Strawberry intelligent precision growth management system and method based on internet of things

Abstract

This invention relates to the field of smart agriculture technology, and specifically discloses an intelligent precision growth management system and method for strawberries based on the Internet of Things. The system includes: a perception layer that collects real-time data on the actual growth environment and growth status of strawberry seedlings; a growth environment analysis layer that compares the actual and target growth environment data to obtain the deviation as a control analysis result; a growth status analysis layer that combines the growth status data with the current target growth stage to provide a growth status analysis result; a growth environment optimization layer that, based on the above two results, calculates the amount of environmental data supplementation and optimizes the target growth environment control data for the next adjacent control cycle to obtain the optimal growth environment control data; and a control layer that, based on the optimal growth environment control data, adjusts the execution equipment in real-time to obtain the latest growth management results of the strawberry seedlings, achieving precise control and optimization of the strawberry seedling growth environment. This improves the accuracy and scientific nature of strawberry growth management, contributing to increased strawberry yield and quality.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture technology, and in particular to an intelligent precision growth management system and method for strawberries based on the Internet of Things. Background Technology

[0002] In recent years, the application of IoT technology in agriculture has gradually deepened, and strawberry cultivation management is also gradually developing towards intelligence and data-driven approaches. In existing technologies, IoT-based strawberry growth monitoring systems typically acquire real-time strawberry growth environment data and plant phenotypic information by deploying environmental sensors (such as temperature, humidity, light intensity, soil pH, and CO2 concentration) and image acquisition equipment. Some systems combine wireless communication technologies (such as LoRa and NB-IoT) to transmit data to a cloud platform for storage and analysis. Regarding environmental control, existing technologies achieve automated control by setting fixed thresholds or simple logical rules (such as threshold-triggered irrigation and ventilation). Some studies attempt to introduce machine learning models (such as decision trees and random forests) to perform correlation analysis between historical environmental data and yield, generating static control strategies. For growth monitoring, existing technologies mostly use image recognition or spectral analysis to assess indicators such as strawberry leaf color, plant height, and fruit maturity, comparing them with preset growth stage models. In addition, some systems integrate expert knowledge bases to provide farmers with fertilization and pest and disease control suggestions.

[0003] However, existing technologies generally focus on single-dimensional data acquisition or control execution, lacking the ability to collaboratively analyze and dynamically optimize multi-source heterogeneous data. Existing systems often process environmental and growth data independently, failing to establish a dynamic coupling relationship between the two, leading to a disconnect between environmental control strategies and the actual physiological needs of the plants. For example, irrigation is triggered solely based on soil moisture thresholds, ignoring the differences in transpiration efficiency and water requirements during fruit enlargement. Relying on preset fixed thresholds or historical data models fails to dynamically adapt to changes in optimal environmental parameters at different strawberry growth stages. Especially during periods of frequent climate change or fluctuations in facility environment, this can easily lead to resource waste (e.g., excessive supplemental lighting) or growth inhibition (e.g., failure to intervene promptly when temperatures rise sharply). Existing growth analysis models are mostly based on general growth cycle divisions, resulting in biased growth diagnosis. For example, the same leaf area index may correspond to opposite control requirements during flower bud differentiation and fruit ripening. Execution equipment controls only compensate for current environmental deviations, failing to incorporate future growth trend predictions for rolling optimization of target parameters for the next control cycle, easily falling into a vicious cycle of "lagging response—frequent adjustments." The perception, analysis, and control layers mostly adopt an isolated architecture, with data flow transmitted in one direction, failing to form a closed loop of "monitoring-decision-execution-feedback", making it difficult to achieve the optimal synergy between environmental parameters and growth targets.

[0004] Therefore, this invention proposes an intelligent precision growth management system and method for strawberries based on the Internet of Things. Summary of the Invention

[0005] This invention provides an intelligent precision growth management system and method for strawberries based on the Internet of Things (IoT), comprising: a sensing layer that collects data in real time, providing an accurate and timely information foundation for subsequent analysis and control; a growth environment analysis layer that identifies deviations in the growth environment, helping to accurately identify problems and take targeted measures; a growth status analysis layer that analyzes growth status data and the current target growth stage to comprehensively assess the growth status of strawberry seedlings; a linkage between the growth environment analysis layer and the growth status analysis layer, combining environmental deviations (such as insufficient CO2 concentration) with growth stages (such as the need for a higher carbon assimilation rate during flowering) to generate differentiated supplementation calculation logic; a growth environment optimization layer that optimizes target growth environment control data by analyzing supplementation amounts, achieving refined management; a rolling update of target environmental parameters (such as time-segmented temperature and humidity curves) for the next cycle based on current analysis results, rather than static thresholds; and a control layer that controls the execution equipment in real time based on optimal growth environment control data, ensuring the timely and effective implementation of management measures. Furthermore, by providing real-time feedback on the latest growth management results, an adaptive iterative optimization chain is formed, ultimately achieving a high-precision match between environmental resource input and the physiological needs of strawberries. By integrating multi-source data at the perception layer, dynamically coupling the growth environment and growth status analysis layer, implementing rolling prediction and regulation at the optimization layer, and closing-loop execution at the control layer, the shortcomings of existing technologies are overcome one by one. This improves the accuracy and scientific nature of strawberry growth management, contributing to increased strawberry yield and quality.

[0006] This invention provides an intelligent precision growth management system for strawberries based on the Internet of Things, comprising:

[0007] The perception layer is used to collect real-time data on the actual growth environment and growth status of strawberry seedlings.

[0008] The growth environment analysis layer is used to determine the deviation between the actual growth environment data and the target growth environment data of strawberry seedlings as the result of the growth environment control analysis of strawberry seedlings.

[0009] The growth analysis layer is used to analyze the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings to obtain the growth analysis results.

[0010] The growth environment optimization layer is used to analyze the supplementary amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control and growth status, and optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the supplementary amount of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0011] The control layer is used to control the execution equipment in real time based on the optimal growth environment control data of the strawberry seedlings in the next adjacent control cycle, so as to obtain the latest growth management results of the strawberry seedlings.

[0012] Preferably, the perception layer includes:

[0013] The growth environment sensing module is used to collect real-time data on the actual growth environment of strawberry seedlings based on multiple sensors distributed in multiple locations within the greenhouse.

[0014] The growth sensing module is used to fit the appearance images of all strawberry seedlings in the greenhouse as growth data based on real-time monitoring images of strawberry seedlings from multiple perspectives.

