Indoor potted plant growth condition monitoring method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an indoor potted plant growth condition monitoring method and system, electronic equipment and a storage medium, and belongs to the field of plant state monitoring. The method comprises the following steps: acquiring indoor environment parameters and a potted leaf video, and processing the indoor environment parameters and the potted leaf video to obtain indoor environment target parameters and a leaf target area; according to the indoor environment target parameters, the growth environment of the potted plants is monitored; and for the leaf target area, a monitoring model is adopted to carry out pest and disease damage monitoring, when pest and disease damage is monitored, early warning information is generated, and the monitoring model is jointly constructed based on a YOLOv11 algorithm and a CNN convolutional neural network. Based on environment parameters collected in real time and a captured potted plant image, the YOLOv11 algorithm is utilized, so that disease spots and insect pests on potted plant leaves can be automatically recognized, early warning can be given out in time, a user can scientifically and efficiently manage plants, the health condition and growth efficiency of the plants are improved, and meanwhile resource saving and environment protection are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of plant status monitoring, and in particular to a method, system, electronic equipment and storage medium for monitoring the growth status of indoor potted plants. Background Art

[0002] The development of intelligent control technology and automation technology enables the system to automatically adjust environmental parameters such as temperature, humidity and light according to monitoring data to optimize plant growth conditions. At the same time, the system can automatically perform operations such as irrigation and spraying, reduce manual intervention, improve maintenance efficiency, and allow plants to grow under optimal conditions.

[0003] The IoT-based smart greenhouse indoor potted plant pest and disease monitoring system came into being, solving many challenges of indoor plant maintenance in modern urban life. With the acceleration of urbanization, more and more people choose to grow potted plants indoors to improve the quality of their living and working environments. However, indoor plants are susceptible to pests and diseases, and traditional maintenance methods rely on manual experience, which is inefficient and difficult to detect and deal with problems in a timely manner. Therefore, a more intelligent and efficient monitoring and management system is particularly necessary. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, system, electronic device and storage medium for monitoring the growth status of indoor potted plants, which are used to completely or at least partially solve the technical problems existing in the above-mentioned prior art.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for monitoring the growth status of indoor potted plants, comprising: Collecting indoor environmental parameters and potted plant leaf videos, and processing the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas; Monitoring the growth environment of the potted plants according to the indoor environmental target parameters; For the target area of ​​leaves, a pre-built monitoring model is used to monitor pests and diseases, and when pests and diseases are detected, early warning information is generated, wherein the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

[0006] Optionally, collecting indoor environmental parameters and a video of potted plant leaves, and processing the indoor environmental parameters and the video of potted plant leaves to obtain indoor environmental target parameters and a leaf target area includes: Indoor temperature, humidity, light, CO2 concentration and soil pH parameters are collected by temperature sensors, humidity sensors, light sensors, CO2 sensors preset at multiple locations indoors, and soil humidity sensors and soil pH sensors preset near the roots of potted plants. Indoor temperature, humidity, light, CO2 concentration and soil pH parameters are subjected to noise reduction to obtain indoor environmental target parameters. According to the cameras installed around the potted plants, the videos of the leaves of the potted plants are collected, and the videos of the leaves of the potted plants are subjected to noise reduction processing, and the brightness and contrast of the videos of the leaves of the potted plants are increased. The videos of the leaves of the potted plants are cropped to obtain the target area of ​​the leaves.

[0007] Optionally, the monitoring model building process includes: Using a high-definition camera to regularly record videos of potted plants indoors, and having experts mark the frames where the locations and types of pests and diseases appear in the videos to obtain marked frames, wherein the videos cover different viewing angles and lighting conditions; In the monitoring model selection and training stage, the CNN convolutional neural network is used to extract local features of the labeled frames. For pest and disease detection, the YOLOv11 target detection model is used to predict the location and category of local features; The loss function uses cross entropy loss and IoU loss, and the optimizer uses Adam optimizer. During the training process, the monitoring model continuously adjusts the weights to minimize the loss function. After the training is completed, the validation set is used to adjust the parameters to obtain the trained monitoring model.

[0008] Optionally, for the target area of ​​the leaf, a pre-built monitoring model is used to monitor pests and diseases, and when pests and diseases are detected, early warning information is generated, including: Dividing the leaf target area into grids, and placing a plurality of anchor frames for each grid, wherein each anchor frame contains a confidence score to indicate the score that each anchor frame contains leaf pests and diseases; The anchor frames are prioritized according to their confidence scores, and high-priority anchor frames are selected for pest and disease monitoring. When pests and diseases are detected, early warning information is generated, where the monitored pest and disease information includes the type, location, severity, and monitoring time of the pests and diseases.

