Smart city data processing method and system based on Beidou positioning

Abstract

The invention relates to the technical field of city management, in particular to a smart city data processing method and system based on Beidou positioning, and the method comprises the following steps: collecting Beidou positioning data and traffic camera records of vehicles in city traffic, associating the position coordinates and timestamps of the vehicles with speed data, generating a vehicle operation state database, and storing the vehicle operation state database in a cloud server; and carrying out time sequence coding on the vehicle operation data in the vehicle operation state database to generate traffic flow time sequence analysis data. Through the sliding time window and the Kalman filtering, the prediction accuracy and the dynamic monitoring capability are improved. Through combination of vehicle positioning and camera data, the real-time analysis efficiency of the traffic flow is improved, and the timeliness and practicability of the data are enhanced through time sequence coding. Furthermore, in combination with greening area image data and geographical location information of the unmanned aerial vehicle, the scientificity of urban greening management is enhanced through normalized vegetation index analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of urban management, and in particular, to a smart city data processing method and system based on Beidou positioning. Background Art

[0002] The technical field of urban management involves a wide range of strategies and tools aimed at improving the efficiency, sustainability, and quality of life of urban operations. By leveraging modern information and communication technologies, optimization in various aspects such as urban infrastructure, traffic flow, public safety, and energy management can be achieved.

[0003] The prior art usually faces challenges in the depth and breadth of data processing; for example, traditional methods fail to effectively integrate location data when dealing with traffic flow, resulting in insufficient adaptability and accuracy of traffic management strategies. In addition, the lack of prediction of dynamic changes leads to a lag in urban planning responses, and the inability to timely adjust countermeasures to cope with the rapidly changing urban environment. Therefore, improvements are needed. Summary of the Invention

[0004] The purpose of the present invention is to solve the drawbacks existing in the prior art, and to propose a smart city data processing method and system based on Beidou positioning.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions. A smart city data processing method based on Beidou positioning includes the following steps:

[0006] Collect the Beidou positioning data of vehicles in urban traffic and traffic camera records, associate the position coordinates and timestamps of the vehicles with speed data to generate a vehicle operation status database, and then perform time series encoding on the vehicle operation data in the vehicle operation status database to generate traffic flow time series analysis data;

[0007] Based on the traffic flow time series analysis data, extract the traffic density and speed information within each time window through a sliding time window algorithm to generate density - speed analysis data, and apply Kalman filtering processing to the density - speed analysis data to obtain a smooth dynamic prediction result;

[0008] Collect image data of urban greening areas through drones, extract the color depth information of the greening areas to generate preliminary greening coverage data, and then combine the Beidou positioning data to locate the geographical location of the preliminary greening coverage data to obtain greening monitoring data;

[0009] Analyze the greening monitoring data using the normalized difference vegetation index to calculate the vegetation health index for each area and generate a vegetation health analysis result.

[0010] Preferably, the step of obtaining the vehicle operation status database is:

[0011] Collect the real-time positioning and monitoring data of vehicles through Beidou navigation and traffic cameras, organize the position coordinates, timestamps and speeds of each vehicle to form a primary data set;

[0012] Calculate the motion vector of each vehicle according to the primary data set The calculation formula is:

[0013]

[0014] where v i represents the vehicle speed, Δt represents the acquisition time interval, and θ i represents the vehicle motion direction angle, is the motion vector;

[0015] Use the motion vector of each vehicle Combine the timestamp and geographical location data of the vehicle to generate a vehicle operation status database.

[0016] Preferably, the steps for obtaining the traffic flow time series analysis data are as follows:

[0017] Access the vehicle operation status database, extract the operation data of all vehicles to obtain the original vehicle operation data set;

[0018] Based on the original vehicle operation data set, use time series coding to sort and code the data of each vehicle in chronological order to obtain a time series coded vehicle data set;

[0019] Based on the time series coded vehicle data set, analyze the vehicle density and flow rate at each time point to generate traffic flow time series analysis data.

[0020] Preferably, the steps for obtaining the density and speed analysis data are as follows:

[0021] Based on the traffic flow time series analysis data, use a sliding time window to process the data, analyze the vehicle flow density and speed within each time window to obtain the processed density and speed information;

[0022] Use the processed density and speed information to construct density and speed analysis data.