[0015] Preferably, the growth environment sensing module includes:

[0016] The temperature sensing submodule is used to monitor the ambient temperature at corresponding locations within the greenhouse in real time based on temperature sensors distributed at different heights and positions within the greenhouse.

[0017] The humidity sensing submodule is used to monitor the ambient humidity at corresponding locations within the greenhouse in real time based on humidity sensors distributed at different heights and positions within the greenhouse.

[0018] The carbon dioxide concentration sensing submodule is used to monitor the carbon dioxide concentration at corresponding locations within the greenhouse in real time based on carbon dioxide concentration sensors distributed at different heights and positions within the greenhouse.

[0019] The actual growth environment data for strawberry seedlings includes: ambient temperature, humidity, and carbon dioxide concentration at multiple locations within the greenhouse.

[0020] Preferably, the growth sensing module includes:

[0021] The strawberry seedling image extraction submodule is used to extract the strawberry seedling image region from the monitoring image of the strawberry seedling from each viewpoint.

[0022] The feature matching submodule is used to generate the feature vector of each pixel in the strawberry seedling image region of each viewpoint, and to take the quotient of the dot product of the feature vectors of any two pixels in the strawberry seedling image region of any two viewspoints and the product of the moduli of the feature vectors of the corresponding two pixels as the feature matching degree between any two pixels in the strawberry seedling image region of any two viewspoints.

[0023] The pixel matching submodule is used to obtain all matching pixel combinations in the strawberry seedling image region of each pair of views, based on the pixel combinations whose feature matching degree exceeds the matching degree threshold.

[0024] The perspective fusion submodule is used to perform perspective fusion on the strawberry seedling image regions of all perspectives based on the combination of all matching pixels in the strawberry seedling image regions of every two perspectives, so as to obtain the appearance images of all strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings.

[0025] Preferably, the view fusion submodule includes:

[0026] The image matching unit is used to summarize the remaining strawberry seedling image regions with the largest total number of matching pixels with a single viewpoint image region to obtain at least one image region group.

[0027] The distortion analysis unit is used to generate distortion data for the strawberry seedling image regions corresponding to the two viewpoints, based on the relative position vectors between pairs of pixels belonging to the same strawberry seedling image region in all matching pixel combinations in every two viewpoints of the strawberry seedling image region in each image region group.

[0028] The distortion correction unit is used to perform uniform distortion correction on all strawberry seedling image regions in the corresponding image region group based on the distortion data of strawberry seedling image regions from every two perspectives in each image region group, so as to obtain the first corrected image group of each image region group.

[0029] The filtering and fusion unit is used to filter and fuse all the first corrected images in all the first corrected image groups to obtain the appearance images of all the strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings.

[0030] Preferably, the filtering and fusion unit includes:

[0031] An interference filtering subunit is used to filter interference pixels in all first corrected images in each first corrected image group to obtain a second corrected image group for each first corrected image group.

[0032] The pixel fusion subunit is used to fuse all matching pixel combinations in each second corrected image group based on pixel weighted averaging to obtain multiple strawberry seedling perspective fused images;

[0033] The cyclic fusion subunit is used to continue fusion of the perspective images of all strawberry seedlings until the appearance images of all strawberry seedlings in the greenhouse are obtained as the growth data of the strawberry seedlings.

[0034] Preferably, the growth analysis layer includes:

[0035] The actual growth stage analysis module is used to determine the actual growth stage of strawberry seedlings based on their growth data.

[0036] The target growth stage acquisition module is used to determine the current target growth stage of strawberry seedlings based on the strawberry planting plan.

[0037] The growth analysis module is used to analyze the growth of strawberry seedlings based on their actual growth stage and current target growth stage.

[0038] Preferably, the actual growth stage analysis module includes:

[0039] The similarity calculation submodule is used to generate multi-dimensional feature vectors of strawberry seedlings based on the growth data of strawberry seedlings. The quotient of the dot product of the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage, and the product of the modulus of the multi-dimensional feature vector of the strawberry seedling and the modulus of the standard multi-dimensional feature vector of the corresponding growth stage, is used as the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage.

[0040] The growth stages are roughly divided into sub-modules to use the growth stages with the highest similarity as the actual rough growth stages of the strawberry seedlings.

[0041] The stage refinement progress determination submodule is used to take the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the sum of the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the next adjacent growth stage of the actual growth stage, as the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling, and take the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling as the actual growth stage of the strawberry seedling.

[0042] Preferably, the growth environment optimization layer includes:

[0043] The primary supplementation analysis module is used to determine the primary supplementation amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control.

[0044] The secondary supplementation analysis module is used to analyze the secondary supplementation amount of strawberry seedling growth environment data based on the growth analysis results of strawberry seedlings;

[0045] The environmental control optimization module is used to optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the primary and secondary replenishment amounts of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0046] The supplementary data on the strawberry seedling growth environment includes both primary and secondary supplementary data.

[0047] This invention provides an IoT-based intelligent precision growth management method for strawberries, applicable to any of the above-mentioned IoT-based intelligent precision growth management systems for strawberries, comprising:

[0048] S1: Real-time collection of actual growth environment data and growth data of strawberry seedlings;

[0049] S2: Determine the deviation data between the actual growth environment data and the target growth environment data of the strawberry seedlings as the results of the strawberry seedling growth environment control analysis;

[0050] S3: Based on the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings, the growth analysis results of strawberry seedlings are obtained;

[0051] S4: Based on the analysis results of the strawberry seedling growth environment control and growth status, the amount of supplementary strawberry seedling growth environment data is determined. Based on the amount of supplementary strawberry seedling growth environment data, the target growth environment control data of strawberry seedlings in the next adjacent control period is optimized to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0052] S5: Based on the optimal growth environment control data of strawberry seedlings in the next adjacent control cycle, the execution equipment is controlled in real time to obtain the latest growth management results of strawberry seedlings.

