Urban tree information rapid acquisition method and system

Abstract

The present application relates to the technical field of tree information collection, in particular to a city tree information rapid collection method and system, comprising the following steps: obtaining the geographic coordinates of each tree in the city through a GNSS receiver, recording the accuracy and timestamp information of each position, performing data synchronization, and generating city tree coordinate data. In the present application, GNSS receivers and microwave remote sensing equipment are introduced to ensure high precision and multidimensional analysis of tree data. GNSS receivers provide accurate coordinates and timestamps, enhancing the real-time and accuracy of geographic data. Microwave remote sensing technology analyzes the dielectric constant of trees to accurately assess tree age and health. Image sensors with automatic focus and exposure adjustment can capture detailed leaf color and shape, improving the detail and accuracy of pest and disease diagnosis. Real-time tree information mapping promotes the efficiency of environmental monitoring and urban planning, providing strong support for the management of urban ecosystems.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of tree information collection, and in particular to a method and system for rapidly collecting urban tree information. BACKGROUND

[0002] The technical field of tree information collection involves the use of various methods and systems to collect and analyze data on urban trees, combining remote sensing technology, geographic information systems, data analysis, and environmental science to provide accurate information on tree location, species, health status, and growth parameters. By using techniques such as satellite imagery, drones, laser scanning, or ordinary digital photography, large amounts of tree data can be quickly collected. In addition, this field also includes data processing and analysis techniques that can automatically identify tree species and assess tree health, which is crucial for urban planning, environmental monitoring, and ecological protection.

[0003] Among them, the method for rapidly collecting urban tree information refers to a technical method specially designed for the rapid and efficient collection and analysis of urban tree data, and its main uses include but are not limited to monitoring urban greening conditions, planning urban green spaces, managing urban forest resources, and assessing and preventing environmental risks caused by tree health problems. By rapidly collecting tree information, urban planners and environmental scientists can better understand and manage urban ecosystems, improve the quality of urban living environments, and provide data support for the sustainable development of cities.

[0004] The existing technology mainly relies on satellite images, drones, and laser scanning, which have a wide coverage but have limitations in real-time data updating and accurate capture of individual tree data. The limitations lie in the timeliness and detail resolution of the data, which cannot effectively capture the small changes in the rapidly changing urban environment, leading to lag in data processing and affecting the timely assessment and fine management of tree health status. For example, the update frequency and resolution limitations of satellite and drone images may miss the early stages of tree diseases, resulting in delayed responses to diseases and increasing the challenges and risks of urban greening management. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and to provide a method and system for rapidly collecting urban tree information.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solution: a method for rapidly collecting urban tree information, comprising the following steps:

[0007] S1: Obtain the geographic coordinates of each tree in the city through a GNSS receiver, record the accuracy and timestamp information of each location, perform data synchronization, and generate urban tree coordinate data;

[0008] S2: Based on the urban tree coordinate data, guide the microwave remote sensing equipment to the target tree, transmit microwave signals from different angles and frequencies, measure the time delay and intensity change of the return signal, calculate the tree dielectric constant, and obtain the tree dielectric constant measurement value;

[0009] S3: Based on the tree dielectric constant measurement values, define a tree age estimation rule, score each dielectric constant value, summarize the scoring data, determine the age range of the tree according to a set threshold, and obtain a predicted tree age result;

[0010] S4: Based on the urban tree coordinate data, in combination with an image sensor, automatically adjusting focus and exposure parameters, taking photos of the trees, analyzing changes in tree leaf color and shape, and generating basic tree health data;

[0011] S5: Based on the basic tree health data, capturing detailed images of leaves, analyzing color distribution and texture changes in the images, identifying differential disease signs on the leaves through visual information, assessing the tree's health status, and generating disease and pest diagnosis results;

[0012] S6: Based on the urban tree coordinate data, predicted tree age results and tree disease and insect pest diagnosis results, the geographical location map of the trees is updated in real time, the health status and growth environment of the trees are comprehensively evaluated and marked, and a real-time urban tree information mapping result is generated.

[0013] As a further solution of the present invention, the urban tree coordinate data includes geographic location coordinates, accuracy level and time records, the tree dielectric constant measurement values ​​include dielectric constant values, signal delay data and signal strength data, the predicted tree age results include age score records, age range classification results and score summary data, the basic tree health data include leaf color feature records and leaf shape feature records, the pest and disease diagnosis results include color distribution characteristics, texture change characteristics and health abnormality indicators, and the real-time urban tree information mapping results include geographic location update records, health status identification and environmental assessment results.

[0014] As a further solution of the present invention, the specific steps of obtaining the geographic coordinates of each tree in the city through a GNSS receiver, recording the accuracy and timestamp information of each location, performing data synchronization, and generating urban tree coordinate data are as follows:

[0015] S101: Use GNSS receivers to measure the geographic coordinates of each tree in the city, synchronously record the accuracy and timestamp of each coordinate point, correct for signal drift, update positioning data, and generate accurate tree coordinate information;

[0016] S102: Based on the tree coordinate accurate information, data is cleaned, coordinate abnormal values are deleted, coordinate data is formatted into a unified format, data standardization is performed, and formatted tree data is obtained;

[0017] S103: Based on the formatted tree data, data synchronization is performed through a city database interface, the cleaned and formatted data is uploaded, data integrity is verified, database records are updated, and city tree coordinate data is obtained.

