An urban environment monitoring and control system and method based on global greening data

Abstract

The present invention discloses an urban environment monitoring and control system and method based on global greening data, including an image acquisition module, a monitoring module, an image analysis module, a sampling and screening module, a global inference module and a strategy generation module. The image acquisition module regularly acquires greening image data; the monitoring module collects vegetation monitoring data through a sensor group; the image analysis module extracts vegetation coverage areas and classifies areas according to texture feature parameters (leaf area index, canopy height, texture uniformity); the sampling and screening module calculates the standard value of each unit area and screens and optimizes the sampling area; the global inference module combines the sampling data to infer the monitoring data of uncovered areas; the strategy generation module generates targeted microclimate control strategies based on the monitoring data and classification results. The present invention combines image analysis with sensor data to achieve accurate monitoring and intelligent control of vegetation distribution, thereby improving the ecological function and microclimate control effect of urban greening areas.

Description

Technical Field

[0001] The present invention relates to the field of urban microclimate control, and in particular to an urban environment monitoring and control system and method based on global greening data. Background Art

[0002] With the accelerating pace of urbanization, urban microclimates are facing increasing challenges. Traditional urban design and construction methods often neglect the protection and regulation of the natural environment, leading to problems such as the exacerbated urban heat island effect, deteriorating air quality, and energy waste. To address these issues, effectively regulating urban microclimates through greenery has become a key research topic in urban environmental management and sustainable development. Greenery plays an irreplaceable role in regulating urban microclimates. Plants' transpiration, shading, and ability to regulate climate factors such as humidity and temperature make them a crucial tool for improving the urban environment. They not only reduce urban temperatures and alleviate air pollution, but also enhance the stability of urban ecosystems and promote biodiversity. However, while urban greenery is currently being used to improve the urban environment and microclimate, the urban heat island effect and air quality vary across regions, and different types of vegetation have varying impacts on these issues. Therefore, simply covering a city with greenery is insufficient to address microclimate issues across different urban areas. The lack of a dynamic understanding of the impact of vegetation on microclimate makes it impossible to achieve a rapid response to regulate microclimate across all urban areas. Summary of the Invention

[0003] The purpose of the present invention is to provide an urban environment monitoring and control system based on global greening data, which has the advantages of establishing the dynamic relationship between the growth status of vegetation types and environmental climate with high precision and wide coverage, intelligently generating control strategies, and accurately adjusting the urban microclimate.

[0004] The above technical objectives of the present invention are achieved through the following technical solutions:

[0005] An urban environment monitoring and control system based on global greening data, including:

[0006] An image acquisition module, configured to acquire green image data within the city at predetermined intervals;

[0007] A monitoring module, comprising a plurality of sensor groups, wherein the sensor groups are used to monitor vegetation and obtain monitoring data;

[0008] An image analysis module is used to process the greening image data to extract vegetation coverage areas, divide the vegetation coverage areas into a number of unit areas according to a preset segmentation rule, extract features from each unit area to obtain texture feature parameters, and classify all unit areas according to the texture feature parameters of each unit area to obtain a number of type areas;

[0009] A sampling and screening module is used to calculate a corresponding standard value based on the characteristic parameters of each unit area, and the standard value is used to quantitatively characterize the characteristics of the vegetation in the unit area; based on the standard value, a number of unit areas within each type of area are screened as sampling areas, and the sampling areas are used to set the sensor group;

[0010] A global estimation module, configured to calculate the monitoring approximate data of each unit area based on the monitoring data and standard values ​​monitored by the sensor group in the sampling area;

[0011] A strategy generation module generates a control strategy by analyzing and calculating the monitoring approximate data of each unit area and the type of area it is located in.

[0012] It is further configured that: the preset segmentation rule is to divide the area into square areas with the maximum detection diameter of the sensor group as the side length or to divide the area into circular areas with the maximum detection radius of the sensor group.

