Intelligent agricultural product pest and disease damage diagnosis system and method based on Internet of Things

Abstract

The invention discloses a smart agricultural product pest diagnosis system and method based on the Internet of Things, and relates to the technical field of smart agricultural products. The method aims to solve the problems that crop diseases and insect pests are various, and the recognition effect on rare or newly appearing diseases and insect pests is possibly poor. The intelligent agricultural product disease and pest diagnosis system based on the Internet of Things comprises an image acquisition unit, a feature extraction unit, a diagnosis decision unit and a remote interaction unit, the image acquisition unit captures crop growth environment and pest and disease damage image data in real time through a camera and sensors deployed in a farmland, the timeliness of pest and disease damage diagnosis is ensured, the feature extraction unit realizes intelligent processing of pest and disease damage images by establishing a pest and disease damage feature database and constructing a key feature recognition model, and the accuracy of pest and disease damage diagnosis is improved. The remote interaction unit improves the convenience of a user, reduces the cost of manual inspection and diagnosis, improves the production efficiency of agricultural products, and improves the yield and quality of crops.

Description

Technical Field

[0001] The present invention relates to the technical field of smart agricultural products, and in particular to a smart agricultural product disease and insect pest diagnosis system and method based on the Internet of Things. Background Art

[0002] Traditional agricultural products have many problems in pest control, such as waste of resources, environmental pollution, low production efficiency, etc. Traditional pest monitoring methods often rely on manual inspections and empirical judgments, which are not only time-consuming and labor-intensive, but also prone to misjudgment. With the rapid development of Internet of Things technology, smart agricultural products have become an important way to solve these problems.

[0003] Now, regarding the intelligent agricultural product pest diagnosis system, the patent application with publication number: CN116524321A discloses a method and system for intelligent diagnosis of crop pests and diseases, including the steps of: obtaining pest images and pest characteristic information; preprocessing the pest images to obtain preprocessed pest images; inputting the preprocessed pest images and the pest characteristic information into a trained crop pest diagnosis model, and obtaining crop pest diagnosis results through the crop pest diagnosis model. By preprocessing the acquired pest images, and then using the trained crop pest diagnosis model to diagnose the preprocessed pest images and pest characteristic information, the crop pest diagnosis results are obtained, and standardized and accurate diagnosis of crop pests and diseases is achieved, which can effectively prevent crop pests and diseases and provide users with major practical guidance for further implementing pest control work.

[0004] Although the above patents use IoT sensors, big data analysis, cloud computing and other technologies to achieve real-time monitoring and data analysis of the crop growth environment, providing a scientific basis for the precise prevention and control of pests and diseases, the following problems still exist:

[0005] There are many types of crop diseases and pests, and they are affected by many factors such as region, climate, and season. Model training has only been conducted for some common diseases and pests. The identification effect may be poor for rare or newly emerging diseases and pests, and it is impossible to ensure the real-time diagnosis of diseases and pests while maintaining a high diagnostic accuracy. Summary of the invention

[0006] The purpose of the present invention is to provide an intelligent agricultural product disease and pest diagnosis system and method based on the Internet of Things, by building a comprehensive disease and pest feature database, training high-quality diagnostic models, improving the comprehensiveness and accuracy of the diagnostic system, real-time monitoring and rapid diagnosis of diseases and pests, and effectively improving the prevention and control efficiency, so as to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The smart agricultural product pest and disease diagnosis system based on the Internet of Things includes:

[0009] Image acquisition unit, used to deploy cameras and sensors in farmland to capture crop growth environment and pest image data in real time;

[0010] A feature extraction unit is used to establish a pest and disease feature database, build a key feature recognition model based on the pest and disease feature database, and process the collected pest and disease images to extract key features in the pest and disease images based on the key feature recognition model;

[0011] A diagnosis decision unit, which is used to construct a pest and disease diagnosis model based on the extracted key features, identify and diagnose the types of pests and diseases on crops based on the pest and disease diagnosis model, determine the pest and disease diagnosis results, and send the real-time acquired image data and the pest and disease diagnosis results to the remote interaction unit based on the Internet of Things;

[0012] The remote interaction unit is used to build a data interaction channel with the remote terminal, and display the pest and disease diagnosis results, occurrence location and prevention and control suggestions on the remote terminal based on the data interaction channel; at the same time, users can view historical diagnosis records based on the interactive interface and receive real-time warnings.

[0013] Furthermore, the image acquisition unit comprises:

[0014] Environmental parameter acquisition module, used to collect environmental parameters in farmland in real time based on various sensors, including temperature and humidity data, light intensity data and soil moisture data;

[0015] Image acquisition module, used to capture the growth status and pest image data of crops in real time based on the camera;

[0016] The data preprocessing module is used to clean and verify the integrity of the data collected from the environmental parameter acquisition module and the image acquisition module, and transmit the preprocessed data to the feature extraction unit based on the packaged generated data set.