[0053] The beneficial effects of this invention compared to existing technologies are as follows: The sensing layer collects data in real time, providing an accurate and timely information foundation for subsequent analysis and control. The growth environment analysis layer identifies deviations in the growth environment, helping to accurately identify problems and take targeted measures. The growth status analysis layer analyzes growth data and the current target growth stage to comprehensively assess the growth status of strawberry seedlings. The growth environment analysis layer and the growth status analysis layer work together to combine environmental deviations (such as insufficient CO2 concentration) with growth stages (such as the need for a higher carbon assimilation rate during flowering) to generate differentiated supplementation calculation logic. The growth environment optimization layer optimizes the target growth environment control data by analyzing the supplementation amount, achieving refined management. Based on the current analysis results, the growth environment optimization layer continuously updates the target environmental parameters (such as time-segmented temperature and humidity curves) for the next cycle, rather than using static thresholds. The control layer controls the execution equipment in real time based on the optimal growth environment control data, ensuring the timely and effective implementation of management measures. By providing real-time feedback on the latest growth management results, an adaptive iterative optimization chain is formed, ultimately achieving a high-precision match between environmental resource input and the physiological needs of strawberries. By integrating multi-source data at the perception layer, dynamically coupling the growth environment and growth status analysis layer, implementing rolling prediction and regulation at the optimization layer, and closing-loop execution at the control layer, the shortcomings of existing technologies are overcome one by one. This improves the accuracy and scientific nature of strawberry growth management, contributing to increased strawberry yield and quality.

[0054] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0055] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0056] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0057] Figure 1 This is a schematic diagram of an IoT-based intelligent precision growth management system for strawberries in an embodiment of the present invention.

[0058] Figure 2 This is a schematic diagram showing the connection of various sensors in the growth environment sensing module of this invention.

[0059] Figure 3 This is a flowchart of the intelligent and precise strawberry growth management method based on the Internet of Things in an embodiment of the present invention. Detailed Implementation

[0060] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0061] Example 1:

[0062] This invention provides an intelligent and precise strawberry growth management system based on the Internet of Things (IoT), with reference to... Figure 1 ,include:

[0063] The perception layer is used to collect real-time data on the actual growth environment and growth status of strawberry seedlings.

[0064] The growth environment analysis layer is used to determine the deviation between the actual growth environment data and the target growth environment data of strawberry seedlings as the result of the growth environment control analysis of strawberry seedlings.

[0065] The growth analysis layer is used to analyze the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings to obtain the growth analysis results.

[0066] The growth environment optimization layer is used to analyze the supplementary amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control and growth status, and optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the supplementary amount of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0067] The control layer is used to control the execution equipment in real time based on the optimal growth environment control data of the strawberry seedlings in the next adjacent control cycle, so as to obtain the latest growth management results of the strawberry seedlings.

[0068] In this embodiment, the target growth environment data are pre-set ideal environmental parameter values ​​suitable for strawberry seedlings at a specific growth stage, such as ideal temperature, humidity, carbon dioxide concentration, etc.

[0069] In this embodiment, the deviation between the actual growth environment data and the target growth environment data of the strawberry seedling is determined by comparing the data of the actual environment of the strawberry seedling (such as actual temperature, humidity, etc.) with the preset ideal environment data to calculate the difference between the two.

[0070] In this embodiment, the current target growth stage of the strawberry seedling refers to the growth and development stage that the strawberry seedling should be in, such as the seedling stage, flowering stage, or fruiting stage, determined according to the strawberry planting plan and growth pattern.

[0071] In this embodiment, based on the analysis results of the growth environment control and growth status analysis of strawberry seedlings, the amount of supplementary data on the growth environment of strawberry seedlings is determined. That is, taking into account the deviation of the growth environment and the growth status of strawberry seedlings, the amount of environmental parameters that need to be supplemented or adjusted in order to improve the growth environment of strawberry seedlings is calculated.

[0072] In this embodiment, the target growth environment control data for strawberry seedlings in the next adjacent control cycle is the expected environmental parameter control target value set for the strawberry seedlings for the upcoming next control cycle.

[0073] In this embodiment, the target growth environment control data of strawberry seedlings in the next adjacent control cycle is optimized based on the amount of supplementary environmental data. This yields the optimal growth environment control data for the strawberry seedlings in the next adjacent control cycle. Specifically, the pre-set target environment data for the next control cycle is adjusted and improved based on the calculated amount of supplementary environmental data, thus obtaining the most suitable environmental control data for strawberry seedling growth. For example, a pre-trained target environment data adjustment and improvement model can be used for optimization. The supplementary amount of strawberry seedling growth environment data is input into the pre-trained target environment data adjustment and improvement model to obtain the optimal growth environment control data for the next adjacent control cycle. This forms a closed-loop control of the environmental data.

[0074] In this embodiment, the latest growth management results of strawberry seedlings are the latest information on the growth status of strawberry seedlings obtained after managing them according to the optimal growth environment control data, including information on growth status, fruit yield and quality, etc.

[0075] The beneficial effects of the above technologies are as follows: The perception layer collects data in real time, providing an accurate and timely information foundation for subsequent analysis and control. The growth environment analysis layer identifies deviations in the growth environment, helping to accurately identify problems and take targeted measures. The growth status analysis layer analyzes growth data and the current target growth stage to comprehensively assess the growth status of strawberry seedlings. The growth environment analysis layer and the growth status analysis layer work together to combine environmental deviations (such as insufficient CO2 concentration) with growth stages (such as the need for a higher carbon assimilation rate during flowering) to generate differentiated supplementation calculation logic. The growth environment optimization layer optimizes the target growth environment control data by analyzing the supplementation amount, achieving refined management. Based on the current analysis results, the growth environment optimization layer continuously updates the target environmental parameters (such as time-segmented temperature and humidity curves) for the next cycle, rather than using static thresholds. The control layer controls the execution equipment in real time based on the optimal growth environment control data, ensuring the timely and effective implementation of management measures. By providing real-time feedback on the latest growth management results, an adaptive iterative optimization chain is formed, ultimately achieving a high-precision match between environmental resource input and the physiological needs of strawberries. By integrating multi-source data at the perception layer, dynamically coupling the growth environment and growth status analysis layer, implementing rolling prediction and regulation at the optimization layer, and closing-loop execution at the control layer, the shortcomings of existing technologies are overcome one by one. This improves the accuracy and scientific nature of strawberry growth management, contributing to increased strawberry yield and quality.

[0076] Example 2:

[0077] Based on Example 1, the sensing layer includes:

[0078] The growth environment sensing module is used to collect real-time data on the actual growth environment of strawberry seedlings based on multiple sensors distributed in multiple locations within the greenhouse.

[0079] The growth sensing module is used to fit the appearance images of all strawberry seedlings in the greenhouse as growth data based on real-time monitoring images of strawberry seedlings from multiple perspectives.

