Apple orchard pest and disease intelligent monitoring and early warning robot

Abstract

The present invention provides an intelligent pest monitoring and early warning robot for apple orchards, which relates to the field of artificial intelligence technology. The robot comprises a power module, a pest attraction and capture module, a data processing and analysis module, a data transmission and communication module, a travel and navigation module, a user interface and control module, and an image acquisition and processing module. The robot is capable of trapping pests in apple orchards, identifying and counting pests, monitoring and early warning, and answering questions. The robot achieves efficient, accurate, and real-time pest monitoring and early warning in apple orchards, improving the automation and intelligence level of pest management in apple orchards.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent monitoring and early warning robot for plant diseases and insect pests in apple orchards. Background Art

[0002] As a commercial fruit, apples play a significant role in rural economic development and increasing farmers' incomes. However, due to their long growth cycle and stable ecosystem, apples are susceptible to numerous pests and diseases, such as apple rust, apple brown spot, borer, apple torrefaction moth, and cotton bollworm, which severely restrict fruit production and quality.

[0003] In the existing technology, the identification of pests and diseases in apple orchards is done manually, which is not only time-consuming and labor-intensive, but also inefficient. On the other hand, static or semi-static monitoring equipment is used, which not only makes it difficult to fully cover all areas, but also has low identification accuracy and efficiency, and cannot respond to sudden pest and disease outbreaks in real time. Summary of the Invention

[0004] The present invention provides an intelligent monitoring and early warning robot for apple orchard pests and diseases, which is used to solve the problems of low efficiency, poor accuracy and poor real-time performance in the prior art of identifying apple orchard pests and diseases, and to achieve efficient, accurate and real-time monitoring and early warning of apple orchard pests and diseases.

[0005] The present invention provides an intelligent monitoring and early warning robot for apple orchard pests and diseases, comprising the following modules:

[0006] Pest attracting and capturing module, image acquisition and processing module, data processing and analysis module, power supply module, and data transmission and communication module;

[0007] The pest attracting and capturing module is used to attract and capture pests and perform inactivation treatment on the pests;

[0008] The image acquisition and processing module includes at least a first camera, a second camera, and a third camera; the first camera and the second camera are used to collect real-time video streams from both sides of the apple orchard; the third camera is used to collect images of inactivated pests;

[0009] The data processing and analysis module includes an orchard environmental data acquisition system, a pest and disease identification and counting system, a pest and disease monitoring and early warning system, and a knowledge question-answering system based on a knowledge graph;

[0010] The orchard environmental data acquisition system is used to collect real-time environmental data of the apple orchard;

[0011] The pest identification and counting system includes a pest identification subsystem and a pest counting subsystem; the pest identification subsystem is used to output pest detection results through the MH-YOLO model based on the real-time video streams on both sides of the apple orchard and the inactivated pest images; the pest counting subsystem is used to output the number of pests through the DeepSORT counting model based on the pest detection results;

[0012] The pest and disease monitoring and early warning system is used to output a pest and disease early warning signal based on the real-time environmental data of the apple orchard, the pest and disease detection results and the number of pests and diseases;

[0013] The knowledge graph-based knowledge question answering system is used to generate comprehensive pest and disease information based on the pest and disease detection results, the pest and disease quantity, and the pest and disease early warning signal;

[0014] The power module is used to provide energy required for the operation of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0015] The data transmission and communication module is used for real-time transmission and storage of data.

[0016] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases is provided, wherein the MH-YOLO model is optimized based on the YOLOv5s model;

[0017] The optimization includes at least a first optimization, a second optimization, a third optimization, and a fourth optimization;

[0018] The first optimization is to introduce a CBAM attention mechanism into the backbone network of the YOLOv5s model, and the first optimization is used to enhance the perception ability of the YOLOv5s model of pest and disease characteristics;

[0019] The second optimization is to introduce Swin-Transformer blocks into the first CSP2_1 module of the neck network of the YOLOv5s model, and the second optimization is used to enhance the information integration capability of the YOLOv5s model;

[0020] The third optimization is to introduce the ASFF adaptive feature fusion module at the end of the neck network of the YOLOv5s model, and the third optimization is used to improve the YOLOv5s model's ability to recognize pest and disease characteristics;

[0021] The fourth optimization is to perform structured pruning on the YOLOv5s model after the first optimization, the second optimization, and the third optimization. The fourth optimization is used to reduce the number of parameters and complexity of the YOLOv5s model.

[0022] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases is provided, wherein the DeepSORT counting model includes a region recognition module, a feature extractor, a Kalman filter, a feature association module, and a re-identification module;

[0023] The region recognition module is used to identify the pest and disease detection results output by the MH-YOLO model to obtain the pest and disease area;

[0024] The feature extractor is used to extract features from the pest area and generate a feature vector describing the appearance features of the pest;

[0025] The Kalman filter is used to predict the state of the pests and diseases based on the eigenvector to obtain a new state estimate;

[0026] The feature association module is used to generate a pest tracking trajectory based on the new state estimation;

[0027] The re-identification module is used to determine the number of pests and diseases based on the feature vector and the pest and disease tracking trajectory.

[0028] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases is provided, wherein the pest attracting and capturing module includes a capturing unit, an insect killing unit, an insect receiving plate, an insect dropping plate, a controller, a conveyor belt, and a cleaner;

[0029] The capture unit is used to capture apple orchard pests;

[0030] The pest control unit is used to perform a deactivation treatment on the pests; the deactivation treatment includes a killing treatment and a drying treatment;

[0031] The insect receiving plate is used to receive the pests after killing;

[0032] The insect drop plate is used to receive the pests after drying and drop a predetermined number of pests onto the conveyor belt through a weight sensor;

[0033] The controller is used to control the opening and closing mechanism so that the pests on the insect receiving plate fall onto the insect dropping plate after being dried;

[0034] The conveyor belt is used to convey the pests dropped from the insect drop plate to the image acquisition and processing module;

[0035] The cleaner is used to clean the pests adhered to or overlapped on the conveyor belt.

[0036] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases is provided, wherein the capture unit includes an impact plate and an insect trap light;

[0037] The impact plates are placed crosswise to capture the lured apple orchard pests;

[0038] The insect-attracting lamp is used for attracting pests in apple orchards.

[0039] According to the intelligent monitoring and early warning robot for apple orchard pests provided by the present invention, a sex attractant core is placed at the center of the impact plate, and the sex attractant core is used to lure apple orchard pests.