[0017] Furthermore, the image acquisition module includes:

[0018] An image capture control module is used to control the camera to capture the growth status and pest image data of crops in real time, and use the growth status and pest image data as target image data;

[0019] An image segmentation module, used to segment the target image data to obtain a plurality of image blocks corresponding to the target image data;

[0020] A gray value extraction module, used for extracting the gray value of the pixel block contained in each image block;

[0021] A gray balance coefficient acquisition module is used to acquire the gray balance coefficient corresponding to each image block according to the gray value of the pixel block contained in each image block; wherein the gray balance coefficient is acquired by the following formula:

[0022]

[0023] Where K represents the gray balance coefficient corresponding to each image block; n represents the number of pixel blocks contained in each image block; S i Represents the grayscale value of the i-th pixel block; S z Indicates the central gray value corresponding to each image block; S h Indicates the central gray value corresponding to the target image data;

[0024] A difference acquisition module is used to compare the gray balance coefficients of every two adjacent image blocks to obtain the difference corresponding to the gray balance coefficients;

[0025] A comparison module, used for comparing the difference value corresponding to the gray balance coefficient with a preset difference threshold value;

[0026] The grayscale adjustment module is used to adjust the grayscale of the two adjacent image blocks corresponding to the grayscale balance coefficients exceeding the preset difference threshold when the difference corresponding to the grayscale balance coefficients of each two adjacent image blocks exceeds the preset difference threshold.

[0027] Furthermore, the grayscale adjustment module includes:

[0028] An image block extraction module, configured to extract two adjacent image blocks corresponding to which the difference value corresponding to the gray balance coefficient exceeds the preset difference threshold value when the difference value corresponding to the gray balance coefficient of each two adjacent image blocks exceeds a preset difference threshold value;

[0029] An image block marking module, used for marking two adjacent image blocks corresponding to which the difference corresponding to the gray balance coefficient exceeds a preset difference threshold as a first image block and a second image block;

[0030] The first target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the first image block by using the grayscale balance coefficient of the first image block; wherein the target grayscale value of each pixel block included in the first image block is obtained by the following formula:

[0031]

[0032] Among them, S m01 represents the target grayscale value of each pixel block included in the first image block; S 01 represents the gray value of each pixel block contained in the first image block; K 01represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 01 Indicates the first digit parameter; at the same time, the value of the first digit parameter is as follows:

[0033] when and When the sign of is the same, let s 01 =-1; when and When the positive and negative are different, let s 01 =1;

[0034] A first grayscale adjustment execution module, used for adjusting each pixel block included in the first image block according to a target grayscale value of each pixel block included in the first image block;

[0035] The second target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the second image block by using the grayscale balance coefficient of the second image block; wherein the target grayscale value of each pixel block included in the second image block is obtained by the following formula:

[0036]

[0037] Among them, S m02 represents the target grayscale value of each pixel block included in the second image block; S 02 represents the gray value of each pixel block contained in the second image block; K 01 represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 02 Indicates the second digit parameter; at the same time, the value of the first digit parameter is as follows:

[0038] when and When the sign of is the same, let s 02 =-1; when and When the positive and negative are different, let s 01 =1;

[0039] The second grayscale adjustment execution module is used to adjust each pixel block included in the second image block according to the target grayscale value of each pixel block included in the second image block.

[0040] Furthermore, the feature extraction unit comprises:

[0041] The database construction module is used to crawl and store professional data of known pests and diseases based on the Internet of Things, including images, feature descriptions, occurrence conditions, and information data of pests and diseases, and to build a pest and disease feature database based on the crawled professional data;

[0042] The recognition model building module is used to extract features based on the professional data in the pest and disease feature database as sample data, extract the features of the sample data and the corresponding pest and disease labels as training data and input them into the preset model to build a key feature recognition model;

[0043] The feature extraction module is used to extract the key features of pests and diseases from the data set based on the key feature recognition model, and to extract the environmental features of the agricultural products in the data set.

[0044] Furthermore, the recognition model building module builds a key feature recognition model, specifically:

[0045] Classify and integrate the professional data of the known pests and diseases to obtain the processed classified data, perform feature extraction on the processed classified data, and obtain an initial feature set of the classified data according to the extraction result;

[0046] Retrieving key features related to pests and diseases from the initial feature set and integrating them into a key feature subset;

[0047] Obtaining time series data of each key feature in the key feature subset, determining the target feature corresponding to the time series data, and determining the first feature of each pest according to the target feature of each key feature;

[0048] Obtaining the change of target characteristics of each pest in crops, and determining the characteristic change rule of each pest according to the change;

[0049] Pests and diseases with feature change rule similarity greater than or equal to a preset threshold are identified as the same type of pests and diseases, and the second feature of any pest and disease in each type of pest and disease is identified as the final target feature of that type of pest and disease;

[0050] The final target features of this type of pests and diseases are used as the model input samples, and the characteristic information of each pest and disease is used as the model output sample to train the preset network model to obtain the recognition model of each type of pest and disease.