[0009] On the other hand, the present invention also provides a system for monitoring the growth status of indoor potted plants applied to the method for monitoring the growth status of indoor potted plants, comprising: A data acquisition and processing module is used to acquire indoor environmental parameters and potted plant leaf videos, and process the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas; A data transmission and storage module is used to transmit the indoor environment target parameters and the blade target area to the central controller or the cloud platform through wireless communication technology, wherein when the central controller or the cloud platform receives the indoor environment target parameters and the blade target area, a local storage device is used for temporary storage, and the cloud platform uses a relational database for storage; The state monitoring module is used to monitor the growth environment of the potted plants according to the indoor environment target parameters, and to monitor the pests and diseases according to the leaf target area using a pre-built monitoring model. When pests and diseases are detected, early warning information is generated, wherein the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

[0010] Optionally, the data transmission and storage module uses SSL / TLS encryption when performing data transmission, and strictly controls user access rights, allowing authorized users to view and manage data.

[0011] Optionally, the indoor potted plant growth condition monitoring system also includes a deployment and application module, which is used to export the trained monitoring model into ONNX format and deploy the monitoring model on an edge device or a cloud platform.

[0012] Optionally, the indoor potted plant growth condition monitoring system further includes a visualization interface for displaying pest and disease information detected by the monitoring system, wherein the pest and disease information includes the type, location, severity and monitoring time of the pest and disease.

[0013] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for monitoring the growth status of indoor potted plants when executing the program.

[0014] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for monitoring the growth status of indoor potted plants are implemented.

[0015] Through the above technical solution, based on the real-time collection of environmental parameters and captured potted plant images, using the YOLOv11 algorithm, it is possible to automatically identify disease spots and pests on potted plant leaves, and issue early warnings in a timely manner, so that users can manage plants scientifically and efficiently, improve the health and growth efficiency of plants, and achieve resource conservation and environmental protection at the same time.

[0016] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 is an implementation flow chart of a method for monitoring the growth status of indoor potted plants provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a system for monitoring the growth status of indoor potted plants applied to a method for monitoring the growth status of indoor potted plants provided by an embodiment of the present invention; Figure 3 It is a working principle diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0019] See also Figure 1 As shown, it is a flowchart of an implementation method of a method for monitoring the growth status of indoor potted plants provided by an embodiment of the present invention, including the following execution steps: Step 100: Collect indoor environmental parameters and potted plant leaf videos, and process the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas.

[0020] Specifically, when executing step 100, the following steps may be specifically performed: S1000: Collect indoor temperature, humidity, light, CO2 concentration and soil pH parameters based on temperature sensors, humidity sensors, light sensors, CO2 sensors preset at multiple locations indoors, and soil moisture sensors and soil pH sensors preset near the roots of potted plants, and perform noise reduction on the indoor temperature, humidity, light, CO2 concentration and soil pH parameters to obtain indoor environmental target parameters.

[0021] S1001: According to the cameras installed around the potted plants, a video of the leaves of the potted plants is collected, and the video of the leaves of the potted plants is subjected to noise reduction processing, and the brightness and contrast of the video of the leaves of the potted plants are increased, and the video of the leaves of the potted plants is cropped to obtain a target leaf area.

[0022] Step 101: monitor the growth environment of the potted plants according to the indoor environmental target parameters.

[0023] Step 102: For the target leaf area, a pre-built monitoring model is used to monitor pests and diseases, and when pests and diseases are detected, early warning information is generated.

[0024] Among them, the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

[0025] Specifically, the construction process of the monitoring model includes the following steps: S1: A high-definition camera is used to regularly record videos of potted plants indoors, and an expert marks frames of locations and types of pests and diseases in the videos to obtain marked frames, wherein the videos cover different viewing angles and lighting conditions.

[0026] S2: In the monitoring model selection and training stage, the CNN convolutional neural network is used to extract local features of the labeled frames. For pest and disease detection, the YOLOv11 target detection model is used to predict the location and category of local features.

[0027] S3: The loss function uses cross entropy loss and IoU loss, and the optimizer uses Adam optimizer. During the training process, the monitoring model continuously adjusts the weights to minimize the loss function. After the training is completed, the validation set is used to adjust the parameters to obtain the trained monitoring model.