[0040] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases is provided, wherein the insecticide unit includes a high-temperature insecticide and an oven;

[0041] The high-temperature insecticide is used to kill pests through high heat;

[0042] The drying oven is used for drying the pests after the killing process.

[0043] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases further includes a walking and navigation module; the walking and navigation module includes a laser radar, a GPS module, a path planning unit, a walking mechanism, and an obstacle avoidance sensor;

[0044] The laser radar is used to generate a three-dimensional environment model based on the terrain, vegetation distribution and obstacle locations in the apple orchard;

[0045] The GPS module is used to generate positioning information according to the real-time position of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0046] The path planning unit is used to generate a path planning map according to the three-dimensional environment model and the positioning information;

[0047] The walking mechanism is used to control the apple orchard pest and disease intelligent monitoring and early warning robot to walk according to the path planning map;

[0048] The obstacle avoidance sensor is used to detect obstacles ahead in real time while the apple orchard pest and disease intelligent monitoring and early warning robot is walking according to the path planning map.

[0049] According to the present invention, an intelligent monitoring and early warning robot for pests and diseases in apple orchards, the walking mechanism includes a walking drive module, a suspension module and a steering module;

[0050] The walking drive module is used to provide power for the apple orchard pest and disease intelligent monitoring and early warning robot to walk;

[0051] The suspension module is used to cushion the impact of uneven ground on the walking of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0052] The steering module is used to control the steering of the apple orchard pest and disease intelligent monitoring and early warning robot.

[0053] According to the present invention, an intelligent monitoring and early warning robot for apple orchard pests and diseases also includes a user interface and a control module, which are used to support information interaction between the user and the intelligent monitoring and early warning robot for apple orchard pests and diseases.

[0054] The present invention provides an intelligent monitoring and early warning robot for apple orchard pests and diseases. The robot uses a pest attracting and capturing module to trap apple orchard pests, uses an image acquisition and processing module to collect apple orchard data in real time to obtain information on apple orchard pests and diseases, and uses a data processing and analysis module to perform real-time data processing and analysis to achieve identification, counting, monitoring and early warning, and knowledge question and answer of pests and diseases. The power module and the data transmission and communication module work together to provide energy and communication guarantees for the operation of the robot, thereby achieving efficient, accurate, and real-time monitoring and early warning of pests and diseases in the apple orchard, and improving the automation and intelligence level of pest and disease management in the apple orchard. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 This is a module schematic diagram of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention.

[0057] Figure 2 This is a schematic diagram of the appearance of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention.

[0058] Figure 3 This is a schematic diagram of the main structure of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention.

[0059] Figure 4 This is a partial structural diagram of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention.

[0060] Figure 5 The present invention provides a chassis structure diagram of an intelligent monitoring and early warning robot for apple orchard pests and diseases.

[0061] Figure 6 This is a schematic diagram of the system embedded in the edge computing platform of the apple orchard pest and disease intelligent monitoring and early warning robot provided by the present invention.

[0062] Figure 7It is a schematic diagram of the YOLOv5s model structure and the MH-YOLO model structure provided by the present invention.

[0063] Figure 8 This is a schematic diagram of the structured pruning of the MH-YOLO model provided by the present invention.

[0064] Reference numerals:

[0065] 1-Solar panel, 2-Insect attractant lamp, 3-Impact plate, 4-Sex attractant core, 5-Insect receiving funnel, 6-Insect receiving plate, 7-Insect killing unit, 8-Opening and closing mechanism, 9-Insect dropping plate, 10-LiDAR, 11-First camera, 12-Fill light, 13-Collection device, 14-Second and third cameras, 15-Sensor module, 16-Display screen, 17-Edge computing platform, 18-Data transmission and communication module, 19-Sweeper, 20-Track, 21-Tire, 22-Axle, 23-Spring, 24-Shock absorber, 25-Motor, 26-Transmission device, 27-Power module. DETAILED DESCRIPTION

[0066] With the modernization of global agriculture, the demand for refined and intelligent apple orchard management is growing. As a commercial fruit, apples play a significant role in rural economic development and increasing farmers' incomes. Due to the long apple growth cycle and stable ecosystem, apples are susceptible to numerous pests and diseases, such as apple rust, apple brown spot, peach borer, pear borer, citrus borer, apple torrefaction moth, and cotton bollworm, which severely restrict fruit production and quality.

[0067] Currently, apple orchard pest and disease identification is primarily performed manually or through monitoring systems. Manual identification is not only time-consuming and labor-intensive, but also inefficient. Existing apple orchard pest and disease monitoring systems, which often utilize static or semi-static monitoring equipment, can achieve a certain degree of automation but have limitations in coverage, flexibility, and real-time performance. This is particularly true in large-scale apple orchards, where traditional equipment struggles to fully cover all areas and respond to pest and disease emergencies in real time. Furthermore, existing systems have limited data processing capabilities, making it difficult to fully utilize multi-source sensor data for accurate pest and disease identification and dynamic early warning.

[0068] Therefore, existing pest and disease monitoring equipment often cannot adapt to the complex and changing terrain of apple orchards. The equipment must be fixed or semi-fixed for monitoring, resulting in a limited monitoring range and inability to achieve comprehensive coverage. Furthermore, these devices lack flexible navigation and mobility, making it difficult to efficiently and autonomously navigate large orchards. Existing monitoring systems also rely primarily on centralized computing for data processing, which limits their real-time performance and response speed, making it impossible to quickly process large amounts of environmental data and pest and disease information.

[0069] Furthermore, traditional pest and disease identification methods rely on manual experience and simple image processing techniques, resulting in low accuracy and efficiency, making them incapable of addressing the diverse and multi-faceted nature of pests and diseases. Regarding pest and disease early warning, existing systems lack effective dynamic early warning mechanisms, resulting in insufficient accuracy and timeliness of early warning information, making it impossible to provide fruit farmers with real-time, scientific decision-making support.

[0070] In order to achieve efficient, accurate and real-time identification and early warning of diseases and pests in apple orchards, the present invention proposes an apple orchard disease and pest intelligent monitoring and early warning robot, which aims to realize automatic identification, monitoring and early warning of diseases and pests in apple orchards.

[0071] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all 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.

[0072] The following combination Figures 1 to 8 The present invention describes an intelligent monitoring and early warning robot for apple orchard pests and diseases.

[0073] Figure 1 This is a module diagram of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention. Figure 1 As shown, the apple orchard pest and disease intelligent monitoring and early warning robot includes at least the following modules: a pest attracting and capturing module, an image acquisition and processing module, a data processing and analysis module, a power supply module, and a data transmission and communication module.