[0018] As a further scheme of the application, in combination with the city tree coordinate data, the microwave remote sensing device is guided to aim at the target tree, microwave signals are emitted from different angles and frequencies, the time delay and intensity change of the returned signals are measured, the dielectric constant of the tree is calculated, and the specific steps for obtaining the dielectric constant measurement value of the tree are,

[0019] S201: Based on the city tree coordinate data, the direction and focus of the microwave remote sensing device are adjusted, the target tree is aimed at, the device angle is adjusted to capture the optimal signal, it is ensured that the microwave covers the target area from multiple angles, and microwave directional data is obtained.

[0020] S202: Based on the microwave directional data, the device configuration is adjusted to emit microwaves from different frequencies, the returned signals under multiple frequencies are monitored, the time delay and signal intensity of each frequency are recorded, and microwave signal response data is obtained.

[0021] S203: Based on the microwave signal response data, the time delay and intensity change of the returned signals at different frequencies are calculated, the dielectric constant of the tree is calculated through data, the consistency of the data is verified by repeated measurement, and the dielectric constant measurement value of the tree is obtained.

[0022] As a further scheme of the application, based on the tree dielectric constant measurement value, a tree age estimation rule is defined, each dielectric constant value is scored, the scoring data is processed, the age range of the tree is judged according to the set threshold, and the specific steps for obtaining the predicted tree age result are,

[0023] S301: Based on the tree dielectric constant measurement value, a correlation scoring standard between tree age and dielectric constant is defined, an age-related score is assigned to each measurement value according to the numerical value, the direct correlation between each score and dielectric constant is revealed, and tree age scoring data is obtained.

[0024] S302: Based on the tree age scoring data, tree scoring is summarized, the difference between the scores of different tree species is identified through aggregation processing, scoring abnormal data is adjusted, the consistency of the scores is optimized through data purification, and the summary scoring result is obtained.

[0025] S303: Based on the summarized scoring results, the age range of each tree's scoring data is determined according to a preset age determination threshold, and the age range of each tree is classified by comparing the relationship between the score and the threshold to obtain a predicted tree age result.

[0026] As a further solution of the present invention, based on the urban tree coordinate data, combined with an image sensor, the focus and exposure parameters are automatically adjusted, photos of the trees are taken, and the color and shape changes of the tree leaves are analyzed to generate basic tree health data. The specific steps are:

[0027] S401: Based on the urban tree coordinate data, configure an image sensor, automatically adjust focus and exposure parameters to match the position and lighting conditions of each tree, ensure image clarity and balanced exposure, and obtain optimized image capture setting results;

[0028] S402: Based on the optimized image capture setting result, take a photo of each tree, capture the color and shape of the tree leaves, and record the tree morphology to obtain tree morphology image data;

[0029] S403: Based on the tree morphological image data, analyze the color changes and shape anomalies of the leaves, evaluate the health status of the trees, and obtain basic health data of the trees.

[0030] As a further embodiment of the present invention, based on the basic tree health data, detailed images of leaves are captured, color distribution and texture changes in the images are analyzed, differential disease signs on the leaves are identified through visual information, the health status of the trees is assessed, and the specific steps of generating disease and insect pest diagnosis results are as follows:

[0031] S501: Based on the basic tree health data, analyze leaf details, optimize exposure and contrast to highlight leaf texture and color differences, and obtain fine leaf image data;

[0032] S502: Based on the refined leaf image data, enhancing image color and texture contrast, analyzing color distribution and texture changes on the leaf surface, identifying potential health issues, including spots, cracks, or discolored areas, and obtaining leaf health feature analysis data;

[0033] S503: Based on the leaf health feature analysis data, the leaf health features are compared with known disease features, and the spot size, crack depth and range of discoloration areas on the leaves are evaluated through edge detection to establish the actual signs of each disease and obtain the tree disease and insect pest diagnosis results.

[0034] As a further solution of the present invention, the edge detection is performed according to the formula:

[0035] ;

[0036] Determine the edge information of the leaf image ,in, and is the pixel position coordinate in the image, is the standard deviation of the Gaussian filter, which controls the smoothness of the filter. and is the offset parameter used to adjust the position of the filter center. Adjust the parameter for the filter strength.

[0037] As a further embodiment of the present invention, based on the urban tree coordinate data, predicted tree age results, and tree disease and insect pest diagnosis results, a geographical location map of trees is updated in real time, and a comprehensive assessment and marking of the tree health status and growth environment is performed. The specific steps for generating a real-time urban tree information mapping result are:

[0038] S601: Based on the urban tree coordinate data, a map update is initiated, the latest coordinate data is imported, map zoom and annotation parameters are adjusted to ensure that the location of each tree is accurately displayed, geographic location information is synchronized to ensure that the data is consistent with actual geographic features, and an updated tree geographic location map is obtained;

[0039] S602: Based on the updated tree geographic location map and the predicted tree age results, each tree is classified into age groups using a map marking tool, color coding is applied to distinguish trees of different age groups, and the age labels on the map are automatically updated to obtain a tree age marking map;

[0040] S603: Using the tree age marking map and the tree disease and insect pest diagnosis results, the health status and growth environment are evaluated, trees affected by diseases are marked, and the affected areas are highlighted using icons and colors, providing real-time visual analysis and generating real-time urban tree information mapping results.