[0080] In this embodiment, the appearance images of all strawberry seedlings in the greenhouse are obtained by extracting, matching, fusing, correcting, and filtering monitoring images of strawberry seedlings from multiple perspectives, resulting in images that comprehensively display the overall shape and growth status of all strawberry seedlings in the greenhouse.

[0081] The beneficial effects of the above technical solutions are as follows: The growth environment sensing module collects data from multiple locations within the greenhouse using various sensors, making the collected environmental data more comprehensive and accurate, reflecting the environmental differences in different areas of the greenhouse. The growth sensing module fits the appearance image of the strawberry seedlings based on monitoring images from multiple perspectives as growth data, providing a more intuitive and comprehensive understanding of the strawberry seedlings' growth status. Comprehensive and accurate growth environment data and intuitive growth data provide a reliable foundation for subsequent analysis and management. This helps to more accurately identify problems and needs in strawberry growth, thereby formulating more effective management strategies. It improves the accuracy and reliability of data collection at the sensing layer, providing strong support for intelligent and precise growth management of strawberries.

[0082] Example 3:

[0083] Based on Example 2, the growth environment sensing module, referencing Figure 2 ,include:

[0084] The temperature sensing submodule is used to monitor the ambient temperature at corresponding locations within the greenhouse in real time based on temperature sensors distributed at different heights and positions within the greenhouse.

[0085] The humidity sensing submodule is used to monitor the ambient humidity at corresponding locations within the greenhouse in real time based on humidity sensors distributed at different heights and positions within the greenhouse.

[0086] The carbon dioxide concentration sensing submodule is used to monitor the carbon dioxide concentration at corresponding locations within the greenhouse in real time based on carbon dioxide concentration sensors distributed at different heights and positions within the greenhouse.

[0087] The actual growth environment data for strawberry seedlings includes: ambient temperature, humidity, and carbon dioxide concentration at multiple locations within the greenhouse.

[0088] The beneficial effects of the above technical solutions are as follows: The temperature sensing submodule, by setting temperature sensors at different heights and locations, can accurately monitor temperature changes throughout the greenhouse, providing a comprehensive understanding of the temperature distribution. Similarly, the humidity sensing submodule, with humidity sensors at different heights and locations, accurately acquires humidity differences within the greenhouse, providing a precise basis for humidity control. The carbon dioxide concentration sensing submodule monitors carbon dioxide concentration at multiple locations, helping to precisely regulate the gaseous environment within the greenhouse to meet the growth needs of strawberries. The comprehensive collection of various environmental data provides rich and accurate basic information for subsequent growth environment analysis and optimization. This improves the accuracy and comprehensiveness of the perception of the greenhouse growth environment, facilitating more precise strawberry growth management.

[0089] Example 4:

[0090] Based on Example 2, the growth sensing module includes:

[0091] The strawberry seedling image extraction submodule is used to extract the strawberry seedling image region from the monitoring image of the strawberry seedling from each viewpoint.

[0092] The feature matching submodule is used to generate the feature vector of each pixel in the strawberry seedling image region of each viewpoint, and to take the quotient of the dot product of the feature vectors of any two pixels in the strawberry seedling image region of any two viewspoints and the product of the moduli of the feature vectors of the corresponding two pixels as the feature matching degree between any two pixels in the strawberry seedling image region of any two viewspoints.

[0093] The pixel matching submodule is used to obtain all matching pixel combinations in the strawberry seedling image region of each pair of views, based on the pixel combinations whose feature matching degree exceeds the matching degree threshold.

[0094] The perspective fusion submodule is used to perform perspective fusion on the strawberry seedling image regions of all perspectives based on the combination of all matching pixels in the strawberry seedling image regions of every two perspectives, so as to obtain the appearance images of all strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings.

[0095] In this embodiment, the strawberry seedling image region is the image range containing a specific part of the strawberry seedling that is identified and extracted from the monitoring image at each viewpoint.

[0096] In this embodiment, generating the feature vector for each pixel in the strawberry seedling image region from each viewpoint involves generating a set of numerical values ​​describing the characteristics of each pixel using a specific algorithm or method. The feature vector for each pixel can be generated in the following ways: For a given pixel, consider its color value (e.g., RGB value), brightness value, and position coordinates in the image. Using a specific mathematical formula or algorithm, this information is converted into a set of numerical values. For example, converting RGB values ​​to grayscale values ​​and then performing a certain operation with the position coordinates yields a vector containing multiple numerical values; this is the feature vector for that pixel. Alternatively, a convolutional neural network algorithm from deep learning can be used. Information about the pixel and its surrounding pixels within a certain range is input into the network, and the network calculates and outputs a set of numerical values ​​as the feature vector for that pixel, used to describe its characteristics in the image.

[0097] In this embodiment, based on the combination of pixels in the strawberry seedling image region of each pair of views where the feature matching degree exceeds the matching degree threshold, obtaining all matching pixel combinations in the strawberry seedling image region of each pair of views involves comparing the feature matching degree between pixels in the strawberry seedling image region of each pair of views, and only selecting pixels whose feature matching degree exceeds the preset matching degree threshold for combination, thereby obtaining all matching pixel combinations that meet the conditions in the image region of each pair of views.

[0098] In this embodiment, the matching threshold is a pre-set numerical standard used to determine whether the feature matching degree between pixels in the strawberry seedling image regions of two perspectives is high enough. Only pixel combinations that exceed this threshold are considered valid matching combinations.

[0099] The beneficial effects of the above technical solutions are as follows: The strawberry seedling image extraction submodule can accurately extract strawberry seedling image regions from monitoring images, providing accurate targets for subsequent analysis. The feature matching submodule determines the feature matching degree between pixels by calculating the dot product of feature vectors, a scientific and effective method. The pixel matching submodule selects matching pixel combinations based on feature matching degrees, improving the accuracy and reliability of the data. The perspective fusion submodule fuses strawberry seedling image regions from multiple perspectives to obtain comprehensive and accurate strawberry seedling appearance images as growth data. This improves the accuracy and reliability of strawberry seedling growth data acquisition, providing strong support for subsequent growth analysis and management.

[0100] Example 5:

[0101] Based on Example 4, the view fusion submodule includes:

[0102] The image matching unit is used to summarize the remaining strawberry seedling image regions with the largest total number of matching pixels with a single viewpoint image region to obtain at least one image region group.