[0074] The pest attracting and capturing module is used to attract and capture pests and perform inactivation treatment on the pests;

[0075] The image acquisition and processing module includes at least a first camera, a second camera, and a third camera; the first camera and the second camera are used to collect real-time video streams from both sides of the apple orchard; the third camera is used to collect images of inactivated pests;

[0076] The data processing and analysis module includes an orchard environmental data acquisition system, a pest and disease identification and counting system, a pest and disease monitoring and early warning system, and a knowledge question-answering system based on a knowledge graph;

[0077] The orchard environmental data acquisition system is used to collect real-time environmental data of the apple orchard;

[0078] The pest identification and counting system includes a pest identification subsystem and a pest counting subsystem; the pest identification subsystem is used to output pest detection results through the MH-YOLO model based on the real-time video streams on both sides of the apple orchard and the inactivated pest images; the pest counting subsystem is used to output the number of pests through the DeepSORT counting model based on the pest detection results;

[0079] The pest and disease monitoring and early warning system is used to output a pest and disease early warning signal based on the real-time environmental data of the apple orchard, the pest and disease detection results and the number of pests and diseases;

[0080] The knowledge graph-based knowledge question answering system is used to generate comprehensive pest and disease information based on the pest and disease detection results, the pest and disease quantity, and the pest and disease early warning signal;

[0081] The power module is used to provide energy required for the operation of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0082] The data transmission and communication module is used for real-time transmission and storage of data.

[0083] Figure 2 FIG. 1 is a schematic diagram of the appearance of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention. Figure 2 As shown, in order to further demonstrate Figure 2 The specific structure of the apple orchard pest and disease intelligent monitoring and early warning robot shown in the figure, the present invention also provides Figures 3 to 5 , and introduces the specific structure of the intelligent monitoring and early warning robot for apple orchard pests and diseases.

[0084] Figure 3 This is a schematic diagram of the main structure of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention. Figure 3 As shown, the main structure of the apple orchard pest intelligent monitoring and early warning robot provided by the embodiment of the present invention includes at least 1-solar panel, 2-insect attractant lamp, 3-impact plate, 4-sex attractant core, 5-insect receiving funnel, 6-insect receiving plate, 7-insect killing unit, 8-opening and closing mechanism, 9-insect dropping plate, 10-lidar, 11-first camera, 12-fill light, 13-collecting device, 14-second and third cameras, 15-sensor module, 16-display screen, 17-edge computing platform, 18-data transmission and communication module and 19-sweeper.

[0085] Figure 4 This is a partial structural diagram of an intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the present invention. Figure 4As shown, the local structure of the intelligent monitoring and early warning robot for apple orchard pests and diseases provided by the embodiment of the present invention includes at least: 20 - tracks, 21 - tires, 22 - axles, 23 - springs and 24 - shock absorbers.

[0086] Figure 5 This is a schematic diagram of the chassis structure of an apple orchard disease and insect pest intelligent monitoring and early warning robot provided by the present invention, such as Figure 5 As shown, the chassis structure of the apple orchard disease and insect pest intelligent monitoring and early warning robot provided by the embodiment of the present invention includes at least: 25-motor, 26-transmission device and 27-power module.

[0087] In an embodiment of the present invention, the power module in the apple orchard pest and disease intelligent monitoring and early warning robot (hereinafter referred to as the robot) includes a built-in power supply and a solar panel, which is used to provide the energy required for the robot to operate and ensure that the robot can operate autonomously for a long time.

[0088] A solar panel mounted on top of the robot's housing effectively utilizes solar energy to power the robot's various control units, track system, and overall operation. The robot also features a built-in power source (such as a battery) that provides reliable power to its internal modules during periods of low light or at night, ensuring the robot's continued operation. This combined power supply and solar panel ensures the robot's continued stable operation in a variety of environments.

[0089] The pest attracting and capturing module in the robot is used to attract and capture pests and inactivate them.

[0090] Optionally, the pest attracting and capturing module includes a capturing unit, an insect killing unit, an insect receiving plate, an insect dropping plate, a controller, a conveyor belt, and a sweeper;

[0091] The capture unit is used to capture apple orchard pests;

[0092] The pest control unit is used to perform a deactivation treatment on the pests; the deactivation treatment includes a killing treatment and a drying treatment;

[0093] The insect receiving plate is used to receive the pests after killing;

[0094] The insect drop plate is used to receive the pests after drying and drop a predetermined number of pests onto the conveyor belt through a weight sensor;

[0095] The controller is used to control the opening and closing mechanism so that the pests on the insect receiving plate fall onto the insect dropping plate after being dried;

[0096] The conveyor belt is used to convey the pests dropped from the insect drop plate to the image acquisition and processing module;

[0097] The cleaner is used to clean the pests adhered to or overlapped on the conveyor belt.

[0098] The capture unit includes an impact plate and an insect trap light;

[0099] The impact plates are placed crosswise to capture the lured apple orchard pests;

[0100] The insect-attracting lamp is used for attracting pests in apple orchards.

[0101] A sex attractant core is placed at the center of the impact plate, and the sex attractant core is used to attract apple orchard pests.

[0102] The insecticide unit includes a high-temperature insecticide and an oven;

[0103] The high-temperature insecticide is used to kill pests through high heat;

[0104] The drying oven is used for drying the pests after the killing process.

[0105] Specifically, the pest attracting and capturing module includes a capturing unit, an insect killing unit, a controller, an insect dropping plate and a sweeper.

[0106] The capturing unit includes an insect trap lamp and an impact plate, wherein the impact plate is made of transparent materials, such as glass or crystal, to make a transparent impact plate.

[0107] Under the impact plates, sex attractants are placed. The synthetic sex pheromones released by the sex attractants attract specific apple orchard pests. Furthermore, insect traps utilize the phototaxis of some pests to release light within a specific spectrum, attracting the pests. The impact plates are then placed crosswise to better capture the attracted pests.

[0108] The pests are inactivated using an insecticide unit, and the inactivation treatment includes killing treatment and drying treatment.

[0109] The insecticide unit is a high-pressure, high-heat unit consisting of a high-heat insecticide and a drying oven. The high-heat insecticide kills pests with high heat, preventing them from escaping; the drying oven dries out the moisture in the pests' bodies, preventing them from spoiling and rotting.

[0110] After being killed, the pests fall onto the insect receiving plate. A controller then controls the opening and closing mechanism. When a preset time (customizable based on actual conditions) or a predetermined number of pests (customizable based on actual conditions) accumulates on the receiving plate, the controller opens the mechanism, allowing the killed pests to fall into the drying oven for drying. Once drying is complete, the pests fall onto the insect drop plate.