[0013] It is further configured that the texture characteristic parameters include leaf area index, canopy height and texture uniformity, and the texture parameters obtained by feature extraction of each unit area specifically include:

[0014] The normalized vegetation index is calculated using multispectral images of vegetation-covered areas, and the leaf area index is calculated based on the normalized vegetation index;

[0015] Use image stereo matching technology to extract three-dimensional height information from the vegetation coverage area, and calculate the canopy height based on the three-dimensional height information;

[0016] A gray-level co-occurrence matrix is ​​constructed for each unit area, and the texture uniformity is calculated.

[0017] It is further configured that the type areas include tree areas, shrub areas and lawn areas, and the classification of all unit areas according to the texture feature parameters of each unit area to obtain several type areas specifically includes:

[0018] The unit areas with leaf area index greater than the first upper threshold and canopy height greater than the second upper threshold are divided into the tree zone;

[0019] The unit areas with leaf area index less than or equal to the first upper threshold and greater than the first lower threshold, and canopy height less than or equal to the second upper threshold and greater than the second lower threshold are divided into shrub areas;

[0020] The unit areas with leaf area index less than or equal to the first lower threshold and canopy height less than or equal to the second lower threshold are divided into lawn areas.

[0021] Further configuration: the sampling and screening module is used to calculate the corresponding standard value according to the characteristic parameters of each unit area using the following calculation formula:

[0022] S i =w1·LAI+w2·CH+w3·TEU

[0023] Where S is the standard value, LAI is the leaf area index, CH is the canopy height, TEU is the texture uniformity, and w1, w2, and w3 are the influence weight parameters corresponding to the leaf area index, canopy height, and texture uniformity, respectively.

[0024] Further setting: the step of selecting a plurality of unit areas within each type of area as sampling areas according to the standard value specifically includes the following steps:

[0025] Calculate the mean and standard deviation of the standardized values ​​within each type of area;

[0026] Calculate the number of samples corresponding to each type of area according to the number of unit areas contained in each type of area;

[0027] The standard values ​​of unit areas in different types of areas are screened according to the standard deviation and mean to obtain the preliminary selected areas for each type of area;

[0028] The centroid position of each type of area and the calibration coordinates of the preliminary selected area within the area of ​​this type are calculated. The preliminary selected area is screened according to the distance between the calibration coordinates and the centroid position and the number of samples to obtain the sampling area of ​​each type of area.

[0029] Further setting: the monitoring approximate data of each unit area calculated based on the monitoring data monitored by the sensor group at the sampling area and the standard value specifically includes:

[0030] The distance weight is calculated based on the distance between the unit area and the sampling area within the same type of area;

[0031] The monitoring approximate data of each unit area in the same type of area is calculated based on the distance weight and the detection data of the sampling area;

[0032] The calculation formula of the distance weight is:

[0033]

[0034] Among them, w ij is the distance weight of the i-th sampling area to the j-th unit area, d ij is the distance between the i-th sampling area and the j-th unit area;

[0035] The calculation formula for the monitoring approximate data is:

[0036]

[0037] Among them, D j is the monitoring approximate data of the jth unit area, D i is the monitoring data of the i-th sampling area, and n is the number of sampling areas in this type of area.

[0038] Further configuration: also includes a regional correction module, the regional correction module is used to obtain the special impact area within the city, and according to the radiation range of the special impact area, correct the monitoring approximate data of the unit area within the radiation range to obtain new monitoring approximate data.

[0039] It is further configured that the monitoring data includes transpiration rate data, liquid flow data, and temperature data.

[0040] Another object of the present invention is to provide an urban environment monitoring and control method based on global greening data, which is applied to the urban environment monitoring and control system based on global greening data mentioned above.

[0041] The above technical objectives of the present invention are achieved through the following technical solutions:

[0042] A method for monitoring and controlling the urban environment based on global greening data specifically comprises the following steps:

[0043] Step 1: Use the image acquisition module to collect green image data within the city at preset intervals;

[0044] Step 2: Process the greening image data to extract the vegetation coverage area; divide the vegetation coverage area into several unit areas according to the preset segmentation rules; extract features from each unit area to obtain texture feature parameters; and classify all unit areas into several types of areas according to the texture feature parameters.