[0041] A rapid urban tree information collection system, comprising:

[0042] The geographic coordinate acquisition module uses a GNSS receiver to measure the geographic coordinates of each tree in the city, synchronously records the accuracy and timestamp of each coordinate point, cleans the data, and performs data synchronization through the city database interface to obtain the coordinate data of urban trees;

[0043] The dielectric constant measurement module adjusts the direction and focus of the microwave remote sensing device based on the urban tree coordinate data, adjusts the device configuration to transmit microwaves at different frequencies, records the time delay and signal strength of each frequency, calculates the time delay and strength change of the return signal at the different frequencies, infers the tree dielectric constant, and obtains the tree dielectric constant measurement value;

[0044] The tree age scoring module defines a correlation scoring standard between tree age and dielectric constant based on the tree dielectric constant measurement value, summarizes the tree scores, identifies the differences in scores between different tree species through aggregation processing, and determines the age range of each tree score data according to a preset age determination threshold to obtain a predicted tree age result;

[0045] The tree morphology acquisition module configures an image sensor based on the urban tree coordinate data, automatically adjusts the focus and exposure parameters to match the position and lighting conditions of each tree, takes a photo of each tree, captures the color and shape of the tree leaves, and records the tree morphology to obtain tree morphology image data;

[0046] The leaf health analysis module analyzes leaf color changes and shape anomalies based on the tree morphology image data, assesses the basic health of the tree, optimizes exposure and contrast to highlight leaf texture and color differences, and obtains detailed leaf image data;

[0047] The tree disease and insect pest diagnosis module analyzes the color distribution and texture changes on the leaf surface based on the fine leaf image data, identifies potential health problems, including spots, cracks, or discolored areas, compares the leaf health characteristics with known disease characteristics, evaluates the size of spots, crack depth, and the extent of discolored areas on the leaves, and obtains tree disease and insect pest diagnosis results;

[0048] The urban tree information mapping module initiates map updates based on the urban tree coordinate data, synchronizes geographic location information, classifies each tree into age groups based on the predicted tree age results, applies color coding to distinguish trees of different age groups, and evaluates the health status and growth environment based on the tree disease and pest diagnosis results, marks trees affected by diseases, and generates real-time urban tree information mapping results.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are:

[0050] In this invention, by introducing GNSS receivers and microwave remote sensing equipment, high-precision and multi-dimensional analysis of tree data is ensured. The GNSS receiver provides precise coordinates and timestamps, enhancing the real-time nature and accuracy of geographic data. Microwave remote sensing technology accurately assesses the age and health of trees by analyzing the dielectric constant of trees. The image sensor, which automatically adjusts the focal length and exposure parameters, can capture the color and shape of leaves in detail, improving the detail and accuracy of pest and disease diagnosis. The real-time updated tree information mapping promotes the efficiency of environmental monitoring and urban planning, providing strong support for the management of urban ecosystems. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of the steps of the present invention;

[0052] Figure 2 A step flow chart for S1 of the present application;

[0053] Figure 3 A step flow chart for S2 of the present application;

[0054] Figure 4 A step flow chart for S3 of the present application;

[0055] Figure 5 A step flow chart for S4 of the present application;

[0056] Figure 6 A step flow chart for S5 of the present application;

[0057] Figure 7 A step flow chart for S6 of the present application;

[0058] Figure 8 A system module chart for the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0060] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0061] Please refer to Figure 1 A method for quickly collecting urban tree information, comprising the following steps:

[0062] S1: Obtain the geographic coordinates of each tree in the city through a GNSS receiver, record the accuracy and timestamp information of each position, perform data synchronization, and generate urban tree coordinate data;

[0063] S2: Combine the urban tree coordinate data to guide the microwave remote sensing device to aim at the target tree, emit microwave signals from different angles and frequencies, measure the time delay and intensity change of the returned signals, calculate the dielectric constant of the tree, and obtain the dielectric constant measurement value of the tree;

[0064] S3: Based on the tree dielectric constant measurement value, define the tree age estimation rule, score each dielectric constant value, aggregate the scoring data, judge the age range of the tree according to the set threshold, and get the predicted tree age result;

[0065] S4: Based on the urban tree coordinate data, combined with the image sensor, automatically adjust the focal length and exposure parameters, take photos of the tree, analyze the color and shape changes of the tree leaves, and generate the basic health data of the tree;

[0066] S5: Based on the basic health data of the tree, capture detailed images of the leaves, analyze the color distribution and texture changes in the images, identify the signs of different diseases on the leaves through visual information, evaluate the health status of the tree, and generate the pest and disease diagnosis result;

[0067] S6: Based on the urban tree coordinate data, the predicted tree age result and the tree pest and disease diagnosis result, update the geographical position map of the tree in real time, comprehensively evaluate and mark the health status and growth environment of the tree, and generate the real-time urban tree information mapping result.

[0068] The urban tree coordinate data includes geographical position coordinates, precision level and time record, the tree dielectric constant measurement value includes dielectric constant value, signal delay data and signal strength data, the predicted tree age result includes age score record, age interval classification result and score aggregation data, the basic health data of the tree includes leaf color feature record and leaf shape feature record, the pest and disease diagnosis result includes color distribution feature, texture change feature and health abnormality index, and the real-time urban tree information mapping result includes geographical position update record, health status identification and environment evaluation result.

[0069] Please refer to Figure 2 , the specific steps of S1 are as follows:

[0070] S101: Use GNSS receiver to measure the geographical coordinates of each tree in the city, record the accuracy and time stamp of each coordinate point synchronously, correct the signal drift, update the positioning data, and generate the tree coordinate accuracy information;

[0071] Using a GNSS receiver, the geographic coordinates of each tree are measured within the city. The device is first initialized to ensure synchronization between the receiver's time and the geocoding system, and the receiver is geo-calibrated to ensure accurate signal reception. Next, data is recorded for each measurement point, including coordinates (longitude and latitude), accuracy indicators, and timestamps. The received raw data is affected by various environmental factors, such as building obstruction and climatic conditions. Therefore, a signal quality assessment is performed to filter out valid data that meets the required signal strength. A sliding time window method is used for the valid data, calculating the average signal value every set time period (e.g., every 10 seconds) to reduce errors and improve the accuracy of the location data. The corrected data is then output according to the specified format to generate precise tree coordinate information.

