation rate is obtained by comparing the white moth ring change induction contrast index with a preset white moth ring change induction threshold;
[0038] Determining whether the contrast index deviation rate is greater than a preset contrast index deviation rate threshold;
[0039] If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, then the suspected high incidence area of white moths does not have a high incidence of white moths;
[0040] If the contrast index deviation rate is less than a preset contrast index deviation rate threshold, the suspected area with high incidence of white moths is marked as a predicted area with high incidence of white moths and a sub-area high incidence warning of white moths is issued.
[0041] In a second aspect, the present application provides a white moth identification and processing system based on big data, the system comprising: a memory and a processor, the memory comprising a program of a white moth identification and processing method based on big data, the program of the white moth identification and processing method based on big data being executed by the processor to implement the following steps:
[0042] Obtaining a pest monitoring image set of the current time period of the area to be identified in multiple same historical time periods and extracting multiple pest image feature data, and then classifying them to obtain multiple types of pest image feature data sets;
[0043] Processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images;
[0044] Acquire image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and perform image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region;
[0045] Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods, and process the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index corresponding to each sub-area;
[0046] Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a suspected white moth high incidence sub-area;
[0047] Obtain multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compare and process the current environmental change data with the average data of multiple historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth;
[0048] A threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and sub-regions with suspected high incidence of white moths that meet the threshold comparison requirements are marked as white moth high incidence prediction areas, and a white moth high incidence warning is issued in the sub-regions.
[0049] Among them, in the big data-based white moth identification and processing system described in the present application, it is characterized in that the acquisition of pest monitoring image sets in multiple historical time periods in the same time period as the current time period of the area to be identified and the extraction of multiple pest image feature data are performed, and then the classification is performed to obtain multiple types of pest image feature data sets, specifically:
[0050] Acquire a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified;
[0051] Extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images;
[0052] Classification processing is performed according to the pest image feature data corresponding to the multiple historical pest monitoring images to obtain multiple types of pest image feature data sets.
[0053] In the third aspect, the present application also provides a readable storage medium, which includes a program for a white moth identification and processing method based on big data. When the program for a white moth identification and processing method based on big data is executed by a processor, the steps of a white moth identification and processing method based on big data as described in any one of the above items are implemented.
[0054] From the above, it can be seen that the present application provides a method, system and medium for identifying and processing white moths based on big data. By obtaining the image feature data of white moths in the current time period of the area to be identified in multiple same historical time periods and the image feature data of multiple preset sub-areas, image feature comparison similarity data is obtained by comparison, historical white moth outbreak rate data of multiple preset sub-areas are obtained, and the data are processed in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index, which is compared with a preset threshold to obtain a white moth suspected high incidence sub-area, current environmental change data of the white moth suspected high incidence sub-area is obtained, and the data is processed with the average data of multiple historical environmental change data to obtain a white moth ring change induced contrast index, which is further compared with the preset white moth ring change induced threshold. If the threshold is met, it is marked as a white moth high incidence. Prediction area, and make early warning of high incidence of white moth in sub-areas. This application not only takes into account the pest monitoring images of the current time period, but also combines multiple pest monitoring image sets of the same historical time period. By extracting and analyzing historical data, it can more comprehensively understand the laws and patterns of pest occurrence, thereby improving the accuracy and reliability of identification, and subdividing the area to be identified into multiple preset sub-areas. This regional subdivision strategy makes the early warning more accurate, and can specifically identify specific areas where white moth may be highly prevalent, which is conducive to the rational allocation of resources and effective response. It also considers the impact of historical environmental change data on the current prediction of high incidence of white moths, and calculates the white moth ring change induced contrast index, which further improves the scientificity and accuracy of the prediction, provides strong support for white moth control plans, and provides data support for the formulation of scientific white moth pest management strategies.
[0055] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0057] Figure 1 A flowchart of a method for identifying and processing white moths based on big data provided in an embodiment of the present application;
[0058] Figure 2 A flowchart of obtaining multiple types of insect pest image feature data sets for a method for identifying and processing white moths based on big data provided in an embodiment of the present application;
[0059] Figure 3 A flowchart of obtaining image feature comparison similarity data corresponding to each sub-region in a method for identifying and processing white moths based on big data provided in an embodiment of the present application;
[0060] Figure 4 A flowchart of obtaining a white moth high incidence prediction index corresponding to each sub-region in a white moth identification and processing method based on big data provided in an embodiment of the present application;
[0061] Figure 5 A flowchart of obtaining suspected high-incidence areas of white moths in a big data-based white moth identification and processing method provided in an embodiment of the present application. DETAILED DESCRIPTION
[0062] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.
[0063] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.
