Crop disease and insect pest detection, reporting and prevention system
By integrating image acquisition, deep learning and big data analysis modules in crop pest detection systems, the problem of the lack of prediction capabilities of existing systems is solved, fast and accurate pest detection and early warning are achieved, and the efficiency of agricultural production is improved.
Patent Information
- Application Number
- CN202411194496.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-26
AI Technical Summary
The existing crop pest and disease detection system lacks in-depth analysis and prediction capabilities for pest and disease occurrence patterns, and it is difficult to provide effective preventive measures and long-term management strategies, and the efficiency of manual detection is low and the accuracy is difficult to guarantee.
A crop pest and disease detection reporting and prevention system was designed, including image acquisition module, image processing and identification module, data storage and management module, big data analysis and prediction module, and user interaction and reporting module, using high-definition cameras, deep learning algorithms, and databases and big data technology to identify and predict pests and diseases, and provide prevention suggestions.
It realizes fast and accurate pest detection and early warning, reduces the time and labor intensity of manual detection, provides real-time monitoring and preventive measures, and improves detection accuracy and agricultural production efficiency.
Smart Images

Figure CN119027818A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of agricultural pest control, and in particular to a crop disease and insect pest detection, reporting and prevention system. Background Art
[0002] In modern agricultural production, timely detection and effective prevention of crop diseases and pests are the key to ensuring healthy crop growth and improving yield and quality. However, traditional crop disease and pest detection mainly relies on manual observation and empirical judgment. This method is not only inefficient, but also greatly affected by subjective factors, making it difficult to achieve large-scale, high-frequency monitoring. In addition, due to the wide variety of diseases and pests, the identification and treatment methods of different diseases and pests are different, and the accuracy of manual detection is difficult to guarantee, which can easily lead to misjudgment or missed judgment, thus affecting the health and yield of crops.
[0003] With the development of information technology, image processing and machine learning technologies have provided new possibilities for the automated detection of crop diseases and pests. However, the application of existing image recognition technology in the agricultural field still faces many challenges. For example, the growing environment of crops is complex and changeable, and factors such as light and weather have a great impact on image quality, which increases the difficulty of image processing. In addition, there are many types of diseases and pests, and their characteristics are slightly different, which puts higher requirements on the recognition ability of the algorithm.
[0004] Existing pest and disease detection systems often only focus on image recognition itself, lacking in-depth analysis and prediction capabilities of the occurrence patterns of pests and diseases. This results in the difficulty in providing effective preventive measures and long-term management strategies even if pests and diseases can be detected. At the same time, the information exchange between farmers and experts is not smooth, resulting in difficulty in sharing knowledge and experience, affecting the efficiency and sustainability of the entire agricultural production. Therefore, technicians in this field provide a crop pest and disease detection, reporting and prevention system to solve the problems raised in the above background. Summary of the invention
[0005] 1. Technical issues to be resolved
[0006] In view of the deficiencies of the prior art, the present invention provides a crop pest and disease detection and reporting prevention system, which solves the problems that the existing pest and disease detection systems lack the ability to understand the occurrence patterns and predictions of pests and diseases and have difficulty in providing effective preventive measures and long-term management strategies.
[0007] (II) Technical solution
[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: A crop pest detection and reporting prevention system, comprising:
[0009] Image acquisition module, which relates to a device for acquiring images of crops, including a high-definition camera and corresponding image acquisition software;
[0010] The image processing and recognition module uses deep learning algorithms to process the collected images, identify the characteristics of pests and diseases, and give a preliminary diagnosis;
[0011] Data storage and management module, to establish pest and disease database, store image data, diagnosis results and pest and disease occurrence;
[0012] Big data analysis and prediction module, which uses big data technology to analyze the occurrence patterns of pests and diseases, predict possible pests and diseases in the future, and provide preventive measures;
[0013] The user interaction and reporting module provides a user interface that allows farmers or agricultural technicians to view test results, prevention recommendations, and report new pest and disease information.