[0103] The distortion analysis unit is used to generate distortion data for the strawberry seedling image regions corresponding to the two viewpoints, based on the relative position vectors between pairs of pixels belonging to the same strawberry seedling image region in all matching pixel combinations in every two viewpoints of the strawberry seedling image region in each image region group.

[0104] The distortion correction unit is used to perform uniform distortion correction on all strawberry seedling image regions in the corresponding image region group based on the distortion data of strawberry seedling image regions from every two perspectives in each image region group, so as to obtain the first corrected image group of each image region group.

[0105] The filtering and fusion unit is used to filter and fuse all the first corrected images in all the first corrected image groups to obtain the appearance images of all the strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings.

[0106] In this embodiment, a matching pixel refers to a pixel whose feature matching degree exceeds the matching degree threshold when comparing strawberry seedling image regions from two different perspectives.

[0107] In this embodiment, the strawberry seedling image regions from other perspectives are the strawberry seedling image regions corresponding to perspectives other than the currently being processed.

[0108] In this embodiment, the relative position vector between any two pixels describes the relative positional relationship between any two pixels in the same strawberry seedling image region. Suppose there are two pixels A and B in a strawberry seedling image region, with coordinates (x1, y1) and coordinates (x2, y2). Then the relative position vector between these two pixels can be represented as (x2-x1, y2-y1). For example, if the coordinates of point A are (3, 5) and the coordinates of point B are (7, 9), then their relative position vector is (7-3, 9-5), which is (4, 4). This vector (4, 4) describes the relative positional relationship between pixels A and B.

[0109] In this embodiment, based on the relative position vectors between pairs of pixels belonging to the same strawberry seedling image region in all matching pixel combinations in every two viewpoints of each image region group, the distortion data of the strawberry seedling image regions corresponding to the two viewpoints is generated by analyzing the relative position vectors between each pair of pixels from the two viewpoints belonging to the same strawberry seedling image region within the same image region group, and calculating the relevant data that can reflect the deformation of the strawberry seedling image regions from these two viewpoints.

[0110] In this embodiment, distortion data of strawberry seedling image regions from every two perspectives within each image region group are used to uniformly correct the distortion of all strawberry seedling image regions in the corresponding image region group. The first corrected image group for each image region group is obtained by correcting all strawberry seedling image regions within that region group based on the distortion data of the strawberry seedling image regions from every two perspectives within that region group. For example, a pre-trained distortion correction model can be used for correction processing. This involves inputting the distortion data of strawberry seedling image regions from every two perspectives within each image region group and all strawberry seedling image regions in the corresponding image region group into the pre-trained distortion correction model to obtain the first corrected image group for each image region group.

[0111] In this embodiment, the first corrected image group is the set of images obtained after the above-described correction process.

[0112] The beneficial effects of the above technical solutions are as follows: The image matching unit provides reasonable grouping for subsequent processing by summarizing the viewpoint image regions with the largest number of matched pixels. The distortion analysis unit generates distortion data based on the relative position vectors of matched pixels, which helps to accurately assess the distortion of the image. The distortion correction unit performs uniform distortion correction on the image regions, improving the accuracy and consistency of the image. The filtering and fusion unit performs interference pixel filtering and pixel fusion to obtain clearer and more accurate strawberry seedling appearance images as growth data. The accuracy and effect of viewpoint fusion are improved, providing high-quality data support for accurately assessing the growth of strawberry seedlings.

[0113] Example 6:

[0114] Based on Example 5, the filtering and fusion unit includes:

[0115] An interference filtering subunit is used to filter interference pixels in all first corrected images in each first corrected image group to obtain a second corrected image group for each first corrected image group.

[0116] The pixel fusion subunit is used to fuse all matching pixel combinations in each second corrected image group based on pixel weighted averaging to obtain multiple strawberry seedling perspective fused images;

[0117] The cyclic fusion subunit is used to continue fusion of the perspective images of all strawberry seedlings until the appearance images of all strawberry seedlings in the greenhouse are obtained as the growth data of the strawberry seedlings.

[0118] In this embodiment, filtering interfering pixels in all first corrected images in each first corrected image group means removing those pixels in the corrected images of each first corrected image group that do not meet the requirements and will affect the accuracy of the image.

[0119] In this embodiment, the second corrected image group is the first corrected image group after filtering out the interference pixels.

[0120] In this embodiment, the combination of all matching pixels in each second correction image group is fused based on the pixel weighted averaging method to obtain multiple strawberry seedling perspective fused images. This is achieved by calculating the average value of the matching pixels in each second correction image group according to a certain weight ratio, thereby combining these pixels together to form multiple strawberry seedling images fused from different perspectives.

[0121] In this embodiment, the perspective fusion of all strawberry seedling images is continued until the appearance image of all strawberry seedlings in the greenhouse is obtained as the growth data of the strawberry seedlings. This involves fusing the previously obtained multiple fused images again (the principle and method of fusion are the same as the process disclosed in this embodiment of fusing multiple strawberry seedling perspective fused images from the strawberry seedling image area), until an image that can fully show the overall appearance and growth of all strawberry seedlings in the greenhouse is obtained, and this image is used as the data for judging the growth of the strawberry seedlings.

[0122] The beneficial effects of the above technical solutions are as follows: The interference filtering subunit can remove interfering pixels, improving image clarity and accuracy. The pixel fusion subunit uses a pixel-weighted averaging method for fusion, making the fusion result smoother and more natural. The cyclic fusion subunit further improves the integrity and accuracy of the strawberry seedling appearance image through multiple fusions. It can obtain higher-quality and more comprehensive strawberry seedling growth data, providing a more reliable basis for subsequent analysis and management. It enhances the effect of image filtering and fusion, helping to more accurately grasp the growth status of strawberry seedlings.

[0123] Example 7:

[0124] Based on Example 1, the growth analysis layer includes:

[0125] The actual growth stage analysis module is used to determine the actual growth stage of strawberry seedlings based on their growth data.

[0126] The target growth stage acquisition module is used to determine the current target growth stage of strawberry seedlings based on the strawberry planting plan.

[0127] The growth analysis module is used to analyze the growth of strawberry seedlings based on their actual growth stage and current target growth stage.

[0128] In this embodiment, determining the actual growth stage of strawberry seedlings based on their growth data involves using relevant data such as plant height, number of leaves, and flower and fruit conditions to clarify the current growth stage of the strawberry seedlings.