[0072] S102: Based on the precise information of tree coordinates, clean the data, delete coordinate outliers, format the coordinate data into a unified format, perform data standardization, and obtain formatted tree data;

[0073] Based on the precise tree coordinate information, a preliminary data check is performed to identify coordinate data that significantly deviates from the normal range. Outliers are caused by equipment errors, signal reflections, or operator errors. Statistical analysis methods, such as IQR (interquartile range) or standard deviation analysis, are used to determine the boundaries of normal data and remove data points that fall outside these boundaries. The retained data is then formatted and standardized, for example, by converting all coordinate data to decimal form and arranging and categorizing them according to a specific template. To ensure data consistency and comparability, all data is standardized and quantified to a uniform standard, such as adjusting precision to five decimal places. Finally, the standardized and formatted tree data is exported for further data synchronization and analysis.

[0074] S103: Based on the formatted tree data, perform data synchronization through the city database interface, upload the cleaned and formatted data, verify data integrity, update database records, and obtain city tree coordinate data;

[0075] Based on the formatted tree data, a data interface with the city database is established to ensure efficient data communication. Data upload tasks are automatically executed, and locally cleaned and formatted tree data is uploaded in batches to the city database. Before uploading, each data item is checked for integrity to ensure there are no missing fields or formatting errors. After data upload, the database's built-in validation procedures are used to check the data's integrity and accuracy, such as using SQL constraints or data validation scripts to ensure data validity. Once data validation passes, the database automatically updates existing tree records to ensure the database information is up to date. Finally, the updated city tree coordinate data is retrieved from the database for subsequent urban planning and greening management.

[0076] See also Figure 3 , the specific steps of S2 are:

[0077] S201: Based on the urban tree coordinate data, adjust the direction and focus of the microwave remote sensing equipment to align with the target tree, adjust the device angle to capture the optimal signal, ensure that the microwave covers the target area from multiple angles, and obtain microwave directional data;

[0078] Based on the urban tree coordinate data, the basic operating parameters of the microwave remote sensing equipment are set first. Using the known tree coordinate data, the operator adjusts the direction and focus of the remote sensing equipment through the control interface to ensure that the target tree is within the central field of view of the equipment. An electronic control system is used to fine-tune the direction of the remote sensing equipment, changing its pitch and yaw angles to cover the different heights and angles of the target trees, thereby maximizing the capture of reflected signals. During the adjustment process, real-time monitoring of feedback information ensures that each adjusted angle can cover the target area from multiple directions, increasing the dimensionality and accuracy of data collection. After multi-angle coverage is completed, a preliminary assessment of the data quality of each angle is conducted, and the data with the best signal is selected as the basis for subsequent processing. The system can obtain multi-angle, high-precision microwave directional data, providing a solid foundation for further analysis.

[0079] S202: Based on the microwave directional data, adjust the device configuration to transmit microwaves at different frequencies, monitor the return signals at multiple frequencies, record the time delay and signal strength of each frequency, and obtain microwave signal response data;

[0080] Based on the microwave directional data, the operator adjusts the frequency setting of the microwave emission through the control system of the remote sensing equipment. According to the pre-set frequency range, the system automatically adjusts the emission frequency step by step from low frequency to high frequency, and collects the return signal at each set frequency. The collected data includes the time delay and signal strength of each frequency point, which will be recorded in a specially designed data collection module. For each frequency, the system analyzes the quality of the return signal through an enhanced signal processing algorithm and records the specific parameter settings when the signal is strongest. In addition, the system also monitors environmental factors such as temperature and humidity in real time, and adjusts the transmission parameters of the microwave signal to compensate for the impact of environmental changes on signal strength and propagation speed. After completing the steps, a set of microwave signal response data containing detailed signal response characteristics at different frequencies will be obtained, preparing for the next step of dielectric constant calculation.

[0081] S203: Based on the microwave signal response data, the time delay and intensity change of the difference frequency return signal are calculated, and the dielectric constant of the tree is inferred from the data. The consistency of the data is verified by repeated measurements to obtain the dielectric constant measurement value of the tree;

[0082] Based on the microwave signal response data, data analysis was first used to calculate the relationship between the time delay and signal strength of the return signal at each frequency. Using this data, physical modeling methods were used to infer the dielectric constant value corresponding to each frequency. To ensure the accuracy and consistency of the calculations, multiple measurements were repeated for each frequency setting, and the consistency of the measurement results was compared. This process was executed by an automated control system, ensuring that each measurement was performed under the same environment and settings. Through this repeated measurement and comparison, abnormal data can be effectively screened out and the high consistency of the resulting data can be guaranteed. Finally, the results at each frequency were combined and a weighted average method was used to calculate the final tree dielectric constant measurement value. This value can reflect the electrical properties of the tree and is of great significance for studying the physiological and ecological characteristics of trees.

[0083] See also Figure 4 , the specific steps of S3 are:

[0084] S301: Based on the tree dielectric constant measurement values, define the correlation scoring standard between tree age and dielectric constant, assign an age-related score to each measurement value according to the numerical value, reveal the direct correlation between each score and dielectric constant, and obtain tree age score data;

[0085] Based on the measured permittivity values ​​of trees, a quantitative scoring system was first developed to measure the correlation between permittivity and tree age. Historical data analysis was used to determine the statistical correlation between permittivity and tree age. A linear regression model was then used to develop a predictive model, using permittivity as the independent variable and tree age as the dependent variable. Based on the results of the regression analysis, a correlation scoring system was generated, which included age-related scores corresponding to different permittivity values. Based on this, a specific age-related score was assigned to each measured permittivity value, revealing the direct correlation between each score and the permittivity. After these steps, all scoring data were collected and organized to form tree age scores for further analysis and evaluation.