[0014] Preferably, the image acquisition module comprises the following steps:
[0015] S1. Environmental settings: Select the appropriate camera resolution and field of view according to the size of the crop planting area and the type of crop. The camera should be installed in a position that can cover the target crop area and avoid direct sunlight or backlight to reduce overexposure or underexposure of the image.
[0016] S2. Image acquisition plan, set a timer task, let the camera automatically capture images at a predetermined time interval, and set a trigger mechanism based on specific events, such as weather changes, temperature or humidity reaching a certain threshold;
[0017] S3. Image preprocessing: In order to reduce the amount of data stored and transmitted, the image is compressed and image enhancement technology is applied to improve the image quality, including the following calculation formula:
[0018] Image compression rate calculation:
[0019] The original image size is S original , the compressed size is S compressed ;
[0020] The compression ratio CR can be calculated using the following formula:
[0021]
[0022] Contrast adjustment in image enhancement:
[0023] For each pixel value P in the image, the adjustment formula is:
[0024]
[0025] Among them, P min and P maxare the minimum and maximum pixel values in the image, L min and L max is the adjusted pixel value range;
[0026] S4. Data transmission. In order to ensure the security of data transmission, the image data is encrypted and a suitable network protocol is selected to transmit the image data to the server or cloud platform.
[0027] Preferably, the image processing and recognition module comprises the following steps:
[0028] S1. Image preprocessing, grayscale conversion: If a color image is used, first convert it to a grayscale image to simplify subsequent processing;
[0029] G ray (x, y)=0.299·R(x, y)+0.587G(x, y)+0.114·B(x, y)
[0030] Among them, R(x, y), G(x, y), B(x, y) are the red, green and blue channel values of the image at position (x, y);
[0031] Filter denoising: Apply Gaussian filtering to remove image noise;
[0032]
[0033] Where G(x, y) is the Gaussian kernel and σ is the standard deviation;
[0034] Contrast enhancement: Histogram equalization enhances image contrast. The specific formula is:
[0035]
[0036] Among them, s is the output pixel value, r is the input pixel value, P ω (ω) is the gray level probability density function of the input image;
[0037] S2. Feature extraction, edge detection: Use Sobel to detect image edges. The specific formula is:
[0038]
[0039] Among them G x and G y are the gradients in the horizontal and vertical directions respectively, and A is the image matrix;
[0040] Texture features: Calculate the texture features of the gray-level co-occurrence matrix of the image;
[0041] S3. Pest and disease identification, deep learning model: using convolutional neural network for image recognition;
[0042] f(x)=max(0,W x+b )
[0043] Among them, f(x) is the activation function, W is the weight matrix, and b is the bias term;
[0044] Training model, using a large amount of labeled crop pest and disease image data to train the CNN model, the specific calculation formula is:
[0045]
[0046] Where I is the input image, K is the convolution kernel, a and b are the sizes of the convolution kernel;
[0047] S4. Result output, classification result: output the type and location of pests and diseases in the image;
[0048] Confidence: Provides a confidence score for each recognition result.
[0049] Preferably, the data storage and management module comprises the following steps:
[0050] S1. Database design: determine the type of data that needs to be stored according to system requirements, including image data, pest and disease types, timestamps, and geographic locations, and design the database table structure, including field definitions, data types, primary keys, and foreign keys;
[0051] S2. Data storage: format the collected data according to the database table structure and insert the formatted data into the database using SQL statements;
[0052] S3. Data query: write SQL query statements according to the data type to be retrieved;
[0053] S4. Data update and deletion, modify data in the database, delete data in the database;
[0054] S5. Data backup and recovery. Back up the database regularly. You can use full backup, incremental backup or differential backup strategies. When data is lost or damaged, use the backup data to restore the database.