[0129] In this embodiment, determining the current target growth stage of strawberry seedlings based on the strawberry planting plan means determining the ideal growth period that the strawberry seedlings should reach at the current time point according to the pre-established strawberry planting plan.

[0130] In this embodiment, the analysis of the growth status of strawberry seedlings based on their actual growth stage and current target growth stage involves comparing and comprehensively considering the actual growth stage of the strawberry seedlings with the planned target growth stage, thereby drawing analytical conclusions about the growth status of the strawberry seedlings.

[0131] The beneficial effects of the above technical solutions are as follows: The actual growth stage analysis module can accurately determine the actual growth stage of strawberry seedlings based on growth data, providing a foundation for subsequent analysis. The target growth stage acquisition module determines the current target growth stage based on the planting plan, giving the analysis a clear standard and direction. The growth analysis module analyzes both the actual and target growth stages, enabling a more comprehensive and objective assessment of the strawberry seedling's growth status. This helps to promptly identify deviations between strawberry seedling growth and expectations, allowing for targeted adjustments and optimizations. It improves the accuracy and scientific rigor of strawberry seedling growth analysis, providing strong support for achieving precise growth management.

[0132] Example 8:

[0133] Based on Example 7, the actual growth stage analysis module includes:

[0134] The similarity calculation submodule is used to generate multi-dimensional feature vectors of strawberry seedlings based on the growth data of strawberry seedlings. The quotient of the dot product of the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage, and the product of the modulus of the multi-dimensional feature vector of the strawberry seedling and the modulus of the standard multi-dimensional feature vector of the corresponding growth stage, is used as the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage.

[0135] The growth stages are roughly divided into sub-modules to use the growth stages with the highest similarity as the actual rough growth stages of the strawberry seedlings.

[0136] The stage refinement progress determination submodule is used to take the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the sum of the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the next adjacent growth stage of the actual growth stage, as the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling, and take the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling as the actual growth stage of the strawberry seedling.

[0137] In this embodiment, generating a multi-dimensional feature vector for strawberry seedlings based on their growth data involves constructing a vector that describes the growth characteristics of the strawberry seedlings from multiple aspects using specific algorithms and methods, based on the relevant data of the seedlings' growth status. Assume the following growth data of the strawberry seedlings are obtained: plant height 20 cm, number of leaves 10, stem thickness 5 mm, and number of flowers 3. We can set an algorithm, for example: multiplying the plant height value by 1, the number of leaves by 2, the stem thickness by 3, and the number of flowers by 4, and then combining these calculation results. Following the above algorithm, the obtained values ​​are 20, 20, 15, and 12, which are combined into a vector (20, 20, 15, 12). This is the multi-dimensional feature vector of the strawberry seedlings generated based on this growth data, describing the growth characteristics of the strawberry seedlings from multiple aspects such as overall plant size, leaf growth, stem development, and flowering status.

[0138] In this embodiment, the actual rough growth stage is the approximate growth period of the strawberry seedling as initially determined, without further fine division.

[0139] In this embodiment, the stage refinement growth progress ratio is a proportional value used to more accurately represent the specific growth degree of strawberry seedlings within the actual rough growth stage.

[0140] The beneficial effects of the above technical solution are as follows: The similarity calculation submodule provides a quantitative basis for judging the growth stage by calculating the similarity of multi-dimensional feature vectors. The rough growth stage division submodule can initially determine the actual rough growth stage of strawberry seedlings, narrowing the scope of analysis. The stage refinement progress determination submodule further determines the stage refinement growth progress ratio, thereby more accurately determining the actual growth stage. This enables more accurate analysis of the actual growth stage of strawberry seedlings, providing more precise information for subsequent growth analysis and management strategy formulation. It improves the accuracy and reliability of actual growth stage analysis, contributing to more refined strawberry planting management.

[0141] Example 9:

[0142] Based on Example 1, the growth environment optimization layer includes:

[0143] The primary supplementation analysis module is used to determine the primary supplementation amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control.

[0144] The secondary supplementation analysis module is used to analyze the secondary supplementation amount of strawberry seedling growth environment data based on the growth analysis results of strawberry seedlings;

[0145] The environmental control optimization module is used to optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the primary and secondary replenishment amounts of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0146] The supplementary data on the strawberry seedling growth environment includes both primary and secondary supplementary data.

[0147] In this embodiment, the primary replenishment amount of strawberry seedling growth environment data determined based on the analysis results of the strawberry seedling growth environment control is the amount of environmental data that needs to be replenished, initially calculated based on the deviation analysis results between the actual and target conditions of the strawberry seedling growth environment. Assume the ideal target environment for strawberry seedling growth is a temperature of 25℃, humidity of 60%, and carbon dioxide concentration of 800ppm. The current growth environment data actually monitored by various sensors are: temperature of 20℃, humidity of 50%, and carbon dioxide concentration of 600ppm. First, calculate the temperature deviation: target temperature 25℃ - actual temperature 20℃ = 5℃. Assuming, based on experience and relevant algorithms, the primary replenishment amount for temperature is initially determined to be 120% of the deviation, i.e., 5℃ × 120% = 6℃. For humidity, the deviation is 60% - 50% = 10%, and similarly, assuming the primary replenishment amount is 120% of the deviation, i.e., 10% × 120% = 12%. For carbon dioxide concentration, the deviation is 800ppm - 600ppm = 200ppm. Assuming the primary supplementation amount is 120% of the deviation, that is, 200ppm × 120% = 240ppm. Thus, the primary supplementation amounts for the strawberry seedling growth environment data are initially determined as follows: temperature supplementation 6℃, humidity supplementation 12%, and carbon dioxide concentration supplementation 240ppm.

[0148] In this embodiment, the primary supplementary amount of strawberry seedling growth environment data refers to the preliminary supplementary value of growth environment data obtained through the above method.

