Holographic perception decision center system for urban governance
By integrating monitoring images and navigation software data, a holographic perception decision-making hub system is built, and the problem of blind spots in a single data source is solved, the full perception and prediction of urban traffic is realized, and the accuracy and efficiency of traffic regulation are improved.
Patent Information
- Application Number
- CN202510715598.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-30
- Publication Date
- 2025-09-02
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology has significant blind spots in traffic perception capabilities that rely on a single data source in complex traffic environments, resulting in insufficient traffic prediction accuracy and the inability to achieve continuous tracking of vehicle trajectories across the road.
By integrating monitoring image data and navigation software trajectory data, a holographic perception system is built, and the vehicle online computing unit is used to identify license plates and track time and time, and combined with regional vehicle classification, driving prediction and comprehensive clogging analysis units, the full perception and prediction of urban traffic is achieved.
It realizes holographic perception of urban traffic flow and vehicle trajectory, breaks through the limitations of a single data source, provides reliable data support, can identify congestion risks in advance and conduct active regulation, and improves the accuracy and efficiency of traffic regulation.
Smart Images
Figure CN120580841A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of urban traffic management, and in particular to a holographic perception decision-making central system for urban management. Background Art
[0002] Urban traffic management is a core scenario in smart city construction. Its core purpose is to achieve accurate monitoring of traffic flow through technical means, thereby regulating traffic flow, improving urban traffic efficiency, alleviating congestion pressure, and optimizing resource allocation. Existing technologies mainly rely on single data sources such as traffic cameras, radar sensors, and navigation software, and achieve local perception and management of traffic scenes through functions such as video monitoring, traffic statistics, and route planning. However, they expose multiple limitations in complex traffic environments, and the perception capabilities of single data sources have significant blind spots: traffic cameras can only cover local image data at fixed points and cannot achieve continuous tracking of vehicle trajectories across the entire road network. Navigation software relies on users to actively upload data, which has sample bias (such as missing data for vehicles without navigation installed), resulting in insufficient traffic prediction accuracy. In order to reduce this situation, a holographic perception decision-making central system for urban governance is proposed. Summary of the Invention
[0003] The purpose of the present invention is to provide a holographic perception decision-making central system for urban governance to solve the problems raised in the above-mentioned background technology.
[0004] To achieve the above objectives, a holographic perception decision-making central system for urban governance is provided, which includes a vehicle online calculation unit, a regional vehicle classification unit, a driving prediction unit, a comprehensive congestion analysis unit, and a traffic adjustment unit. The vehicle online calculation unit is used to obtain monitoring image data of urban traffic and perform license plate recognition, and at the same time obtain each road section area and combine it with license plate recognition to perform regional vehicle online calculation; The regional vehicle classification unit is used to connect to the navigation software, obtain the geographical location of the navigation vehicle according to the navigation software, and then classify the regional vehicles into known route vehicles and unknown route vehicles based on the geographical location of all navigation vehicles combined with the monitoring image data; The driving prediction unit is used to combine historical monitoring image data with unknown route vehicles to perform historical driving route analysis, extract real-time driving routes of unknown route vehicles, and combine historical driving routes with real-time driving routes and time periods to perform predicted driving route analysis; The comprehensive congestion analysis unit is used to perform vehicle number prediction analysis on each road section area by combining the predicted driving routes of vehicles with known routes with vehicles with unknown routes, and to perform comprehensive congestion analysis on each road section area in combination with the corresponding predicted vehicle number; The traffic adjustment unit is used to perform route adjustment analysis on the blocked road section area in combination with vehicles on known routes, and to make urban traffic adjustments on the vehicles on known routes and the road section area according to the analysis results.
[0005] As a further improvement of this technical solution, the vehicle online calculation unit obtains all monitoring image data of the city from the city traffic management terminal by connecting to the city traffic management terminal, and at the same time divides the city traffic into road sections and areas, so that the overall city traffic consists of multiple road sections and areas.
