Traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation

Abstract

The application discloses a traffic volume dynamic remote measurement and real-time communication scheduling system based on vehicle-road cooperation, and relates to the technical field of vehicle-road cooperation traffic management.The system comprises a vehicle terminal module for collecting vehicle data, a roadside remote measurement module integrated with an old facility modular adaptation unit and a multi-scene parameter iteration unit, a communication transmission module for realizing data interaction between modules, a scheduling control module for generating traffic scheduling strategies, a data storage module for storing system-related data, and an operation and maintenance monitoring module for monitoring the operating states of the modules.The application integrates an old traffic facility modular adaptation unit and a multi-scene adaptive remote measurement parameter dynamic iteration unit in the roadside remote measurement module.The former realizes seamless connection of old facilities in a pluggable structure and by using relevant algorithms, thereby reducing deployment costs and reconstruction difficulty.The latter accurately identifies road scenes by using multiple algorithms, optimizes remote measurement parameters, improves traffic volume remote measurement accuracy and efficiency, and solves the problems of poor adaptability and weak anti-interference of existing systems.

Description

Technical Field

[0001] This invention relates to the field of vehicle-road cooperative traffic management technology, specifically a vehicle-road cooperative dynamic traffic volume telemetry and real-time communication scheduling system. Background Technology

[0002] With the rapid development of vehicle-road cooperative technology, traffic volume dynamic telemetry, as a core component of traffic dispatching and management, directly impacts the efficiency and safety of traffic management in terms of accuracy and adaptability. Currently, a large number of outdated traffic facilities are still deployed in my country's urban and highway transportation networks. These facilities have diverse interface types, non-standardized data outputs, and inconsistent power supply specifications. Existing vehicle-road cooperative telemetry systems are mostly designed for entirely new scenarios and lack adaptation mechanisms for outdated facilities. Furthermore, the traffic flow characteristics vary significantly across different road scenarios, leading to different requirements for telemetry parameters. Therefore, there is an urgent need for a traffic volume dynamic telemetry and communication dispatching system that can automatically adapt to multiple scenarios and is compatible with outdated facilities to meet diverse traffic management needs. Traditional vehicle-road cooperative telemetry systems have significant shortcomings. On the one hand, existing systems lack dedicated adaptation units for older infrastructure, making them incompatible with different types of older traffic facilities. To deploy such systems, the entire existing infrastructure must be dismantled and replaced, increasing deployment costs and extending the construction period, making it difficult to achieve rapid collaborative operation between new and old facilities. On the other hand, the telemetry parameters of traditional systems are mostly fixed, lacking a dynamic iterative adjustment mechanism. This prevents them from adaptively optimizing the telemetry frequency and sensor fusion weights based on changes in road scenarios, resulting in unstable telemetry accuracy and weak anti-interference capabilities under different scenarios, making it difficult to meet the actual needs of precise traffic scheduling. For example, the "Traffic Operation Management System Based on Multidimensional Data and Internet of Things Integration" with publication number CN119723872A focuses on the collaboration of front-end perception, terminal processing, and back-end supervision in its core architecture, aiming to break down "data silos" to improve supervision accuracy. However, its multidimensional data fusion is only used for illegal operation, dangerous goods transportation and other violation supervision scenarios, without involving adaptation mechanisms for old traffic facilities, nor is it designed for dynamic adjustment of telemetry parameters. On the other hand, the "Traffic Volume Telemetry Statistics Device" with publication number CN216014470U only achieves convenient device mobility and internal component protection by optimizing the hardware structure. It is only a hardware improvement of a single device and does not form a multi-module collaborative design at the system level. It has neither the ability to be compatible with old facilities nor the ability to achieve adaptive adjustment of telemetry parameters under different road scenarios. Therefore, the existing technologies still cannot solve the core problems of difficult compatibility with old facilities and poor scenario adaptability. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a vehicle-road cooperative traffic volume dynamic telemetry and real-time communication dispatch system. This invention builds six major modules, including vehicle-mounted terminals, roadside telemetry, and communication transmission, and addresses the problems of traditional systems through two key units in the roadside telemetry module. First, a pluggable structure combined with automatic interface identification and data conversion correction algorithms enables smooth integration with aging traffic facilities without requiring complete equipment replacement. Second, through multi-dimensional scene recognition, telemetry parameter iteration, and sensor weight adjustment algorithms, it automatically adapts to different road scenarios. The system reduces deployment and upgrade costs while improving the accuracy and anti-interference capability of traffic volume telemetry, making traffic dispatch more flexible and efficient, and solving the practical problems of traditional systems' difficulty in compatibility with aging facilities and insufficient scene adaptation.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a traffic volume dynamic telemetry and real-time communication dispatch system based on vehicle-road cooperation, the system comprising an on-board terminal module, a roadside telemetry module, a communication transmission module, a dispatch control module, a data storage module, and an operation and maintenance monitoring module; The vehicle-mounted terminal module is used to collect vehicle-related data, the communication transmission module is used to realize data transmission between modules, the dispatch control module is used to generate traffic dispatch strategies, the data storage module is used to store system-related data, and the operation and maintenance monitoring module is used to monitor the operating status of each module. The vehicle-mounted terminal module is bidirectionally connected to the roadside telemetry module, and the roadside telemetry module, communication transmission module, dispatch control module, and data storage module are sequentially connected to each other. The operation and maintenance monitoring module is also connected to all other modules. The roadside telemetry module integrates a modular adaptation unit for old traffic facilities and a dynamic iteration unit for multi-scenario adaptive telemetry parameters. The modular adaptation unit for old traffic facilities is used to achieve seamless connection between old traffic facilities and the system, and the dynamic iteration unit for multi-scenario adaptive telemetry parameters is used to automatically identify road scenarios and dynamically iterate telemetry parameters. The modular adaptation unit for old transportation facilities adopts a pluggable modular structure, including an interface adaptation subunit, a data conversion subunit, and a power supply adaptation subunit. The interface adaptation subunit uses an automatic interface identification algorithm to achieve automatic adaptation of the interfaces of old equipment, and the data conversion subunit uses a data conversion accuracy correction algorithm to convert non-standard data into standardized data for system adaptation. The multi-scenario adaptive telemetry parameter dynamic iteration unit includes a scene recognition subunit, a parameter iteration subunit, a sensor fusion subunit, and a parameter caching subunit. The scene recognition subunit uses a multi-dimensional scene recognition algorithm to achieve accurate recognition of road scenes. The parameter iteration subunit uses a telemetry parameter dynamic iteration algorithm to achieve dynamic adjustment of telemetry frequency and sensor fusion weight. The sensor fusion subunit uses a sensor weight iteration algorithm to achieve accurate fusion of multi-sensor data.

