Acousto-optic pest prevention and control system and method

Abstract

The invention discloses a pest acousto-optic prevention and control system and method, and relates to the technical field of pest recognition. According to the invention, the identification image set generation unit is arranged to determine the corresponding local acquisition node or cloud acquisition node based on the growth characteristics of crops in the image data and the acquisition time so as to obtain the node number and generate the corresponding insect pest identification image set; corresponding models are correspondingly selected and started for local collection nodes or cloud collection nodes according to the node numbers to conduct pest recognition, if the nodes are local collection nodes, pest special recognition models corresponding to the local collection nodes are started to conduct corresponding pest type recognition, and if the nodes are cloud collection nodes, the cloud pest prevention and control server conducts pest type recognition; the corresponding recognition model is intelligently selected for operation and special recognition, so that on one hand, excessive unnecessary pest type recognition conditions are avoided, and on the other hand, the recognition rate of the corresponding pest type is increased.

Description

Technical Field

[0001] The present invention relates to the technical field of pest identification, and specifically provides a pest prevention and control system and method using sound and light. Background Art

[0002] With the development of smart agriculture, traditional pest control methods (such as chemical pesticide spraying and manual inspections) are gradually being replaced by intelligent solutions. Currently, the field of agricultural pest prevention and control mainly relies on intelligent identification and prevention and control technologies. The traditional method provides pest identification services for each farming area through a cloud server. The specific process is as follows: The monitoring equipment in the farming area collects image data and transmits it to the cloud. A pre-trained general pest identification model is used to analyze the images, and finally the identification results are returned to the local area to trigger prevention and control measures. However, in this way, a large amount of image data in the farming area needs to be uploaded to the cloud in real time. Limited by network bandwidth and transmission stability, the feedback of the identification results is delayed, making it difficult to meet the timeliness requirements of pest prevention and control. Moreover, the general pest identification model needs to cover various crop and pest types, resulting in a high model complexity and large consumption of computing resources.

[0003] To solve the above problems, the prior art proposes to sink the pest identification task to the local area by deploying special identification models for specific crops or pest types in the corresponding areas. However, multiple crops may be planted in the same farming area, and there are periodic differences in the high-incidence periods of pests for different crops. To cover all possible pest types, multiple special models need to run for a long time, resulting in redundant consumption of computing resources and electrical energy.

[0004] To solve the above problems, the present invention proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide a pest prevention and control system and method using sound and light to solve the problems raised in the above background art.

[0006] The present invention provides a pest prevention and control system using sound and light, including:

[0007] An identification atlas generation unit, configured to identify the growth characteristics of the crops in the image data after receiving real-time image data of the planting area, and determine the growth stage of the crops corresponding to the image data.

[0008] The identification atlas generation unit is further configured to determine the node number of the image data based on the growth stage of the crops corresponding to the image data and the acquisition time corresponding to the image data.

[0009] An identification atlas generation unit is also used to generate a pest identification atlas with the node number when the sum of the acquisition times of all the image data of the planting area stored therein is consistent with the acquisition duration of the local acquisition node or the cloud acquisition node corresponding to the node number of any one of the all image data, according to all the image data of the planting area stored therein;

[0010] A local branch identification unit is used to perform pest identification on the pest identification atlas according to a preset identification step after receiving the pest identification atlas with the node number to obtain the pest identification result data with the node number;

[0011] The pest identification result data contains an identification signal, which is selected from the numbers 1 and 0. When the identification signal is the number 1, the pest identification result data also contains several pest types;

[0012] An acoustic-optic prevention and control response module is used to obtain a corresponding acoustic-optic prevention and control strategy according to several pest types contained in the pest identification result data after receiving the pest identification result data with the identification signal being 1, and adjust the acoustic-optic prevention and control of the planting area according to the acoustic-optic prevention and control strategy;

[0013] A cloud pest prevention and control server is used to provide identification services for the pest prevention and control of the planting area. The cloud pest prevention and control server includes a cloud pest identification unit and a cloud pest analysis unit.