[0086] S302: Summarize tree scores based on tree age score data, identify differences in scores between different tree species through aggregation processing, adjust abnormal score data, optimize score consistency through data purification, and obtain a summary score result;

[0087] Based on the tree age score data, detailed data aggregation and analysis are carried out. First, through data aggregation processing, the differences in scores between different tree species are identified. Using cluster analysis methods, trees are divided into several groups based on dielectric constant and age score, and the differences in scores within and between groups are analyzed. Through these analyses, abnormal scoring data that deviates significantly from the group average are discovered and adjusted to optimize the consistency of the scores. Then, the adjusted data are aggregated again, and the average score of each group and the overall score of the entire data set are obtained by arithmetic mean or weighted mean method. Finally, the summary score results after data purification and optimization are output to provide a basis for the next step of age determination.

[0088] S303: Based on the summarized scoring results, the age range of each tree is determined according to a preset age determination threshold. The age range of each tree is classified by comparing the score with the threshold to obtain a predicted tree age result.

[0089] Based on the aggregated scoring results, the tree ages are classified and predicted. Each tree's scoring data is analyzed according to a previously set age threshold. Using a threshold segmentation method, each tree's scoring data is compared with a preset threshold. If a tree's score is above a certain threshold, it is classified into an older age range; if the score is below the threshold, it is classified into a younger age range. In this way, each tree is assigned a specific age range. Furthermore, to improve classification accuracy, multiple thresholds can be used to further categorize trees into more detailed age levels. The age range classification results for all trees are then collected and organized, and the final predicted tree age result is output.

[0090] See also Figure 5 , the specific steps of S4 are:

[0091] S401: Based on the urban tree coordinate data, the image sensor is configured to automatically adjust the focus and exposure parameters to match the position and lighting conditions of each tree, ensuring image clarity and balanced exposure, and obtaining optimized image capture settings.

[0092] Based on the coordinate data of urban trees, the initial settings of the image sensor are configured. The operator inputs this urban tree coordinate data into the image capture system, which automatically locates each tree's specific location based on the coordinates. Next, the image sensor's focus and exposure parameters are automatically adjusted based on the lighting conditions at each location. The system uses ambient light sensing technology to detect the current ambient light intensity in real time and adjusts the camera's ISO, shutter speed, and aperture size based on the detection results to adapt to different lighting conditions, ensuring image clarity and balanced exposure. Image quality is further enhanced by optimizing the image's color balance and contrast. After adjustments are completed, the system saves the optimal image capture settings for each tree, providing accurate configuration information for subsequent image acquisition.

[0093] S402: Based on the optimized image capture setting result, take a photo of each tree, capture the color and shape of the tree leaves, and record the tree morphology to obtain tree morphology image data;

[0094] Based on the optimized image capture settings, the operator begins photographing each tree. The image sensor automatically captures high-definition images of the trees according to pre-set optimized settings. During the photography process, special attention is paid to capturing the color and shape characteristics of the tree's leaves, ensuring accurate recording of every detail. Each tree is photographed from various angles, including front, side, and top views, to fully capture its morphology. After the photography is completed, all image data is categorized and stored by tree ID and capture time. Each set of images includes a complete record of the tree's morphology, allowing for assessment of its growth status and environmental adaptability.

[0095] S403: Analyze leaf color changes and shape anomalies based on tree morphology image data, assess tree health status, and obtain basic tree health data;

[0096] Based on tree morphological image data, the system analyzes tree health. It performs color and shape analysis on collected leaf images, automatically identifying the RGB values ​​of leaf color and comparing them with the standard color range of healthy leaves. This helps identify color changes that may indicate nutrient deficiencies or disease infestations. It also analyzes leaf shape, such as cracks, curling, or abnormal growth patterns. These abnormal shapes are often associated with environmental stress or biological invasion. Combining the color and shape analysis results, the system assesses the health of each tree and generates a detailed health assessment report. Ultimately, this data is aggregated to form basic tree health data, providing a scientific basis for urban greening management.

[0097] See also Figure 6 , the specific steps of S5 are:

[0098] S501: Based on the tree's basic health data, analyze leaf details, optimize exposure and contrast to highlight leaf texture and color differences, and obtain fine leaf image data;

[0099] Based on the tree's basic health data, optimize the acquired leaf images. According to the key information recorded in the health data, such as lighting conditions and leaf reflection characteristics, adjust the exposure level and contrast of the image, so that the texture and color differences of the leaves are more prominent, and the visual contrast of chlorophyll and non-chlorophyll components is enhanced, especially in the parts of leaf veins and leaf edges. In addition, local contrast enhancement algorithms such as local histogram equalization are applied to ensure that the details of each region can be accurately presented. After careful adjustment, every detail in the image, including tiny color differences and texture changes, can be clearly captured and recorded, and the fine leaf image data generated is used for further health analysis.