[0045] Step 3: Calculate the standard value of the texture feature parameters of each unit area; select several unit areas within each type of area as sampling areas based on the standard value; and arrange sensor groups in the sampling areas to obtain monitoring data;

[0046] Step 4: Calculate the monitoring approximate data of each unit area based on the monitoring data and standard value of the sensor group at the sampling area and the distance weight between the unit area in the type area and the sampling area;

[0047] Step 5: Generate urban microclimate control strategies based on the monitoring approximate data of each unit area and the type of area to which it belongs.

[0048] In summary, the present invention has the following beneficial effects:

[0049] 1. This solution utilizes an image acquisition module. By periodically collecting green image data within the city, combined with an image analysis module, it can accurately extract vegetation coverage areas and perform feature extraction on each unit area. By processing image data, it can accurately identify and analyze different types of green vegetation in the city, including trees, shrubs, and lawns, and provide a scientific basis for subsequent microclimate control. Compared with traditional manual surveys and static monitoring methods, image acquisition and analysis can achieve efficient and accurate vegetation monitoring over a larger area, making it particularly suitable for large-scale urban greening management. This method not only improves the efficiency and accuracy of data acquisition, but also reduces manual intervention and monitoring costs.

[0050] 2. The image analysis module extracts multiple texture features of vegetation coverage (such as leaf area index, canopy height, and texture uniformity) and scientifically classifies green areas based on these features. Different types of areas (such as tree areas, shrub areas, and lawn areas) play different roles in microclimate regulation. Accurate regional classification can help develop personalized regulation strategies for each area.

[0051] 3. A sampling and screening module is implemented to achieve dynamic monitoring within urban green areas by calculating standard values ​​based on the characteristic parameters of each unit area and selecting sampling areas. These sampling areas are not only selected based on the actual characteristics of the vegetation, but the sampling locations can also be dynamically adjusted based on changes in standard values ​​and regional characteristics. This dynamic monitoring mechanism ensures that the system can better adapt to environmental changes in actual applications, improving monitoring coverage and data representativeness. In addition, the rational selection of sampling areas reduces the redundancy of sensor deployment, saves monitoring costs, and improves the system's operational efficiency.

[0052] 4. Global inference technology overcomes the limitations of sensor locations, efficiently inferring microclimate data for unmonitored areas. This significantly expands monitoring coverage and ensures effective climate control throughout the city. This inference method better addresses the incompleteness of data collection and the complexity of the urban environment. A comprehensive deployment of sensors would significantly increase costs and data processing.

[0053] 5. Based on the approximate monitoring data for each unit area and the type of area it belongs to, analyze and generate appropriate urban microclimate control strategies. This process, based on a comprehensive analysis of sensor data, image analysis results, and regional characteristics, can develop personalized control plans based on the microclimate characteristics of different regions. This precise control strategy improves the flexibility and sustainability of microclimate management, enabling more scientific and efficient urban greening and climate control. Through refined microclimate control, the livability and sustainable development capabilities of the city are enhanced, providing scientific and technological support for the optimization of the urban ecological environment. At the same time, by optimizing green vegetation management, energy consumption and water waste are reduced, contributing to the construction of green cities.

[0054] 6. The regional correction module can modify the monitoring approximate data within the radiation range of special impact areas (such as urban buildings and high-temperature island effect areas). This correction mechanism significantly improves the system's adaptability to different urban microclimate zones, ensuring that microclimate control can be continuously and effectively implemented in complex and changing urban environments, and preventing the impact of external environmental changes on system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is an overall structural block diagram of the embodiment. DETAILED DESCRIPTION

[0056] The present invention will be further described in detail below with reference to the accompanying drawings.

[0057] Example:

[0058] like Figure 1 As shown, an urban environment monitoring and control system based on global greening data includes:

[0059] An image acquisition module, configured to acquire green image data within the city at predetermined intervals;

[0060] A monitoring module, comprising a plurality of sensor groups, wherein the sensor groups are used to monitor vegetation and obtain monitoring data;

[0061] An image analysis module is used to process the greening image data to extract vegetation coverage areas, divide the vegetation coverage areas into a number of unit areas according to a preset segmentation rule, extract features from each unit area to obtain texture feature parameters, and classify all unit areas according to the texture feature parameters of each unit area to obtain a number of type areas;

[0062] A sampling and screening module is used to calculate a corresponding standard value based on the characteristic parameters of each unit area, and the standard value is used to quantitatively characterize the characteristics of the vegetation in the unit area; based on the standard value, a number of unit areas within each type of area are screened as sampling areas, and the sampling areas are used to set the sensor group;

[0063] A global estimation module, configured to calculate the monitoring approximate data of each unit area based on the monitoring data and standard values ​​monitored by the sensor group in the sampling area;

[0064] A strategy generation module generates a control strategy by analyzing and calculating the monitoring approximate data of each unit area and the type of area it is located in.