[0014] Furthermore, several growth stages of the crops are divided by agricultural technicians according to the growth cycle of the crops.

[0015] Furthermore, a crop pest and disease identification model is pre-stored in the cloud pest identification unit.

[0016] Furthermore, a cloud pest analysis unit stores several pest identification record data. The pest identification record data contains an identification signal, a planting area, the acquisition time of the starting image, the acquisition time of the ending image, several pest types and their type feature atlases.

[0017] Furthermore, the cloud pest analysis unit analyzes all the stored pest identification record data to obtain pest identification branch data of the crops in the planting area at several growth stages. The pest identification branch data includes several independent pest types, combined pest types and their associated type sets.

[0018] Further, agricultural technicians, for the crops in the planting area at any growth stage, divide the interval duration of the growth stage into several local collection nodes and cloud collection nodes based on the pest identification and decomposition data of the crops in the growth stage, and preset a collection duration for each local collection node and cloud collection node. Among them, one local collection node corresponds to one pest special identification model;

[0019] After the division, number the several local collection nodes and cloud collection nodes divided from this growth stage, and the numbering starts from 1 and continues in sequence.

[0020] A pest sound and light prevention and control method includes the following steps:

[0021] Step 1: After receiving the image data of the real-time planting area, the identification atlas generation unit identifies the growth characteristics of the crops in the image data to determine the growth stage of the crops corresponding to the image data. The node number of the image data is determined by the growth stage of the crops corresponding to the determined image data and the collection time corresponding to the image data;

[0022] Step 2: When the sum of the collection times of all the image data of the planting area stored in the identification atlas generation unit is consistent with the collection duration of the local collection node or cloud collection node corresponding to the node number of any one of the all image data, the pest identification atlas of the node number is generated according to all the image data of the planting area stored in it, and it is transmitted to the local branch identification unit;

[0023] Step 3: After receiving the pest identification atlas of the node number, the local branch identification unit performs pest identification on the pest identification atlas according to the preset identification steps to obtain the pest identification result data of the node number. The pest identification result data contains an identification signal, and the identification signal is selected from the numbers 1 and 0. When the identification signal is the number 1, the pest identification result data also contains several pest types;

[0024] When the identification signal is 1, the pest identification result data is transmitted to the sound and light prevention and control response module;

[0025] Step 4: After receiving the pest identification result data with the identification signal of 1, the sound and light prevention and control response module obtains the corresponding sound and light prevention and control strategy according to the several pest types contained in the pest identification result data and adjusts the sound and light prevention and control of the planting area according to the sound and light prevention and control strategy.

[0026] Compared with the prior art, it has the following beneficial effects:

[0027] The present invention generates a corresponding local acquisition node or cloud acquisition node based on the growth characteristics of crops in the image data and the acquisition time, thereby obtaining a node number and generating a corresponding pest identification atlas. According to the node number, a corresponding model is selected and enabled for pest identification for the local acquisition node or cloud acquisition node. If it is a local acquisition node, the pest special identification model corresponding to the local acquisition node is further enabled to identify the corresponding pest type. For a cloud acquisition node, it is transmitted to the cloud pest prevention and control server to identify the pest type using the crop pest identification model. In this way, the corresponding identification model is intelligently selected for operation and special identification. On the one hand, it avoids the occurrence of too many unnecessary pest type identification situations and the waste of resources caused by running multiple identification models locally. On the other hand, it speeds up the identification rate of the corresponding pest type;

[0028] The present invention analyzes the pest identification record data of crops in different planting areas through the cloud pest analysis unit to determine the pest identification branch data of the crops in the corresponding planting areas at several growth stages. The cloud pest disassembly unit disassembles all the pest identification disassembly data of the corresponding crops in several growth stages within all planting areas from the crop pest identification model. And agricultural technicians divide the growth stages of the corresponding crops into local acquisition nodes and cloud acquisition nodes according to the identified pest types. In this way, the pest types with fewer occurrences and more resource consumption for deploying identification models locally are identified in the cloud, which not only optimizes the use of the pest type identification model, simplifies the complexity of the pest identification model, but also meets the timeliness requirements of pest prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a system block diagram of the present invention;