[0064] Please refer to Figure 1 , Figure 1 1 is a flowchart of a method for identifying and processing white moths based on big data in some embodiments of the present application. The method for identifying and processing white moths based on big data is used in terminal devices, such as computers, mobile phone terminals, etc. The method for identifying and processing white moths based on big data includes the following steps:
[0065] S101, obtaining a set of pest monitoring images of a current time period of a region to be identified in a plurality of same historical time periods and extracting a plurality of pest image feature data, and then classifying them to obtain a plurality of types of pest image feature data sets;
[0066] S102, processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images;
[0067] S103, acquiring image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and performing image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region;
[0068] S104, obtaining historical white moth outbreak rate data of the plurality of preset sub-regions in the plurality of same historical time periods, and processing the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index corresponding to each sub-region;
[0069] S105, comparing the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a sub-area suspected to have a high incidence of white moth;
[0070] S106, obtaining a plurality of historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and performing a comparison process based on the current environmental change data and the average data of the plurality of historical environmental change data, to obtain a white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth;
[0071] S107, performing a threshold comparison between the white moth ring change induction contrast index and a preset white moth ring change induction threshold, marking the suspected high-incidence sub-region of white moths that meets the threshold comparison requirements as a white moth high-incidence prediction region, and issuing a white moth high-incidence warning for the sub-region.
[0072] Among them, the present application obtains the image feature data of white moths in the current time period of the area to be identified in multiple same historical time periods and the image feature data of multiple preset sub-areas, compares and obtains the image feature comparison similarity data, obtains the historical white moth outbreak rate data of multiple preset sub-areas, and processes them in combination with the corresponding image feature comparison similarity data to obtain the white moth high incidence prediction index, compares it with the preset threshold, obtains the white moth suspected high incidence sub-area, obtains the current environmental change data of the white moth suspected high incidence sub-area, processes it with the average data of multiple historical environmental change data, obtains the white moth ring change induced contrast index, further compares the threshold with the preset white moth ring change induced threshold, and if it meets the threshold, it is marked as a white moth high incidence prediction area, and the sub-area white moth high incidence is compared. Early warning, this application not only considers the pest monitoring images of the current time period, but also combines multiple pest monitoring image sets of the same historical time period. By extracting and analyzing historical data, it can more comprehensively understand the laws and patterns of pest occurrence, thereby improving the accuracy and reliability of identification, and subdividing the area to be identified into multiple preset sub-areas. This regional subdivision strategy makes the early warning more accurate, and can specifically identify specific areas where white moths may occur frequently, which is helpful for the rational allocation of resources and effective response. It also considers the impact of historical environmental change data on the current prediction of high incidence of white moths, and calculates the white moth ring change induced contrast index, which further improves the scientificity and accuracy of the prediction, provides strong support for white moth control plans, and provides data support for the formulation of scientific white moth pest management strategies.
[0073] Please refer to Figure 2 , Figure 2 This is a flowchart of obtaining multiple types of pest image feature data sets in a method for identifying and processing white moths based on big data in some embodiments of the present application. According to an embodiment of the present invention, the acquisition of pest monitoring image sets in multiple historical time periods in the same time period as the current time period of the area to be identified and the extraction of multiple pest image feature data sets, and then classification to obtain multiple types of pest image feature data sets, specifically:
[0074] S201, obtaining a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified;
[0075] S202, extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images;
[0076] S203: performing classification processing according to the pest image feature data corresponding to the plurality of historical pest monitoring images to obtain a plurality of types of pest image feature data sets.
[0077] Among them, in order to extract the characteristic data of pests in the image, a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified is obtained. For example, a set of pest monitoring images covering multiple time periods (such as spring, summer, autumn, and winter) is obtained through a historical database, and fuzzy, repeated, and irrelevant images are checked and removed. Image feature information is extracted from the pest monitoring image set, such as the type, quantity, location, severity, etc. of pests. These feature information are organized into a structured data form to obtain pest image feature data corresponding to multiple historical pest monitoring images. The pest image feature data corresponding to the multiple historical pest monitoring images are classified and processed to obtain multiple types of pest image feature data sets.
[0078] Please refer to Figure 3 , Figure 3 This is a flowchart of obtaining image feature comparison similarity data corresponding to each sub-region of a method for white moth identification based on big data in some embodiments of the present application. According to an embodiment of the present invention, the image feature data of multiple preset sub-regions in the current time period of the area to be identified are obtained, and image feature similarity comparison is performed with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region, specifically:
[0079] S301, obtaining image feature data of a plurality of preset sub-regions in the current time period of the region to be identified, including contour size identification data, texture pattern data, color distribution data and structure space relationship data;
[0080] S302, performing image feature similarity comparison between the image feature data of the preset sub-region and the image feature data of the white moth, to obtain image feature comparison similarity data corresponding to each sub-region.