[0065] For the impact collection module, drones, multispectral cameras, or satellite remote sensing are used to acquire high-resolution imagery (recommended resolution <1 meter) within the city. The monitoring data includes transpiration rate, sap flow, and temperature data. Stomatal conductance sensors measure the degree of stomata opening in plants, indirectly inferring transpiration rate. Thermal pulse sensors measure the pressure difference within the plant body at the stem or root level to infer sap flow direction. Temperature sensors collect temperature data within the sampling area. The transpiration rate reflects a plant's ability to evaporate water through its stomata and is a key indicator of its impact on surrounding air humidity, temperature, and the water cycle. By monitoring the transpiration rate across sampling areas, the transpiration effect of each vegetation type can be understood and further inferred from their role in modulating the urban heat island effect. Transpiration is the process by which plants dissipate heat through water evaporation, effectively reducing the temperature of the surrounding air. Therefore, areas with higher transpiration rates help mitigate the urban heat island effect. By monitoring the transpiration rate, green areas with good transpiration rates can be identified, providing guidance for the development of green infrastructure (such as green spaces and parks). Transpiration also releases water vapor, increasing the humidity of the surrounding air. Proper distribution of plants with high transpiration rates helps increase air humidity, especially during dry seasons, and has a positive effect on improving urban air quality and alleviating drought conditions. Liquid flow direction monitoring primarily reflects the flow of water through plants and soil. Liquid flow direction data allows for more accurate determination of the path and transformation of water flow, which is of great significance for the effective management of water resources and the optimization of irrigation systems. Liquid flow direction and transpiration rate jointly affect plant water balance. If the liquid flow direction is unreasonable or the water distribution is uneven, some areas will have too much water while others will have insufficient water, thus affecting plant growth.

[0066] The preset segmentation rule is to divide the area into squares with the maximum detection diameter of the sensor group as the side length or circular areas with the maximum detection radius of the sensor group. The unit area is divided according to the range that the sensor group can monitor to ensure the accuracy of the monitored data.

[0067] The texture characteristic parameters include leaf area index, canopy height and texture uniformity. The texture parameters obtained by feature extraction of each unit area specifically include:

[0068] The vegetation normalized index is calculated using multispectral images of the vegetation coverage area, and the leaf area index is calculated based on the vegetation normalized index. The calculation formula of the vegetation normalized index is:

[0069]

[0070] Among them, NDVI is the normalized difference between vegetation index, NIR and RED are the reflectance of near infrared and red light bands.

[0071] The calculation formula for leaf area index is:

[0072]

[0073] Image stereo matching technology is used to extract three-dimensional height information from the vegetation coverage area. The canopy height is calculated based on the three-dimensional height information, and the difference between the canopy vertex height and the ground surface height is calculated as the canopy height.

[0074] A gray level co-occurrence matrix is ​​constructed for each unit area, and the uniformity features are extracted from the gray level co-occurrence matrix to obtain the texture uniformity.

[0075] The type areas include tree areas, shrub areas and lawn areas. The classification of all unit areas according to the texture feature parameters of each unit area to obtain several type areas specifically includes:

[0076] The unit areas with leaf area index greater than the first upper threshold and canopy height greater than the second upper threshold are divided into the tree zone;

[0077] The unit areas with leaf area index less than or equal to the first upper threshold and greater than the first lower threshold, and canopy height less than or equal to the second upper threshold and greater than the second lower threshold are divided into shrub areas;

[0078] The unit areas with leaf area index less than or equal to the first lower threshold and canopy height less than or equal to the second lower threshold are divided into lawn areas.