[0006] As a further improvement of the technical solution, the vehicle online calculation unit includes an online vehicle calculation module; The online vehicle calculation module is used to identify license plate numbers based on monitoring image data, save the identified license plate numbers in real time, and then use the number of license plate numbers saved in real time as the number of online vehicles in the corresponding road section area.
[0007] As a further improvement of the technical solution, the online vehicle calculation module calculates the number of online vehicles; A deletion time threshold is set based on the speed of traffic flow. If the license plate number cannot be re-identified within the deletion time threshold, the license plate number will be deleted from the online vehicles. At the same time, when the license plate number appears in other road sections, the license plate number is assigned to the road section area where it appears in the latest recognition, so that the same license plate number appears in at most one road section area.
[0008] As a further improvement of this technical solution, the regional vehicle classification unit includes a navigation access module and a vehicle classification module; The navigation access module is used to establish a data transmission channel with the navigation software to obtain the navigation route of each vehicle and obtain the geographical location of the navigation vehicle in real time through the navigation software; The vehicle classification module is used to locate the license plate number of all navigation vehicles by combining the geographical locations with the monitoring image data, obtain the license plate number corresponding to each navigation vehicle, and then use the license plate number corresponding to the navigation vehicle as a known route vehicle; Except for navigation vehicles, all other license plate numbers are regarded as unknown route vehicles.
[0009] As a further improvement of the present technical solution, the driving prediction unit includes a historical driving analysis module and a predicted driving analysis module; The historical driving analysis module is used to extract historical monitoring image data, then extract individual images based on the license plate numbers corresponding to vehicles on unknown routes from the historical monitoring image data, and perform driving route analysis based on the extracted images to obtain the historical driving routes corresponding to each vehicle on the unknown route; The predictive driving analysis module is used to obtain the traveled route and the road section area of the unknown route vehicle based on the monitoring image data, and then combine the traveled route and the road section area of the unknown route vehicle with the corresponding historical driving route and the current time period to perform a predictive driving route analysis to obtain the predicted driving route of the unknown route vehicle for the subsequent travel.
[0010] As a further improvement of the present technical solution, when the predicted driving analysis module predicts a vehicle with an unknown route, if the predicted driving route of the vehicle with the unknown route cannot be supported by sufficient basic historical driving routes, the next road section area driving analysis is performed based on the real-time geographic location combined with the current lane, and the next road section area corresponding to the lane is used as the short-distance predicted driving route of the vehicle with the unknown route.
[0011] As a further improvement of the technical solution, the comprehensive congestion analysis unit includes a quantity prediction module and a congestion analysis module; The number prediction module is used to extract the navigation routes of vehicles with known routes in the navigation software, and then combine the navigation routes with the predicted driving routes of vehicles with unknown routes to perform vehicle number prediction analysis on each road section area, and obtain the predicted number of vehicles corresponding to each road section area in the subsequent time period; The congestion analysis module is used to analyze the traffic flow carrying capacity of each road section area, and then perform congestion analysis based on the traffic flow carrying capacity of the road section area and the predicted number of vehicles. When the traffic flow carrying capacity cannot bear the predicted number of vehicles, it is judged that the road section area will be congested. Conversely, when the traffic flow carrying capacity is sufficient to bear the predicted number of vehicles, it is judged that the road section area will be normal.
[0012] As a further improvement of this technical solution, the traffic adjustment unit extracts vehicles with known routes from the congested road section area. The urban traffic adjustment method is as follows: The congested road area is sent to the navigation software, which then plans to avoid the congested road area, thereby adjusting the driving route of vehicles on known routes; Traffic lights in all road sections will be adjusted comprehensively, and the traffic flow rate in congested road sections will be adjusted.