[0081] Among them, in order to determine whether there is a white moth in the area to be identified, the area to be identified is first divided into multiple preset sub-areas, and the image feature data of the multiple preset sub-areas in the current time period of the area to be identified are obtained, including contour size identification data, texture pattern data, color distribution data and structural spatial relationship data. The contour size identification data refers to the edge shape and size information of the object or area in the image. These data are usually obtained through edge detection algorithms and are used to describe the geometric properties of the object such as the outer contour shape, aspect ratio, area, etc. The texture pattern data describes the pixel arrangement mode of the local area in the image, which is usually related to the physical properties of the object such as the material and surface roughness. The color distribution data refers to the distribution of different colors or color combinations in the image, including the type, quantity, position and spatial relationship between the colors. The structural spatial relationship data describes the spatial position, direction, distance and other mutual relationships between objects or areas in the image. The image feature data of the preset sub-areas are compared with the white moth image feature data for image feature similarity, and the image feature comparison similarity data corresponding to each sub-area is obtained, so that it can be determined which preset sub-areas are similar to the white moth image and how similar they are.
[0082] The calculation formula of the image feature comparison similarity data is:
[0083]
[0084] Among them, M ds is the image feature comparison similarity data, l c 、w n 、c t , g k They are the outline size identification data, texture pattern data, color distribution data and structure space relationship data of the preset sub-area, respectively. cb 、w nb 、c tb , g kb are the contour size identification data, texture pattern data, color distribution data and structural space relationship data of the white moth image respectively; β, α1, α2, α3, α4, ξ1, ξ2, ξ3 and ξ4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth identification parameter database).
[0085] Please refer to Figure 4 , Figure 4 It is a flowchart of obtaining the high incidence prediction index of white moths corresponding to each sub-region in a method for identifying and processing white moths based on big data in some embodiments of the present application. According to an embodiment of the present invention, the historical white moth outbreak rate data of the plurality of preset sub-regions in the plurality of same historical time periods are obtained, and the white moth high incidence prediction index corresponding to each sub-region is obtained by combining the corresponding image feature comparison similarity data for processing, specifically:
[0086] S401, obtaining historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods;
[0087] S402, processing the historical white moth outbreak rate data in combination with the corresponding image feature comparison similarity data through a preset high incidence prediction model to obtain a white moth high incidence prediction index corresponding to each sub-region.
[0088] Among them, in order to further determine whether there are white moths in the area to be identified, the historical white moth outbreak rate data of multiple preset sub-areas in multiple same historical time periods are obtained, and the actual outbreak of white moths in each sub-area in these time periods is recorded. According to the historical white moth outbreak rate data combined with the corresponding image feature comparison similarity data, the preset high-incidence prediction model is used for processing to obtain the white moth high-incidence prediction index corresponding to each sub-area, which indicates the possibility and severity of the white moth outbreak in each sub-area in a certain time period in the future;
[0089] The calculation formula of the high incidence prediction model is:
[0090]
[0091] Among them, G f is the high incidence prediction index of white moth, H b is the historical outbreak rate data of white moth, M ds is the image feature comparison similarity data, ∈, η, θ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth identification parameter database).
[0092] Please refer to Figure 5 , Figure 5 The flowchart of obtaining sub-regions suspected of high incidence of white moths in a method for identifying and processing white moths based on big data in some embodiments of the present application is as follows. According to an embodiment of the present invention, the white moth high incidence prediction index corresponding to each sub-region is compared with a preset prediction index threshold to obtain the sub-region suspected of high incidence of white moths, specifically:
[0093] S501, comparing the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a prediction index deviation rate;
[0094] S502, determining whether the prediction index deviation rate is greater than a preset prediction index deviation rate threshold;
[0095] S503: If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-region is not a sub-region with high incidence of white moth;
[0096] S504: If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-region is a sub-region suspected of being a high-incidence sub-region of white moth.
[0097] Among them, in order to further determine whether there is a high incidence of white moths in the area to be identified, the white moth high incidence prediction index corresponding to each sub-area is compared with the preset prediction index threshold to obtain the prediction index deviation rate, and determine whether the prediction index deviation rate is greater than the preset prediction index deviation rate threshold. If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-area is not a sub-area with a high incidence of white moths. If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-area is a sub-area with a suspected high incidence of white moths.
[0098] According to an embodiment of the present invention, the acquisition of multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moths, and the comparison and processing between the current environmental change data and the average data of multiple historical environmental change data, to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moths, is specifically:
[0099] Obtain multiple historical environmental change data for the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data, and historical precipitation accumulation data;
[0100] Obtaining the current environmental change data of each suspected high-incidence sub-area of white moth in the current time period, including temperature and humidity fluctuation rate data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data;
[0101] By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained;
[0102] The calculation formula of the contrast index induced by the white moth ring change is:
[0103]
[0104] Among them, E φ is the contrast index induced by the white moth ring change, e bn is the current environmental change data, e hn is the average data of multiple historical environmental change data, and χ1, κ2, μ1, and μ2 are preset characteristic coefficients.