[0030] Figure 2 is a method flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] Please refer to Figure 1 、 Figure 2 , this application provides a pest sound and light prevention and control system and method, including a pest monitoring terminal, a pest branch identification module, a sound and light prevention and control response module, and a cloud pest prevention and control server;

[0033] The pest monitoring terminal is used to monitor all planting areas in the target site. The pest monitoring terminal includes a number of pest monitoring modules, and one pest monitoring module corresponds to one planting area in the target site;

[0034] In this application, the planting area is a greenhouse. The environment inside it is controllable throughout the year, that is, the control factors such as temperature, humidity, and light inside the greenhouse are controlled by humans. Therefore, the pests inside are not restricted by seasons;

[0035] In this application, the delineation of the planting area is carried out by agricultural technicians according to the types of crops, growth distribution characteristics, historical occurrence laws of pests and diseases, and ecological environment conditions in the target site, combined with GIS spatial analysis technology;

[0036] In this application, there is and only one type of crop planted in the same planting area at the same time. In this application, the type of crop planted in any planting area in the target site is selected by agricultural technicians;

[0037] In this application, only one type of crop is planted in any planting area in the target site;

[0038] The pest monitoring module collects the image data of the corresponding planting area in real time and transmits it to the pest branch recognition module. The pest branch recognition module includes an identification atlas generation unit and a local branch recognition unit;

[0039] After receiving the image data, the pest branch recognition module transmits it to the identification atlas generation unit. After receiving the image data, the identification atlas generation unit identifies the growth characteristics of the crops in the image data to determine the growth stage of the crops corresponding to the image data;

[0040] Specifically: extract several growth characteristics of the crops in the image data, calculate the similarity between the several growth characteristics and several standard growth characteristics of the crops in each growth stage stored in advance, and determine the standard growth characteristic with the highest similarity as the growth stage of the crops corresponding to the image data;

[0041] In this application, the growth characteristics include but are not limited to morphological characteristics such as the roots, stems, leaves, and flowers of the crops;

[0042] In this application, the several growth stages of any one of the crops are divided by agricultural technicians according to the growth cycle of the crops;

[0043] Determine the node number of the image data through the growth stage of the crops corresponding to the image data and the acquisition time corresponding to the image data. The determination steps are as follows:

[0044] In the pest branch identification module, obtain the collection durations and digital numbers of several local collection nodes of the crop at the growth stage, and the collection durations and digital numbers of several cloud collection nodes;

[0045] Then, obtain all the image data currently stored in the pest branch identification module corresponding to the growth stage, and sort all the obtained image data from left to right according to the chronological order of the acquisition times of the image data. If the sum Z1 of the image data before the image data after sorting satisfies Y1 + Y2 +... + Yy1 ≤ Z1 ≤ Y1 + Y2 +... + Yy1 + 1, then determine that the node number of the image data is y1 + 1, where Y1, Y2,..., Yy1 are the collection durations of the local collection nodes or cloud collection nodes corresponding to the digital numbers 1, 2,..., y1, Yy1 + 1 in sequence;

[0046] Temporarily store the image data and its node number;

[0047] For a planting area, when the total acquisition time of all the image data of the planting area stored in the recognition atlas generation unit reaches the acquisition duration of the local collection node or cloud collection node corresponding to its node number, generate a pest recognition atlas with the node number according to all the image data of the planting area stored therein;

[0048] It should be noted here that the node numbers corresponding to all the image data included in the generated pest recognition atlas are the same;

[0049] After receiving the transmitted pest recognition atlas with the node number, the local branch identification unit performs pest identification on the pest recognition atlas according to the preset identification steps. The identification steps are as follows:

[0050] S11: If the node number corresponds to a local collection node, obtain the pest special identification model corresponding to the local collection node with the node number, use the pest recognition atlas as the input of the pest special identification model, and perform identification on it by the pest special identification model to obtain the pest recognition result data with the node number. The pest recognition result data contains an identification signal;