[0111] A weight sensor is installed at the bottom of the insect drop plate. When the pests accumulate to a predetermined number (the specific number can be customized according to actual conditions), the weight sensor triggers a switch to ensure that the pests fall evenly onto the conveyor belt in the crawler system, thereby effectively controlling the distribution of pests, preventing pest accumulation, and improving conveying and processing efficiency.

[0112] In order to clean up stuck or overlapping pests and to facilitate subsequent capture of high-quality pest images, an embodiment of the present invention further provides a sweeper above the conveyor belt, so that the inactivated pests on the conveyor belt are cleaned by the sweeper and then transmitted to the image acquisition and processing module, so that the subsequent camera can capture clear images of the inactivated pests, thereby improving recognition accuracy.

[0113] In order to facilitate the smooth descent of the pests, an insect receiving funnel is further provided below the impact plate. Both the insect receiving plate and the insect receiving funnel are made of smooth materials to prevent the pests from stagnating during the descent, thereby ensuring that the pests can enter the insect killing unit smoothly.

[0114] In the embodiment of the present invention, the image acquisition and processing module includes at least a first camera, a second camera, and a third camera. In addition, in order to improve the shooting quality of the camera, a fill light may be added.

[0115] During the robot's monitoring process, the first and second cameras capture real-time video streams from both sides of the apple orchard, while the third camera captures images of inactivated pests. In dimly lit areas, supplemental lighting can be used to improve image quality.

[0116] The videos and images captured by these cameras are fed into the robot's data processing and analysis module. This core module integrates the orchard's environmental data collection system, pest and disease identification and counting system, pest and disease monitoring and early warning system, and a knowledge graph-based question-and-answer system through an edge computing platform.

[0117] Figure 6 This is a schematic diagram of the system embedded in the edge computing platform of the apple orchard pest and disease intelligent monitoring and early warning robot provided by the present invention. Figure 6 shown.

[0118] The orchard environmental data collection system integrates a variety of high-precision sensors, including temperature, humidity, light, wind speed, and direction sensors. These sensors are connected to an edge computing platform to collect real-time environmental data from the orchard. This system uses these sensors to monitor and analyze the orchard's microclimate in real time, providing a scientific basis for subsequent assessments of pest and disease development patterns.

[0119] Through the monitoring and data transmission of these sensors, the robot can obtain parameters such as temperature, humidity, and light in the orchard, realize real-time monitoring and accurate assessment of the orchard's climatic conditions, and provide high-precision data support for the identification and prevention of pests and diseases.

[0120] The pest and disease identification and counting system integrates both the pest and disease identification subsystem and the pest and disease counting subsystem. It also connects to the image acquisition and processing module, enabling real-time acquisition of high-definition image and video data from the module. This data is then analyzed and processed using a deep learning model (i.e., the MH-YOLO model) to achieve real-time automatic identification and classification of pests and diseases. Furthermore, the DeepSORT counting algorithm, based on the preliminary processing results of the MH-YOLO model on captured pests, allows for real-time tracking and counting of pests. This accurately tracks the movement of individual pests, avoids double counting, and thus improves pest identification accuracy.

[0121] In an embodiment of the present invention, the pest and disease identification and counting system can accurately determine the type and number of pests and diseases through efficient image processing, data analysis, and quantitative statistics. The pest and disease identification subsystem is used to detect and classify pests and diseases in the video frames and pest images based on the real-time video streams from both sides of the apple orchard and the images of inactivated pests using the MH-YOLO model, and output pest and disease detection results including bounding boxes, category labels, and confidence scores. The pest and disease counting subsystem is used to output the number of pests and diseases based on the pest and disease detection results using the DeepSORT counting model.

[0122] Based on the above embodiments, the pest and disease monitoring and early warning system provided by the present invention outputs a pest and disease early warning signal based on the real-time environmental data of the apple orchard, the pest and disease detection results and the number of pests and diseases.

[0123] Specifically, the pest and disease monitoring and early warning system first integrates the environmental data collected by the orchard environmental data collection system and the pest and disease type and quantity information obtained by the pest and disease identification and counting system to construct a multidimensional data set, and adopts the Bayesian data fusion algorithm to integrate multi-source data to improve the reliability and consistency of the data; then the AutoRegressiveIntegrated Moving Average (hereinafter referred to as ARIMA) model is used to perform time series prediction on the number of pests and diseases to identify seasonal and trend changes. Among them, the ARIMA model captures the temporal dynamic characteristics of the data through differencing, stabilization processing and autoregressive moving average methods; then, combined with the environmental data, the vector autoregression (VAR) model is used to evaluate the impact of environmental factors on the number of pests and diseases. Among them, the VAR model predicts future changes in the number of pests and diseases by capturing the interdependence of multivariate time series.

[0124] In addition, the pest and disease monitoring and early warning system also uses a random forest model to classify pest and disease levels. By integrating multiple decision trees and using bagging technology, the model's stability and generalization ability are improved. During the model training process, grid search is used for hyperparameter optimization, and cross-validation technology is used to evaluate model performance to ensure that the model can accurately classify pest and disease levels, thereby achieving accurate and timely early warnings.

[0125] In an embodiment of the present invention, the pest and disease monitoring and early warning system is connected to the pest and disease identification and counting system, and through real-time data analysis and processing, dynamic monitoring and early warning of pests and diseases are achieved. Based on the data provided by the pest and disease identification and counting system, the occurrence and development trends of pests and diseases are evaluated in real time, and early warning information is generated.

[0126] Through rapid analysis and response from the pest and disease monitoring and early warning system, the robot can promptly detect early signs of pests and diseases and send warning signals to fruit farmers. These warning signals are displayed in real time on the user interface and display screens in the control module, helping fruit farmers implement scientific pest and disease control.

[0127] The knowledge question answering system based on knowledge graph is used to generate comprehensive information on pests and diseases based on pest and disease detection results, pest and disease quantity, and pest and disease early warning signals.

[0128] The knowledge graph-based question-and-answer system integrates a vast amount of agricultural knowledge and pest control information to form a comprehensive knowledge graph. Leveraging natural language processing and intelligent reasoning, the knowledge graph-based question-and-answer system generates targeted answers based on data provided by pest and disease monitoring and early warning systems and pest and disease identification systems, including comprehensive pest and disease information, pest and disease numbers, and pest and disease types. Users can query pest and disease-related information through the system and obtain scientific prevention and control recommendations and solutions.