[0100] S502: Based on the fine leaf image data, enhance the color and texture contrast of the image, analyze the color distribution and texture changes on the leaf surface, identify potential health problems including spots, cracks or discolored areas, and obtain tree leaf health feature analysis data;

[0101] Based on the fine leaf image data, conduct more in-depth image analysis to identify and evaluate the health status of the leaves, enhance the color and texture contrast of the leaf surface to make the differences between healthy and damaged areas more obvious, and use image segmentation techniques such as threshold-based segmentation to separate normal green areas from abnormal color areas (such as yellowing, wilting or red spots) in the image. At the same time, detect tiny cracks and spots on the leaf surface, not only identify potential health problems such as leaf spot disease or water deficiency symptoms, but also quantitatively evaluate the overall health status of the leaves. All this information is integrated into the tree leaf health feature analysis data, providing scientific basis for the final disease diagnosis.

[0102] S503: Based on the tree leaf health feature analysis data, compare the leaf health features with known disease characteristics, evaluate the size of spots, the depth of cracks and the range of discolored areas on the leaves through edge detection, establish the actual signs of each disease, and obtain tree disease and pest diagnosis results;

[0103] Edge detection, according to the formula:

[0104] ;

[0105] Determine the edge information of the leaf image , where, and are the pixel position coordinates in the image, is the standard deviation of the Gaussian filter, which controls the smoothing degree of the filter, and Offset parameter, used to adjust the position of the filter center, so that specific areas can be enhanced processing, Filter strength adjustment parameter, allows dynamic change of standard deviation to adapt to the detail features of specific areas of the image.

[0106] The execution process is as follows:

[0107] First, by adding offset parameter And Allow the filter to focus on specific areas of the image, and highlight the special signs of disease on the leaves, such as spots or cracks around them, second, introduce filter strength adjustment parameter According to the size and shape of the disease area, dynamically adjust the value of Improve the adaptability and flexibility of the filter, finally, according to the image processed by the above parameters, Canny edge detection is carried out, and the boundaries of spot size, crack depth and discoloration area on the leaves are determined, so as to more accurately evaluate and diagnose tree diseases.

[0108] Please refer to Figure 7 The specific steps of S6 are as follows:

[0109] S601: Based on the coordinate data of urban trees, start the map update, import the latest coordinate data, adjust the map zoom and labeling parameters to ensure the accurate display of the position of each tree, synchronize the geographic location information, and ensure that the data is consistent with the actual geographic features, and obtain the updated tree geographic location map;

[0110] Based on the coordinate data of urban trees, first start the map update program, import the latest tree coordinate data into the map update system. The system automatically checks and synchronizes the data to ensure that each data point matches the actual geographic features. Next, adjust the zoom level and labeling parameters of the map, such as icon size and label font, to ensure that the position of each tree can be accurately and clearly displayed on the map. The map update program uses advanced rendering technology to dynamically adjust the map view, optimize the visual effect and user interaction experience. In addition, the geographic location information is synchronized in real time to ensure that the displayed data is consistent with the actual geographic features in the geographic information system (GIS), and the updated tree geographic location map is generated and saved, providing a basis for further data analysis and utilization.

[0111] S602: Based on the updated tree geographic location map, combined with the predicted tree age results, classify each tree by age through the map marking tool, apply color coding to distinguish trees of different ages, automatically update the age label on the map, and obtain the tree age label map;

[0112] Based on the updated tree geographic location map and combined with the predicted tree age results, the map is marked and each tree is classified into an age group. Based on the tree age data, the system automatically applies different color codes to distinguish trees of different age groups, such as using dark green for old trees and light green for young trees. Color coding not only increases the visual recognition of the map, but also allows users to quickly understand the age distribution of trees. As new data is input, the age labels on the map will automatically update to keep the information up to date. The generated tree age labeling map provides an intuitive and practical analysis tool for urban greening management and planning.

[0113] S603: Use tree age-labeled maps and tree disease and insect pest diagnosis results to assess health status and growth environment, mark trees affected by diseases, highlight affected areas using icons and colors, provide real-time visual analysis, and generate real-time urban tree information mapping results;

[0114] Using tree age-labeled maps and tree pest and disease diagnosis results, a comprehensive assessment of health status and growth environment is conducted. Pest and disease diagnosis results are combined with tree age data to mark trees affected by diseases. Different icons and colors are used to highlight affected areas, such as red warnings for the most severely affected trees and yellow for slightly affected trees. This visual marking method not only provides real-time tree health analysis but also facilitates rapid and effective disease management decisions. All assessment and marking processes are conducted on dynamically updated maps, ensuring that all information is real-time and accurate, generating the final real-time urban tree information mapping results, providing an important decision-making support tool for urban management departments.

[0115] See also Figure 8 , a rapid urban tree information collection system, comprising:

[0116] The geographic coordinate acquisition module uses a GNSS receiver to measure the geographic coordinates of each tree in the city, synchronously records the accuracy and timestamp of each coordinate point, cleans the data, and performs data synchronization through the city database interface to obtain the coordinate data of urban trees;

[0117] The dielectric constant measurement module adjusts the direction and focus of the microwave remote sensing equipment based on the urban tree coordinate data, adjusts the equipment configuration to transmit microwaves at different frequencies, records the time delay and signal strength of each frequency, calculates the time delay and intensity change of the return signal at different frequencies, infers the tree dielectric constant, and obtains the tree dielectric constant measurement value;

[0118] The tree age scoring module defines a correlation scoring standard between tree age and dielectric constant based on the measured values ​​of tree dielectric constants, summarizes tree scores, identifies differences in scores between different tree species through aggregation processing, and determines the age range of each tree's score data based on the preset age determination threshold to obtain the predicted tree age result;

[0119] The tree morphology acquisition module is based on urban tree coordinate data, configured with an image sensor, automatically adjusting focus and exposure parameters to match the location and lighting conditions of each tree, taking photos of each tree, capturing the color and shape of the tree leaves, and recording the tree morphology to obtain tree morphology image data;

[0120] The leaf health analysis module analyzes leaf color changes and shape anomalies based on tree morphological image data, assesses the basic health of trees, optimizes exposure and contrast to highlight leaf texture and color differences, and obtains detailed leaf image data;

[0121] The tree pest and disease diagnosis module uses detailed leaf image data to analyze the color distribution and texture changes on the leaf surface, identifying potential health issues, including spots, cracks, or discolored areas. It then compares leaf health characteristics with known disease characteristics, assessing the size of spots, crack depth, and the extent of discolored areas on the leaves to obtain tree pest and disease diagnosis results.