[0051] In this application, an identification signal is selected from the digits 1 and 0. When the identification signal is the digit 1, it indicates that pests are identified at the local acquisition node. At this time, the pest identification result data further includes the planting area corresponding to the crop, the growth stage, the local acquisition node, the acquisition time of the starting image, the acquisition time of the ending image, several pest types and their type feature atlases. An image data identifying the corresponding pest type is included in one type feature atlas, and all the image data included in one type feature atlas are in order, arranged from left to right in the order of acquisition. The starting image and the ending image are the image data located at the leftmost and rightmost ends of the pest identification atlas respectively;

[0052] If the identification signal is the digit 0, it indicates that no pests are identified at the local acquisition node;

[0053] If the identification signal in the pest identification result data is 1, the pest identification result data is transmitted to the sound and light prevention and control response module;

[0054] S12: If the node number corresponds to a cloud acquisition node, the pest identification atlas is transmitted to the cloud pest prevention and control server;

[0055] The cloud pest prevention and control server is used to provide identification services for pest prevention and control in several planting areas within the target site. The cloud pest prevention and control server includes a cloud pest identification unit, a cloud pest analysis unit, and a cloud pest decomposition unit;

[0056] After receiving the transmitted pest identification atlas, the cloud pest prevention and control server transmits it to the cloud pest identification unit;

[0057] A pre-trained crop pest identification model is stored in the cloud pest identification unit for identifying various types of crop pests from the image data;

[0058] After receiving the transmitted pest identification atlas, the cloud pest identification unit inputs it into the crop pest identification model to obtain the pest identification result data of the node number;

[0059] If the identification signal in the pest identification result data is 1, the pest identification result data is transmitted to the sound and light prevention and control response module;

[0060] The sound and light prevention and control response module is used to perform sound and light prevention and control on the corresponding planting areas according to the pest types identified in several planting areas within the target area. Several sound and light prevention and control strategies for crops based on several pest types are pre-stored in the sound and light prevention and control response model. A sound and light prevention and control strategy correspondingly includes light adjustment parameters and sound wave adjustment parameters for preventing and controlling the corresponding pest type;

[0061] After receiving the transmitted pest identification result data, the acousto-optic prevention and control response module obtains the corresponding acousto-optic prevention and control strategy according to the pest types included in the pest identification result data, and adjusts the acousto-optic prevention and control of the corresponding planting area according to the acousto-optic prevention and control strategy;

[0062] The cloud pest analysis unit stores pest identification record data of all planting areas in a target site at several growth stages. The pest identification record data includes identification signals, planting areas, acquisition times of starting images, acquisition times of ending images, several pest types and their type feature atlases;

[0063] The identification signals in all pest identification record data stored in the cloud pest analysis unit are all 1;

[0064] The cloud pest analysis unit analyzes all the stored pest identification record data, and the analysis steps are as follows:

[0065] S11: First, randomly select a planting area in the target site as the analysis area, select the crops planted in the analysis area as the analysis crops, and sequentially mark all the growth stages divided according to the growth cycle of the analysis crops in the analysis area as A1, A2,..., Aa, where a≥1;

[0066] S12: Obtain all the pest identification record data of the analysis crops in the analysis area at the growth stage A1 stored in the cloud pest analysis unit and traverse them to obtain all the pest types included therein, and mark them as B1, B2,..., Bb respectively, where b≥1;

[0067] S13: Extract all the pest identification record data containing the pest type B1 from the obtained all pest identification record data, and mark them as C1, C2,..., Cc respectively, where c≥1;

[0068] S14: Calculate and obtain the identification adaptation evaluation index F1 of the pest type B1 in the pest identification record data C1 according to the preset calculation rule. The calculation rule is as follows:

[0069] S141: Extract the type feature atlas of the pest type B1 from the pest identification record data C1, and extract the acquisition times of the image data at the leftmost and rightmost ends of the type feature atlas respectively, and mark them as D1 and D2 correspondingly;