[0055] Preferably, the big data analysis and prediction module includes the following steps:
[0056] S1. Data integration, data cleaning: clear or correct inconsistent, erroneous or missing data;
[0057] Data fusion: integrating data from different sources into a unified data set;
[0058] S2. Feature engineering, feature selection: Select the most useful features for the prediction model from the integrated data;
[0059] Feature construction: construct new features as needed, such as time series features and statistical features;
[0060] S3. Data exploration and visualization, statistical analysis: Calculate statistical indicators of the data set, such as mean, median and standard deviation;
[0061] Visualization: Use charts to show data distribution and trends;
[0062] S4. Model selection and training,Model selection: Select a suitable prediction model according to the problem type,Model training: Use historical data to train the selected model and perform parameter tuning;
[0063] S5. Model evaluation, cross validation: Use cross validation method to evaluate the generalization ability of the model, performance indicators: Calculate the performance indicators of the model;
[0064] S6. Prediction and deployment, future trend prediction: use the trained model to predict the future trend of pests and diseases, result deployment: integrate the prediction results into the system for users to view and use.
[0065] Preferably, the user interaction and reporting module comprises the following steps:
[0066] S1. User interface design: Design an intuitive and easy-to-use user interface, including pest and disease detection result display, historical data query and preventive measures suggestions, to ensure that users can easily perform data query, feedback and reporting operations;
[0067] S2. Collect user feedback, provide a form for users to verify the accuracy of the system's identification results, allow users to report new pest and disease cases, record and analyze user feedback for subsequent model optimization;
[0068] S3. Pest and disease reporting: Design a simple process to allow users to upload pest and disease pictures and descriptions, and verify the data reported by users to ensure the validity and accuracy of the data;
[0069] S4. Preventive measures recommendations: Based on the pest and disease detection results and historical data, the system automatically generates preventive measures recommendations, taking into account factors such as different regions and crop types, and provides personalized preventive measures;
[0070] S5. Notifications and reminders: When the system detects pests and diseases or has new preventive measures recommended, it will promptly notify users via email, SMS or in-app notifications, and regularly remind users to check the condition of crops and prevent the occurrence of pests and diseases.
[0071] (III) Beneficial effects
[0072] The present invention provides a crop pest detection and reporting prevention system, which has the following beneficial effects:
[0073] 1. In the present invention, image recognition technology can be used to quickly analyze a large amount of image data, reducing the time and labor intensity required for manual detection. Through the training of deep learning models, the system can identify subtle characteristics of pests and diseases and improve the accuracy of detection.
[0074] 2. In the present invention, the system can realize real-time monitoring of crop diseases and insect pests, timely discover and report problems, provide early warning for farmers, and through big data analysis, the system can predict the trend of disease and insect pest occurrence, take measures in advance, and reduce losses.
[0075] 3. In the present invention, scalability is taken into consideration and it can adapt to farmlands of different sizes and different types of crops. Through modular design, the system can add new functions or adjust existing functions as needed. BRIEF DESCRIPTION OF THE DRAWINGS
[0076] Figure 1 It is a schematic diagram of the overall system of the present invention;
[0077] Figure 2 It is a specific flow chart of the image acquisition module in the present invention;
[0078] Figure 3 It is a schematic diagram of the specific flow of the image processing and recognition module in the present invention;
[0079] Figure 4 A schematic diagram of a specific process of the data storage and management module in the present invention;
[0080] Figure 5 This is a schematic diagram of the specific process of the big data analysis and prediction module in the present invention;
[0081] Figure 6 It is a specific flow chart of the user interaction and reporting module in the present invention. DETAILED DESCRIPTION
[0082] 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.
[0083] Embodiment 1:
[0084] like Figure 1-6As shown, the embodiment of the present invention provides a crop pest detection, reporting and prevention system, including:
[0085] Image acquisition module, which relates to a device for acquiring images of crops, including a high-definition camera and corresponding image acquisition software;
[0086] The image processing and recognition module uses deep learning algorithms to process the collected images, identify the characteristics of pests and diseases, and give a preliminary diagnosis;
[0087] Data storage and management module, to establish pest and disease database, store image data, diagnosis results and pest and disease occurrence;
[0088] Big data analysis and prediction module, which uses big data technology to analyze the occurrence patterns of pests and diseases, predict possible pests and diseases in the future, and provide preventive measures;
[0089] The user interaction and reporting module provides a user interface that allows farmers or agricultural technicians to view test results, prevention recommendations, and report new pest and disease information.