[0079] The sampling and screening module is used to calculate the corresponding standard value according to the characteristic parameters of each unit area using the following calculation formula:

[0080] S i=w1·LAI+W2·CH+W3·TEU

[0081] Where S is the standard value, LAI is the leaf area index, CH is the canopy height, TEU is the texture uniformity, and w1, w2, and w3 are the influence weight parameters corresponding to the leaf area index, canopy height, and texture uniformity, respectively.

[0082] Further setting: the step of selecting a plurality of unit areas within each type of area as sampling areas according to the standard value specifically includes the following steps:

[0083] Calculate the mean and standard deviation of the standardized values ​​within each type of area;

[0084] mean The calculation formula is:

[0085]

[0086] Standard deviation σ S The calculation formula is:

[0087]

[0088] The number of samples corresponding to each type of area is calculated based on the number of unit areas contained in each type of area. In this embodiment, the proportion of sampled areas is selected to be 1%, that is, if the number of unit areas is 500, the number of samples selected is 5;

[0089] The standard values ​​of unit areas in different types of areas are screened according to the standard deviation and mean to obtain the preliminary selected areas for each type of area. The specific screening process is to sort the standard values ​​of all unit areas and screen out areas with standard values ​​close to the mean and small dispersion. The screening conditions are:

[0090]

[0091] Here, k is a flexibly adjustable screening range factor (e.g., k=1 indicates selecting an area within one standard deviation).

[0092] After the preliminary selection area is obtained by satisfying the previous screening conditions, spatial constraints are imposed on the preliminary selection area to ensure that the sampling area is evenly distributed. Calculate the centroid position (x c ,y c ) and the calibration coordinates of the primary selected area within this type of area (x i ,y i ), the preliminary selected areas are screened according to the distance of the calibration coordinates from the centroid position and the number of samples to obtain the sampling areas of each type of area. According to the spatial distribution density of the area (Voronoi diagram or nearest neighbor distance analysis), the areas with larger spacing are selected to ensure uniformity.

[0093] The monitoring approximate data of each unit area calculated based on the monitoring data monitored by the sensor group at the sampling area and the standard value specifically includes:

[0094] The distance weight is calculated based on the distance between the unit area and the sampling area within the same type of area;

[0095] The monitoring approximate data of each unit area in the same type of area is calculated based on the distance weight and the detection data of the sampling area;

[0096] The calculation formula of the distance weight is:

[0097]

[0098] Among them, w ij is the distance weight of the i-th sampling area to the j-th unit area, d ij is the distance between the i-th sampling area and the j-th unit area;

[0099] The calculation formula for the monitoring approximate data is:

[0100]

[0101] Among them, D j is the monitoring approximate data of the jth unit area, D i is the monitoring data of the i-th sampling area, and n is the number of sampling areas in this type of area.

[0102] The system also includes a regional correction module, which is used to identify special impact areas within the city and modify the monitoring approximate data of the unit area within the radiation range to obtain new monitoring approximate data based on the radiation range of the special impact area. For example, some industrial areas generate a lot of heat or dust during production, which may affect the growth, transpiration rate and temperature of green plants within the radiation range. Therefore, the monitoring approximate data within the affected area needs to be modified to ensure data accuracy.

[0103] Based on the monitoring approximate data of all unit areas, the following control strategies can be adopted:

[0104] (1) Optimize the layout of urban greening. Based on the transpiration rate and liquid flow data of different areas, it is possible to identify which areas have better greening effects and which areas have weaker vegetation transpiration effects. By analyzing these data, the greening areas for key improvements are determined. Priority is given to strengthening vegetation coverage in areas with lower transpiration rates, or appropriate vegetation adjustments are made in areas with higher transpiration rates. Areas with high transpiration rates: Priority is given to building large-scale greening areas such as parks and green spaces to increase vegetation coverage and further optimize the climate regulation effect. Areas with low transpiration rates: Strengthen plant irrigation and soil improvement to increase transpiration rates; or select vegetation varieties with high transpiration efficiency for planting.