[0129] The robot also includes a user interface and control module, including a display screen and a remote control interface. The user interface and control module are used to support information interaction between the user and the apple orchard pest and disease intelligent monitoring and early warning robot.

[0130] The knowledge question and answer system based on the knowledge graph interacts with users through the display screen in the user interface and control module to realize intelligent question and answer.

[0131] The knowledge question-answering system based on the knowledge graph builds an agricultural knowledge graph and combines it with natural language processing technology to provide intelligent answers to user queries and provide fruit farmers with real-time and accurate pest and disease management recommendations.

[0132] The construction of the knowledge graph of apple orchard pests and diseases includes the following steps:

[0133] (1) Collect data from a variety of data sources such as agricultural literature, expert manuals, and pest control records. Use web crawler technology to automatically capture relevant information on the Internet and combine it with manually organized expert knowledge base data to form a rich original data set.

[0134] (2) Clean, convert and normalize the collected data to ensure its accuracy and consistency;

[0135] (3) Use natural language processing technology to preprocess text data and extract key information;

[0136] (4) Use information extraction algorithms to extract entities, attributes, and relationships from the preprocessed data. The entity types include pest and disease types, symptom descriptions, prevention and control methods, and drug names.

[0137] (5) Extracting complex knowledge structures through the BERT model and constructing a knowledge graph;

[0138] (6) Store the knowledge graph in a graph database, storing entities and relationships in a structured manner using nodes and edges.

[0139] When the knowledge graph-based question-answering system is running, it first uses natural language processing technology to understand and analyze the questions input by the user. For example, it identifies and extracts keywords in the question and uses Word2Vec word embedding technology to convert the keywords into vector representations to facilitate subsequent knowledge retrieval.

[0140] Secondly, perform knowledge retrieval in the knowledge graph, use Cypher to write query language, and find relevant entities and relationships in the knowledge graph based on question type and keywords;

[0141] Next, a graph-based similarity algorithm is used to calculate the knowledge nodes related to the question, filter out the most relevant knowledge items, and integrate and organize the retrieved knowledge items to generate a structured answer;

[0142] Finally, natural language processing technology is used to convert structured data into natural language descriptions to ensure the readability and accuracy of the answers.

[0143] In this embodiment of the present invention, a knowledge graph-based question-answering system synchronizes the knowledge graph and user interaction data to a central server in real time via a wireless communication module, ensuring data consistency. This allows users to enter queries through the robot's display and receive real-time answers. The display interface is simple and easy to use, supporting both text and voice input, enhancing the user experience.

[0144] The knowledge graph-based Q&A system provides intelligent answers displayed in real time on a display screen, helping fruit farmers implement scientific pest and disease control. Furthermore, the knowledge graph-based Q&A system features a user feedback mechanism, allowing users to evaluate and provide feedback on answers via the display screen. The knowledge graph-based Q&A system can continuously optimize the knowledge graph and Q&A model based on this feedback, thereby continuously improving service quality.

[0145] Based on any of the above embodiments, the robot also includes a data transmission and communication module, which is used for real-time transmission and storage of data, and realizes real-time data transmission between various systems in the robot through wireless communication, including receiving and sending instructions, so that the robot can perform various tasks such as path adjustment, speed control and navigation correction in real time according to instructions, thereby improving the efficiency of the robot's intelligent monitoring and early warning of pests and diseases in apple orchards.

[0146] The data transmission and communication module is connected to the edge computing platform, and the data transmission and communication module includes a communication unit and a data storage unit.

[0147] The communication unit uses wireless communication technology to achieve efficient transmission of data between the orchard environment collection system, pest and disease identification and counting system, pest and disease monitoring and early warning system, and the knowledge question and answer system based on knowledge graph.

[0148] The data storage unit is used to store data, for example, the video data and image data collected by the robot through the camera are stored in a memory card, so that remote monitoring can be achieved through the camera in combination with the communication unit.

[0149] The data transmission and communication module can ensure the stable transmission of real-time data, support high-speed transmission and processing of large amounts of data, ensure data synchronization and information sharing between systems, and provide reliable communication guarantee for the overall coordination and efficient operation of the robot.

[0150] The present invention provides an intelligent monitoring and early warning robot for apple orchard pests and diseases, which traps apple orchard pests through a pest luring and capturing module, collects apple orchard data in real time through an image acquisition and processing module, monitors apple orchard pest information, performs real-time data processing and analysis through a data processing and analysis module, and combines environmental data collected by multiple sensors to achieve identification, counting, monitoring and early warning of pests and diseases, as well as knowledge question and answer. The power module and the data transmission and communication module work together to provide energy and communication guarantees for the operation of the robot, thereby achieving efficient, accurate and real-time pest and disease monitoring and early warning in the apple orchard, and improving the level of automation and intelligence in apple orchard pest and disease management.

[0151] Optionally, the MH-YOLO model is optimized based on the YOLOv5s model;

[0152] The optimization includes at least a first optimization, a second optimization, a third optimization, and a fourth optimization;

[0153] The first optimization is to introduce a CBAM attention mechanism into the backbone network of the YOLOv5s model, and the first optimization is used to enhance the perception ability of the YOLOv5s model of pest and disease characteristics;

[0154] The second optimization is to introduce Swin-Transformer blocks into the first CSP2_1 module of the neck network of the YOLOv5s model, and the second optimization is used to enhance the information integration capability of the YOLOv5s model;

[0155] The third optimization is to introduce the ASFF adaptive feature fusion module at the end of the neck network of the YOLOv5s model, and the third optimization is used to improve the YOLOv5s model's ability to recognize pest and disease characteristics;

[0156] The fourth optimization is to perform structured pruning on the YOLOv5s model after the first optimization, the second optimization, and the third optimization. The fourth optimization is used to reduce the number of parameters and complexity of the YOLOv5s model.

[0157] Specifically, the pest identification and counting system includes a pest identification subsystem and a pest counting subsystem. The pest identification subsystem uses the MH-YOLO model to output pest detection results based on real-time video streams from both sides of the apple orchard and images of inactivated pests.

[0158] Figure 7 It is a schematic diagram of the YOLOv5s model structure and the MH-YOLO model structure provided by the present invention, as shown Figure 7 shown. Figure 7 (a) in the figure shows the schematic diagram of the YOLOv5s model structure. Figure 7 (b) in the figure shows the MH-YOLO model architecture. To facilitate edge deployment of models for identifying pests and diseases in apple orchards, this embodiment of the present invention uses the YOLOv5s model, which has low training cost and parameter count, as the baseline network and improves upon it to obtain the MH-YOLO model.