[0028] Specifically, when executing step 102, the following steps may be specifically performed: S1020: Divide the leaf target area into grids, and place multiple anchor frames for each grid, wherein each anchor frame contains a confidence score to indicate the score that each anchor frame contains leaf pests and diseases.

[0029] S1021: Prioritize the anchor frames according to the confidence score of each anchor frame, and select the anchor frames with high priority for pest monitoring. When pests are detected, generate warning information, wherein the detected pest information includes the type, location, severity and monitoring time of the pests.

[0030] See also Figure 2 FIG. 1 is a schematic diagram of a structure of a monitoring system for indoor potted plant growth conditions applied to a monitoring method for indoor potted plant growth conditions provided by an embodiment of the present invention, comprising: The data acquisition and processing module 20 is used to acquire indoor environmental parameters and potted plant leaf videos, and process the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas; The data transmission and storage module 21 is used to transmit the indoor environment target parameters and the blade target area to the central controller or the cloud platform through wireless communication technology, wherein when the central controller or the cloud platform receives the indoor environment target parameters and the blade target area, a local storage device is used for temporary storage, and the cloud platform uses a relational database for storage; The status monitoring module 22 is used to monitor the growth environment of the potted plants according to the indoor environment target parameters, and to monitor pests and diseases according to the leaf target area using a pre-built monitoring model. When pests and diseases are detected, early warning information is generated, wherein the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

[0031] In some embodiments, the data acquisition and processing module 20 monitors the environmental parameters in the greenhouse in real time by integrating multiple sensors to ensure that the plants grow under optimal conditions. Specifically, the module includes a temperature sensor, a humidity sensor, a light sensor, a CO2 sensor, and a soil pH sensor, which are installed at different locations in the greenhouse to comprehensively and accurately monitor the environmental parameters.

[0032] Temperature sensors are installed at multiple key locations in the greenhouse, such as near the roots of plants, near the leaves, and at the entrance and exit of the greenhouse to fully monitor temperature changes. Data is collected every 5 minutes to ensure real-time grasp of temperature changes. Humidity sensors are installed at different heights and locations in the greenhouse, such as air humidity sensors installed on the top of the greenhouse, and soil humidity sensors installed near the roots of plants, to monitor air and soil humidity, maintain a suitable humidity environment, and prevent over-humidity or over-dryness. Light sensors are installed at different locations in the greenhouse, such as near windows or light sources, to monitor light intensity at different locations to ensure that plants get enough light to promote photosynthesis. CO2 sensors are installed at vents and densely planted areas in the greenhouse to monitor carbon dioxide concentrations, optimize the growth environment of plants, and improve photosynthesis efficiency. Soil pH sensors are installed in the soil near the roots of plants to detect soil acidity and alkalinity to ensure that the soil is suitable for plant growth and avoid poor plant growth due to improper soil acidity and alkalinity.

[0033] The sensor collects environmental parameters regularly, collecting temperature, humidity, light, CO2 and soil pH data every 5 minutes. The collected data is output in a standard format for subsequent processing. The sensor transmits the data to the central controller or cloud platform through wireless communication technology. Each data packet contains the sensor type, collection time and collection data to ensure the integrity and traceability of the data. The central controller receives the data from the sensor and performs preliminary processing and storage. The central controller transmits the processed data to the cloud platform via the Internet, and the cloud platform is responsible for long-term storage and management of the data. The cloud platform uses a relational database to store data to ensure data security and reliability.

[0034] The data processing module cleans the collected data, removes outliers and noise, and ensures the accuracy of the data. Different types of sensor data are integrated to comprehensively evaluate the growth environment of plants. By combining temperature, humidity and light data, the plant growth index is calculated; by combining soil moisture and pH data, the suitability of the soil is evaluated. Through multimodal data fusion, a comprehensive environmental assessment is provided to help users better understand the growth status of plants. The system can automatically detect abnormal changes in environmental parameters and issue early warnings in time to help users take measures to avoid plant damage. Users can view environmental parameters anytime and anywhere through mobile applications or web interfaces to achieve remote monitoring and management.

[0035] In some embodiments, by integrating high-definition cameras and multiple sensors, video of plant leaves and environmental parameters are collected and processed in real time to provide high-quality input for pest and disease detection.