[0090] The image acquisition module includes the following steps:
[0091] S1. Environmental settings: Select the appropriate camera resolution and field of view according to the size of the crop planting area and the type of crop. The camera should be installed in a position that can cover the target crop area and avoid direct sunlight or backlight to reduce overexposure or underexposure of the image.
[0092] S2. Image acquisition plan, set a timer task, let the camera automatically capture images at a predetermined time interval, and set a trigger mechanism based on specific events, such as weather changes, temperature or humidity reaching a certain threshold;
[0093] S3. Image preprocessing: In order to reduce the amount of data stored and transmitted, the image is compressed and image enhancement technology is applied to improve the image quality, including the following calculation formula:
[0094] Image compression rate calculation:
[0095] The original image size is S original , the compressed size is S compressed ;
[0096] The compression ratio CR can be calculated using the following formula:
[0097]
[0098] Contrast adjustment in image enhancement:
[0099] For each pixel value P in the image, the adjustment formula is:
[0100]
[0101] Among them, P min and P max are the minimum and maximum pixel values in the image, L min and L max is the adjusted pixel value range;
[0102] S4. Data transmission. In order to ensure the security of data transmission, the image data is encrypted and a suitable network protocol is selected to transmit the image data to the server or cloud platform.
[0103] The image processing and recognition module includes the following steps:
[0104] S1. Image preprocessing, grayscale conversion: If a color image is used, first convert it to a grayscale image to simplify subsequent processing;
[0105] G ray (x, y)=0.299·R(x,y)+0.587·G(x,y)+0.114·B(x,y)
[0106] Among them, R(x, y), G(x, y), B(x, y) are the red, green and blue channel values of the image at position (x, y);
[0107] Filter denoising: Apply Gaussian filtering to remove image noise;
[0108]
[0109] Where G(x, y) is the Gaussian kernel and σ is the standard deviation;
[0110] Contrast enhancement: Histogram equalization enhances image contrast. The specific formula is:
[0111]
[0112] Among them, s is the output pixel value, r is the input pixel value, P ω (ω) is the gray level probability density function of the input image;
[0113] S2. Feature extraction, edge detection: Use Sobel to detect image edges. The specific formula is:
[0114]
[0115] Among them G x and G y are the gradients in the horizontal and vertical directions respectively, and A is the image matrix;
[0116] Texture features: Calculate the texture features of the gray-level co-occurrence matrix of the image;
[0117] S3. Pest and disease identification, deep learning model: using convolutional neural network for image recognition;
[0118] f(x)=max(0,W x+b )
[0119] Among them, f(x) is the activation function, W is the weight matrix, and b is the bias term;
[0120] Training model, using a large amount of labeled crop pest and disease image data to train the CNN model, the specific calculation formula is:
[0121]
[0122] Where I is the input image, K is the convolution kernel, a and b are the sizes of the convolution kernel;
[0123] S4. Result output, classification result: output the type and location of pests and diseases in the image;
[0124] Confidence: Provides a confidence score for each recognition result.
[0125] The data storage and management module includes the following steps:
[0126] S1. Database design: determine the type of data that needs to be stored according to system requirements, including image data, pest and disease types, timestamps, and geographic locations, and design the database table structure, including field definitions, data types, primary keys, and foreign keys;
[0127] S2. Data storage: format the collected data according to the database table structure and insert the formatted data into the database using SQL statements;
[0128] S3. Data query: write SQL query statements according to the data type to be retrieved;
[0129] S4. Data update and deletion, modify data in the database, delete data in the database;
[0130] S5. Data backup and recovery. Back up the database regularly. You can use full backup, incremental backup or differential backup strategies. When data is lost or damaged, use the backup data to restore the database.
[0131] The big data analysis and prediction module includes the following steps:
[0132] S1. Data integration, data cleaning: clear or correct inconsistent, erroneous or missing data;
[0133] Data fusion: integrating data from different sources into a unified data set;
[0134] S2. Feature engineering, feature selection: Select the most useful features for the prediction model from the integrated data;
[0135] Feature construction: construct new features as needed, such as time series features and statistical features;
[0136] S3. Data exploration and visualization, statistical analysis: Calculate statistical indicators of the data set, such as mean, median and standard deviation;
[0137] Visualization: Use charts to show data distribution and trends;
[0138] S4. Model selection and training,Model selection: Select a suitable prediction model according to the problem type,Model training: Use historical data to train the selected model and perform parameter tuning;
[0139] S5. Model evaluation, cross validation: Use cross validation method to evaluate the generalization ability of the model, performance indicators: Calculate the performance indicators of the model;
[0140] S6. Prediction and deployment, future trend prediction: use the trained model to predict the future trend of pests and diseases, result deployment: integrate the prediction results into the system for users to view and use.