[0013] Compared with the prior art, the present invention has the following beneficial effects: 1. This holographic perception decision-making central system for urban governance integrates monitoring image data and navigation software trajectory data to build a full-scale traffic perception system covering vehicles on known routes and unknown routes. The vehicle online calculation unit uses license plate recognition and spatiotemporal tracking technology to achieve dynamic and accurate statistics on the number of online vehicles in the road section area. The deletion time threshold is dynamically set in combination with the traffic speed to ensure the real-time and accuracy of vehicle location and quantity statistics. The regional vehicle classification unit divides vehicle behavior into two categories: known routes and unknown routes through navigation data and monitoring images, providing a data basis for differentiated analysis, breaking through the limitations of a single data source, and achieving holographic perception of urban traffic flow and vehicle trajectories, providing reliable data support for subsequent predictions and decision-making.
[0014] 2. This holographic perception decision-making central system for urban governance achieves a quantitative assessment of road congestion by comparing the predicted number of vehicles with the traffic carrying capacity, transforming traditional passive monitoring into active prediction. It can identify congestion risk sections in advance and gain a time window for traffic control. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 It is the overall structural principle diagram of the present invention. DETAILED DESCRIPTION
[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0017] See also Figure 1 As shown, the purpose of this embodiment is to provide a holographic perception decision-making central system for urban governance, including a vehicle online calculation unit, a regional vehicle classification unit, a driving prediction unit, a comprehensive congestion analysis unit, and a traffic adjustment unit; The vehicle online calculation unit is used to obtain monitoring image data of urban traffic and perform license plate recognition. At the same time, it obtains each road section area and combines license plate recognition to perform regional vehicle online calculation; The vehicle online computing unit obtains all the monitoring image data of the city from the city traffic management terminal by connecting to the city traffic management terminal, and at the same time divides the city traffic into road sections and areas, so that the overall city traffic consists of multiple road sections and areas.
[0018] Establish a stable connection channel with the urban traffic management end to ensure smooth and secure data transmission, receive all monitoring image data within the city in real time from the urban traffic management end, and determine the road section area division standards based on the urban road layout (such as road grade, intersection location, etc.), traffic flow characteristics (flow size, flow direction, etc.), and geographic information (blocks, landmarks, etc.).
[0019] The vehicle online calculation unit includes an online vehicle calculation module; The online vehicle calculation module is used to identify license plate numbers based on monitoring image data, save the identified license plate numbers in real time, and then use the number of license plate numbers saved in real time as the number of online vehicles in the corresponding road section area.
[0020] When the online vehicle calculation module calculates the number of online vehicles; A deletion time threshold is set based on the speed of traffic flow. If the license plate number cannot be re-identified within the deletion time threshold, the license plate number will be deleted from the online vehicles. At the same time, when the license plate number appears in other road sections, it is assigned to the road section area where it appears in the latest recognition time, so that the same license plate number appears in at most one road section area. The specific steps are as follows: License plate recognition and data collection: Grayscale, noise reduction, and contrast enhancement are performed on surveillance images to improve the clarity of the license plate area. Target detection algorithms are used to identify the license plate location in the image, extract the license plate ROI, and then perform character segmentation on the license plate ROI. OCR technology is used to recognize license plate characters and convert them into text format. A timestamp (recognition time) and location information (corresponding to the road section area ID) are added to each recognized license plate. Online vehicle database maintenance: Establish an in-memory database Redis, dynamically calculate the deletion time threshold based on the traffic speed of the current road section, and if a new license plate is recognized, add a record and initialize the parameters; If an existing license plate is recognized: If it is the same as the currently recorded road segment ID, only the last identification time is updated; If it is different from the currently recorded segment ID, update the segment ID and the last identification time, and record the historical trajectory.
[0021] Online vehicle statistics: Periodically scan the database to delete vehicles that have not been identified for a long time. The formula is as follows: ; Among them, T is the deletion time threshold, L is the length of the road section, v is the average speed of the traffic flow in the current road section, and k is the safety factor; ; Among them, N onlineis the number of online vehicles on road section s, P is the set of all recognized license plates, I is the indicator function, which returns 1 if the condition in the brackets is true, otherwise it returns 0, plate is the license plate, plate section is the road section to which the license plate currently belongs, s is the road section, plate time The timestamp of the last time the license plate was recognized, t now The current timestamp.