[0105] Among them, in order to evaluate the environmental characteristics and changes of historical white moth outbreaks in suspected high-incidence areas of white moths and compare them with the current environment, multiple historical environmental change data of the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area of white moths were obtained, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data and historical precipitation accumulation data; the current environmental change data of each suspected high-incidence sub-area of white moths in the current time period were obtained, including temperature and humidity fluctuation data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data; the temperature and humidity fluctuation data include day and night temperature difference, humidity fluctuation, etc., because these factors directly affect the survival and reproduction of white moths; the light intensity change data records the changes in light intensity every day or in a specific period of time, which is an important factor in the life cycle of white moths and affects their activities and reproduction; the vegetation gnawing rate data is recorded by regularly investigating the damage to vegetation (such as the proportion of leaves gnawing), which directly reflects the degree of harm to vegetation caused by white moths; the precipitation accumulation data counts the cumulative precipitation in a specific time period, which affects the survival rate of white moth larvae and the migration ability of adults. By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained.
[0106] According to an embodiment of the present invention, a threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and a suspected high-incidence sub-region of white moths that meets the threshold comparison requirements is marked as a white moth high-incidence prediction region, and a white moth high-incidence warning is performed in the sub-region, specifically:
[0107] The contrast index deviation rate is obtained by comparing the white moth ring change induction contrast index with a preset white moth ring change induction threshold;
[0108] Determining whether the contrast index deviation rate is greater than a preset contrast index deviation rate threshold;
[0109] If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, then the suspected high incidence area of white moths does not have a high incidence of white moths;
[0110] If the contrast index deviation rate is less than a preset contrast index deviation rate threshold, the suspected area with high incidence of white moths is marked as a predicted area with high incidence of white moths and a sub-area high incidence warning of white moths is issued.
[0111] Among them, in order to further determine the impact of environmental changes in areas suspected of high incidence of white moths on the growth and outbreak of white moths, the white moth ring change induced contrast index is compared with the preset white moth ring change induced threshold to obtain the contrast index deviation rate, and determine whether the contrast index deviation rate is greater than the preset contrast index deviation rate threshold. If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, there is no high incidence of white moths in the suspected high incidence area of white moths. If the contrast index deviation rate is less than the preset contrast index deviation rate threshold, the suspected high incidence area of white moths is marked as a high incidence prediction area of white moths and a sub-area high incidence warning of white moths is issued.
[0112] According to an embodiment of the present invention, it also includes:
[0113] Extracting white moth identification image feature data according to the white moth identification image;
[0114] Extracting the growth cycle data of the white moth according to the white moth identification image feature data, including egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data;
[0115] The egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data are processed by a preset white moth growth evaluation model to obtain a white moth growth rate index;
[0116] The calculation formula of the white moth growth evaluation model is:
[0117]
[0118] Among them, M r is the white moth growth rate index, l g ,y g 、b g 、h g are the egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data respectively, and η1, η2, μ1, μ2 and π are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth growth monitoring database).
[0119] Among them, in order to reflect the characteristics of each growth cycle of the white moth, the growth cycle data of the white moth is extracted according to the feature data of the white moth identification image, including growth data in the egg stage, such as the size, color, shape of the eggs, growth data in the larval stage, such as body length, color change, screen shape, etc., growth data in the pupal stage, such as the size, color, shape of the pupae, and growth data in the adult stage, such as wing color, number of spots, etc. The data is processed through the preset white moth growth evaluation model to obtain the white moth growth rate index, which is used to quantify the growth rate of the white moth, understand the growth rate of the white moth and the growth characteristics of different stages, predict the population outbreak time according to the growth rate, and formulate corresponding prevention and control strategies.
[0120] The present invention also discloses a white moth identification and processing system based on big data, comprising a memory and a processor, wherein the memory comprises a white moth identification and processing method program based on big data, and when the white moth identification and processing method program based on big data is executed by the processor, the following steps are implemented:
[0121] Obtaining a pest monitoring image set of the current time period of the area to be identified in multiple same historical time periods and extracting multiple pest image feature data, and then classifying them to obtain multiple types of pest image feature data sets;
[0122] Processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images;
[0123] Acquire image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and perform image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region;
[0124] Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods, and process the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index corresponding to each sub-area;
[0125] Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a suspected white moth high incidence sub-area;
[0126] Obtain multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compare and process the current environmental change data with the average data of multiple historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth;
[0127] A threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and sub-regions with suspected high incidence of white moths that meet the threshold comparison requirements are marked as white moth high incidence prediction areas, and a white moth high incidence warning is issued in the sub-regions.
[0128] Among them, the present application obtains the image feature data of white moths in the current time period of the area to be identified in multiple same historical time periods and the image feature data of multiple preset sub-areas, compares and obtains the image feature comparison similarity data, obtains the historical white moth outbreak rate data of multiple preset sub-areas, and processes them in combination with the corresponding image feature comparison similarity data to obtain the white moth high incidence prediction index, compares it with the preset threshold, obtains the white moth suspected high incidence sub-area, obtains the current environmental change data of the white moth suspected high incidence sub-area, processes it with the average data of multiple historical environmental change data, obtains the white moth ring change induced contrast index, further compares the threshold with the preset white moth ring change induced threshold, and if it meets the threshold, it is marked as a white moth high incidence prediction area, and the sub-area white moth high incidence is compared. Early warning, this application not only considers the pest monitoring images of the current time period, but also combines multiple pest monitoring image sets of the same historical time period. By extracting and analyzing historical data, it can more comprehensively understand the laws and patterns of pest occurrence, thereby improving the accuracy and reliability of identification, and subdividing the area to be identified into multiple preset sub-areas. This regional subdivision strategy makes the early warning more accurate, and can specifically identify specific areas where white moths may occur frequently, which is helpful for the rational allocation of resources and effective response. It also considers the impact of historical environmental change data on the current prediction of high incidence of white moths, and calculates the white moth ring change induced contrast index, which further improves the scientificity and accuracy of the prediction, provides strong support for white moth control plans, and provides data support for the formulation of scientific white moth pest management strategies.