[0141] The user interaction and reporting module includes the following steps:
[0142] S1. User interface design: Design an intuitive and easy-to-use user interface, including pest and disease detection result display, historical data query and preventive measures suggestions, to ensure that users can easily perform data query, feedback and reporting operations;
[0143] S2. Collect user feedback, provide a form for users to verify the accuracy of the system's identification results, allow users to report new pest and disease cases, record and analyze user feedback for subsequent model optimization;
[0144] S3. Pest and disease reporting: Design a simple process to allow users to upload pest and disease pictures and descriptions, and verify the data reported by users to ensure the validity and accuracy of the data;
[0145] S4. Preventive measures recommendations: Based on the pest and disease detection results and historical data, the system automatically generates preventive measures recommendations, taking into account factors such as different regions and crop types, and provides personalized preventive measures;
[0146] S5. Notifications and reminders: When the system detects pests and diseases or has new preventive measures recommended, it will promptly notify users via email, SMS or in-app notifications, and regularly remind users to check the condition of crops and prevent the occurrence of pests and diseases.
[0147] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A crop pest detection, reporting and prevention system, characterized by: include: Image acquisition module, which relates to a device for acquiring images of crops, including a high-definition camera and corresponding image acquisition software; The image processing and recognition module uses deep learning algorithms to process the collected images, identify the characteristics of pests and diseases, and give a preliminary diagnosis; Data storage and management module, to establish pest and disease database, store image data, diagnosis results and pest and disease occurrence; Big data analysis and prediction module, which uses big data technology to analyze the occurrence patterns of pests and diseases, predict possible pests and diseases in the future, and provide preventive measures; The user interaction and reporting module provides a user interface that allows farmers or agricultural technicians to view test results, prevention recommendations, and report new pest and disease information.
2. A crop pest detection, reporting and prevention system according to claim 1, characterized in that: The image acquisition module comprises the following steps: S1. Environmental settings: Select the appropriate camera resolution and field of view according to the size of the crop planting area and the type of crop. The camera should be installed in a position that can cover the target crop area and avoid direct sunlight or backlight to reduce overexposure or underexposure of the image. S2. Image acquisition plan, set a timer task, let the camera automatically capture images at a predetermined time interval, and set a trigger mechanism based on specific events, such as weather changes, temperature or humidity reaching a certain threshold; S3. Image preprocessing: In order to reduce the amount of data stored and transmitted, the image is compressed and image enhancement technology is applied to improve the image quality, including the following calculation formula: Image compression rate calculation: The original image size is S original , the compressed size is S compressed ; The compression ratio CR can be calculated using the following formula: Contrast adjustment in image enhancement: For each pixel value P in the image, the adjustment formula is: Among them, P min and P max are the minimum and maximum pixel values in the image, L min and L max is the adjusted pixel value range; S4. Data transmission. In order to ensure the security of data transmission, the image data is encrypted and a suitable network protocol is selected to transmit the image data to the server or cloud platform.