[0122] The urban tree information mapping module initiates map updates based on urban tree coordinate data, synchronizes geographic location information, classifies each tree into age groups based on predicted tree age results, applies color coding to distinguish trees of different age groups, and evaluates health conditions and growth environments based on tree disease and insect pest diagnosis results, marking trees affected by diseases and generating real-time urban tree information mapping results.

[0123] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for quickly collecting urban tree information, characterized in that: The following steps are involved: Obtain the geographic coordinates of every tree in the city through a GNSS receiver, record the accuracy and timestamp information of each location, perform data synchronization, and generate urban tree coordinate data; Based on the urban tree coordinate data, the microwave remote sensing device is directed toward the target tree, microwave signals are transmitted at different angles and frequencies, the time delay and intensity change of the return signal are measured, the dielectric constant of the tree is calculated, and the dielectric constant measurement value of the tree is obtained; Based on the tree dielectric constant measurement values, a tree age estimation rule is defined, each dielectric constant value is scored, the scoring data is aggregated, and the age range of the tree is determined according to a set threshold to obtain a predicted tree age result; Based on the urban tree coordinate data, combined with the image sensor, the focus and exposure parameters are automatically adjusted, photos of the trees are taken, and changes in the color and shape of the tree leaves are analyzed to generate basic tree health data; Based on the basic tree health data, detailed images of leaves are captured, color distribution and texture changes in the images are analyzed, and differential disease signs on the leaves are identified through visual information to assess the health of the trees and generate disease and insect pest diagnosis results; Based on the urban tree coordinate data, predicted tree age results and tree disease and insect pest diagnosis results, the geographical location map of the trees is updated in real time, the health status and growth environment of the trees are comprehensively evaluated and marked, and real-time urban tree information mapping results are generated.

2. The method for quickly collecting urban tree information according to claim 1, characterized in that: The urban tree coordinate data includes geographic location coordinates, accuracy level and time records; the tree dielectric constant measurement values ​​include dielectric constant values, signal delay data and signal strength data; the predicted tree age results include age score records, age range classification results and score summary data; the basic tree health data includes leaf color feature records and leaf shape feature records; the pest and disease diagnosis results include color distribution features, texture change features and health abnormality indicators; the real-time urban tree information mapping results include geographic location update records, health status identification and environmental assessment results.

3. The method for quickly collecting urban tree information according to claim 1, characterized in that: The specific steps to obtain the geographic coordinates of each tree in the city through the GNSS receiver, record the accuracy and timestamp information of each location, perform data synchronization, and generate the coordinate data of urban trees are as follows: Use GNSS receivers to measure the geographic coordinates of every tree in the city, synchronously record the accuracy and timestamp of each coordinate point, correct for signal drift, update positioning data, and generate accurate tree coordinate information; Based on the precise tree coordinate information, the data is cleaned, coordinate outliers are deleted, the coordinate data is formatted into a unified format, data standardization is performed, and formatted tree data is obtained; Based on the formatted tree data, data synchronization is performed through the city database interface, the cleaned and formatted data is uploaded, the data integrity is verified, the database records are updated, and the city tree coordinate data is obtained.

4. The method for quickly collecting urban tree information according to claim 1, characterized in that: Combined with the urban tree coordinate data, the microwave remote sensing equipment is guided to the target tree, microwave signals are emitted from different angles and frequencies, the time delay and intensity change of the return signal are measured, and the dielectric constant of the tree is calculated. The specific steps for obtaining the measured value of the dielectric constant of the tree are as follows: Based on the urban tree coordinate data, the direction and focus of the microwave remote sensing equipment are adjusted to align with the target trees, and the device angle is adjusted to capture the optimal signal, ensuring that the microwave covers the target area from multiple angles and obtaining microwave directional data; Based on the microwave directional data, adjusting the equipment configuration to transmit microwaves at different frequencies, monitoring the return signals at multiple frequencies, recording the time delay and signal strength at each frequency, and obtaining microwave signal response data; Based on the microwave signal response data, the time delay and intensity change of the difference frequency return signal are calculated, the dielectric constant of the tree is inferred through the data, and repeated measurements are made to verify the consistency of the data to obtain the dielectric constant measurement value of the tree.

5. The method for quickly collecting urban tree information according to claim 1, characterized in that: Based on the tree dielectric constant measurement values, the tree age estimation rules are defined, each dielectric constant value is scored, the scoring data is summarized and processed, and the age range of the tree is determined according to the set threshold. The specific steps for obtaining the predicted tree age result are as follows: Based on the tree dielectric constant measurement values, a correlation scoring standard between tree age and dielectric constant is defined, an age-related score is assigned to each measurement value according to the numerical value, a direct correlation between each score and dielectric constant is revealed, and tree age score data is obtained; Based on the tree age score data, tree scores are summarized, differences in scores between different tree species are identified through aggregation processing, abnormal score data are adjusted, and consistency of scores is optimized through data purification to obtain a summary score result; Based on the summarized scoring results, the age range of each tree's scoring data is determined according to a preset age determination threshold. The age range of each tree is classified by comparing the relationship between the score and the threshold to obtain a predicted tree age result.