[0022] The regional vehicle classification unit is used to connect to the navigation software, obtain the geographical location of the navigation vehicle according to the navigation software, and then classify the regional vehicles into known route vehicles and unknown route vehicles based on the geographical location of all navigation vehicles combined with the monitoring image data; The regional vehicle classification unit includes a navigation access module and a vehicle classification module; The navigation access module is used to establish a data transmission channel with the navigation software to obtain the navigation route of each vehicle and obtain the geographical location of the navigation vehicle in real time through the navigation software; Establish an API interface with navigation software providers (such as AutoNavi and Baidu Maps) to obtain real-time vehicle location streams (GPS coordinates, timestamps) and preset navigation route data (waypoint sequence, estimated arrival time); Use WebSocket or MQTT protocol to achieve real-time data push, ensuring location update delay <1 second.
[0023] The vehicle classification module is used to locate the license plate number of all navigation vehicles by combining the geographical location with the monitoring image data, obtain the license plate number corresponding to each navigation vehicle, and then use the license plate number corresponding to the navigation vehicle as a known route vehicle; Except for navigation vehicles, all other license plate numbers are regarded as unknown route vehicles.
[0024] After obtaining the license plate number, the license plate number of each navigation vehicle is determined in combination with the vehicle location information provided by the navigation software. By comparing the geographic location of the navigation information and the monitoring image, the position matching degree can be calculated. Using the distance formula, the license plate number with the shortest distance is selected to correspond to the navigation vehicle, thereby matching the corresponding license plate number for each navigation vehicle.
[0025] The driving prediction unit is used to combine historical monitoring image data with vehicles on unknown routes to perform historical driving route analysis, extract real-time driving routes for vehicles on unknown routes, and perform predicted driving route analysis by combining historical driving routes with real-time driving routes and time periods; The driving prediction unit includes a historical driving analysis module and a predicted driving analysis module; The historical driving analysis module is used to extract historical monitoring image data, then extract individual images based on the license plate numbers corresponding to vehicles on unknown routes from the historical monitoring image data, and perform driving route analysis based on the extracted images to obtain the historical driving routes corresponding to each vehicle on an unknown route. The specific steps are as follows: Historical data preprocessing: Batch extract surveillance image data within a specified time range (e.g., the past 30 days) from storage systems (e.g., HDFS, object storage), associate the corresponding timestamps, camera IDs, and geographic location information, and create an inverted index based on license plate recognition results. Single license plate data extraction: For each license plate number of a vehicle on an unknown route, all historical identification records are extracted from the index, sorted in ascending order by timestamp, and associated with the camera's corresponding geographic location (latitude and longitude). For records with long time intervals, a map matching algorithm (such as HMM-MapMatching) is used to supplement the possible driving path.
[0026] Driving route analysis: Calculate the time difference and displacement between adjacent identification points. When the time difference is greater than the dwell time threshold (5 minutes), it is determined to be a dwell point. When the displacement is less than the displacement distance threshold (50 meters), it is determined to be a dwell point. The trajectory is divided into multiple trip segments (trips) based on the dwell points. Each trip segment represents a continuous movement. Sequential pattern mining is performed on multiple trip segments of the same license plate to identify frequently occurring path combinations. Route feature extraction: Convert the geographic coordinate sequence into a road segment ID sequence (through map matching) to generate a standardized path representation. Then extract the departure time, arrival time, and duration of each trip segment, calculate the time distribution characteristics (such as the frequency of occurrence during peak hours), and then calculate the path length, average speed, number of stops, and other characteristics to construct a vehicle behavior profile.