[0149] In this embodiment, the secondary supplementation amount of strawberry seedling growth environment data, calculated based on the analysis results of the strawberry seedling growth status, is the amount of supplementation amount of growth environment data further calculated according to the analysis results of the strawberry seedling growth status. Assume we have analyzed the growth status of the strawberry seedlings as follows: the leaves are pale green, the plant growth rate is slow, and the number of flowers is low. After professional botanical analysis, it is determined that the problem may be insufficient light intensity and inadequate soil fertility. First, regarding light intensity, the original target value was 8 hours of sufficient light per day, but the actual monitored average daily light intensity was only 6 hours. According to research, for every hour of light deficiency, an additional 1.2 hours of supplementary light may be needed in the subsequent growth stage to improve growth. Therefore, the secondary supplementation amount of light intensity is (8-6)×1.2=2.4 hours. Second, regarding soil fertility, soil testing revealed that the content of major nutrients such as nitrogen, phosphorus, and potassium was lower than the ideal value. Assuming the ideal nitrogen content is 150 ppm, and the actual measured value is 100 ppm, for every 10 ppm deficiency of nitrogen, an additional 15 ppm needs to be added to promote growth. Therefore, the secondary supplementation amount of nitrogen is (150-100)÷10×15=75ppm. Using the same method, the secondary supplementation amounts of other nutrients such as phosphorus and potassium, as well as other environmental factors that may be involved (such as ventilation), can be calculated. Combining these calculation results, we obtain the secondary supplementation amounts based on the strawberry seedling growth analysis data, such as supplementing with 25ppm of nitrogen for every hour of light intensity, to more accurately adjust the growth environment of the strawberry seedlings and promote better growth.

[0150] In this embodiment, the secondary supplementary amount of strawberry seedling growth environment data refers to the additional supplementary value of growth environment data obtained based on growth analysis.

[0151] In this embodiment, the target growth environment control data for strawberry seedlings in the next adjacent control cycle is optimized based on the primary and secondary supplementation amounts of the strawberry seedling growth environment data. Obtaining the optimal growth environment control data for the next adjacent control cycle involves comprehensively considering the previously calculated primary and secondary supplementation amounts, adjusting and improving the target growth environment control data for the strawberry seedlings in the next control cycle, thereby obtaining the most favorable environmental control data for strawberry seedling growth. For example, the current primary supplementation amount for temperature is +3℃, and the primary supplementation amount for humidity is +10%; the secondary supplementation amount for temperature is +2℃, and the secondary supplementation amount for humidity is +5%. In the next control cycle, the originally set target temperature value is 22℃, and the target humidity value is 50%. Considering both primary and secondary supplementation amounts, the optimized temperature value is 22℃ + 3℃ + 2℃ = 27℃, and the optimized humidity value is 50% + 10% + 5% = 65%. This yields the optimal growth environment control data for the strawberry seedlings in the next control cycle, namely a temperature of 27℃ and a humidity of 65%, which is more conducive to the growth of the strawberry seedlings.

[0152] The beneficial effects of the above technical solution are as follows: The primary supplementation analysis module determines the primary supplementation amount based on the growth environment control analysis results, providing data support for preliminary optimization. The secondary supplementation analysis module determines the secondary supplementation amount based on the growth status analysis results, further supplementing the optimization basis from a growth status perspective. The environmental control optimization module integrates the primary and secondary supplementation amounts for optimization, making the optimization results more comprehensive and accurate. This allows for more scientific and rational optimization of the strawberry seedling growth environment control data to meet the growth needs of strawberry seedlings. It improves the accuracy and effectiveness of growth environment optimization, helping to create more suitable growth conditions for strawberry seedlings.

[0153] Example 10:

[0154] This invention provides an IoT-based intelligent precision growth management method for strawberries, applicable to any of the IoT-based intelligent precision growth management systems for strawberries in Examples 1 to 9, with reference to... Figure 3 ,include:

[0155] S1: Real-time collection of actual growth environment data and growth data of strawberry seedlings;

[0156] S2: Determine the deviation data between the actual growth environment data and the target growth environment data of the strawberry seedlings as the results of the strawberry seedling growth environment control analysis;

[0157] S3: Based on the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings, the growth analysis results of strawberry seedlings are obtained;

[0158] S4: Based on the analysis results of the strawberry seedling growth environment control and growth status, the amount of supplementary strawberry seedling growth environment data is determined. Based on the amount of supplementary strawberry seedling growth environment data, the target growth environment control data of strawberry seedlings in the next adjacent control period is optimized to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period.

[0159] S5: Based on the optimal growth environment control data of strawberry seedlings in the next adjacent control cycle, the execution equipment is controlled in real time to obtain the latest growth management results of strawberry seedlings.

[0160] The beneficial effects of the above technologies are as follows: Step S1 collects data in real time, providing an accurate and timely information foundation for subsequent analysis and control. Step S2 determines deviation data of the growth environment, which helps to accurately identify problems and take targeted measures. Step S3 can analyze the growth data and the current target growth stage to comprehensively evaluate the growth status of strawberry seedlings. Steps S2 and S3 are linked, combining environmental deviations (such as insufficient CO2 concentration) with growth stages (such as the need for a higher carbon assimilation rate during flowering) to generate differentiated supplementation calculation logic. Step S4 optimizes the target growth environment control data by analyzing the supplementation amount, realizing refined management. Based on the current analysis results, the target environmental parameters (such as time-segmented temperature and humidity curves) for the next cycle are updated on a rolling basis, rather than static thresholds. Step S5 controls the execution equipment in real time according to the optimal growth environment control data, ensuring the timely and effective implementation of management measures. By providing real-time feedback on the latest growth management results, an adaptive iterative optimization chain is formed, ultimately achieving a high-precision match between environmental resource input and the physiological needs of strawberries. By employing multi-source data fusion in step S1, dynamic coupling between steps S2 and S3, rolling prediction and control in step S4, and closed-loop execution in step S5, the shortcomings of existing technologies are overcome one by one. This improves the accuracy and scientific nature of strawberry growth management, contributing to increased strawberry yield and quality.