[0051] Furthermore, the feature extraction module further includes:

[0052] The extracted key features are screened according to the environmental characteristics of agricultural products, and the key features that are significantly affected by environmental characteristics and have a correlation with the occurrence of diseases and pests are extracted;

[0053] Adjusting the weight of the key feature in the pest and disease identification model according to the degree to which the key feature is affected by the environmental feature and the closeness of the correlation relationship;

[0054] The pest and disease identification model is optimized based on the influence of agricultural product environmental characteristics on the key characteristics of pests and diseases and the weight of the key characteristics in the pest and disease identification model;

[0055] At the same time, the environmental adaptability of the extracted key features is analyzed to determine the occurrence patterns and changing trends of pests and diseases under different environmental conditions. At the same time, the occurrence trends of future pests and diseases are predicted based on the occurrence patterns and changing trends.

[0056] Furthermore, the diagnosis decision unit includes:

[0057] The feature diagnosis module is used to diagnose pests and diseases based on the extracted key features, and determine the type of pests and diseases, the degree of impact on crops, and the scope of impact based on the diagnosis results;

[0058] The characteristic diagnosis module is also used to obtain the abnormal situation data of the abnormality detection module and determine whether the abnormal situation data is a rare or newly emerging pest and disease characteristic;

[0059] Anomaly detection module, which is used to detect anomalies of crops with key characteristics that are free of pests and diseases, and identify anomalies that do not conform to normal growth patterns;

[0060] The control plan management module is used to match the corresponding pest and disease control plan based on the diagnosis results and abnormal situation data, evaluate the control results of the pest and disease control plan, and generate feedback data based on the evaluation results.

[0061] Furthermore, the control scheme management module matches the corresponding pest control scheme, specifically:

[0062] Determine the pest and disease level of the crop based on the diagnosis results and abnormal situation data, and build a pest and disease control plan corresponding to the crop category based on the pest and disease level of the crop;

[0063] Among them, the specific measures of the pest control plan include source control measures, pest control process measures and terminal control measures;

[0064] Analyze pest and disease control programs and determine the priority of the pest and disease control programs;

[0065] Corresponding crop management personnel are assigned based on the specific measures of the pest control plan, and the crop management personnel execute the specific measures of the pest control plan based on the priority of the pest control plan.

[0066] The present invention provides another technical solution, a smart agricultural product pest and disease diagnosis method based on the Internet of Things, comprising the following steps:

[0067] Step 1: Data collection: The camera and sensor network deployed in the farmland collects crop growth environment and pest image data in real time;

[0068] Step 2: Data processing: Process the collected pest and disease images and extract the key features in the pest and disease images based on the constructed key feature recognition model;

[0069] Step 3: Intelligent diagnosis and decision-making: Real-time diagnosis of key feature inputs, and generation of pest and disease diagnosis reports and pest and disease control plans;

[0070] Step 4: Result display and early warning: Display the pest diagnosis report and pest control plan to the user through the user interface, and send early warning information to the remote terminal;

[0071] Step 5: Database query and prevention and control suggestions: Users query the pest and disease feature database based on the acquired abnormal image data and the diagnosis results, identify rare and newly emerging pests and diseases, and generate corresponding pest and disease control methods and suggestions.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] The image acquisition unit captures crop growth environment and pest image data in real time through cameras and sensors deployed in farmland, ensuring the timeliness of pest diagnosis. The feature extraction unit realizes intelligent processing of pest images by establishing a pest feature database and building a key feature recognition model, identifying and diagnosing a variety of pest types, including rare or newly emerging pests and diseases. With the continuous addition of new data, the diagnosis model is adaptively updated and optimized to improve its adaptability and accuracy. The remote interaction unit builds a data interaction channel with the remote terminal, allowing users to view pest diagnosis results, occurrence locations and prevention and control recommendations through the remote terminal anywhere, improving user convenience, timely obtaining professional pest control knowledge and help, improving users' response capabilities, reducing the cost of manual inspections and diagnosis, improving agricultural product production efficiency, increasing crop yield and quality, and reducing the impact of pests and diseases on crops. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1This is a module diagram of the smart agricultural product disease and insect pest diagnosis system based on the Internet of Things of the present invention;

[0075] Figure 2 This is a flow chart of the smart agricultural product disease and insect pest diagnosis method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In order to solve the technical problem that crop pests and diseases are diverse and are affected by multiple factors such as region, climate, season, etc., only some common pests and diseases are trained. The recognition effect may be poor for rare or newly emerging pests and diseases, and it is impossible to ensure the real-time diagnosis of pests and diseases while maintaining a high diagnostic accuracy. Please refer to Figure 1 , this embodiment provides the following technical solutions:

[0078] The smart agricultural product pest and disease diagnosis system based on the Internet of Things includes:

[0079] Image acquisition unit, used to deploy cameras and sensors in farmland, such as temperature and humidity sensors, light sensors, soil moisture sensors, etc., to capture crop growth environment and pest image data in real time, including:

[0080] Environmental parameter acquisition module, used to collect environmental parameters in farmland in real time based on various sensors, including temperature and humidity data, light intensity data and soil moisture data;

[0081] Image acquisition module, used to capture the growth status and pest image data of crops in real time based on the camera;

[0082] The data preprocessing module is used to clean and verify the integrity of the data collected from the environmental parameter acquisition module and the image acquisition module, and transmit the preprocessed data to the feature extraction unit based on the packaged data set to improve the accuracy and reliability of the data and provide a high-quality data foundation for subsequent data analysis and decision support;