[0105] (2) Irrigation system optimization: Using liquid flow direction and transpiration rate data, we can accurately understand the distribution and demand of water in different areas, dynamically adjust the irrigation system, reduce water waste, and ensure that plants can grow in a suitable water environment. Real-time monitoring and adjustment: Using liquid flow direction data, we can dynamically adjust the water volume and water supply time of the irrigation system to avoid oversupply or undersupply of water resources in local areas. Soil moisture monitoring: Based on liquid flow data, we predict the path of water infiltration, and provide additional irrigation or install drainage systems in areas with uneven infiltration to ensure a balanced distribution of soil moisture.

[0106] (3) Microclimate control in special areas. For special areas (such as residential areas, commercial areas, industrial areas, etc.), differentiated control strategies can be formulated based on the transpiration rate and liquid flow data of the area. Residential areas: Focus on the health of greening, ensuring that plants with high transpiration rates can effectively reduce temperature and increase humidity, and improve the comfort of residential areas. Industrial areas: Greening in industrial areas should focus on enhancing water circulation, regulating the effective use of water resources through liquid flow and transpiration rate, and reducing the heat island effect. Temperature monitoring data combined with transpiration rate and liquid flow direction can more accurately assess the impact of the growth status of green plants on the local microclimate, and can more accurately adjust the regional microclimate by regulating the types and growth conditions of plants to better adapt to people's lives.

[0107] In addition to the above data, the following data can also further improve the urban microclimate control strategy: (1) Soil moisture data. Soil moisture directly affects plant growth and water supply. Combined with transpiration rate and liquid flow data, soil moisture can provide more accurate information for irrigation control and help us better understand the balance of water supply and demand. (2) Air quality monitoring data. The impact of air quality on urban microclimate cannot be ignored, especially in urban areas with more serious pollution. By monitoring the concentration of air pollutants (such as PM2.5, C02, etc.) and combining it with transpiration rate data, the layout of green areas can be further optimized and the ability of vegetation to regulate air quality can be improved. (3) Wind speed and direction data. Wind speed and direction data can help analyze the air flow in the city, further optimize the layout of green belts, improve the efficiency of plant transpiration, and reduce the heat island effect. Areas with higher wind speeds are suitable for planting plants with high transpiration rates. Using wind direction to adjust air flow can effectively alleviate areas with excessively high temperatures.

[0108] The present invention also provides an urban environment monitoring and control method based on global greening data, which is applied to the urban environment monitoring and control system based on global greening data mentioned above.

[0109] The above technical objectives of the present invention are achieved through the following technical solutions:

[0110] A method for monitoring and controlling the urban environment based on global greening data specifically comprises the following steps:

[0111] Step 1: Use the image acquisition module to collect green image data within the city at preset intervals;

[0112] Step 2: Process the greening image data to extract the vegetation coverage area; divide the vegetation coverage area into several unit areas according to the preset segmentation rules; extract features from each unit area to obtain texture feature parameters; and classify all unit areas into several types of areas according to the texture feature parameters.

[0113] Step 3: Calculate the standard value of the texture feature parameters of each unit area; select several unit areas within each type of area as sampling areas based on the standard value; and arrange sensor groups in the sampling areas to obtain monitoring data;

[0114] Step 4: Calculate the monitoring approximate data of each unit area based on the monitoring data and standard value of the sensor group at the sampling area and the distance weight between the unit area in the type area and the sampling area;

[0115] Step 5: Generate urban microclimate control strategies based on the monitoring approximate data of each unit area and the type of area to which it belongs.

[0116] In summary, the present invention has the following beneficial effects:

[0117] 7. This solution utilizes an image acquisition module. By periodically collecting green image data within the city, combined with an image analysis module, it can accurately extract vegetation coverage areas and perform feature extraction on each unit area. By processing image data, it can accurately identify and analyze different types of green vegetation in the city, including trees, shrubs, and lawns, and provide a scientific basis for subsequent microclimate control. Compared with traditional manual surveys and static monitoring methods, image acquisition and analysis can achieve efficient and accurate vegetation monitoring over a larger area, making it particularly suitable for large-scale urban greening management. This method not only improves the efficiency and accuracy of data acquisition, but also reduces manual intervention and monitoring costs.