3. A crop pest detection, reporting and prevention system according to claim 1, characterized in that: The image processing and recognition module comprises the following steps: S1. Image preprocessing, grayscale conversion: If a color image is used, first convert it to a grayscale image to simplify subsequent processing; G ray (x,y)=0.299·R(x,y)+0.587·G(x,y)+0.114·B(x,y) Among them, R(x,y), G(x,y), B(x,y) are the red, green and blue channel values of the image position (x,y) respectively; Filter denoising: Apply Gaussian filtering to remove image noise; Where G(x,y) is the Gaussian kernel and σ is the standard deviation; Contrast enhancement: Histogram equalization enhances image contrast. The specific formula is: Among them, s is the output pixel value, r is the input pixel value, P ω (ω) is the gray level probability density function of the input image; S2. Feature extraction, edge detection: Use Sobel to detect image edges. The specific formula is: Among them G x and G y are the gradients in the horizontal and vertical directions respectively, and A is the image matrix; Texture features: Calculate the texture features of the gray-level co-occurrence matrix of the image; S3. Pest and disease identification, deep learning model: using convolutional neural network for image recognition; f(x)=max(0,W x+b ) Among them, f(x) is the activation function, W is the weight matrix, and b is the bias term; Training model, using a large amount of labeled crop pest and disease image data to train the CNN model, the specific calculation formula is: Where I is the input image, K is the convolution kernel, a and b are the sizes of the convolution kernel; S4. Result output, classification result: output the type and location of pests and diseases in the image; Confidence: Provides a confidence score for each recognition result.
4. A crop pest detection, reporting and prevention system according to claim 1, characterized in that: The data storage and management module includes the following steps: S1. Database design: determine the type of data that needs to be stored according to system requirements, including image data, pest and disease types, timestamps and geographic locations, and design the database table structure, including field definitions, data types, primary keys and foreign keys; S2. Data storage: format the collected data according to the database table structure and insert the formatted data into the database using SQL statements; S3. Data query: write SQL query statements according to the data type to be retrieved; S4. Data update and deletion, modify data in the database, delete data in the database; S5. Data backup and recovery. Back up the database regularly. You can use full backup, incremental backup or differential backup strategies. When data is lost or damaged, use the backup data to restore the database.
5. A crop pest detection, reporting and prevention system according to claim 1, characterized in that: The big data analysis and prediction module includes the following steps: S1. Data integration, data cleaning: remove or correct inconsistent, erroneous or missing data; Data fusion: integrating data from different sources into a unified data set; S2. Feature engineering, feature selection: Select the most useful features for the prediction model from the integrated data; Feature construction: construct new features as needed, such as time series features and statistical features; S3. Data exploration and visualization, statistical analysis: Calculate statistical indicators of the data set, such as mean, median and standard deviation; Visualization: Use charts to show data distribution and trends; S4. Model selection and training,Model selection: Select a suitable prediction model according to the problem type,Model training: Use historical data to train the selected model and perform parameter tuning; S5. Model evaluation, cross validation: Use cross validation method to evaluate the generalization ability of the model, performance indicators: Calculate the performance indicators of the model; S6. Prediction and deployment, future trend prediction: use the trained model to predict the future trend of pests and diseases, result deployment: integrate the prediction results into the system for users to view and use.
6. A crop pest detection, reporting and prevention system according to claim 1, characterized in that: The user interaction and reporting module includes the following steps: S1. User interface design: Design an intuitive and easy-to-use user interface, including pest and disease detection result display, historical data query and preventive measures suggestions, to ensure that users can easily perform data query, feedback and reporting operations; S2. Collect user feedback, provide a form for users to verify the accuracy of the system's identification results, allow users to report new pest and disease cases, record and analyze user feedback for subsequent model optimization; S3. Pest and disease reporting: Design a simple process to allow users to upload pest and disease pictures and descriptions, and verify the data reported by users to ensure the validity and accuracy of the data; S4. Preventive measures suggestions: Based on the pest and disease detection results and historical data, the system automatically generates preventive measures suggestions, taking into account factors such as different regions and crop types, and provides personalized preventive measures; S5. Notifications and reminders: When the system detects pests and diseases or has new preventive measures recommended, it will promptly notify users via email, SMS or in-app notifications, and regularly remind users to check the condition of crops and prevent the occurrence of pests and diseases.
Citation Information
Patent Citations
Crop disease and insect pest mobile terminal identification method based on deep learning
CN115512227A
Agricultural intelligent monitoring system and method based on machine vision
CN116448760A
Intelligent agricultural management system based on big data
CN117994650A
Cited By
Agricultural pest monitoring and early warning method and system based on image processing
CN120451138A
Agricultural pest and disease monitoring and early warning method and system based on image processing
CN120451138B