[0023] Preferably, the steps for obtaining the smoothed dynamic prediction result are as follows:

[0024] Based on the density and speed analysis data, extract the traffic flow and speed data to obtain density and speed data;

[0025] Based on the density and speed data, apply Kalman filtering for data smoothing processing to obtain the Kalman filtering processing result, and the formula is:

[0026] x k|k = x k|k-1 + K k (z k - H k x k|k-1 )

[0027] where x k|k is the updated traffic flow estimate, K k is the Kalman gain, z k is the observation value, and H k is the observation model coefficient;

[0028] Based on the Kalman filtering processing result, smooth dynamic prediction data is generated.

[0029] Preferably, the steps for obtaining the preliminary greening coverage data are as follows:

[0030] Fly a drone over the urban greening area to take pictures and collect image data of the greening area to obtain the original image data;

[0031] Based on the original image data, calculate the average depth of the greening area in each image. The calculation formula is:

[0032]

[0033] where C i represents the average depth of the greening color in image i, p ij is the color value of the j-th pixel in image i, N is the total number of pixels in the image, and μ is the average value of all pixel color values;

[0034] Based on the average depth, generate preliminary greening coverage data on the urban greening coverage range and density.

[0035] Preferably, the steps for obtaining the greening monitoring data are as follows:

[0036] Use the geographic location data of Beidou positioning to match the geographic location of each greening area in the preliminary greening coverage data to generate a greening data set associated with the geographic location;

[0037] Based on the greening data set associated with the geographic location, integrate the geographic location and the greening coverage characteristics to construct and obtain the greening monitoring data.

[0038] Preferably, the steps for obtaining the vegetation health analysis result are as follows: [[ID=·63]]

[0039] Obtain the greening monitoring data, including the geographic location and greening characteristics of each greening area in the city, to obtain the greening monitoring data;

[0040] Based on the greening monitoring data, calculate the normalized difference vegetation index (NDVI) for each area. The calculation formula is as follows:

[0041]

[0042] where NIR represents the square of the reflectance value in the near-infrared light band, Red represents the square of the reflectance value in the red light band, α is an adjustment coefficient, and NDVI is the normalized difference vegetation index;

[0043] Based on the normalized difference vegetation index, analyze and generate the vegetation health index for each area to form the vegetation health analysis result.

[0044] The present invention provides a data processing system, including:

[0045] An urban traffic analysis module that collects vehicle Beidou positioning data and traffic camera records, extracts position coordinates, timestamps, and speed information, generates a vehicle operation status database through set operations, performs time series encoding on the vehicle data, and generates traffic flow time series analysis data;

[0046] A dynamic prediction module that, based on the traffic flow time series analysis data, applies a sliding time window to collect and aggregate traffic density and speed information within each time window to generate density-speed analysis data;

[0047] A greening coverage monitoring module that uses the image data collected by drones, extracts the information on the color depth of the greening areas, combines it with the Beidou positioning data to locate the greening areas, processes the data using the normalized difference vegetation index, analyzes the vegetation health of each area, and generates the vegetation health analysis result.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0049] Through the sliding time window and Kalman filter, the present invention improves the prediction accuracy and dynamic monitoring ability. The combination of vehicle positioning and camera data not only improves the real-time analysis efficiency of traffic flow but also enhances the timeliness and practicality of the data through time series encoding. Further, by combining the greening area image data of drones and geographical location information and analyzing through the normalized difference vegetation index, the scientific nature of urban greening management is enhanced. This multi-dimensional data fusion improves the decision-making quality, ensures the timeliness and effectiveness of urban management strategies, and provides solid data support for the sustainable development of the city. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic diagram of the steps of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not used to limit the present invention.