[0036] Install high-definition cameras around the plants to record videos of the plant leaves regularly. The camera records a video every hour to ensure that the latest status of the plant is captured. The recorded video is transmitted to the central controller or cloud platform through wireless communication technology. In order to improve the video quality, the system uses a video processing library to pre-process the collected video, including operations such as denoising, enhancement, and cropping. The denoising step removes noise from the video and improves the clarity of the video; the enhancement step adjusts the brightness and contrast of the video to make the details of the leaves more obvious; the cropping step crops out irrelevant parts of the video and focuses on the leaf area.

[0037] The system uses the YOLOv11 algorithm to detect pests and diseases in videos, and can quickly and accurately detect and locate disease spots and pests on plant leaves in a real-time environment. The algorithm extracts features from video frames, identifies abnormal areas on leaves, and generates detection results. When the system detects pests and diseases, it immediately generates an early warning message and pushes it to the user's mobile phone or computer through wireless communication technology. The system also provides specific treatment suggestions, such as spraying pesticides and pruning, to help users take timely measures to prevent the spread of pests and diseases.

[0038] In some embodiments, the data transmission and storage module 21 is responsible for the transmission, storage and management of video data collected from field cameras to ensure the integrity and availability of the data. First, a high-definition camera is used to regularly record videos of crops in the field. These videos should cover different viewing angles and lighting conditions to increase the generalization ability of the model. The camera records a video every hour to ensure that the latest status of the plant is captured. The recorded video is transmitted to the central controller or cloud platform via wireless communication technology. Each video clip is accompanied by a timestamp and geographic location information to ensure the integrity and traceability of the data. In order to ensure the stability and reliability of data transmission, dual-channel transmission is adopted to prevent data loss or damage.

[0039] The central controller receives data from the camera and performs preliminary processing and storage. The central controller uses local storage devices to temporarily store data to ensure the temporary security of the data. Preliminary processing includes video decoding, compression, and format conversion to facilitate subsequent transmission and processing. The central controller transmits the processed data to the cloud platform via the Internet, and the cloud platform is responsible for long-term storage and management of data. The cloud platform uses a relational database to store data to ensure data security and reliability. The cloud platform also provides data backup and recovery functions to ensure data persistence and availability. Data backup can be performed regularly to prevent accidental data loss.

[0040] The cloud platform further processes the uploaded data, including video preprocessing and data cleaning, to ensure data accuracy and consistency. The processed data can be used to train and verify deep learning models to improve model performance and generalization capabilities. The cloud platform provides a user-friendly interface, where users can access and manage data through web pages or mobile applications. Users can view historical video records, test results, and environmental parameters for remote monitoring and management. The system also supports data export, where users can export data to a standard format for further analysis and research.

[0041] In some embodiments, in order to protect the security of data, the cloud platform adopts a variety of security measures, including data encryption, identity authentication and access control. The data transmission and storage module 21 adopts SSL / TLS encryption mode for data transmission, and strictly controls user access rights, allowing authorized users to view and manage data, and regularly record crop videos through drones or fixed cameras to detect pests and diseases in real time. The test results can be pushed to the user terminal in real time through the cloud platform to help users take measures in time. The system can also combine meteorological data, soil data, etc. to provide more accurate pest and disease control solutions. Users can view historical data through the cloud platform, analyze the occurrence patterns and trends of pests and diseases, and provide a scientific basis for future pest and disease prevention. The system supports data visualization, and users can generate charts and reports to intuitively display data changes and analysis results.

[0042] In some embodiments, the indoor potted plant growth condition monitoring system further includes a deployment and application module for exporting the trained monitoring model into ONNX format and deploying the monitoring model on an edge device or a cloud platform.

[0043] In some embodiments, the construction of the status monitoring module 22 includes: 1. Data collection and preprocessing: Data collection is the basis of the entire process. Use high-definition cameras to regularly record videos of crops in the field. These videos should cover different viewing angles and lighting conditions to increase the generalization ability of the model. After the video is recorded, experts will annotate the frames in the video to mark the location and type of pests and diseases. Next, the video is preprocessed, including video enhancement to increase the diversity of the data set, normalization for model training, and data segmentation. 2. Model selection and training: In the model selection and training stage, a convolutional neural network (CNN) is used to effectively extract local features of the image. For pest and disease detection, the target detection model YOLOv11 is used, which can simultaneously predict the location and category of the target. Data loading uses PyTorch's DataLoader to batch load preprocessed video data. The loss function uses cross entropy loss (for classification tasks) and IoU loss (for target detection tasks). The optimizer uses Adam. During the training process, the model will continuously adjust the weights to minimize the loss function. After the training is completed, the validation set is used to adjust the parameters to ensure the generalization ability of the model. Export the trained model to ONNX format. The model can be deployed on edge devices (such as embedded devices, drones) to achieve low-latency real-time detection, or it can be deployed on cloud platforms to provide services through API interfaces. Specific application scenarios include regularly recording crop videos through drones or fixed cameras to detect pests and diseases in real time; developing mobile applications, users can obtain pest and disease detection results and treatment suggestions by uploading recorded videos; combining meteorological data, soil data, etc. to provide more accurate pest and disease control solutions.