[0129] According to an embodiment of the present invention, the acquisition of pest monitoring image sets in multiple historical time periods that are the same as the current time period of the area to be identified and the extraction of multiple pest image feature data are performed, and then the classification is performed to obtain multiple types of pest image feature data sets, specifically:
[0130] Acquire a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified;
[0131] Extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images;
[0132] Classification processing is performed according to the pest image feature data corresponding to the multiple historical pest monitoring images to obtain multiple types of pest image feature data sets.
[0133] Among them, in order to extract the characteristic data of pests in the image, a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified is obtained. For example, a set of pest monitoring images covering multiple time periods (such as spring, summer, autumn, and winter) is obtained through a historical database, and fuzzy, repeated, and irrelevant images are checked and removed. Image feature information is extracted from the pest monitoring image set, such as the type, quantity, location, severity, etc. of pests. These feature information are organized into a structured data form to obtain pest image feature data corresponding to multiple historical pest monitoring images. The pest image feature data corresponding to the multiple historical pest monitoring images are classified and processed to obtain multiple types of pest image feature data sets.
[0134] According to an embodiment of the present invention, the image feature data of multiple preset sub-areas in the current time period of the area to be identified are obtained, and image feature similarity comparison is performed with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-area, specifically:
[0135] Acquire image feature data of a plurality of preset sub-areas in the current time period of the area to be identified, including contour size identification data, texture pattern data, color distribution data, and structure space relationship data;
[0136] The image feature data of the preset sub-region is compared with the image feature data of the white moth to obtain image feature comparison similarity data corresponding to each sub-region.
[0137] Among them, in order to determine whether there is a white moth in the area to be identified, the area to be identified is first divided into multiple preset sub-areas, and the image feature data of the multiple preset sub-areas in the current time period of the area to be identified are obtained, including contour size identification data, texture pattern data, color distribution data and structural spatial relationship data. The contour size identification data refers to the edge shape and size information of the object or area in the image. These data are usually obtained through edge detection algorithms and are used to describe the geometric properties of the object such as the outer contour shape, aspect ratio, area, etc. The texture pattern data describes the pixel arrangement mode of the local area in the image, which is usually related to the physical properties of the object such as the material and surface roughness. The color distribution data refers to the distribution of different colors or color combinations in the image, including the type, quantity, position and spatial relationship between the colors. The structural spatial relationship data describes the spatial position, direction, distance and other mutual relationships between objects or areas in the image. The image feature data of the preset sub-areas are compared with the white moth image feature data for image feature similarity, and the image feature comparison similarity data corresponding to each sub-area is obtained, so that it can be determined which preset sub-areas are similar to the white moth image and how similar they are.
[0138] The calculation formula of the image feature comparison similarity data is:
[0139]
[0140] Among them, M ds is the image feature comparison similarity data, l c 、w n 、c t , g k They are the outline size identification data, texture pattern data, color distribution data and structure space relationship data of the preset sub-area, respectively. cb 、w nb 、c tb , g kb are the contour size identification data, texture pattern data, color distribution data and structural space relationship data of the white moth image respectively; β, α1, α2, α3, α4, ξ1, ξ2, ξ3 and ξ4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth identification parameter database).
[0141] According to an embodiment of the present invention, the historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods are obtained, and the white moth high incidence prediction index corresponding to each sub-area is obtained by combining the corresponding image feature comparison similarity data for processing, specifically:
[0142] Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods;
[0143] The historical white moth outbreak rate data is combined with the corresponding image feature comparison similarity data and processed through a preset high incidence prediction model to obtain a white moth high incidence prediction index corresponding to each sub-region.
[0144] Among them, in order to further determine whether there are white moths in the area to be identified, the historical white moth outbreak rate data of multiple preset sub-areas in multiple same historical time periods are obtained, and the actual outbreak of white moths in each sub-area in these time periods is recorded. According to the historical white moth outbreak rate data combined with the corresponding image feature comparison similarity data, the preset high-incidence prediction model is used for processing to obtain the white moth high-incidence prediction index corresponding to each sub-area, which indicates the possibility and severity of the white moth outbreak in each sub-area in a certain time period in the future;
[0145] The calculation formula of the high incidence prediction model is:
[0146]
[0147] Among them, G f is the high incidence prediction index of white moth, H b is the historical outbreak rate data of white moth, Mds is the image feature comparison similarity data, ∈, η, θ are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth identification parameter database).