[0052] Please refer to Figure 1 , the present invention provides a technical solution, a method for processing smart city data based on Beidou positioning, including the following steps:

[0053] Collect the Beidou positioning data of vehicles in urban traffic and the records of traffic cameras, associate the position coordinates, timestamps and speed data of the vehicles to generate a vehicle operation status database, and then perform time series encoding on the vehicle operation data in the vehicle operation status database to generate traffic flow time series analysis data;

[0054] Based on the traffic flow time series analysis data, extract the traffic density and speed information within each time window through a sliding time window algorithm to generate density-speed analysis data, and apply Kalman filtering to the density-speed analysis data to obtain a smooth dynamic prediction result;

[0055] Extract the color depth information of the greening area from the image data of the urban greening area collected by the drone to generate preliminary greening coverage data, and then combine the Beidou positioning data to locate the geographical location of the preliminary greening coverage data to obtain greening monitoring data;

[0056] Analyze the greening monitoring data using the normalized difference vegetation index to calculate the vegetation health index of each area and generate a vegetation health analysis result.

[0057] The steps for obtaining the vehicle operation status database are as follows:

[0058] Collect the real-time positioning and monitoring data of vehicles through Beidou navigation and traffic cameras, and organize the position coordinates, timestamps and speeds of each vehicle to form a primary data set;

[0059] According to the primary data set, calculate the motion vector of each vehicle The calculation formula is:

[0060]

[0061] where v i represents the vehicle speed, Δt represents the acquisition time interval, and θ i represents the vehicle motion direction angle, is the motion vector;

[0062] Using the motion vector of each vehicle Combined with the timestamp and geographical location data of the vehicle, a vehicle operation status database is generated.

[0063] Specifically, real-time positioning and monitoring data of vehicles are collected, the position coordinates, timestamps, and speeds of each vehicle are identified to form a primary dataset. The longitude and latitude of each vehicle are obtained, and a timing device is used to record the exact time when the data is acquired. The speed is directly measured by a ground speed sensor to ensure the accurate capture and recording of each data point. The data is preliminarily screened to eliminate outliers (such as data with speeds exceeding the normal driving range of 100 - 120 km / h). These screening criteria are set based on current road traffic regulations and vehicle performance safety standards.

[0064] The benefit of the formula is that by combining the vehicle speed v i , the time interval Δt, and the average values of the cosine and sine of the vehicle traveling direction angle θ i to simulate the direction and distance of vehicle movement, the movement state of the vehicle can be quantified in vector form, facilitating further movement analysis and status monitoring; the vehicle speed v i is obtained by traffic cameras and speed sensors, the time interval Δt refers to the data acquisition frequency, and the direction angle θ i is calculated through the Beidou system combined with the vehicle's real-time position data;

[0065] Calculation process: The speed of a vehicle is 30 km / h; The time interval is 1 second, and the traveling direction is 30 degrees east of north. Then:

[0066]

[0067] This result indicates that within 1 second, the vehicle has moved approximately 5.69 meters in the direction of north by east, which can help the traffic management system accurately grasp the movement trend and status of the vehicle, facilitating the adjustment of traffic flow and prevention of congestion.

[0068] Using the calculated movement vectors of each vehicle, integrating the timestamps and geographical location information of the vehicles, a vehicle operation status database is generated. First, match the movement vectors of the vehicles with their corresponding time tags and position data, and store this information in a structured database through the database. Each record is marked with the accurate time and position. During this process, data formatting is performed to ensure that all data conforms to the database storage format. For example, the time is converted to a unified timestamp format, and the position coordinates are also standardized to ensure data consistency and queryability; the final database contains comprehensive vehicle operation data.

[0069] The steps to obtain traffic flow time series analysis data are as follows:

[0070] Access the vehicle operation status database, extract the operation data of all vehicles to obtain the original vehicle operation dataset;

[0071] Based on the original vehicle operation dataset, time - series encoding is used to sort and encode the data of each vehicle in chronological order, obtaining a vehicle dataset with time - series encoding.

[0072] Based on the vehicle dataset with time - series encoding, analyze the vehicle density and flow velocity at each time point to generate traffic flow time - series analysis data.

[0073] Specifically, access the vehicle operation status database, collect the detailed data of each vehicle, including GPS coordinates, speed, and timestamp, verify and screen the collected data, exclude incorrect or incomplete records, and ensure the reliability and validity of the data.

[0074] Encode the vehicle data in the database in chronological order, including time - aligning the position, speed, and timestamp information of each vehicle, sorting the data using a unified time standard to ensure the time continuity and order correctness between data points. This time - series encoding not only reflects the dynamic characteristics of vehicle movement but also provides accurate baseline data for subsequent analysis models.