[0083] The feature extraction unit is used to establish a pest and disease feature database, including images, feature descriptions, occurrence conditions, and control methods of known pests and diseases, and to build a key feature recognition model based on the pest and disease feature database to provide training data and reference basis for the diagnosis model. At the same time, the collected pest and disease images are processed, including denoising, contrast enhancement, image segmentation, etc., to improve image quality and facilitate subsequent analysis. Key features in the pest and disease images, such as shape, color, texture, etc., are extracted based on the key feature recognition model;

[0084] A diagnosis decision unit, which is used to construct a pest and disease diagnosis model based on the extracted key features, identify and diagnose the types of pests and diseases on crops based on the pest and disease diagnosis model, determine the pest and disease diagnosis results, and send the real-time acquired image data and the pest and disease diagnosis results to the remote interaction unit based on the Internet of Things;

[0085] The remote interaction unit is used to build a data interaction channel with the remote terminal, and display the pest and disease diagnosis results, occurrence location and prevention and control suggestions on the remote terminal based on the data interaction channel; at the same time, users can view historical diagnosis records based on the interactive interface and receive real-time warnings. The remote terminal can provide a rich pest and disease control knowledge base and detailed help documents to help users better understand and deal with pest and disease problems.

[0086] In this embodiment, the image acquisition unit captures the crop growth environment and pest and disease image data in real time through cameras and sensors deployed in the farmland, ensuring the timeliness of pest and disease diagnosis. The feature extraction unit realizes intelligent processing of pest and disease images by establishing a pest and disease feature database and constructing a key feature recognition model, and identifies and diagnoses a variety of pest and disease types, including rare or newly emerging pests and diseases. As new data is continuously added, the diagnosis model is adaptively updated and optimized to improve its adaptability and accuracy. The remote interaction unit constructs a data interaction channel with the remote terminal, allowing users to view pest and disease diagnosis results, occurrence locations and prevention and control recommendations through the remote terminal at any place, thereby improving user convenience, timely obtaining professional pest and disease control knowledge and help, improving user response capabilities, reducing the cost of manual inspections and diagnosis, improving agricultural product production efficiency, increasing crop yield and quality, and reducing the impact of pests and diseases on crops.

[0087] Specifically, the image acquisition module includes:

[0088] An image capture control module is used to control the camera to capture the growth status and pest image data of crops in real time, and use the growth status and pest image data as target image data;

[0089] An image segmentation module, used to segment the target image data to obtain a plurality of image blocks corresponding to the target image data;

[0090] A gray value extraction module, used for extracting the gray value of the pixel block contained in each image block;

[0091] A gray balance coefficient acquisition module is used to acquire the gray balance coefficient corresponding to each image block according to the gray value of the pixel block contained in each image block; wherein the gray balance coefficient is acquired by the following formula:

[0092]

[0093] Where K represents the gray balance coefficient corresponding to each image block; n represents the number of pixel blocks contained in each image block; S i Represents the grayscale value of the i-th pixel block; S z Indicates the central gray value corresponding to each image block; S h Indicates the central gray value corresponding to the target image data;

[0094] A difference acquisition module is used to compare the gray balance coefficients of every two adjacent image blocks to obtain the difference corresponding to the gray balance coefficients;

[0095] A comparison module, used for comparing the difference value corresponding to the gray balance coefficient with a preset difference threshold value;

[0096] The grayscale adjustment module is used to adjust the grayscale of the two adjacent image blocks corresponding to the grayscale balance coefficients exceeding the preset difference threshold when the difference corresponding to the grayscale balance coefficients of each two adjacent image blocks exceeds the preset difference threshold.

[0097] The technical effect of the above technical solution is: through the image capture control module, the growth status of crops and pest image data can be captured in real time, providing an accurate data basis for subsequent image analysis and processing. The image segmentation module divides the target image data into multiple image blocks, which facilitates the subsequent independent processing and analysis of each image block, thereby improving processing efficiency.

[0098] The gray value extraction module and the gray balance coefficient acquisition module work together to accurately extract the gray value of each image block and calculate the corresponding gray balance coefficient, providing a basis for subsequent gray adjustment. Through the joint action of the difference acquisition module, the comparison module and the gray adjustment module, the image blocks with unbalanced grayscale can be intelligently identified, and the corresponding grayscale adjustment can be performed to make the grayscale of the entire image more uniform, thereby improving the quality and analyzability of the image. Through the processing of the above technical solution, the growth status of crops and the image data of pests and diseases can be made clearer and more accurate, thereby improving the accuracy of pest and disease recognition and providing more powerful technical support for agricultural production.

[0099] In summary, this technical solution effectively improves the quality and analysis efficiency of crop growth status and pest and disease image data through a series of steps such as real-time capture, precise segmentation, grayscale value extraction and balance, and intelligent adjustment, providing more intelligent and precise technical support for agricultural production.