[0070] Use the formula E1 = (D2 - D1) / D3 to calculate and obtain the identification span weight E1 of the pest type B1 in the type feature atlas. It should be noted here that the identification span weight is defined artificially and is used to measure the coverage integrity of the image data that can identify the pest type B1 in the type feature atlas;

[0071] S142: Obtain the acquisition time of the starting image and the acquisition time of the ending image in the pest identification record data C1, and mark them as D4 and D5 respectively;

[0072] S143: Use the formula E2 = (D1 - D4) -1 ×ɑ1 + (D2 - D1) / (D5 - D4)×ɑ2 to calculate and obtain the recognition proportion weight E2 of pest type B1 in the type feature map set. In the formula, D2 - D1 is the initial feature time of pest type B1 in the pest identification record data C1, D5 - D4 is the final feature time of pest type B1 in the pest identification record data C1, and ɑ1 and ɑ2 are the preset first and second feature dimension factors respectively, which are used to adjust the features of different calculation dimensions to the same calculation dimension for calculation. It should be noted here that the recognition proportion weight E2 is artificially defined to measure the time span interval degree feature of the image data of pest type B1 recognized in the type feature map set;

[0073] S144: Use the formula F1 = [P1 - (E1×β1 + E2×β2) 2 / E3 to calculate and obtain the recognition adaptation evaluation index F1 of pest type B1 in the pest identification record data C1. It should be noted here that the recognition adaptation evaluation index is artificially defined to comprehensively evaluate the deployment adaptability of recognizing pest type F1 in three dimensions: the recognition span weight, the recognition proportion weight, and the data capacity size of the input pest identification map set. In the formula, P1 is the preset standard compensation constant, and E3 is the data capacity size of the pest identification map set input when the crop pest identification model recognizes the pest identification record data C1;

[0074] S15: Calculate and obtain the recognition adaptation evaluation indexes F2, F3,..., Fc of pest type B1 in the pest identification record data C1, C2,..., Cc in sequence according to S13 to S14, and synchronously obtain the initial feature time and the final feature time of pest type B1 in the pest identification record data C2, C3,..., Cc;

[0075] Use the discrete point filtering algorithm to process the obtained recognition adaptation evaluation indexes F1, F2,..., Fc, and calculate the average value of all the remaining recognition adaptation evaluation indexes after data processing. Calibrate the average value as the recognition adaptation index G1 of pest type B1 of the analyzed crop in the growth stage A1 in the analysis area. Similarly, obtain the branch initial time and the branch final time of pest type B1 of the analyzed crop in the growth stage A1 in the analysis area;

[0076] The initial recognition moment of the branch of pest type B1 of the analyzed crop in the analysis area at growth stage A1 is obtained by using the discrete point filtering algorithm to process the initial recognition feature moments of pest type B1 in the obtained pest recognition record data C1, C2, ..., Cc, and calculating the average value of all the remaining initial recognition feature moments after data processing for calibration;

[0077] The final recognition moment of the branch of pest type B1 of the analyzed crop in the analysis area at growth stage A1 is obtained by using the discrete point filtering algorithm to process the final recognition feature moments of pest type B1 in the obtained pest recognition record data C1, C2, ..., Cc, and calculating the average value of all the remaining final recognition feature moments after data processing for calibration;

[0078] In this application, the discrete point filtering algorithm can be one of the Z-score filtering algorithm, the IQR filtering algorithm, and the density filtering algorithm;

[0079] S16: Successively extract all the pest recognition record data containing pest types B2, B3, ..., Bb from the obtained all pest recognition record data, and calculate the recognition adaptation indexes of pest types B2, B3, ..., Bb of the analyzed crop in the analysis area at growth stage A1 in sequence according to S14 to S15;

[0080] S17: Compare the recognition adaptation indexes of the pest types B1, B2, ..., Bb with P2 in size successively, and obtain the pest types corresponding to the recognition adaptation indexes with all values greater than or equal to P2 and mark them as H1, H2, ..., Hh respectively, where 1 ≤ h ≤ b, and P2 is a preset pest recognition branch comparison quantity;