[0075] Conduct traffic flow analysis on the vehicle data with time - series encoding, including calculating the vehicle density and flow velocity at each time point, updating the driving speed and density of vehicles every minute, so as to be able to capture and analyze the changing trend of traffic flow in real - time. Through continuous monitoring, these data can directly support the real - time management and long - term planning of urban traffic, and the generated results are traffic flow time - series analysis data.

[0076] The steps for obtaining density - speed analysis data are as follows:

[0077] Based on the traffic flow time - series analysis data, use a sliding time window to process the data, analyze the vehicle flow density and speed within each time window, and obtain the processed density - speed information.

[0078] Utilize the processed density - speed information to construct density - speed analysis data.

[0079] Specifically, based on the obtained traffic flow time - series analysis data, execute a sliding time window to process traffic data. First, determine the length of each time window, which should be long enough to cover a sufficient amount of data to ensure the representativeness and accuracy of the analysis results. Then, gradually move the time window, collect the number of vehicles and speed data within each time window, calculate the average vehicle speed and vehicle density in each window through statistics. At the same time, it is necessary to ensure that any outliers or illogical data points, such as records with speeds outside the normal range, are excluded during the data cleaning process.

[0080] Using the density and velocity information obtained within each time window, the next step of data construction is carried out. By integrating the data from each time window, a comprehensive density and velocity analysis dataset is formed. This dataset will contain records of vehicle flow density and velocity for each time window, which is used for further traffic behavior analysis and pattern recognition. During the construction process, special attention needs to be paid to the consistency and integrity of the data. Quality assessment and verification are carried out for each data point to ensure that the obtained density and velocity analysis data not only reflects the real traffic flow state but also meets the requirements of the analysis model.

[0081] The steps to obtain the smoothed dynamic prediction results are as follows:

[0082] Based on the density and velocity analysis data, traffic flow and velocity data are extracted to obtain density and velocity data;

[0083] Based on the density and velocity data, Kalman filtering is applied for data smoothing to obtain the Kalman filtering processing result. The formula is:

[0084] x k|k = x k|k-1 + K k (z k - H k x k|k-1 )

[0085] Where x k|k is the updated traffic flow estimate value, K k is the Kalman gain, z k is the observed value, and H k is the observation model coefficient;

[0086] Based on the Kalman filtering processing result, smoothed dynamic prediction data is generated.

[0087] Specifically, first, retrieve the data stored in the traffic data management system, including the speed and flow information of various vehicles. Identify and exclude abnormal data caused by special events such as traffic accidents or temporary road closures. This process involves checking the data timestamps and comparing with historical data of the same period to identify mutations or discontinuity points in the data. Then, classify and organize the remaining valid data. Use data analysis techniques to evaluate the main trends and periodic fluctuations of the traffic flow. This step is achieved through time series analysis of the data. The analysis methods include calculating the moving average and seasonal exponential smoothing to determine the long-term trend and seasonal pattern of the data. Each analysis step must ensure the representativeness of the data and the accuracy of the analysis to ensure that the subsequent traffic prediction model can accurately reflect the actual traffic flow state. Finally, incorporate these verified and processed data into the final analysis report for subsequent traffic flow management and decision-making.

[0088] The advantage of the formula is that by updating data in real time, it can reflect the immediate changes in traffic flow, thereby optimizing traffic flow management and reducing congestion; x k|k The steps to obtain the parameter are to calculate through the traffic flow data collected in real time, K k is the gain coefficient adjusted based on historical data error analysis, z k is the actual traffic flow observed currently, H k is the observation model coefficient established according to past data;

[0089] Calculation process: At time t k , the observed actual traffic flow is 320 vehicles per hour. Historical data shows that the predicted flow under the same conditions is 300 vehicles per hour. The Kalman gain is set to 0.05, and the observation model coefficient is 1. Then:

[0090] x k|k = 300 + 0.05 × (320 - 1 × 300) = 301

[0091] This result indicates that after Kalman filtering, the actual observed data has been fine-tuned, and the actual traffic flow has been predicted more accurately.