[0100] Specifically, the grayscale adjustment module includes:

[0101] An image block extraction module, configured to extract two adjacent image blocks corresponding to which the difference value corresponding to the gray balance coefficient exceeds the preset difference threshold value when the difference value corresponding to the gray balance coefficient of each two adjacent image blocks exceeds a preset difference threshold value;

[0102] An image block marking module, used for marking two adjacent image blocks corresponding to which the difference corresponding to the gray balance coefficient exceeds a preset difference threshold as a first image block and a second image block;

[0103] The first target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the first image block by using the grayscale balance coefficient of the first image block; wherein the target grayscale value of each pixel block included in the first image block is obtained by the following formula:

[0104]

[0105] Among them, S m01 represents the target grayscale value of each pixel block included in the first image block; S 01 represents the gray value of each pixel block contained in the first image block; K 01 represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 01 Indicates the first digit parameter; at the same time, the value of the first digit parameter is as follows:

[0106] when and When the sign of is the same, let s 01 =-1; when and When the positive and negative are different, let s 01 =1;

[0107] A first grayscale adjustment execution module, used for adjusting each pixel block included in the first image block according to a target grayscale value of each pixel block included in the first image block;

[0108] The second target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the second image block by using the grayscale balance coefficient of the second image block; wherein the target grayscale value of each pixel block included in the second image block is obtained by the following formula:

[0109]

[0110] Among them, S m02 represents the target grayscale value of each pixel block included in the second image block; S 02 represents the gray value of each pixel block contained in the second image block; K 01 represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 02 Indicates the second digit parameter; at the same time, the value of the first digit parameter is as follows:

[0111] when and When the sign of is the same, let s 02 =-1; when and When the positive and negative are different, let s 01 =1;

[0112] The second grayscale adjustment execution module is used to adjust each pixel block included in the second image block according to the target grayscale value of each pixel block included in the second image block.

[0113] The technical effect of the above technical solution is: through the image block extraction module, the adjacent image blocks with grayscale imbalance can be accurately identified, providing accurate positioning for subsequent grayscale adjustment. Using the first target grayscale value acquisition module and the second target grayscale value acquisition module, the target grayscale value of each pixel block in two adjacent image blocks can be calculated respectively, realizing accurate adjustment of grayscale imbalance.

[0114] When calculating the target grayscale value, the first digit parameter and the second digit parameter are introduced. The value selection principle of these two parameters takes into account the difference between the grayscale balance coefficient and the center grayscale value, making the grayscale adjustment more intelligent and accurate. Through the grayscale adjustment execution module, each pixel block in the image block can be adjusted according to the calculated target grayscale value, making the grayscale of the entire image more uniform, improving the quality and analyzability of the image. The image after grayscale adjustment is clearer, and the characteristics of pests and diseases are more obvious, which helps to improve the accuracy of pest and disease identification and provide more powerful technical support for agricultural production. Through modular design, each module undertakes specific tasks, making the entire grayscale adjustment process more efficient and orderly.

[0115] In summary, this technical solution provides more intelligent and precise technical support for image analysis and processing in agricultural production through a series of advantages such as precise grayscale adjustment, intelligent parameter selection, improved image quality, enhanced pest and disease identification capabilities, and improved processing efficiency.

[0116] In this embodiment, the feature extraction unit includes:

[0117] The database construction module is used to crawl and store professional data of known pests and diseases based on the Internet of Things, including images, feature descriptions, occurrence conditions, and information data of pests and diseases, and to build a pest and disease feature database based on the crawled professional data;

[0118] The recognition model building module is used to extract features based on the professional data in the pest and disease feature database as sample data, extract the features of the sample data and the corresponding pest and disease labels as training data and input them into the preset model to build a key feature recognition model;

[0119] A feature extraction module is used to extract key features of pests and diseases from the data set based on a key feature recognition model, and to extract environmental features of agricultural products in the data set, and further includes:

[0120] The extracted key features are screened according to the environmental characteristics of agricultural products, and the key features that are significantly affected by environmental characteristics and have a correlation with the occurrence of diseases and pests are extracted;

[0121] The weight of the key features in the pest and disease identification model is adjusted according to the degree to which the key features are affected by environmental features and the closeness of the correlation relationship, thereby realizing the intelligence and adaptability of the model;

[0122] The pest and disease identification model is optimized based on the influence of agricultural product environmental characteristics on the key characteristics of pests and diseases and the weight of the key characteristics in the pest and disease identification model;

[0123] At the same time, the environmental adaptability of the extracted key features is analyzed to determine the occurrence patterns and changing trends of pests and diseases under different environmental conditions. At the same time, the occurrence trends of future pests and diseases are predicted based on the occurrence patterns and changing trends.

[0124] In this embodiment, extensive and in-depth professional data on known pests and diseases are crawled and stored through the Internet of Things technology, ensuring the accuracy and richness of the pest and disease feature database, laying a solid foundation for subsequent feature extraction and model training. The recognition model construction module not only improves the accuracy of the model, but also enables the model to identify a variety of pests and diseases, including rare or newly emerging pests and diseases. While extracting the key features of pests and diseases, it also considers the impact of agricultural product environmental characteristics on the occurrence of pests and diseases. The occurrence of future pests and diseases is predicted based on the occurrence patterns and changing trends, providing farmers with timely prevention and control suggestions, reducing the impact of pests and diseases on crops, and comprehensively considering the environmental characteristics of agricultural products and the key features of pests and diseases to more accurately diagnose pests and diseases, reduce false alarms and omissions, and improve diagnostic efficiency.