[0081] S18: Successively obtain the initial recognition moment and the final recognition moment of the branch of pest types H1, H2, ..., Hh of the analyzed crop in the analysis area at growth stage A1 and traverse them. If there are several pest types that simultaneously satisfy that the difference between the initial moment of the branch and the initial moment of the branch of pest type H1 and the difference between the final moment of the branch and the final moment of the branch of pest type H1 are both less than or equal to P3, then re-calibrate pest type H1 as the merged pest type, and use these several pest types as the associated type set of pest type H1. Otherwise, re-calibrate pest type H1 as an independent pest type, where P3 is a preset collaborative recognition difference determination standard quantity;

[0082] Similarly, determine whether there are several pest types that simultaneously satisfy that the differences between the initial branch times and the initial branch times of pest types H2, H3, ..., Hh are less than or equal to P3, and the differences between the final branch times and the final branch times of pest types H2, H3, ..., Hh are less than or equal to P3, so as to obtain several combined pest types and their associated type sets, and several independent pest types;

[0083] Generate pest identification branch data of the analyzed crops in the growth stage A1 in the analysis area according to the obtained several combined pest types and their associated type sets, and several independent pest types;

[0084] S19: Generate pest identification branch data of the analyzed crops in the growth stages A2, A3, ..., Aa in the analysis area in sequence according to S11 to S18;

[0085] S110: Select all planting areas in the target site as the analysis area one by one, and calculate and obtain the pest identification branch data of the corresponding crops in several growth stages in all planting areas in sequence according to S11 to S19;

[0086] Transmit the pest identification branch data of the corresponding crops in several growth stages in all the planting areas to the cloud pest disassembly unit;

[0087] After receiving the transmitted pest identification branch data of the corresponding crops in several growth stages in all the planting areas, the cloud pest disassembly unit disassembles several pest identification disassembly data of the corresponding crops in several growth stages in all the planting areas from the crop pest identification model according to the preset disassembly rules. The disassembly rules are as follows:

[0088] S21: Select any one planting area in the target site as the branch area, and sequentially mark all the growth stages divided according to the growth cycle of the crops in the branch area as I1, I2, ..., Ii,i 1;

[0090] S22: Obtain all the pest identification branch data in the growth stage I1 from all the pest identification branch data of the corresponding crops in several growth stages in the received branch area, and extract all the combined pest types and their associated type sets included from the obtained all the pest identification branch data;

[0091] According to any one of the extracted combined pest types and its associated type set, split a sub-model that can simultaneously identify all the pest types in the combined pest type and its associated type set from the crop pest identification model, and calibrate the sub-model as the pest special identification model of the combined pest type;

[0092] S23: Extract all independent pest types included in the pest identification branch data. According to any one of the extracted independent pest types, split a sub-model that can identify the independent pest type from the crop pest and disease identification model, and label the sub-model as the pest special identification model for the independent pest type;

[0093] S24: Generate pest identification decomposition data for the crops in the branch area at growth stage I1 based on all the pest special identification models obtained by splitting in S22 to S23 and the several pest types they can identify;

[0094] S25: Generate pest identification decomposition data for the crops in the branch area at growth stages I2, I3,..., Ii in sequence according to S21 to S24;

[0095] S26: Select all planting areas in the target site as branch areas in sequence, and generate pest identification decomposition data for the crops in all planting areas in the target site at several growth stages according to S21 to S25;

[0096] The cloud pest decomposition unit transmits the pest identification decomposition data for the crops in all planting areas in the target site at several growth stages to the local branch identification unit of the pest branch identification module;

[0097] After receiving the transmitted pest identification decomposition data for the crops in all planting areas in the target site based on several growth stages, the local branch identification unit first divides several local collection nodes and cloud collection nodes for the crops in all planting areas corresponding to all growth stages by agricultural technicians, sets the collection duration for each, and assigns digital numbers;

[0098] Specifically, for the crops in any one planting area, at any one of its growth stages, based on the pest identification decomposition data of the crops in this growth stage (including several pest special identification models and the several pest types they respectively identify), the agricultural technician divides the interval duration of this growth stage into several local collection nodes and cloud collection nodes, and presets a collection duration for each local collection node and cloud collection node. In this process, one local collection node corresponds to one pest special identification model;