6. The method for quickly collecting urban tree information according to claim 1, characterized in that: Based on the urban tree coordinate data, combined with the image sensor, the focus and exposure parameters are automatically adjusted, the photos of the trees are taken, the color and shape changes of the tree leaves are analyzed, and the specific steps of generating the basic health data of the trees are as follows: Based on the urban tree coordinate data, an image sensor is configured to automatically adjust focus and exposure parameters to match the position and lighting conditions of each tree, ensuring image clarity and balanced exposure, and obtaining optimized image capture settings. Based on the optimized image capture setting result, taking a photo of each tree, capturing the color and shape of the tree leaves, and recording the tree morphology to obtain tree morphology image data; Based on the tree morphological image data, the color changes and shape anomalies of the leaves are analyzed to evaluate the health status of the trees and obtain basic tree health data.

7. The method for quickly collecting urban tree information according to claim 1, characterized in that: Based on the basic tree health data, the detailed images of the leaves are captured, the color distribution and texture changes in the images are analyzed, the differential disease signs on the leaves are identified through visual information, the health status of the trees is assessed, and the specific steps for generating the disease and insect pest diagnosis results are as follows: Based on the basic tree health data, leaf details are analyzed, exposure and contrast are optimized to highlight leaf texture and color differences, and fine leaf image data is obtained; Based on the fine leaf image data, enhancing image color and texture contrast, analyzing color distribution and texture changes on the leaf surface, identifying potential health problems, including spots, cracks, or discolored areas, and obtaining leaf health feature analysis data; Based on the leaf health characteristic analysis data, the leaf health characteristics are compared with known disease characteristics, and the spot size, crack depth and range of discoloration areas on the leaves are evaluated through edge detection to establish the actual signs of each disease and obtain tree disease and insect pest diagnosis results.

8. The method for quickly collecting urban tree information according to claim 7, characterized in that: The edge detection is based on the formula: ； Determine the edge information of the leaf image ,in, and is the pixel position coordinate in the image, is the standard deviation of the Gaussian filter, which controls the smoothness of the filter. and is the offset parameter used to adjust the position of the filter center. Adjust the parameter for the filter strength.

9. The method for quickly collecting urban tree information according to claim 1, characterized in that: Based on the urban tree coordinate data, predicted tree age results and tree disease and insect pest diagnosis results, the geographical location map of the trees is updated in real time, and the health status and growth environment of the trees are comprehensively evaluated and marked. The specific steps for generating real-time urban tree information mapping results are as follows: Based on the urban tree coordinate data, a map update is initiated, the latest coordinate data is imported, map zoom and annotation parameters are adjusted to ensure that the location of each tree is accurately displayed, geographic location information is synchronized to ensure that the data is consistent with actual geographic features, and an updated tree geographic location map is obtained; Based on the updated tree geographic location map and the predicted tree age results, each tree is classified into age groups using a map marking tool, color coding is applied to distinguish trees of different age groups, and the age labels on the map are automatically updated to obtain a tree age marking map; The tree age marking map and tree disease and pest diagnosis results are used to evaluate the health status and growth environment, mark trees affected by diseases, highlight the affected areas using icons and colors, provide real-time visual analysis, and generate real-time urban tree information mapping results.

10. A rapid urban tree information collection system, characterized in that: The method for quickly collecting urban tree information according to any one of claims 1 to 9, wherein the system comprises: The geographic coordinate acquisition module uses a GNSS receiver to measure the geographic coordinates of each tree in the city, synchronously records the accuracy and timestamp of each coordinate point, cleans the data, and performs data synchronization through the city database interface to obtain the coordinate data of urban trees; The dielectric constant measurement module adjusts the direction and focus of the microwave remote sensing device based on the urban tree coordinate data, adjusts the device configuration to transmit microwaves at different frequencies, records the time delay and signal strength of each frequency, calculates the time delay and strength change of the return signal at the different frequencies, infers the tree dielectric constant, and obtains the tree dielectric constant measurement value; The tree age scoring module defines a correlation scoring standard between tree age and dielectric constant based on the tree dielectric constant measurement value, summarizes the tree scores, identifies the differences in scores between different tree species through aggregation processing, and determines the age range of each tree score data according to a preset age determination threshold to obtain a predicted tree age result; The tree morphology acquisition module configures an image sensor based on the urban tree coordinate data, automatically adjusts the focus and exposure parameters to match the position and lighting conditions of each tree, takes a photo of each tree, captures the color and shape of the tree leaves, and records the tree morphology to obtain tree morphology image data; The leaf health analysis module analyzes leaf color changes and shape anomalies based on the tree morphology image data, assesses the basic health of the tree, optimizes exposure and contrast to highlight leaf texture and color differences, and obtains detailed leaf image data; The tree disease and insect pest diagnosis module analyzes the color distribution and texture changes on the leaf surface based on the fine leaf image data, identifies potential health problems, including spots, cracks, or discolored areas, compares the leaf health characteristics with known disease characteristics, evaluates the size of spots, crack depth, and the extent of discolored areas on the leaves, and obtains tree disease and insect pest diagnosis results; The urban tree information mapping module initiates map updates based on the urban tree coordinate data, synchronizes geographic location information, classifies each tree into age groups based on the predicted tree age results, applies color coding to distinguish trees of different age groups, and evaluates the health status and growth environment based on the tree disease and pest diagnosis results, marks trees affected by diseases, and generates real-time urban tree information mapping results.

Images