[0148] According to an embodiment of the present invention, the white moth high incidence prediction index corresponding to each sub-region is compared with a preset prediction index threshold to obtain a sub-region suspected of high incidence of white moth, specifically:
[0149] Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a prediction index deviation rate;
[0150] Determining whether the prediction index deviation rate is greater than a preset prediction index deviation rate threshold;
[0151] If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-region is not a high-incidence sub-region of white moth;
[0152] If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-region is a sub-region suspected of being a high-incidence sub-region of white moth.
[0153] Among them, in order to further determine whether there is a high incidence of white moths in the area to be identified, the white moth high incidence prediction index corresponding to each sub-area is compared with the preset prediction index threshold to obtain the prediction index deviation rate, and determine whether the prediction index deviation rate is greater than the preset prediction index deviation rate threshold. If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-area is not a sub-area with a high incidence of white moths. If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-area is a sub-area with a suspected high incidence of white moths.
[0154] According to an embodiment of the present invention, the acquisition of multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moths, and the comparison and processing between the current environmental change data and the average data of multiple historical environmental change data, to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moths, is specifically:
[0155] Obtain multiple historical environmental change data for the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data, and historical precipitation accumulation data;
[0156] Obtaining the current environmental change data of each suspected high-incidence sub-area of white moth in the current time period, including temperature and humidity fluctuation rate data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data;
[0157] By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained;
[0158] The calculation formula of the contrast index induced by the white moth ring change is:
[0159]
[0160] Among them, E φ is the contrast index induced by the white moth ring change, e bn is the current environmental change data, e hn is the average data of multiple historical environmental change data, κ1, κ z , μ1, μ2 are preset characteristic coefficients.
[0161] Among them, in order to evaluate the environmental characteristics and changes of historical white moth outbreaks in suspected high-incidence areas of white moths and compare them with the current environment, multiple historical environmental change data of the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area of white moths were obtained, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data and historical precipitation accumulation data; the current environmental change data of each suspected high-incidence sub-area of white moths in the current time period were obtained, including temperature and humidity fluctuation data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data; the temperature and humidity fluctuation data include day and night temperature difference, humidity fluctuation, etc., because these factors directly affect the survival and reproduction of white moths; the light intensity change data records the changes in light intensity every day or in a specific period of time, which is an important factor in the life cycle of white moths and affects their activities and reproduction; the vegetation gnawing rate data is recorded by regularly investigating the damage to vegetation (such as the proportion of leaves gnawing), which directly reflects the degree of harm to vegetation caused by white moths; the precipitation accumulation data counts the cumulative precipitation in a specific time period, which affects the survival rate of white moth larvae and the migration ability of adults. By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained.
[0162] According to an embodiment of the present invention, a threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and a suspected high-incidence sub-region of white moths that meets the threshold comparison requirements is marked as a white moth high-incidence prediction region, and a white moth high-incidence warning is performed in the sub-region, specifically:
[0163] The contrast index deviation rate is obtained by comparing the white moth ring change induction contrast index with a preset white moth ring change induction threshold;
[0164] Determining whether the contrast index deviation rate is greater than a preset contrast index deviation rate threshold;
[0165] If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, then the suspected high incidence area of white moths does not have a high incidence of white moths;
[0166] If the contrast index deviation rate is less than a preset contrast index deviation rate threshold, the suspected area with high incidence of white moths is marked as a predicted area with high incidence of white moths and a sub-area high incidence warning of white moths is issued.
[0167] Among them, in order to further determine the impact of environmental changes in areas suspected of high incidence of white moths on the growth and outbreak of white moths, the white moth ring change induced contrast index is compared with the preset white moth ring change induced threshold to obtain the contrast index deviation rate, and determine whether the contrast index deviation rate is greater than the preset contrast index deviation rate threshold. If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, there is no high incidence of white moths in the suspected high incidence area of white moths. If the contrast index deviation rate is less than the preset contrast index deviation rate threshold, the suspected high incidence area of white moths is marked as a high incidence prediction area of white moths and a sub-area high incidence warning of white moths is issued.
[0168] According to an embodiment of the present invention, it also includes:
[0169] Extracting white moth identification image feature data according to the white moth identification image;
[0170] Extracting the growth cycle data of the white moth according to the white moth identification image feature data, including egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data;
[0171] The egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data are processed by a preset white moth growth evaluation model to obtain a white moth growth rate index;
[0172] The calculation formula of the white moth growth evaluation model is:
[0173]
[0174] Among them, M r is the white moth growth rate index, l g ,y g , b g 、h g are the egg stage growth data, larval stage growth data, pupal stage growth data and adult stage growth data respectively, and η1, η2, μ1, μ2 and π are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset white moth growth monitoring database).