[0125] In this embodiment, the recognition model construction module constructs a key feature recognition model, specifically:

[0126] Classify and integrate the professional data of the known pests and diseases to obtain the processed classified data, perform feature extraction on the processed classified data, and obtain an initial feature set of the classified data according to the extraction result;

[0127] Retrieving key features related to pests and diseases from the initial feature set and integrating them into a key feature subset;

[0128] Obtaining time series data of each key feature in the key feature subset, determining the target feature corresponding to the time series data, and determining the first feature of each pest according to the target feature of each key feature;

[0129] Obtaining the change of target characteristics of each pest in crops, and determining the characteristic change rule of each pest according to the change;

[0130] Identifying pests and diseases with feature change rule similarity greater than or equal to a preset threshold as the same type of pests and diseases helps to simplify the complexity of the model, and identifying the second feature of any pest and disease in each type of pest and disease as the final target feature of that type of pest and disease;

[0131] The final target features of this type of pests and diseases are used as the model input samples, and the characteristic information of each pest and disease is used as the model output sample to train the preset network model to obtain the recognition model of each type of pest and disease.

[0132] In this embodiment, through classification processing, key features related to pests and diseases can be extracted more effectively, providing a high-quality data basis for the construction of subsequent models, and key features related to pests and diseases are retrieved from the initial feature set and integrated into a key feature subset, which not only improves the efficiency of feature extraction, but also ensures the comprehensiveness and representativeness of key features. The feature change rules determined by analyzing the changes in pests and diseases in crops can more truly reflect the biological characteristics and occurrence laws of pests and diseases, ensuring that the identification model of each type of pests and diseases can more accurately identify different manifestations of the same type of pests and diseases, thereby improving the recognition accuracy of the model. Moreover, since the model is trained based on data from multiple types of pests and diseases, it also has a strong generalization ability and can identify new or unknown pests and diseases.

[0133] In this embodiment, the diagnosis decision unit includes:

[0134] The feature diagnosis module is used to diagnose pests and diseases based on the extracted key features, and determine the type of pests and diseases, the degree of impact on crops, and the scope of impact based on the diagnosis results;

[0135] The characteristic diagnosis module is also used to obtain the abnormal situation data of the abnormality detection module and determine whether the abnormal situation data is a rare or newly emerging pest and disease characteristic;

[0136] Anomaly detection module, which is used to detect anomalies of crops with key characteristics that are free of pests and diseases, and identify anomalies that are inconsistent with normal growth patterns, including sudden changes in crop color, slowed growth, and leaf wilting;

[0137] A control plan management module is used to match the corresponding pest and disease control plan based on the diagnosis results and abnormal situation data, evaluate the control results of the pest and disease control plan, and generate feedback data based on the evaluation results;

[0138] In this embodiment, the control scheme management module matches the corresponding pest control scheme, specifically:

[0139] Determine the pest and disease level of the crop based on the diagnosis results and abnormal situation data, and build a pest and disease control plan corresponding to the crop category based on the pest and disease level of the crop;

[0140] Among them, the specific measures of the pest control plan include source control measures, pest control process measures and terminal control measures;

[0141] Analyze pest and disease control programs and determine the priority of the pest and disease control programs;

[0142] Corresponding crop management personnel are assigned based on the specific measures of the pest control plan. The crop management personnel execute the specific measures of the pest control plan based on the priority of the pest control plan. By assigning crop management personnel and executing specific control measures, efficient coordination between various links can be achieved, which not only improves the control efficiency, but also ensures the effective implementation of the control measures.

[0143] In this embodiment, the feature diagnosis module can accurately extract the key features of pests and diseases, and diagnose pests and diseases based on these features. It can not only quickly determine the types of pests and diseases, but also evaluate the degree and scope of their impact on crops, identify rare or newly emerging pest and disease characteristics, and provide the possibility for timely response. The abnormal detection module can monitor the growth status of crops and promptly detect abnormal conditions that are inconsistent with the normal growth pattern and issue timely warnings to prevent the spread of pests and diseases and the loss of crop yields. It not only takes into account the types and levels of pests and diseases, but also combines the specific conditions and growth environment of crops. By assigning crop management personnel and implementing specific control measures, scientific control of pests and diseases is achieved to ensure the healthy growth of crops and the stable increase in yields.

[0144] In order to better demonstrate the realization of smart agricultural product pest and disease diagnosis system based on the Internet of Things, please refer to Figure 2 The present invention provides another smart agricultural product pest and disease diagnosis method based on the Internet of Things, comprising the following steps:

[0145] Step 1: Data collection: The camera and sensor network deployed in the farmland collects crop growth environment and pest image data in real time;

[0146] Step 2: Data processing: Process the collected pest and disease images and extract the key features in the pest and disease images based on the constructed key feature recognition model;

[0147] Step 3: Intelligent diagnosis and decision-making: Real-time diagnosis of key feature inputs, and generation of pest and disease diagnosis reports and pest and disease control plans;

[0148] Step 4: Result display and early warning: Display the pest diagnosis report and pest control plan to the user through the user interface, and send early warning information to the remote terminal;

[0149] Step 5: Database query and prevention and control suggestions: Users query the pest and disease feature database based on the acquired abnormal image data and the diagnosis results, identify rare and newly emerging pests and diseases, and generate corresponding pest and disease control methods and suggestions.