[0159] The MH-YOLO model is obtained by performing multi-angle structural optimization based on the YOLOv5s model, including at least the first optimization, the second optimization, the third optimization, and the fourth optimization.

[0160] The first optimization involves optimizing the feature extraction part of the YOLOv5s model's backbone network and adding the Convolutional Block Attention Module (CBAM) attention mechanism to enhance the model's ability to perceive the key features of pest and disease images.

[0161] CBAM can effectively enhance the model's perception of key features of pest and disease images by combining channel attention and spatial attention.

[0162] Channel attention is to highlight the key channel features by learning the importance of different channels; spatial attention is to enhance the feature expression of salient areas by weighting the spatial dimensions of the feature map.

[0163] The second optimization involves integrating Swin-Transformer blocks into the first CSP2_1 module of the YOLOv5s model's neck network. Swin-Transformer is a Transformer variant based on a windowed attention mechanism. It uses local attention calculations to achieve efficient feature extraction and representation. By introducing Swin-Transformer blocks into the CSP2_1 module and implementing feature fusion through the Add operation, this not only improves the richness of feature extraction but also enhances the model's information integration capabilities.

[0164] The third optimization, multi-scale feature fusion, integrates the Adaptive Spatial Feature Fusion (ASFF) module at the end of the YOLOv5s model's neck network. The ASFF module adaptively weights and fuses feature maps from different scales, effectively addressing information loss and redundancy during multi-scale feature fusion. This improves the model's ability to identify pest and disease features at different scales. By learning the weights of features at different scales and flexibly adjusting the feature fusion strategy, the model can achieve high-precision recognition in complex backgrounds.

[0165] The fourth optimization involves structured pruning. While the YOLOv5s model, after the first, second, and third optimizations, can efficiently detect pests and diseases in apple orchards, its structure and parameters are not yet optimal, consuming a significant amount of resources. To further simplify the model, improve its detection efficiency, and facilitate its embedding on edge platforms, this paper prunes the model through structured pruning to reduce its parameters and complexity, achieving an optimal balance between accuracy and speed.

[0166] Figure 8 This is a schematic diagram of the structured pruning of the MH-YOLO model provided by the present invention, as shown Figure 8shown. Figure 8 in i -thconv-layer represents the 𝑖th convolutional layer of the MH-YOLO model, ( i +1)= j The -th conv-layer represents the 𝑗th convolutional layer in the network, which has the same number as the 𝑖+1th layer.

[0167] Specifically, the process of structured pruning involves first training the initial network with channel sparsity regularization, then pruning channels with smaller scaling factors, and finally fine-tuning the pruned network to obtain a compact network. Channels represented by factors close to 0 after sparsification contribute less to the model, so these channels and input and output aspects can be pruned, primarily through channel pruning. The essence of channel pruning is to eliminate channels that contribute little to model performance. Through channel pruning, the network's redundant parameters and computational complexity can be effectively reduced, resulting in a compact pruned network. This achieves the effect of compressing the model structure and improving computational speed without affecting model performance.

[0168] In order to improve the network's rapid convergence and generalization capabilities, convolutional neural networks often use batch normalization as a standard method. When pruning channels, the input and output of the BN layer are and , At the same time, the scaling factor and bias are introduced in the batch normalization layer of each channel to normalize the channel data, as shown in the formula:

[0169]

[0170]

[0171] Where: and Represent the mean and standard deviation of each batch, Indicates a small positive constant used to avoid the denominator being 0. represents the normalized result, represents the scaling factor in normalization, Represents the bias factor in normalization.

[0172] During training, L1 regularization is used for sparseness, and the total loss function in the channel pruning algorithm is The expression is as follows:

[0173]

[0174] Where: Represent the input and output of training respectively, represents the weight parameter, Represents the scaling factor penalty items. Represents the regularization coefficient, which is used to control the weight of the regularization term in the loss function.

[0175] In order to improve the inference speed of the model, the embodiment of the present invention adopts the TensorRT framework for deployment. TensorRT is an efficient inference engine launched by NVIDIA. It can efficiently deploy trained deep learning models to edge platforms for inference, and can provide low latency and high throughput for deep learning models.

[0176] Specifically, the embodiments of the present invention use TensorRT to optimize two main aspects. The first aspect is inter-layer fusion or tensor fusion. Through vertical fusion, layers with the same structure but different weights can be merged into a wider layer. That is, the horizontal layer can merge the convolution, bias, and activation layers into a CBR structure, thereby reducing the number of calculation steps and data transmission time. The second aspect is data precision calibration. Since the network precision trained by the PyTorch framework is 32-bit floating point (FP32), there are forward propagation and backpropagation during the model training process, which requires higher-precision network parameters. However, during the model inference process, there is only forward propagation, which does not require high parameters and can appropriately reduce parameter performance. Therefore, the data precision can be reduced to FP16 or INT8 precision, reducing the amount of calculation and thus improving the inference speed of the model.

[0177] The embodiment of the present invention optimizes the YOLOv5s model in multiple aspects to obtain a lightweight MH-YOLO model. Compared with the original YOLOv5s model, the MH-YOLO model has stronger perception, information integration, and recognition capabilities of pest and disease characteristics. In addition, through structured pruning and TensorRT optimization, the model has lower parameters and complexity, reducing the amount of computation. As a result, the MH-YOLO model can improve the inference speed while improving the recognition accuracy, thereby enabling the robot to accurately and efficiently identify pests and diseases.

[0178] Optionally, the DeepSORT counting model includes a region recognition module, a feature extractor, a Kalman filter, a feature association module, and a re-identification module;

[0179] The region recognition module is used to identify the pest and disease detection results output by the MH-YOLO model to obtain the pest and disease area;

[0180] The feature extractor is used to extract features from the pest area and generate a feature vector describing the appearance features of the pest;

[0181] The Kalman filter is used to predict the state of the pests and diseases based on the eigenvector to obtain a new state estimate;

[0182] The feature association module is used to generate a pest tracking trajectory based on the new state estimation;

[0183] The re-identification module is used to determine the number of pests and diseases based on the feature vector and the pest and disease tracking trajectory.

[0184] Specifically, the pest identification and counting system includes a pest identification subsystem and a pest counting subsystem. The pest counting subsystem can output the number of pests based on the pest detection results through the DeepSORT counting model.

[0185] The DeepSORT counting model works in conjunction with the MH-YOLO model. The first and second cameras collect real-time video streams from both sides of the apple orchard, as well as images of inactivated pests captured by the third camera. The MH-YOLO model first detects and classifies pests and diseases in the video frames and pest images, and then inputs the detection results into the DeepSORT algorithm for target tracking.