[0175] Among them, in order to reflect the characteristics of each growth cycle of the white moth, the growth cycle data of the white moth is extracted according to the feature data of the white moth identification image, including growth data in the egg stage, such as egg size, color, shape, etc., growth data in the larval stage, such as body length, color change, screen shape, etc., growth data in the pupal stage, such as pupa size, color, shape, etc., growth data in the adult stage, such as wing color, number of spots, etc., which are processed through the preset white moth growth evaluation model to obtain the white moth growth rate index, which is used to quantify the growth rate of the white moth, understand the growth rate of the white moth and the growth characteristics of different stages, predict the population outbreak time according to the growth rate, and formulate corresponding prevention and control strategies; thereby, the identification and prediction of the high incidence of white moths in the region are realized through image recognition and data processing.
[0176] The third aspect of the present invention also provides a readable storage medium, which includes a program for a white moth identification and processing method based on big data. When the program for a white moth identification and processing method based on big data is executed by a processor, the steps of a white moth identification and processing method based on big data as described in any one of the above items are implemented.
[0177] The present invention discloses a method, system and medium for identifying and processing white moths based on big data. The method comprises the following steps: obtaining white moth image feature data of a current time period in a region to be identified in a plurality of same historical time periods and image feature data of a plurality of preset sub-regions, and comparing and obtaining image feature comparison similarity data; obtaining historical white moth outbreak rate data of a plurality of preset sub-regions; and processing the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index, which is compared with a preset threshold value to obtain a white moth suspected high incidence sub-region; obtaining current environmental change data of the white moth suspected high incidence sub-region, and processing the data with the average data of a plurality of historical environmental change data to obtain a white moth ring change induced contrast index, which is further compared with a preset white moth ring change induced threshold value, and if the index meets the threshold value, it is marked as a white moth high incidence prediction region. domain, and conduct early warning of high incidence of white moth in sub-regions. This application not only considers the pest monitoring images of the current time period, but also combines multiple pest monitoring image sets of the same historical time period. By extracting and analyzing historical data, it is possible to more comprehensively understand the laws and patterns of pest occurrence, thereby improving the accuracy and reliability of identification, and subdividing the area to be identified into multiple preset sub-regions. This regional subdivision strategy makes the early warning more accurate, and can specifically identify specific areas where white moths may be highly prevalent, which is conducive to the rational allocation of resources and effective response. It also considers the impact of historical environmental change data on the current prediction of high incidence of white moths, and calculates the white moth ring change induced contrast index, which further improves the scientificity and accuracy of the prediction, provides strong support for white moth control plans, and provides data support for the formulation of scientific white moth pest management strategies.
[0178] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0179] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0180] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0181] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories, random access memories, magnetic disks or optical disks, and other media that can store program codes.
[0182] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
Claims
1. A method for identifying and processing white moths based on big data, characterized in that: The following steps are involved: Obtaining a pest monitoring image set of the current time period of the area to be identified in multiple same historical time periods and extracting multiple pest image feature data, and then classifying them to obtain multiple types of pest image feature data sets; Processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images; Acquire image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and perform image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region; Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods, and process the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index corresponding to each sub-area; Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a suspected white moth high incidence sub-area; Obtain multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compare and process the current environmental change data with the average data of multiple historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth; A threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and sub-regions with suspected high incidence of white moths that meet the threshold comparison requirements are marked as white moth high incidence prediction areas, and a white moth high incidence warning is issued in the sub-regions.
2. A method for identifying and processing white moths based on big data according to claim 1, characterized in that: The method of obtaining a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified and extracting multiple pest image feature data, and then classifying to obtain multiple types of pest image feature data sets, is specifically: Acquire a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified; Extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images; Classification processing is performed according to the pest image feature data corresponding to the multiple historical pest monitoring images to obtain multiple types of pest image feature data sets.
3. A method for identifying and processing white moths based on big data according to claim 2, characterized in that: The acquiring of the image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and performing image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region, is specifically: Acquire image feature data of a plurality of preset sub-areas in the current time period of the area to be identified, including contour size identification data, texture pattern data, color distribution data, and structure space relationship data; The image feature data of the preset sub-region is compared with the image feature data of the white moth to obtain image feature comparison similarity data corresponding to each sub-region.
4. A method for identifying and processing white moths based on big data according to claim 3, characterized in that: The historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods are obtained, and the white moth high incidence prediction index corresponding to each sub-area is obtained by combining the corresponding image feature comparison similarity data for processing, specifically: Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods; The historical white moth outbreak rate data is combined with the corresponding image feature comparison similarity data and processed through a preset high incidence prediction model to obtain a white moth high incidence prediction index corresponding to each sub-region.
5. A method for identifying and processing white moths based on big data according to claim 4, characterized in that: The prediction index of high incidence of white moth corresponding to each sub-region is compared with a preset prediction index threshold to obtain a sub-region suspected of high incidence of white moth, specifically: Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a prediction index deviation rate; Determining whether the prediction index deviation rate is greater than a preset prediction index deviation rate threshold; If the prediction index deviation rate is greater than or equal to the preset prediction index deviation rate threshold, the current sub-region is not a high-incidence sub-region of white moth; If the prediction index deviation rate is less than the preset prediction index deviation rate threshold, the current sub-region is a suspected high-incidence sub-region of white moth.