[0150] In this embodiment, through real-time data collection of integrated cameras and sensor networks, image features are processed and identified, and pest and disease diagnosis and decision-making are carried out accurately and quickly. At the same time, user-friendly database query and prevention and control suggestion functions are provided, which significantly improves the efficiency and accuracy of crop pest and disease management, reduces production costs, protects the ecological environment, and enhances farmers' ability to cope with pests and diseases, providing strong support for the sustainable development of agricultural product production.

[0151] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The smart agricultural product pest and disease diagnosis system based on the Internet of Things is characterized by: include: Image acquisition unit, used to deploy cameras and sensors in farmland to capture crop growth environment and pest image data in real time; A feature extraction unit is used to establish a pest and disease feature database, build a key feature recognition model based on the pest and disease feature database, and process the collected pest and disease images to extract key features in the pest and disease images based on the key feature recognition model; A diagnosis decision unit is used to build a pest and disease diagnosis model based on the extracted key features, identify and diagnose the types of pests and diseases on crops based on the pest and disease diagnosis model, determine the pest and disease diagnosis results, and send the real-time acquired image data and pest and disease diagnosis results to the remote interaction unit based on the Internet of Things; The remote interaction unit is used to build a data interaction channel with the remote terminal, and display the pest and disease diagnosis results, occurrence location and prevention and control suggestions on the remote terminal based on the data interaction channel; at the same time, users can view historical diagnosis records based on the interactive interface and receive real-time warnings.

2. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 1, characterized in that: Image acquisition unit, comprising: Environmental parameter acquisition module, used to collect environmental parameters in farmland in real time based on various sensors, including temperature and humidity data, light intensity data and soil moisture data; Image acquisition module, used to capture the growth status and pest image data of crops in real time based on the camera; The data preprocessing module is used to clean and verify the integrity of the data collected from the environmental parameter acquisition module and the image acquisition module, and transmit the preprocessed data to the feature extraction unit based on the packaged generated data set.

3. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 2, characterized in that: Image acquisition module, including: An image capture control module is used to control the camera to capture the growth status and pest image data of crops in real time, and use the growth status and pest image data as target image data; An image segmentation module, used to segment the target image data to obtain a plurality of image blocks corresponding to the target image data; A gray value extraction module, used for extracting the gray value of the pixel block contained in each image block; A gray balance coefficient acquisition module is used to acquire the gray balance coefficient corresponding to each image block according to the gray value of the pixel block contained in each image block; wherein the gray balance coefficient is acquired by the following formula: Where K represents the gray balance coefficient corresponding to each image block; n represents the number of pixel blocks contained in each image block; S i Represents the grayscale value of the i-th pixel block; S z Indicates the central gray value corresponding to each image block; S h Indicates the central gray value corresponding to the target image data; A difference acquisition module is used to compare the gray balance coefficients of every two adjacent image blocks to obtain the difference corresponding to the gray balance coefficients; A comparison module, used for comparing the difference value corresponding to the gray balance coefficient with a preset difference value threshold; The grayscale adjustment module is used to adjust the grayscale of the two adjacent image blocks exceeding the preset difference threshold when the difference corresponding to the grayscale balance coefficients of each two adjacent image blocks exceeds the preset difference threshold.

4. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 3, characterized in that: Grayscale adjustment module, including: An image block extraction module, configured to extract two adjacent image blocks corresponding to which the difference value corresponding to the gray balance coefficient exceeds the preset difference threshold value when the difference value corresponding to the gray balance coefficient of each two adjacent image blocks exceeds a preset difference threshold value; An image block marking module, used for marking two adjacent image blocks corresponding to which the difference corresponding to the gray balance coefficient exceeds a preset difference threshold as a first image block and a second image block; The first target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the first image block by using the grayscale balance coefficient of the first image block; wherein the target grayscale value of each pixel block included in the first image block is obtained by the following formula: Among them, S m01 represents the target grayscale value of each pixel block included in the first image block; S 01 represents the gray value of each pixel block contained in the first image block; K 01 represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 01 Indicates the first digit parameter; at the same time, the value principle of the first digit parameter is as follows: when and When the sign of is the same, let s 01 =-1; when and When the positive and negative are different, let s 01 =1; A first grayscale adjustment execution module, used for adjusting each pixel block included in the first image block according to a target grayscale value of each pixel block included in the first image block; The second target grayscale value acquisition module is used to obtain the target grayscale value of each pixel block included in the second image block by using the grayscale balance coefficient of the second image block; wherein the target grayscale value of each pixel block included in the second image block is obtained by the following formula: Among them, S m02 represents the target grayscale value of each pixel block included in the second image block; S 02 represents the gray value of each pixel block contained in the second image block; K 01 represents the gray balance coefficient corresponding to the first image block; K 02 represents the gray balance coefficient corresponding to the second image block; S 01z represents the central gray value corresponding to the first image block; S 02z represents the central gray value corresponding to the second image block; S h Indicates the central gray value corresponding to the target image data; s 02 Indicates the second digit parameter; at the same time, the value of the first digit parameter is as follows: when and When the sign of is the same, let s 02 =-1; when and When the positive and negative are different, let s 01 =1; The second grayscale adjustment execution module is used to adjust each pixel block included in the second image block according to the target grayscale value of each pixel block included in the second image block.

5. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 2, characterized in that: Feature extraction unit, including: The database construction module is used to crawl and store professional data of known pests and diseases based on the Internet of Things, including images, feature descriptions, occurrence conditions, and information data of pests and diseases, and to build a pest and disease feature database based on the crawled professional data; The recognition model building module is used to extract features based on the professional data in the pest and disease feature database as sample data, extract the features of the sample data and the corresponding pest and disease labels as training data and input them into the preset model to build a key feature recognition model; The feature extraction module is used to extract the key features of pests and diseases from the data set based on the key feature recognition model, and to extract the environmental features of the agricultural products in the data set.

6. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 5, characterized in that: The recognition model building module builds a key feature recognition model, specifically: Classify and integrate the professional data of the known pests and diseases to obtain the processed classified data, perform feature extraction on the processed classified data, and obtain an initial feature set of the classified data according to the extraction result; Retrieving key features related to pests and diseases from the initial feature set and integrating them into a key feature subset; Obtaining time series data of each key feature in the key feature subset, determining the target feature corresponding to the time series data, and determining the first feature of each pest according to the target feature of each key feature; Obtaining the change of target characteristics of each pest in crops, and determining the characteristic change rule of each pest according to the change; Pests and diseases with feature change rule similarity greater than or equal to a preset threshold are identified as the same type of pests and diseases, and the second feature of any pest and disease in each type of pest and disease is identified as the final target feature of that type of pest and disease; The final target features of this type of pests and diseases are used as the model input samples, and the characteristic information of each pest and disease is used as the model output sample to train the preset network model to obtain the recognition model of each type of pest and disease.

7. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 6, characterized in that: The feature extraction module further includes: The extracted key features are screened according to the environmental characteristics of agricultural products, and the key features that are significantly affected by environmental characteristics and have a correlation with the occurrence of diseases and pests are extracted; Adjusting the weight of the key feature in the pest and disease identification model according to the degree to which the key feature is affected by the environmental feature and the closeness of the correlation relationship; The pest and disease identification model is optimized based on the influence of agricultural product environmental characteristics on the key characteristics of pests and diseases and the weight of the key characteristics in the pest and disease identification model; At the same time, the environmental adaptability of the extracted key features is analyzed to determine the occurrence patterns and changing trends of pests and diseases under different environmental conditions. At the same time, the occurrence trends of future pests and diseases are predicted based on the occurrence patterns and changing trends.

8. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 7, characterized in that: Diagnostic decision unit, including: The feature diagnosis module is used to diagnose pests and diseases based on the extracted key features, and determine the type of pests and diseases, the degree of impact on crops, and the scope of impact based on the diagnosis results; The characteristic diagnosis module is also used to obtain the abnormal situation data of the abnormality detection module and determine whether the abnormal situation data is a rare or newly emerging pest and disease characteristic; Anomaly detection module, which is used to detect anomalies of crops with key characteristics that are free of pests and diseases, and identify anomalies that do not conform to normal growth patterns; The control plan management module is used to match the corresponding pest and disease control plan based on the diagnosis results and abnormal situation data, evaluate the control results of the pest and disease control plan, and generate feedback data based on the evaluation results.

9. The smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 8, characterized in that: The control scheme management module matches the corresponding pest control scheme, specifically: Determine the pest and disease level of the crop based on the diagnosis results and abnormal situation data, and build a pest and disease control plan corresponding to the crop category based on the pest and disease level of the crop; Among them, the specific measures of the pest control plan include source control measures, pest control process measures and terminal control measures; Analyze pest and disease control programs and determine the priority of the pest and disease control programs; Corresponding crop management personnel are assigned based on the specific measures of the pest control plan, and the crop management personnel execute the specific measures of the pest control plan based on the priority of the pest control plan.

10. The smart agricultural product pest and disease diagnosis method based on the Internet of Things is applied to the smart agricultural product pest and disease diagnosis system based on the Internet of Things as claimed in claim 9, characterized in that: The following steps are involved: Step 1: Data collection: Real-time image data of crop growth environment and pests and diseases are collected through cameras and sensor networks deployed in farmland; Step 2: Data processing: Process the collected pest and disease images and extract the key features in the pest and disease images based on the constructed key feature recognition model; Step 3: Intelligent diagnosis and decision-making: Real-time diagnosis of key feature inputs, and generation of pest and disease diagnosis reports and pest and disease control plans; Step 4: Result display and early warning: The pest diagnosis report and pest control plan are displayed to the user through the user interface, and early warning information is sent to the remote terminal; Step 5: Database query and prevention and control recommendations: Users query the pest and disease feature database based on the acquired abnormal image data and the diagnosis results, identify rare and newly emerging pests and diseases, and generate corresponding pest and disease control methods and recommendations.

Images