[0118] 8. The image analysis module extracts multiple texture features of vegetation coverage (such as leaf area index, canopy height, and texture uniformity) and scientifically classifies green areas based on these features. Different types of areas (such as tree areas, shrub areas, and lawn areas) play different roles in microclimate regulation. Accurate regional classification can help develop personalized regulation strategies for each area.

[0119] 9. A sampling and screening module is implemented to achieve dynamic monitoring within urban green areas by calculating standard values ​​based on the characteristic parameters of each unit area and selecting sampling areas. These sampling areas are not only selected based on the actual characteristics of the vegetation, but the sampling locations can also be dynamically adjusted based on changes in standard values ​​and regional characteristics. This dynamic monitoring mechanism ensures that the system can better adapt to environmental changes in actual applications, improving monitoring coverage and data representativeness. In addition, the rational selection of sampling areas reduces the redundancy of sensor deployment, saves monitoring costs, and improves the system's operational efficiency.

[0120] 10. Global inference technology overcomes the limitations of sensor locations, efficiently inferring microclimate data from unmonitored areas. This significantly expands monitoring coverage and ensures effective climate control across the entire city. This inference method better addresses the incompleteness of data collection and the complexity of the urban environment. A comprehensive sensor deployment would significantly increase costs and data processing requirements.

[0121] 11. Based on the approximate monitoring data for each unit area and the type of area it belongs to, an appropriate urban microclimate control strategy is analyzed and generated. This process, based on a comprehensive analysis of sensor data, image analysis results, and regional characteristics, can develop personalized control plans based on the microclimate characteristics of different regions. This precise control strategy improves the flexibility and sustainability of microclimate management, enabling more scientific and efficient urban greening and climate control. Through refined microclimate control, the livability and sustainable development capabilities of the city are enhanced, providing scientific and technological support for the optimization of the urban ecological environment. At the same time, by optimizing green vegetation management, energy consumption and water waste are reduced, contributing to the construction of green cities.

[0122] The regional correction module can modify the monitoring approximate data within the radiation range of special impact areas (such as urban buildings and high-temperature island effect areas). This correction mechanism significantly improves the system's adaptability to different urban microclimate zones, ensuring that microclimate control can be continuously and effectively implemented in complex and changing urban environments, and preventing the impact of external environmental changes on system performance.

[0123] The above-described embodiments do not constitute a limitation on the scope of protection of this technical solution. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the above-described embodiments shall be included in the scope of protection of this technical solution.

Claims

1. An urban environment monitoring and control system based on global greening data, characterized by: include: An image acquisition module, configured to acquire green image data within the city at predetermined intervals; A monitoring module, comprising a plurality of sensor groups, wherein the sensor groups are used to monitor vegetation and obtain monitoring data; An image analysis module is used to process the greening image data to extract vegetation coverage areas, divide the vegetation coverage areas into a number of unit areas according to a preset segmentation rule, extract features from each unit area to obtain texture feature parameters, and classify all unit areas according to the texture feature parameters of each unit area to obtain a number of type areas; A sampling and screening module, the sampling and screening module is used to calculate the corresponding standard value according to the characteristic parameters of each unit area, and the standard value is used to quantitatively characterize the characteristics of the vegetation in the unit area; According to the standard value, a number of unit areas within each type of area are screened out as sampling areas, and the sampling areas are used to set the sensor group; A global estimation module, configured to calculate the monitoring approximate data of each unit area based on the monitoring data and standard values ​​monitored by the sensor group in the sampling area; A strategy generation module, which generates a control strategy by analyzing and calculating the monitoring approximate data of each unit area and the type of area it is located in; The sampling and screening module is used to calculate the corresponding standard value according to the characteristic parameters of each unit area using the following calculation formula: <h2 style=";text-align:left;direction:ltr">S<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> = w1 LAI + w2 CH + w3 TEU Where S is the standard value, LAI is the leaf area index, CH is the canopy height, TEU is the texture uniformity, w1, w2, and w3 are the influence weight parameters corresponding to the leaf area index, canopy height, and texture uniformity, respectively; The method of selecting a plurality of unit areas within each type of area as sampling areas according to the standard value specifically includes the following steps: Calculate the mean and standard deviation of the standardized values ​​within each type of area; Calculate the number of samples corresponding to each type of area according to the number of unit areas contained in each type of area; The standard values ​​of unit areas in different types of areas are screened according to the standard deviation and mean to obtain the preliminary selected areas for each type of area; Calculate the centroid position of each type of area and the calibration coordinates of the preliminary selected area within the area of ​​that type, and filter the preliminary selected area according to the distance from the calibration coordinates to the centroid position and the number of samples to obtain the sampling area of ​​each type of area; The monitoring approximate data of each unit area calculated based on the monitoring data monitored by the sensor group at the sampling area and the standard value specifically includes: The distance weight is calculated based on the distance between the unit area and the sampling area within the same type of area; The monitoring approximate data of each unit area in the same type of area is calculated based on the distance weight and the detection data of the sampling area; The calculation formula of the distance weight is: Among them, w ij is the distance weight of the i-th sampling area to the j-th unit area, d ij is the distance between the i-th sampling area and the j-th unit area; The calculation formula for the monitoring approximate data is: Among them, D j is the monitoring approximate data of the jth unit area, D i is the monitoring data of the i-th sampling area, and n is the number of sampling areas in this type of area.