[0186] The DeepSORT model mainly includes a region recognition module, a feature extractor, a Kalman filter, a feature association module, and a re-identification module. The operation process of each module of the DeepSORT model is as follows:

[0187] The MH-YOLO model detects pests and diseases captured by the first, second, and third cameras, generating detection results including bounding boxes, category labels, and confidence scores.

[0188] The detection results are input into the region recognition module of the DeepSORT model to detect and identify the pest and disease areas;

[0189] The feature extractor extracts features from each detected pest area and generates a feature vector describing the appearance characteristics of the pest;

[0190] The Kalman filter is used to predict the pest status, including its position and velocity, based on the feature vector. For example, based on the status information of the previous frame and the detection results of the current frame, the predicted position of the pest is updated to generate a new state estimate.

[0191] The Hungarian algorithm in the feature association module is combined with the new state estimation to associate the detection frame with the tracking path. By calculating the association score between the current detection result and the existing tracking path, the continuous tracking of pests and diseases in the video sequence is ensured. For successfully associated pests and diseases, the pest tracking trajectory is updated, including position, speed, and appearance features. For detection results that are not successfully associated, a new pest tracking trajectory is generated and its state information is initialized. That is, the state of the pest track that cannot be detected in the current frame will be updated. If it is not detected for multiple consecutive frames, its tracking trajectory will be terminated.

[0192] The re-identification module calculates the similarity between feature vectors based on the appearance characteristics of pests and diseases, identifies the pests and diseases, and accurately tracks the pests and diseases based on their tracking trajectories, ensuring the consistency of the pests and diseases in different frames, thereby accurately determining the number of pests and diseases.

[0193] Finally, all tracking trajectory data, including the number, location, speed, feature vector and other information of pests and diseases, are stored in the edge computing platform.

[0194] Optionally, the robot further includes a walking and navigation module; the walking and navigation module includes a laser radar, a GPS module, a path planning unit, a walking mechanism, and an obstacle avoidance sensor;

[0195] The laser radar is used to generate a three-dimensional environment model based on the terrain, vegetation distribution and obstacle locations in the apple orchard;

[0196] The GPS module is used to generate positioning information according to the real-time position of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0197] The path planning unit is used to generate a path planning map according to the three-dimensional environment model and the positioning information;

[0198] The walking mechanism is used to control the apple orchard pest and disease intelligent monitoring and early warning robot to walk according to the path planning map;

[0199] The obstacle avoidance sensor is used to detect obstacles ahead in real time while the apple orchard pest and disease intelligent monitoring and early warning robot is walking according to the path planning map.

[0200] Specifically, the lidar generates high-resolution point cloud data by scanning the orchard environment in real time, and transmits the data to the edge computing platform for processing; the edge computing platform integrates high-performance processors and GPU units to denoise, filter and align the point cloud data generated by the lidar to generate a high-quality three-dimensional environmental model; then, SLAM technology is used, and real-time positioning and map construction are performed through the GPS module to ensure dynamic updating and precise positioning of the environmental model; the path planning unit adopts the Dijkstra algorithm to calculate the optimal cruising path according to the three-dimensional environmental model, comprehensively considering the terrain undulations, vegetation density and obstacle positions, obtains the optimal path information, generates a path planning map, and stores it in the edge computing platform; the walking mechanism controls the robot to cruise in the apple orchard according to the path planning map; during the cruising process, the obstacle avoidance sensor is used in combination with the dynamic obstacle avoidance algorithm to detect and avoid obstacles in front in real time to ensure driving safety, and the robot's position and posture information is updated in real time through the GPS module.

[0201] The embodiment of the present invention generates a high-precision three-dimensional environmental model by scanning and collecting data on the overall environment of the apple orchard, thereby enabling the robot to accurately identify the terrain, vegetation distribution and obstacle locations within the apple orchard, providing reliable data support for the robot's path planning and automatic navigation, and improving the robot's efficiency and safety in intelligent monitoring of pests and diseases in the apple orchard.

[0202] Optionally, the walking mechanism includes a walking drive module, a suspension module and a steering module;

[0203] The walking drive module is used to provide power for the apple orchard pest and disease intelligent monitoring and early warning robot to walk;

[0204] The suspension module is used to cushion the impact of uneven ground on the walking of the apple orchard pest and disease intelligent monitoring and early warning robot;

[0205] The steering module is used to control the steering of the apple orchard pest and disease intelligent monitoring and early warning robot.

[0206] Specifically, the robot's walking mechanism (see Figure 4 The robot consists of a drive module, a suspension module, and a steering module. The drive module provides power for the robot, the suspension module provides shock absorption, and the steering module controls the robot's flexible steering in complex terrain.

[0207] The travel drive module includes four tires, axles, motors and transmissions (see Figure 4 and Figure 5 The motor drives the wheel axle to rotate through the transmission device, thereby driving the tires to move. Each tire is driven independently, thus achieving all-terrain adaptability.

[0208] The suspension module consists of springs, shock absorbers and suspension arms, which can effectively cushion the impact of uneven ground on the robot and improve the stability and comfort of the robot during walking.

[0209] The steering module includes a steering shaft, a steering motor, and a steering controller. The steering motor drives the front wheels through the steering shaft, thus enabling the robot to turn flexibly.

[0210] The embodiment of the present invention provides power for the robot to walk through the walking drive module, the suspension module cushions the impact of uneven ground on the robot, and the steering module controls the robot's flexible steering in complex terrain, thereby controlling the robot to walk smoothly in the apple orchard, allowing the robot to adapt to various complex terrains in the apple orchard, increasing the scope of intelligent monitoring of diseases and pests in the apple orchard, and realizing effective monitoring of large-scale apple orchards.

[0211] In order to further enable the robot to adapt to complex terrain such as wet, muddy or potholes when working in the apple orchard, the embodiment of the present invention also uses high-strength lightweight materials to make the chassis of the robot (see Figure 5 ), which makes it have stronger load-bearing capacity and corrosion resistance, thus providing better support for the robot.

[0212] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0213] It should also be noted that the terms "target," "first," and "second," etc., used in the present invention are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than that illustrated or described herein. Furthermore, the terms "first" and "second" generally distinguish objects of the same type, and do not limit the number of objects. For example, the first object can be one or more.