[0044] On the other hand, the indoor potted plant growth status monitoring system also includes a visualization interface for displaying pest and disease information detected by the monitoring system, wherein the pest and disease information includes the type, location, severity and monitoring time of the pest and disease.

[0045] Specifically, first, the user enters the system by entering the username and password through the login page. New users can create an account through the registration page, fill in the necessary information such as name, email address and mobile phone number, and use the system after completing the registration.

[0046] After logging in, users enter the homepage overview page, which displays the overall health of the current crops, including the latest pest and disease detection results, real-time environmental parameters (such as temperature, humidity, light intensity, etc.), and the most recent video surveillance footage. The homepage also provides quick navigation buttons for users to quickly access other functional modules.

[0047] The video monitoring page displays the video stream transmitted in real time from the field camera. Users can select different cameras to view the real-time images of different plots. The timeline below the video allows users to play back historical videos and view the monitoring status of a specific time period. The video monitoring page also supports the screenshot function, so users can save key images for further analysis or recording.

[0048] The detection results page displays information about pests and diseases that the system automatically detects, including the type, location, severity, and detection time of the pests and diseases. Users can view a detailed detection report that includes images of the pests and diseases, location annotations, and recommended treatment measures. The page also provides search and filtering functions, allowing users to find specific detection records based on date, plot, or pest and disease type.

[0049] The environmental parameters page displays real-time environmental data in the field, including temperature, humidity, light intensity, carbon dioxide concentration, soil pH, etc. The data is displayed in charts, and users can view trend charts of historical data and analyze the impact of environmental changes on crops. The page also provides an alarm function. When environmental parameters exceed the set range, the system will automatically send an alarm to notify the user.

[0050] The history page records all system operations and test results. Users can view past video surveillance records, test reports, and environmental parameter data. The page supports export functions, and users can export data to CSV or PDF files for easy archiving and sharing.

[0051] The settings and management page allows users to configure various parameters of the system, including camera settings, environmental parameter thresholds, notification settings, etc. Users can add or delete cameras, set data transmission frequency, and adjust the alarm thresholds of environmental parameters. The page also provides account management functions, where users can modify personal information, change passwords, or log out of their accounts.

[0052] The Help and Support page provides a guide to using the system and answers to frequently asked questions. Users can view detailed instructions to learn how to operate each functional module. The page also provides an online customer service function, where users can contact the technical support team through a chat window or email to solve problems encountered during use.

[0053] See also Figure 3As shown, it is a working principle diagram provided by an embodiment of the present invention, including: firstly, data collection (high-definition camera recording, labeling tool LabelMe, video preprocessing), data transmission (using wireless communication technology, transmission data including timestamp and geographic location, redundant transmission mechanism), then data storage (central controller, local storage device, cloud platform, database, data backup and recovery), data management (video preprocessing, data clarity, data access and management, data security), model training (model selection, data loading, loss function, optimizer, training and parameter adjustment), model evaluation and optimization (evaluation indicators, confusion matrix, hyperparameter tuning, integrated learning, transfer learning), model deployment (export to ONNX format, edge device deployment, cloud platform deployment), user page (login and registration, homepage overview, video monitoring, detection results, environmental parameters, history, settings and management, help and support).

[0054] On the other hand, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for monitoring the growth status of indoor potted plants when executing the program.

[0055] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for monitoring the growth status of indoor potted plants are implemented.