[0027] The predictive driving analysis module is used to obtain the traveled route and road section area of the unknown route vehicle based on the monitoring image data, and then combine the traveled route and road section area of the unknown route vehicle with the corresponding historical driving route and the current time period to perform predictive driving route analysis to obtain the predicted driving route of the unknown route vehicle in the subsequent travel. The specific steps are as follows; Data preparation and preprocessing: We collect information such as the vehicle's license plate number, time of passing, and location coordinates (road section ID, longitude and latitude) from surveillance image data. We then sort the passing records of vehicles with the same license plate by time to generate a traveled route sequence. Extract the traveled route and current position: the sequence of road sections that the vehicle has passed from the starting point to the current moment is the traveled route, and the road section and position coordinates of the vehicle are the current road section area; Matching historical driving routes: Retrieve the vehicle's historical driving routes from the historical database based on the license plate number. Each historical route contains information such as time and road segment sequence. Filter historical data by current time period (e.g., weekday morning rush hour, weekend afternoon, etc.); Match historical routes that are similar to the previous n segments of the route traveled; Build a prediction model: Use the frequency of subsequent road segments in historical routes to predict the next route, adjust the prediction results based on the traffic conditions of the current time period (such as congestion index and speed limit), and then output the sequence of road segments that may be traversed in the future and the estimated time. The specific formula is as follows: ; Among them, P ( |·) is the conditional probability, indicating that under given conditions, the vehicle will enter the road section next. The probability of is the predicted target road section, R history is the sequence of traveled routes, r current is the current road section, count (H match → ) is the number of steps that are transferred from the current segment to the target segment in the set of historical routes that match the current route. Total number of times, H match is the set of matched historical routes, Total (H match ) is the total number of routes in the matched historical route set, Weight (t now ) is the weight factor (0.5~1.5) for adjusting the predicted probability according to the current period. The more congested the traffic, the lower the probability; the less congested the traffic, the higher the probability; and the peak value is 1.
[0028] When the predictive driving analysis module predicts a vehicle with an unknown route, if the predicted driving route of the vehicle with the unknown route cannot be supported by sufficient basic historical driving routes, it will perform driving analysis on the next road section area based on the real-time geographic location and the current lane, and use the next road section area corresponding to the lane as the short-distance predicted driving route of the vehicle with the unknown route.
[0029] The vehicle's current lane is identified through monitoring images, and the possible next road section is determined based on lane functions (such as left-turn lanes and straight lanes).
[0030] The comprehensive congestion analysis unit is used to perform vehicle count prediction analysis for each road section area by combining the predicted driving routes of vehicles with known routes with vehicles with unknown routes, and to perform comprehensive congestion analysis for each road section area in combination with the corresponding predicted vehicle count; The comprehensive congestion analysis unit includes a quantity prediction module and a congestion analysis module; The number prediction module is used to extract the navigation routes of vehicles with known routes from the navigation software, and then combine the navigation routes with the predicted driving routes of vehicles with unknown routes to perform vehicle number prediction analysis on each road section area, and obtain the predicted number of vehicles corresponding to each road section area in the subsequent time period; Extract navigation route information for vehicles with known routes from navigation software, including the vehicle's starting point, end point, complete sequence of route segments, and the estimated time range for passing each segment; Obtain the predicted driving routes of vehicles on unknown routes. These routes are derived by analyzing historical driving data and real-time conditions, including the sections of road the vehicle is expected to pass through and the corresponding time points; For vehicles with known routes, each vehicle is assigned to a corresponding road section and time period based on its navigation route and estimated travel time. For vehicles with unknown routes, the vehicle is also assigned to each road section and corresponding time period based on its predicted travel route and time. The estimated number of vehicles with unknown routes on each road section at different time periods is counted. The number of vehicles with known routes and the estimated number of vehicles with unknown routes in the same time period of each road section are added together to obtain the predicted number of vehicles in each road section area in the subsequent time period.