[0092] After the Kalman filtering algorithm is processed, the density and speed data are smoothed. Then, these smoothed data are input into the dynamic traffic prediction model. This model predicts the future traffic flow state based on current and historical data. The model adjustment is completed by gradually reducing the prediction error. The specific methods include adjusting the response speed and sensitivity of the model to adapt to different traffic flow conditions and change trends. In addition, it is necessary to continuously optimize the parameters of the algorithm, such as the learning rate and error tolerance, to ensure the reliability and accuracy of the prediction results. The generated prediction data will provide real-time decision support for the traffic control center.

[0093] The steps to obtain the preliminary greening coverage data are as follows:

[0094] Fly a drone to take pictures in the urban greening area to collect image data about the greening area and obtain the original image data;

[0095] Based on the original image data, calculate the average depth of the greening area in each image. The calculation formula is:

[0096]

[0097] Among them, C i represents the average depth of the greening color in image i, p ij is the color value of the jth pixel in image i, N is the total number of pixels in the image, and μ is the average value of all pixel color values;

[0098] Based on the average shade depth, preliminary greening coverage data regarding the urban greening coverage area and density is generated. Specifically, by flying a drone over the urban greening area to collect image data of the greening area, the high-resolution camera carried by the drone captures green vegetation in different areas, ensuring that the collected images cover a wide range of urban greening areas. The collected images are preliminarily screened, and images with high image quality, wide coverage area, and rich greening information are selected for analysis.

[0099] In the formula, C i represents the average shade depth of the greening color in image i, indicating the overall color depth of the vegetation in this image, and p ij is the color value of the j-th pixel in image i, referring to the color depth of a specific pixel point. N is the total number of pixels in the image, representing the total number of pixels participating in the calculation. μ is the average value of all pixel color values, representing the average color depth of the entire image;

[0100] The benefit of the formula is that by calculating the square root absolute value of the difference between each pixel and the average color, it can more accurately describe the color variability and complexity of the image, providing an effective quantification method for evaluating the health status and coverage quality of the greening area;

[0101] Calculation process: An image has 10,000 pixels, the average color value μ is 120, and the color value p ij of a specific pixel is 150. Substitute it into the formula for calculation:

[0102]

[0103] This result indicates that the average shade depth of the greening area in the image is 5.48, indicating that the greening coverage is relatively uniform. If this value is low, it indicates shallow greening, which may be newly planted vegetation or sparse vegetation; a high value may indicate mature or dense vegetation; a value between 3 and 5 may indicate relatively uniform but not dense vegetation coverage. Such an area may be growing vegetation or a partially mature vegetation area. A value greater than 5, especially a value close to or exceeding 8, may indicate that the vegetation in this area is very dense and mature.

[0104] Based on the average shade depth of each image, preliminary greening coverage data regarding the urban greening coverage area and density is generated, and the shade depth data is converted into a visual greening coverage map to display the greening coverage status of different areas in the city.

[0105] The steps for obtaining greening monitoring data are as follows:

[0106] Using the geographical location data of Beidou positioning, the geographical location of each greening area in the preliminary greening coverage data is matched to generate a greening data set associated with geographical locations;

[0107] A greening dataset associated with geographical location integrates geographical location and greening coverage characteristics to construct and obtain greening monitoring data.

[0108] Specifically, using the geographical location data from Beidou positioning and combining with the image data collected by drones, start to correspond the greening information contained in these image data with specific geographical locations. First, retrieve the GPS coordinates recorded in each image, and these coordinates are from the real-time interaction between the drone and the Beidou system during shooting. Subsequently, compare the specific location information of each greening area with the known urban geographical information database. Through matching, ensure that each greening area can be correctly marked on the urban map. This process includes coordinate conversion and map scaling adjustment to adapt to different display requirements and analysis accuracies. Next, to improve the accuracy of matching.

[0109] Based on the newly generated greening dataset associated with geographical location, further integrate geographical location and greening coverage characteristics. By analyzing the spatial relationship between the coordinate points in the geographical data and the corresponding greening areas, extract the greening rate and type distribution of each area through spatial interpolation and regional division algorithms, and convert them into specific greening coverage characteristics, such as tree density, grassland area and its relationship with the surrounding environment. In addition, to enhance the application value of the data, seasonal analysis will also be carried out on the greening data. Considering the growth state changes of greening vegetation in different seasons, predict the future greening trend through time series analysis.