2. The urban environment monitoring and control system based on global greening data according to claim 1 is characterized in that: The preset segmentation rule is to divide the area into square areas with the maximum detection diameter of the sensor group as the side length or to divide the area into circular areas with the maximum detection radius of the sensor group as the side length.

3. The urban environment monitoring and control system based on global greening data according to claim 1 is characterized in that: The texture characteristic parameters include leaf area index, canopy height and texture uniformity. The texture parameters obtained by feature extraction of each unit area specifically include: The normalized vegetation index is calculated using multispectral images of vegetation-covered areas, and the leaf area index is calculated based on the normalized vegetation index; Use image stereo matching technology to extract three-dimensional height information from the vegetation coverage area, and calculate the canopy height based on the three-dimensional height information; A gray-level co-occurrence matrix is ​​constructed for each unit area, and the texture uniformity is calculated.

4. The urban environment monitoring and control system based on global greening data according to claim 3 is characterized in that: The type areas include tree areas, shrub areas and lawn areas. The classification of all unit areas according to the texture feature parameters of each unit area to obtain several type areas specifically includes: The unit areas with leaf area index greater than the first upper threshold and canopy height greater than the second upper threshold are divided into the tree zone; The unit areas with leaf area index less than or equal to the first upper threshold and greater than the first lower threshold, and canopy height less than or equal to the second upper threshold and greater than the second lower threshold are divided into shrub areas; The unit areas with leaf area index less than or equal to the first lower threshold and canopy height less than or equal to the second lower threshold are divided into lawn areas.

5. The urban environment monitoring and control system based on global greening data according to claim 1 is characterized in that: It also includes a regional correction module, which is used to obtain special impact areas within the city, and correct the monitoring approximate data of the unit area within the radiation range according to the radiation range of the special impact area to obtain new monitoring approximate data.

6. The urban environment monitoring and control system based on global greening data according to claim 1 is characterized in that: The monitoring data includes transpiration rate data, liquid flow data, and temperature data.

7. A method for monitoring and controlling the urban environment based on global greening data, applied to the system for monitoring and controlling the urban environment based on global greening data according to any one of claims 1 to 6, characterized in that: The specific steps include: Step 1: Use the image acquisition module to collect green image data within the city at preset intervals; Step 2: Process the green image data to extract the vegetation coverage area; divide the vegetation coverage area into several unit areas according to the preset segmentation rules; extract features from each unit area to obtain texture feature parameters; and classify all unit areas into several types of areas based on the texture feature parameters; Step 3: Calculate the standard value of the texture feature parameters of each unit area; select several unit areas within each type of area as sampling areas based on the standard value; and arrange sensor groups in the sampling areas to obtain monitoring data; Step 4: Calculate the monitoring approximate data of each unit area based on the monitoring data and standard value of the sensor group at the sampling area and the distance weight between the unit area in the type area and the sampling area; Step 5: Generate urban microclimate control strategies based on the monitoring approximate data of each unit area and the type of area to which it belongs.

Images