[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0057] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0058] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0059] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0060] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0061] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0062] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0063] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0064] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for monitoring the growth status of indoor potted plants, characterized in that: include: Collecting indoor environmental parameters and potted plant leaf videos, and processing the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas; Monitoring the growth environment of the potted plants according to the indoor environmental target parameters; For the target area of ​​leaves, a pre-built monitoring model is used to monitor pests and diseases, and when pests and diseases are detected, early warning information is generated, wherein the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

2. The method for monitoring the growth status of indoor potted plants according to claim 1, characterized in that: Collecting indoor environmental parameters and potted plant leaf videos, and processing the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas, including: Indoor temperature, humidity, light, CO2 concentration and soil pH parameters are collected by temperature sensors, humidity sensors, light sensors, CO2 sensors preset at multiple locations indoors, and soil humidity sensors and soil pH sensors preset near the roots of potted plants. Indoor temperature, humidity, light, CO2 concentration and soil pH parameters are subjected to noise reduction to obtain indoor environmental target parameters. According to the cameras installed around the potted plants, the videos of the leaves of the potted plants are collected, and the videos of the leaves of the potted plants are subjected to noise reduction processing, and the brightness and contrast of the videos of the leaves of the potted plants are increased. The videos of the leaves of the potted plants are cropped to obtain the target area of ​​the leaves.

3. The method for monitoring the growth status of indoor potted plants according to claim 1, characterized in that: The monitoring model construction process includes: Using a high-definition camera to regularly record videos of potted plants indoors, and having experts mark the frames where the locations and types of pests and diseases appear in the videos to obtain marked frames, wherein the videos cover different viewing angles and lighting conditions; In the monitoring model selection and training stage, the CNN convolutional neural network is used to extract local features of the labeled frames. For pest and disease detection, the YOLOv11 target detection model is used to predict the location and category of local features; The loss function uses cross entropy loss and IoU loss, and the optimizer uses Adam optimizer. During the training process, the monitoring model continuously adjusts the weights to minimize the loss function. After the training is completed, the validation set is used to adjust the parameters to obtain the trained monitoring model.

4. The method for monitoring the growth status of indoor potted plants according to claim 1, characterized in that: For the target area of ​​the leaves, a pre-built monitoring model is used to monitor pests and diseases. When pests and diseases are detected, early warning information is generated, including: Dividing the leaf target area into grids, and placing a plurality of anchor frames for each grid, wherein each anchor frame contains a confidence score to indicate the score that each anchor frame contains leaf pests and diseases; The anchor frames are prioritized according to their confidence scores, and high-priority anchor frames are selected for pest and disease monitoring. When pests and diseases are detected, early warning information is generated, where the monitored pest and disease information includes the type, location, severity, and monitoring time of the pests and diseases.

5. A system for monitoring the growth status of indoor potted plants applied to the method for monitoring the growth status of indoor potted plants according to any one of claims 1 to 4, characterized in that: include: A data acquisition and processing module is used to acquire indoor environmental parameters and potted plant leaf videos, and process the indoor environmental parameters and potted plant leaf videos to obtain indoor environmental target parameters and leaf target areas; A data transmission and storage module is used to transmit the indoor environment target parameters and the blade target area to the central controller or the cloud platform through wireless communication technology, wherein when the central controller or the cloud platform receives the indoor environment target parameters and the blade target area, a local storage device is used for temporary storage, and the cloud platform uses a relational database for storage; The state monitoring module is used to monitor the growth environment of the potted plants according to the indoor environment target parameters, and to monitor the pests and diseases according to the leaf target area using a pre-built monitoring model. When pests and diseases are detected, early warning information is generated, wherein the pre-built monitoring model is jointly constructed based on the YOLOv11 algorithm and the CNN convolutional neural network.

6. The indoor potted plant growth status monitoring system according to claim 5, characterized in that: The data transmission and storage module uses SSL / TLS encryption when performing data transmission, and strictly controls user access rights, allowing authorized users to view and manage data.

7. The indoor potted plant growth status monitoring system according to claim 5, characterized in that: The indoor potted plant growth condition monitoring system also includes a deployment and application module, which is used to export the trained monitoring model into ONNX format and deploy the monitoring model on an edge device or a cloud platform.

8. The indoor potted plant growth status monitoring system according to claim 5, characterized in that: The indoor potted plant growth condition monitoring system also includes a visualization interface for displaying pest and disease information detected by the monitoring system, wherein the pest and disease information includes the type, location, severity and monitoring time of the pest and disease.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for monitoring the growth status of indoor potted plants as described in any one of claims 1 to 4 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring the growth status of indoor potted plants as described in any one of claims 1 to 4 are implemented.

Images