[0099] After the division is completed, digital numbers are assigned to the several local collection nodes and cloud collection nodes divided from this growth stage, starting from 1 and continuing in sequence. The larger the number, the farther the corresponding collection node is from the starting point of this growth stage in terms of development degree;

[0100] The local branch recognition unit stores the collection duration and digital numbers of a number of local collection nodes and their corresponding pest special recognition models, as well as the collection duration and digital numbers of cloud collection nodes corresponding to all crops in all growth stages in all planting areas, and synchronously transmits the collection duration and digital numbers of a number of local collection nodes and their corresponding pest special recognition models, as well as the collection duration and digital numbers of cloud collection nodes corresponding to all crops in all growth stages in all planting areas to the local branch recognition unit for storage.

[0101] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well known to those skilled in the art.

[0102] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A pest sound and light control system, characterized in that: include: An identification atlas generation unit is used to identify the growth characteristics of crops in the image data after receiving the real-time image data of the planting area to determine that the image data corresponds to the growth stage of the crops; The identification atlas generation unit is further used to determine the node number of the image data by determining the growth stage of the crop corresponding to the image data and the acquisition time corresponding to the image data; The identification atlas generating unit is also used to generate an insect pest identification atlas of the node number according to all the image data of the planting area stored therein when the sum of the acquisition time of all the image data of the planting area stored therein is consistent with the acquisition time of the local acquisition node or the cloud acquisition node corresponding to the node number of any image data among all the image data; A local branch identification unit, configured to perform pest identification on the pest identification atlas according to a preset identification step after receiving the pest identification atlas of the node number to obtain pest identification result data of the node number; The pest identification result data includes an identification signal, and the identification signal is selected from the numbers 1 and 0. When the identification signal is 1, the pest identification result data also includes several pest types; An acoustic and optical control response module is used to obtain corresponding acoustic and optical control strategies according to several pest types contained in the pest identification result data after receiving the pest identification result data with an identification signal of 1, and adjust the acoustic and optical control of the planting area according to the acoustic and optical control strategy; The cloud pest control service end is used to provide identification services for pest control in the planting area. The cloud pest control service end includes a cloud pest identification unit and a cloud pest analysis unit.

2. The insect pest sound and light control system according to claim 1, characterized in that: Several growth stages of crops are divided by agricultural technicians according to the growth cycle of the crops.

3. The insect pest sound and light control system according to claim 1, characterized in that: The cloud pest identification unit pre-stores a crop pest identification model.

4. The insect pest sound and light control system according to claim 1, characterized in that: It also includes a number of pest identification record data stored in the cloud pest analysis unit, and the pest identification record data includes an identification signal, a planting area, a start image acquisition time, an end image acquisition time, and a number of pest types and their type feature atlases.

5. The insect pest sound and light control system according to claim 1, characterized in that: The cloud pest analysis unit analyzes all the stored pest identification record data to obtain pest identification branch data of the crops in the planting area at several growth stages, and the pest identification branch data includes several independent pest types, combined pest types and their associated type sets.

6. The pest sound and light control system according to claim 5, characterized in that: The cloud pest control service end further includes a cloud pest disassembly unit. The cloud pest disassembly unit receives the pest identification branch data of the crops in the planting area at several growth stages and disassembles several pest identification disassembly data of the crops in the planting area at several growth stages from the crop pest identification model. The disassembly steps are as follows: S21: taking the planting area as a branch area, marking all growth stages divided according to the growth cycle of crops in the branch area as I1, I2, ..., Ii in the order of the time of crop growth, i≥1; S22: acquiring all pest identification branch data at the growth stage I1 from all pest identification branch data corresponding to the crops in the branch area at several growth stages received, and extracting all merged pest types and associated type sets contained in the acquired all pest identification branch data; According to any one of the extracted combined pest types and its associated type set, a sub-model capable of simultaneously identifying all pest types in the combined pest type and its associated type set is separated from the crop pest identification model, and the sub-model is marked as a special pest identification model for the combined pest type; S23: extracting all independent pest types contained in the pest identification branch data, and according to any extracted independent pest type, splitting a sub-model capable of identifying the independent pest type from the crop pest identification model, and marking the sub-model as a special pest identification model for the independent pest type; S24: Generate pest identification disassembly data of crops in the branch area at the growth stage I1 according to all pest-specific identification models obtained by splitting from S22 to S23 and several pest types that can be identified; S25: Generate pest identification and disassembly data of crops in the branch areas at growth stages I2, I3, ..., Ii in sequence according to S21 to S24.