[0031] The congestion analysis module is used to analyze the traffic carrying capacity of each road section, and then combine the traffic carrying capacity of the road section with the predicted number of vehicles to perform congestion analysis. If the traffic carrying capacity cannot bear the predicted number of vehicles, the road section is judged to be congested. Conversely, if the traffic carrying capacity is sufficient to bear the predicted number of vehicles, the road section is judged to be normal. The specific steps are as follows; Analyze traffic flow capacity: Collect basic information about each road section, such as the number of lanes, the number of vehicles that can pass through a single lane per hour under ideal conditions, and the length of the road section. Based on the number of lanes and the capacity of a single lane, calculate the maximum traffic flow capacity of each road section. This is the maximum number of vehicles that the road section can theoretically accommodate when there are no obstacles. At the same time, consider factors such as real-time road conditions, weather, and special events to adjust the maximum traffic flow capacity. For example, in the event of congestion, heavy rain, or road construction, reduce the traffic flow capacity of the road section; when the road is clear, maintain or appropriately increase it. The formula is as follows: ; Among them, Cadjust(s, t) is the traffic carrying capacity, C is the basic traffic capacity of a single lane, M(s) is the number of lanes in section s, and α(s, t) is the traffic capacity correction factor of section s in time period t. Conduct congestion analysis: Compare the predicted number of vehicles in each road section in the subsequent time period with the revised traffic carrying capacity; If the predicted number of vehicles is greater than the traffic carrying capacity, it means that there are too many vehicles in the road section during the corresponding period, exceeding its normal carrying capacity, and it is determined that the road section will be congested; When the predicted number of vehicles is less than or equal to the traffic carrying capacity, it indicates that the road section area can accommodate the expected number of vehicles, and it is judged that the road section area will maintain normal traffic status.
[0032] The traffic adjustment unit is used to perform route adjustment analysis on the congested road section area in combination with vehicles on known routes, and to make urban traffic adjustments on vehicles on known routes and road section areas based on the analysis results.
[0033] The traffic adjustment unit extracts vehicles with known routes from the congested road area (based on the previous congestion analysis results, the congested road area is determined, and then the vehicles originally planned to pass through the congested road area are filtered out from the known route vehicle data). The urban traffic adjustment method is as follows: The congested road area is sent to the navigation software, which then plans to avoid the congested road area, thereby adjusting the driving route of vehicles on known routes; The information about the congested road sections is sent to the navigation software. The navigation software re-plans new driving routes for these vehicles based on real-time traffic conditions and road network information, avoiding the congested sections, and pushes the new routes to the users of the corresponding vehicles.
[0034] Traffic lights in all road sections will be adjusted comprehensively, and the traffic flow rate in congested road sections will be adjusted.
[0035] Comprehensively consider factors such as traffic flow, congestion, and road grade in all road sections, and conduct a unified analysis of the signal light timing plan for the entire city. For congested road sections, the traffic flow rate in the section will be increased by extending the green light duration and adjusting the phase sequence to alleviate congestion. The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.
Claims
1. A holographic perception and decision-making central system for urban governance, characterized by: It includes vehicle online calculation unit, regional vehicle classification unit, driving prediction unit, comprehensive congestion analysis unit and traffic adjustment unit; The vehicle online calculation unit is used to obtain monitoring image data of urban traffic and perform license plate recognition, and at the same time obtain each road section area and combine it with license plate recognition to perform regional vehicle online calculation; The regional vehicle classification unit is used to connect to the navigation software, obtain the geographical location of the navigation vehicle according to the navigation software, and then classify the regional vehicles into known route vehicles and unknown route vehicles based on the geographical location of all navigation vehicles combined with the monitoring image data; The driving prediction unit is used to combine historical monitoring image data with unknown route vehicles to perform historical driving route analysis, extract real-time driving routes of unknown route vehicles, and combine historical driving routes with real-time driving routes and time periods to perform predicted driving route analysis; The comprehensive congestion analysis unit is used to perform vehicle number prediction analysis on each road section area by combining the predicted driving routes of vehicles with known routes with vehicles with unknown routes, and to perform comprehensive congestion analysis on each road section area in combination with the corresponding predicted vehicle number; The traffic adjustment unit is used to perform route adjustment analysis on the blocked road section area in combination with vehicles on known routes, and to make urban traffic adjustments on the vehicles on known routes and the road section area according to the analysis results.
2. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The vehicle online calculation unit obtains all monitoring image data of the city from the city traffic management terminal by connecting to the city traffic management terminal, and at the same time divides the city traffic into road section areas, so that the overall city traffic consists of multiple road section areas.
3. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The vehicle online calculation unit includes an online vehicle calculation module; The online vehicle calculation module is used to identify license plate numbers based on monitoring image data, save the identified license plate numbers in real time, and then use the number of license plate numbers saved in real time as the number of online vehicles in the corresponding road section area.
4. The urban governance holographic perception decision-making central system according to claim 3 is characterized by: When the online vehicle calculation module calculates the number of online vehicles; A deletion time threshold is set based on the speed of traffic flow. If the license plate number cannot be re-identified within the deletion time threshold, the license plate number will be deleted from the online vehicles. At the same time, when the license plate number appears in other road sections, the license plate number is assigned to the road section area where it appears in the latest recognition, so that the same license plate number appears in at most one road section area.
5. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The regional vehicle classification unit includes a navigation access module and a vehicle classification module; The navigation access module is used to establish a data transmission channel with the navigation software to obtain the navigation route of each vehicle and obtain the geographical location of the navigation vehicle in real time through the navigation software; The vehicle classification module is used to locate the license plate number of all navigation vehicles by combining the geographical locations with the monitoring image data, obtain the license plate number corresponding to each navigation vehicle, and then use the license plate number corresponding to the navigation vehicle as a known route vehicle; Except for navigation vehicles, all other license plate numbers are regarded as unknown route vehicles.
6. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The driving prediction unit includes a historical driving analysis module and a predicted driving analysis module; The historical driving analysis module is used to extract historical monitoring image data, then extract individual images based on the license plate numbers corresponding to vehicles on unknown routes from the historical monitoring image data, and perform driving route analysis based on the extracted images to obtain the historical driving routes corresponding to each vehicle on the unknown route; The predictive driving analysis module is used to obtain the traveled route and the road section area of the unknown route vehicle based on the monitoring image data, and then combine the traveled route and the road section area of the unknown route vehicle with the corresponding historical driving route and the current time period to perform a predictive driving route analysis to obtain the predicted driving route of the unknown route vehicle for the subsequent travel.
7. The urban governance holographic perception decision-making central system according to claim 6 is characterized by: When the predictive driving analysis module predicts a vehicle with an unknown route, if the predicted driving route of the vehicle with the unknown route cannot be supported by sufficient basic historical driving routes, the module performs driving analysis on the next road section area based on the real-time geographic location and the current lane, and uses the next road section area corresponding to the lane as the short-distance predicted driving route of the vehicle with the unknown route.
8. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The comprehensive congestion analysis unit includes a quantity prediction module and a congestion analysis module; The number prediction module is used to extract the navigation routes of vehicles with known routes in the navigation software, and then combine the navigation routes with the predicted driving routes of vehicles with unknown routes to perform vehicle number prediction analysis on each road section area, and obtain the predicted number of vehicles corresponding to each road section area in the subsequent time period; The congestion analysis module is used to analyze the traffic flow carrying capacity of each road section area, and then perform congestion analysis based on the traffic flow carrying capacity of the road section area and the predicted number of vehicles. When the traffic flow carrying capacity cannot bear the predicted number of vehicles, it is judged that the road section area will be congested. Conversely, when the traffic flow carrying capacity is sufficient to bear the predicted number of vehicles, it is judged that the road section area will be normal.
9. The urban governance holographic perception decision-making central system according to claim 1 is characterized by: The traffic adjustment unit extracts vehicles with known routes from the congested road section. The urban traffic adjustment method is as follows: The congested road area is sent to the navigation software, which then plans to avoid the congested road area, thereby adjusting the driving route of vehicles on known routes; Traffic lights in all road sections will be adjusted comprehensively, and the traffic flow rate in congested road sections will be adjusted.