[0161] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A strawberry intelligent precision growth management system based on the Internet of Things, characterized in that, include: The perception layer is used to collect real-time data on the actual growth environment and growth status of strawberry seedlings. The growth environment analysis layer is used to determine the deviation between the actual growth environment data and the target growth environment data of strawberry seedlings as the result of the growth environment control analysis of strawberry seedlings. The growth analysis layer is used to analyze the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings to obtain the growth analysis results. The growth environment optimization layer is used to analyze the supplementary amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control and growth status, and optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the supplementary amount of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period. The control layer is used to control the execution equipment in real time based on the optimal growth environment control data of the strawberry seedlings in the next adjacent control cycle, so as to obtain the latest growth management results of the strawberry seedlings. The perception layer includes: The growth environment sensing module is used to collect real-time data on the actual growth environment of strawberry seedlings based on multiple sensors distributed in multiple locations within the greenhouse. The growth perception module is used to fit the appearance images of all strawberry seedlings in the greenhouse as growth data based on real-time collected monitoring images of strawberry seedlings from multiple perspectives. The growth sensing module includes: The strawberry seedling image extraction submodule is used to extract the strawberry seedling image region from the monitoring image of the strawberry seedling from each viewpoint. The feature matching submodule is used to generate the feature vector of each pixel in the strawberry seedling image region of each viewpoint, and to take the quotient of the dot product of the feature vectors of any two pixels in the strawberry seedling image region of any two viewspoints and the product of the moduli of the feature vectors of the corresponding two pixels as the feature matching degree between any two pixels in the strawberry seedling image region of any two viewspoints. The pixel matching submodule is used to obtain all matching pixel combinations in the strawberry seedling image region of each pair of views, based on the pixel combinations whose feature matching degree exceeds the matching degree threshold. The perspective fusion submodule is used to perform perspective fusion on the strawberry seedling image regions of all perspectives based on the combination of all matching pixels in the strawberry seedling image regions of every two perspectives, so as to obtain the appearance images of all strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings. The view fusion submodule includes: The image matching unit is used to summarize the remaining strawberry seedling image regions with the largest total number of matching pixels with a single viewpoint image region to obtain at least one image region group. The distortion analysis unit is used to generate distortion data for the strawberry seedling image regions corresponding to the two viewpoints, based on the relative position vectors between pairs of pixels belonging to the same strawberry seedling image region in all matching pixel combinations in every two viewpoints of the strawberry seedling image region in each image region group. The distortion correction unit is used to perform uniform distortion correction on all strawberry seedling image regions in the corresponding image region group based on the distortion data of strawberry seedling image regions from every two perspectives in each image region group, so as to obtain the first corrected image group of each image region group. The filtering and fusion unit is used to filter and fuse all the first corrected images in all the first corrected image groups to obtain the appearance images of all the strawberry seedlings in the greenhouse as the growth data of the strawberry seedlings. The filtering and fusion unit includes: An interference filtering subunit is used to filter interference pixels in all first corrected images in each first corrected image group to obtain a second corrected image group for each first corrected image group. The pixel fusion subunit is used to fuse all matching pixel combinations in each second corrected image group based on pixel weighted averaging to obtain multiple strawberry seedling perspective fused images; The cyclic fusion subunit is used to continue fusion of the perspective images of all strawberry seedlings until the appearance images of all strawberry seedlings in the greenhouse are obtained as the growth data of the strawberry seedlings. The growth analysis layer includes: The actual growth stage analysis module is used to determine the actual growth stage of strawberry seedlings based on their growth data. The target growth stage acquisition module is used to determine the current target growth stage of strawberry seedlings based on the strawberry planting plan. The growth analysis module is used to analyze the growth of strawberry seedlings based on their actual growth stage and current target growth stage. The actual growth stage analysis module includes: The similarity calculation submodule is used to generate multi-dimensional feature vectors of strawberry seedlings based on the growth data of strawberry seedlings. The quotient of the dot product of the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage, and the product of the modulus of the multi-dimensional feature vector of the strawberry seedling and the modulus of the standard multi-dimensional feature vector of the corresponding growth stage, is used as the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of each growth stage. The growth stages are roughly divided into sub-modules to use the growth stages with the highest similarity as the actual rough growth stages of the strawberry seedlings. The stage refinement progress determination submodule is used to take the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the sum of the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the actual growth stage, and the similarity between the multi-dimensional feature vector of the strawberry seedling and the standard multi-dimensional feature vector of the next adjacent growth stage of the actual growth stage, as the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling, and take the stage refinement growth progress ratio of the actual coarse growth stage of the strawberry seedling as the actual growth stage of the strawberry seedling.

2. The intelligent and precise strawberry growth management system based on the Internet of Things as described in claim 1, characterized in that, The growth environment sensing module includes: The temperature sensing submodule is used to monitor the ambient temperature at corresponding locations within the greenhouse in real time based on temperature sensors distributed at different heights and positions within the greenhouse. The humidity sensing submodule is used to monitor the ambient humidity at corresponding locations within the greenhouse in real time based on humidity sensors distributed at different heights and positions within the greenhouse. The carbon dioxide concentration sensing submodule is used to monitor the carbon dioxide concentration at corresponding locations within the greenhouse in real time based on carbon dioxide concentration sensors distributed at different heights and positions within the greenhouse. The actual growth environment data for strawberry seedlings includes: ambient temperature, humidity, and carbon dioxide concentration at multiple locations within the greenhouse.

3. The intelligent and precise strawberry growth management system based on the Internet of Things as described in claim 1, characterized in that, The growth environment optimization layer includes: The primary supplementation analysis module is used to determine the primary supplementation amount of strawberry seedling growth environment data based on the analysis results of strawberry seedling growth environment control. The secondary supplementation analysis module is used to analyze the secondary supplementation amount of strawberry seedling growth environment data based on the growth analysis results of strawberry seedlings; The environmental control optimization module is used to optimize the target growth environment control data of strawberry seedlings in the next adjacent control period based on the primary and secondary replenishment amounts of strawberry seedling growth environment data, so as to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period. The supplementary data on the strawberry seedling growth environment includes both primary and secondary supplementary data.

4. A method for intelligent and precise growth management of strawberries based on the Internet of Things, characterized in that: The strawberry intelligent precision growth management system based on the Internet of Things, as described in any one of claims 1 to 3, comprises: S1: Real-time collection of actual growth environment data and growth data of strawberry seedlings; S2: Determine the deviation data between the actual growth environment data and the target growth environment data of the strawberry seedlings as the results of the strawberry seedling growth environment control analysis; S3: Based on the growth data of strawberry seedlings and the current target growth stage of strawberry seedlings, the growth analysis results of strawberry seedlings are obtained; S4: Based on the analysis results of the strawberry seedling growth environment control and growth status, the amount of supplementary strawberry seedling growth environment data is determined. Based on the amount of supplementary strawberry seedling growth environment data, the target growth environment control data of strawberry seedlings in the next adjacent control period is optimized to obtain the best growth environment control data of strawberry seedlings in the next adjacent control period. S5: Based on the optimal growth environment control data of strawberry seedlings in the next adjacent control cycle, the execution equipment is controlled in real time to obtain the latest growth management results of strawberry seedlings.

Images