[0214] In the embodiments of the present application, "determine B based on A" means that the factor A must be considered when determining B. It is not limited to "B can be determined based on A alone", and should also include: "determine B based on A and C", "determine B based on A, C and E", "determine C based on A, and further determine B based on C", etc. It can also include taking A as a condition for determining B, for example, "when A meets the first condition, use the first method to determine B"; for example, "when A meets the second condition, determine B", etc.; for example, "when A meets the third condition, determine B based on the first parameter", etc. Of course, it can also be a condition that takes A as a factor in determining B, for example, "when A meets the first condition, use the first method to determine C, and further determine B based on C", etc.

[0215] In the present invention, the term "multiple" refers to two or more than two, and other quantifiers are similar to it.

[0216] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent monitoring and early warning robot for apple orchard pests and diseases, characterized by: include: Pest attracting and capturing module, image acquisition and processing module, data processing and analysis module, power supply module, and data transmission and communication module; The pest attracting and capturing module is used to attract and capture pests and perform inactivation treatment on the pests; The image acquisition and processing module includes at least a first camera, a second camera, and a third camera; the first camera and the second camera are used to collect real-time video streams from both sides of the apple orchard; the third camera is used to collect images of inactivated pests; The data processing and analysis module includes an orchard environmental data acquisition system, a pest and disease identification and counting system, a pest and disease monitoring and early warning system, and a knowledge question-answering system based on a knowledge graph; The orchard environmental data acquisition system is used to collect real-time environmental data of the apple orchard; The pest identification and counting system includes a pest identification subsystem and a pest counting subsystem; the pest identification subsystem is used to output pest detection results through the MH-YOLO model based on the real-time video streams on both sides of the apple orchard and the inactivated pest images; the pest counting subsystem is used to output the number of pests through the DeepSORT counting model based on the pest detection results; The pest and disease monitoring and early warning system is used to output a pest and disease early warning signal based on the real-time environmental data of the apple orchard, the pest and disease detection results and the number of pests and diseases; The knowledge graph-based knowledge question answering system is used to generate comprehensive pest and disease information based on the pest and disease detection results, the pest and disease quantity, and the pest and disease early warning signal; The power module is used to provide energy required for the operation of the apple orchard pest and disease intelligent monitoring and early warning robot; The data transmission and communication module is used for real-time transmission and storage of data.

2. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 1 is characterized in that: The MH-YOLO model is optimized based on the YOLOv5s model; The optimization includes at least a first optimization, a second optimization, a third optimization, and a fourth optimization; The first optimization is to introduce a CBAM attention mechanism into the backbone network of the YOLOv5s model, and the first optimization is used to enhance the perception ability of the YOLOv5s model of pest and disease characteristics; The second optimization is to introduce Swin-Transformer blocks into the first CSP2_1 module of the neck network of the YOLOv5s model, and the second optimization is used to enhance the information integration capability of the YOLOv5s model; The third optimization is to introduce the ASFF adaptive feature fusion module at the end of the neck network of the YOLOv5s model, and the third optimization is used to improve the YOLOv5s model's ability to recognize pest and disease characteristics; The fourth optimization is to perform structured pruning on the YOLOv5s model after the first optimization, the second optimization, and the third optimization. The fourth optimization is used to reduce the number of parameters and complexity of the YOLOv5s model.

3. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 1 is characterized in that: The DeepSORT counting model includes a region recognition module, a feature extractor, a Kalman filter, a feature association module and a re-identification module; The region recognition module is used to identify the pest and disease detection results output by the MH-YOLO model to obtain the pest and disease area; The feature extractor is used to extract features from the pest area and generate a feature vector describing the appearance features of the pest; The Kalman filter is used to predict the state of the pests and diseases based on the eigenvector to obtain a new state estimate; The feature association module is used to generate a pest tracking trajectory based on the new state estimation; The re-identification module is used to determine the number of pests and diseases based on the feature vector and the pest and disease tracking trajectory.

4. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 1 is characterized in that: The pest attracting and capturing module includes a capturing unit, an insect killing unit, an insect receiving plate, an insect dropping plate, a controller, a conveyor belt and a sweeper; The capture unit is used to capture apple orchard pests; The pest control unit is used to perform a deactivation treatment on the pests; the deactivation treatment includes a killing treatment and a drying treatment; The insect receiving plate is used to receive the pests after killing; The insect drop plate is used to receive the pests after drying and drop a predetermined number of pests onto the conveyor belt through a weight sensor; The controller is used to control the opening and closing mechanism so that the pests on the insect receiving plate fall onto the insect dropping plate after being dried; The conveyor belt is used to convey the pests dropped from the insect drop plate to the image acquisition and processing module; The cleaner is used to clean the pests adhered to or overlapped on the conveyor belt.

5. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 4 is characterized in that: The capture unit includes an impact plate and an insect trap light; The impact plates are placed crosswise to capture the lured apple orchard pests; The insect-attracting lamp is used for attracting pests in apple orchards.

6. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 5 is characterized in that: A sex attractant core is placed at the center of the impact plate, and the sex attractant core is used to attract apple orchard pests.

7. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 4 is characterized in that: The insecticide unit includes a high-temperature insecticide and an oven; The high-temperature insecticide is used to kill pests through high heat; The drying oven is used for drying the pests after the killing process.

8. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 1 is characterized in that: It also includes a walking and navigation module; the walking and navigation module includes a laser radar, a GPS module, a path planning unit, a walking mechanism and an obstacle avoidance sensor; The laser radar is used to generate a three-dimensional environment model based on the terrain, vegetation distribution and obstacle locations in the apple orchard; The GPS module is used to generate positioning information according to the real-time position of the apple orchard pest and disease intelligent monitoring and early warning robot; The path planning unit is used to generate a path planning map according to the three-dimensional environment model and the positioning information; The walking mechanism is used to control the apple orchard pest and disease intelligent monitoring and early warning robot to walk according to the path planning map; The obstacle avoidance sensor is used to detect obstacles ahead in real time while the apple orchard pest and disease intelligent monitoring and early warning robot is walking according to the path planning map.

9. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 8, characterized in that: The walking mechanism includes a walking drive module, a suspension module and a steering module; The walking drive module is used to provide power for the apple orchard pest and disease intelligent monitoring and early warning robot to walk; The suspension module is used to cushion the impact of uneven ground on the walking of the apple orchard pest and disease intelligent monitoring and early warning robot; The steering module is used to control the steering of the apple orchard pest and disease intelligent monitoring and early warning robot.

10. The apple orchard pest and disease intelligent monitoring and early warning robot according to claim 1, characterized in that: It also includes a user interface and a control module, which are used to support information interaction between the user and the apple orchard pest and disease intelligent monitoring and early warning robot.

Images