7. The insect pest sound and light control system according to claim 6, characterized in that: The agricultural technician divides the interval time of the crops in the planting area at any growth stage into a number of local collection nodes and cloud collection nodes according to the pest identification and disassembly data of the crops based on the growth stage, and pre-sets a collection time for each local collection node and cloud collection node, wherein one local collection node corresponds to one pest-specific identification model; After the division is completed, the local collection nodes and cloud collection nodes divided by the growth stage are numbered, starting from 1 and continuing in sequence.

8. The insect pest sound and light control system according to claim 7, characterized in that: The steps of performing pest identification on the pest identification atlas to obtain the pest identification result data of the node number are as follows: S11: If the node number corresponds to a local collection node, a pest identification model corresponding to the local collection node corresponding to the node number is obtained, the pest identification atlas is used as an input of the pest identification model, and the pest identification model is used to identify the pests to obtain pest identification result data of the node number; S12: If the node number corresponds to a cloud collection node, the pest identification atlas is transmitted to the cloud pest identification unit. After receiving the transmitted pest identification atlas, the cloud pest identification unit inputs it into the crop pest identification model to obtain the pest identification result data of the node number.

9. The pest sound and light control system according to claim 7, characterized in that: The steps of determining the node number of the image data are as follows: Acquiring, in the pest branch identification module, the collection duration and digital numbers of several local collection nodes and the collection duration and digital numbers of several cloud collection nodes of the crop at the growth stage; Then, all image data corresponding to the growth stage currently stored in the pest branch identification module are obtained, and all the acquired image data are sorted from left to right according to the order of the acquisition time of the image data. If the sum Z1 of the image data before the image data after sorting satisfies Y1+Y2+...+Yy1≤Z1≤Y1+Y2+...+Yy1+1, then the node number of the image data is determined to be y1+1, where Y1, Y2, ..., Yy1 are the acquisition time of the local acquisition nodes or cloud acquisition nodes corresponding to the digital numbers 1, 2, ..., y1, and Yy1+1, respectively.

10. A method for controlling pests with sound and light, characterized in that: The following steps are involved: Step 1: After receiving the real-time image data of the planting area, the identification atlas generation unit identifies the growth characteristics of the crops in the image data to determine that the image data corresponds to the growth stage of the crops, and determines the node number of the image data by determining that the image data corresponds to the growth stage of the crops and the acquisition time corresponding to the image data; Step 2: When the sum of the acquisition time of all the image data of the planting area stored therein is consistent with the acquisition time of the local acquisition node or the cloud acquisition node corresponding to the node number of any image data among all the image data, the identification atlas generation unit generates an insect pest identification atlas of the node number according to all the image data of the planting area stored therein, and transmits it to the local branch identification unit; Step 3: After receiving the pest identification atlas of the node number, the local branch identification unit performs pest identification on the pest identification atlas according to the preset identification steps to obtain the pest identification result data of the node number, wherein the pest identification result data includes an identification signal, and the identification signal selects one from the numbers 1 and 0. When the identification signal is 1, the pest identification result data also includes several pest types; when the identification signal is 1, the pest identification result data is transmitted to the sound and light prevention and control response module; Step 4: After receiving the pest identification result data with an identification signal of 1, the sound and light control response module obtains the corresponding sound and light control strategy according to the several pest types contained in the pest identification result data and adjusts the sound and light control of the planting area according to the sound and light control strategy.

Images