[0110] The steps to obtain the vegetation health analysis results are as follows:

[0111] Obtain greening monitoring data, including the geographical location and greening characteristics of each greening area in the city, to obtain greening monitoring data;

[0112] Based on the greening monitoring data, calculate the normalized difference vegetation index (NDVI) for each area. The calculation formula is:

[0113]

[0114] Where, NIR represents the square of the reflectance value in the near-infrared light band, Red represents the square of the reflectance value in the red light band, α is the adjustment coefficient, and NDVI is the normalized difference vegetation index;

[0115] Based on the normalized difference vegetation index, analyze and generate the vegetation health index for each area to form the vegetation health analysis results.

[0116] Specifically, the benefit of the formula lies in enhancing the sensitivity to outliers through squaring, making the NDVI calculation more robust when evaluating vegetation health; the steps for obtaining the NIR and Red parameters are as follows: First, collect data on the infrared and red light bands of the target area through a multispectral sensor carried by a drone. The data for each light band will be directly recorded by the sensor and downloaded to the ground station after the flight to obtain spectral data. The adjustment coefficient α is adjusted based on previous experimental data and on-site environmental variables to adapt to the vegetation characteristics and lighting conditions in different regions. The specific value needs to be adjusted according to ground verification data to ensure that the calculated result of NDVI can truly reflect the health status of the vegetation;

[0117] Calculation process: The NIR and Red reflectance values of an area are 0.6 and 0.2 respectively. Then, according to the formula, NIR^2 = 0.36, Red^2 = 0.04. If α is taken as 0.05, then

[0118] NDVI = (0.36 - 0.04) / (0.36 + 0.04 + 0.05) = 0.32 / 0.45 = 0.711; This result indicates that the vegetation health status in this area is good. An NDVI value close to 1 indicates dense vegetation, and the value closer to -1 indicates sparser vegetation.

[0119] Based on the obtained normalized difference vegetation index, vegetation health analysis is carried out. First, compare the calculated NDVI results with historical data, analyze the vegetation health trend through comparative analysis, use statistical software to perform regression analysis on the data, and find out possible reasons for the health decline, such as pests and diseases or drought, etc. Then generate a vegetation health index report for each area, which details the vegetation type, coverage rate, health status and its change trend in each area.

[0120] The present invention provides a data processing system, including:

[0121] An urban traffic analysis module that collects vehicle Beidou positioning data and traffic camera records, extracts position coordinates, timestamps and speed information, generates a vehicle operation status database through set operations, and encodes the vehicle data in a time series to generate traffic flow time series analysis data;

[0122] A dynamic prediction module that, based on the traffic flow time series analysis data, applies a sliding time window to collect and aggregate the traffic density and speed information within each time window to generate density-speed analysis data;

[0123] A greening coverage monitoring module that uses the image data collected by a drone, extracts the color depth information of the greening area, combines it with the Beidou positioning data to locate the greening area, processes the data using the normalized difference vegetation index, analyzes the vegetation health of each area, and generates vegetation health analysis results.

[0124] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for processing smart city data based on Beidou positioning, characterized in that, It includes the following steps: Collect the Beidou positioning data of vehicles in urban traffic and the records of traffic cameras, associate the position coordinates, timestamps of vehicles with speed data to generate a vehicle operation status database, and then perform time series encoding on the vehicle operation data in the vehicle operation status database to generate traffic flow time series analysis data; Based on the traffic flow time series analysis data, extract the traffic density and speed information within each time window through a sliding time window algorithm to generate density-speed analysis data, and apply Kalman filtering to the density-speed analysis data to obtain a smooth dynamic prediction result; Collect the image data of urban greening areas through drones, extract the color depth information of the greening areas to generate preliminary greening coverage data, and then combine the Beidou positioning data to locate the geographical positions of the preliminary greening coverage data to obtain greening monitoring data; Analyze the greening monitoring data using the normalized difference vegetation index, calculate the vegetation health indicators for each area, and generate a vegetation health analysis result.

2. The method for processing smart city data based on Beidou positioning according to claim 1, wherein The steps for obtaining the vehicle operation status database are as follows: Collect the real-time positioning and monitoring data of vehicles through Beidou navigation and traffic cameras, and organize the position coordinates, timestamps, and speeds of each vehicle to form a primary data set; Calculate the motion vector of each vehicle according to the primary data set The calculation formula is as follows: where, v i represents the vehicle speed, Δt represents the acquisition time interval, θ i represents the vehicle motion direction angle, is the motion vector; Using the motion vector of each vehicle Combining the timestamp and geographical location data of the vehicle to generate a vehicle operation status database.