6. A method for identifying and processing white moths based on big data according to claim 5, characterized in that: The method obtains a plurality of historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compares the current environmental change data with the average data of the plurality of historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth, specifically: Obtain multiple historical environmental change data for the same historical time period when historical white moth outbreaks occurred in each suspected high-incidence sub-area, including historical temperature and humidity fluctuation data, historical light intensity change data, historical vegetation gnawing rate data, and historical precipitation accumulation data; Obtaining the current environmental change data of each suspected high-incidence sub-area of white moth in the current time period, including temperature and humidity fluctuation rate data, light intensity change data, vegetation gnawing rate data and precipitation accumulation data; By comparing the current environmental change data with the average data of multiple historical environmental change data, the contrast index of the white moth ring change induction corresponding to each suspected high-incidence sub-area of the white moth is obtained; The calculation formula of the contrast index induced by the white moth ring change is: Among them, E φ is the contrast index induced by the white moth ring change, e bn is the current environmental change data, e hn is the average data of multiple historical environmental change data, and κ1, κ2, μ1, and μ2 are preset characteristic coefficients.
7. A method for identifying and processing white moths based on big data according to claim 6, characterized in that: The threshold comparison is performed based on the white moth ring change induction contrast index and the preset white moth ring change induction threshold, and the suspected high-incidence sub-region of white moths that meets the threshold comparison requirements is marked as a white moth high-incidence prediction region, and a white moth high-incidence warning is issued in the sub-region, specifically: The contrast index deviation rate is obtained by comparing the white moth ring change induction contrast index with a preset white moth ring change induction threshold; Determining whether the contrast index deviation rate is greater than a preset contrast index deviation rate threshold; If the contrast index deviation rate is greater than or equal to the preset contrast index deviation rate threshold, then the suspected high incidence area of white moths does not have a high incidence of white moths; If the contrast index deviation rate is less than a preset contrast index deviation rate threshold, the suspected area with high incidence of white moths is marked as a predicted area with high incidence of white moths and a sub-area high incidence warning of white moths is issued.
8. A white moth identification and processing system based on big data, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a white moth identification and processing method program based on big data, and the white moth identification and processing method program based on big data is executed by the processor to implement the following steps: Obtaining a pest monitoring image set of the current time period of the area to be identified in multiple same historical time periods and extracting multiple pest image feature data, and then classifying them to obtain multiple types of pest image feature data sets; Processing the plurality of types of pest monitoring image feature data sets through a preset pest category image feature recognition model to obtain white moth image feature data and corresponding white moth identification images; Acquire image feature data of a plurality of preset sub-regions in the current time period of the area to be identified, and perform image feature similarity comparison with the white moth image feature data to obtain image feature comparison similarity data corresponding to each sub-region; Acquire historical white moth outbreak rate data of the plurality of preset sub-areas in the plurality of same historical time periods, and process the data in combination with the corresponding image feature comparison similarity data to obtain a white moth high incidence prediction index corresponding to each sub-area; Compare the white moth high incidence prediction index corresponding to each sub-area with a preset prediction index threshold to obtain a suspected white moth high incidence sub-area; Obtain multiple historical environmental change data of historical white moth outbreaks in each suspected high-incidence sub-region of white moth, and compare and process the current environmental change data with the average data of multiple historical environmental change data to obtain the white moth ring change induced contrast index corresponding to each suspected high-incidence sub-region of white moth; A threshold comparison is performed based on the white moth ring change induction contrast index and a preset white moth ring change induction threshold, and sub-regions with suspected high incidence of white moths that meet the threshold comparison requirements are marked as white moth high incidence prediction areas, and a white moth high incidence warning is issued in the sub-regions.
9. A white moth identification and processing system based on big data according to claim 8, characterized in that: The method of obtaining a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified and extracting multiple pest image feature data, and then classifying to obtain multiple types of pest image feature data sets, is specifically: Acquire a set of pest monitoring images in multiple historical time periods that are the same as the current time period of the area to be identified; Extracting image feature information according to the pest monitoring image set to obtain pest image feature data corresponding to a plurality of historical pest monitoring images; Classification processing is performed according to the pest image feature data corresponding to the multiple historical pest monitoring images to obtain multiple types of pest image feature data sets.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a method, system and medium program for identifying and processing white moths based on big data. When the method, system and medium program for identifying and processing white moths based on big data are executed by a processor, the steps of a method for identifying and processing white moths based on big data as described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Garden pest identification method and system, computer equipment and storage medium
CN113887595A
Recognition and early warning method and system for spodoptera frugiperda
CN114550108A
Agricultural pest diagnosis and early warning system based on big data
CN114972843A
Rice pest interactive image segmentation method, system and equipment
CN116433912A
Forestry insect disaster prediction method and system based on regional historical data
CN116884041A
Cited By
Intelligent codling moth monitoring system based on multi-source trapping data fusion
CN120951226A