3. The method for processing smart city data based on Beidou positioning according to claim 1, wherein, The steps for obtaining the traffic flow time series analysis data are as follows: Access the vehicle operation status database, extract the operation data of all vehicles to obtain the original vehicle operation data set; Based on the original vehicle operation data set, use time series encoding to sort and encode the data of each vehicle in chronological order to obtain a time series encoded vehicle data set; Based on the time series encoded vehicle data set, analyze the vehicle density and flow rate at each time point to generate traffic flow time series analysis data.

4. The method for processing smart city data based on Beidou positioning according to claim 1, wherein The steps for obtaining the density-speed analysis data are as follows: Based on the traffic flow time series analysis data, use a sliding time window to process the data, analyze the vehicle flow density and speed within each time window to obtain the processed density-speed information; Utilize the processed density-speed information to construct density-speed analysis data.

5. The method for processing smart city data based on Beidou positioning according to claim 1, characterized in that, The steps for obtaining the smooth dynamic prediction result are as follows: Based on the density-speed analysis data, extract the traffic flow and speed data to obtain density-speed data; Based on the density-speed data, apply Kalman filtering for data smoothing to obtain the Kalman filtering processing result, and the formula is: x k|k = x k|k-1 + K k (z k - H k x k|k-1 ) where x k|k is the updated traffic flow estimate, K k is the Kalman gain, z k is the observation value, and H k is the observation model coefficient; Based on the Kalman filtering processing result, generate smooth dynamic prediction data.

6. The method for processing smart city data based on Beidou positioning according to claim 1, characterized in that, The steps for obtaining the preliminary greening coverage data are as follows: Fly and take pictures in urban greening areas through drones to collect image data of the greening areas to obtain the original image data; Based on the original image data, calculate the average depth of the greening areas in each image, and the calculation formula is: Among them, C i represents the average darkness of the greening color in image i, p ij is the color value of the j-th pixel in image i, N is the total number of pixels in the image, and μ is the average value of all pixel color values; Based on the average depth, generate preliminary greening coverage data regarding the urban greening coverage range and density.

7. The method for processing smart city data based on Beidou positioning according to claim 1, wherein The steps for obtaining the greening monitoring data are as follows: Use the geographical position data of Beidou positioning to match the geographical positions of each greening area in the preliminary greening coverage data to generate a geographically associated greening data set; Based on the greening data set associated with the geographical location, integrate the geographical location and greening coverage characteristics to construct and obtain greening monitoring data.

8. The method for processing smart city data based on Beidou positioning according to claim 1, wherein The steps for obtaining the vegetation health analysis result are as follows: Obtain the greening monitoring data, including the geographical locations and greening characteristics of each greening area in the city, to obtain the greening monitoring data; Based on the greening monitoring data, calculate the normalized difference vegetation index (NDVI) for each area. The calculation formula is: where NIR represents the square of the reflectance value in the near-infrared light band, Red represents the square of the reflectance value in the red light band, α is an adjustment coefficient, and NDVI is the normalized difference vegetation index; Based on the normalized difference vegetation index, analyze and generate the vegetation health index for each area to form the vegetation health analysis result.

9. A data processing system for the smart city data processing method based on Beidou positioning according to any one of claims 1-8, characterized in that, It includes: An urban traffic analysis module that collects vehicle Beidou positioning data and traffic camera records, extracts location coordinates, timestamps, and speed information, performs set operations to generate a vehicle operation status database, and encodes the vehicle data in a time series to generate traffic flow time series analysis data; A dynamic prediction module that, based on the traffic flow time series analysis data, applies a sliding time window to collect and aggregate the traffic density and speed information within each time window to generate density-speed analysis data; A greening coverage monitoring module that uses the image data collected by drones, extracts the color depth information of the greening areas, combines it with the Beidou positioning data to locate the greening areas, processes the data using the normalized difference vegetation index, analyzes the vegetation health of each area, and generates the vegetation health analysis result.

Images