[0005] Furthermore, the interface adaptation subunit of the modular adaptation unit for aging transportation facilities integrates multiple standardized interfaces and supports interface expansion. The automatic interface identification algorithm quantifies the compatibility between aging equipment and the adaptation unit to achieve automatic identification and adaptation of the interfaces of aging equipment. Its core formula is: ,in, For compatibility rating, the value ranges from 0 to 1; , , Let be the weighting coefficient, satisfying + + =1, its value is determined based on the adaptation priority of interfaces, power supply, and data formats of old transportation facilities, and is optimized through multiple sets of old equipment adaptation experiments. The specific value is... =0.4、 =0.3、 =0.3; The number of interfaces that can be matched between the old equipment interface and the built-in interface of the adapter unit; This represents the total number of interfaces on the outdated equipment. To accommodate the power supply voltage that the adapter unit can output; The rated power supply voltage for older equipment; The data transmission rate for older equipment; To adapt to the standardized data transmission rate supported by the unit, its value is determined based on the data transmission requirements of the vehicle-road cooperative system through system compatibility test calibration, and the default value is 115200bps.

[0006] Furthermore, the data conversion subunit of the modular adaptation unit for aging transportation facilities can parse various non-standardized data output by aging equipment. The core formula of the data conversion accuracy correction algorithm is: ,in, This is the corrected, standardized telemetry data; This is the uncorrected, raw transformed data; The error correction coefficient ranges from 0.05 to 0.2. Its value is determined based on the service life of the old equipment. The longer the service life, the larger the value. It is obtained through data conversion experiments of multiple sets of old equipment with different service lives. A compatibility score is given. The amount of noise data in the output data of older equipment; The total amount of data output by older equipment.

[0007] Furthermore, the power supply adaptation subunit of the modular adaptation unit for old transportation facilities supports wide voltage adaptation and can be directly connected to the existing power supply lines of old equipment. It has built-in overvoltage, overcurrent, and short circuit protection modules, and can monitor the power supply status in real time and provide feedback on power supply anomalies.

[0008] Furthermore, the scene recognition subunit of the multi-scene adaptive telemetry parameter dynamic iteration unit collects multi-dimensional scene data through roadside multi-sensors and the vehicle-mounted terminal module. The multi-dimensional scene recognition algorithm is used to quantify the adaptability between the current scene and the preset scene, and its core formula is: ,in, The degree of fit between the current scene data and the i-th preset scene ranges from 0 to 1. The number of scene feature dimensions. =4, corresponding to the four core scenario characteristics of traffic flow, vehicle speed, road width, and environmental interference coefficient in the vehicle-road cooperative scenario. Its value was determined through the full-scenario demand analysis and experimental verification of vehicle-road cooperative. The weight of the k-th scene feature is determined based on the influence of each scene feature on the scene recognition result. It is calibrated through multi-scene recognition experiments in vehicle-road cooperative systems, and its specific value is [value missing]. =0.35、 =0.25、 =0.2、 =0.2; This represents the measured value of the k-th scene feature currently collected; The standard threshold for the k-th feature in the i-th preset scenario is obtained through statistical analysis and experimental optimization of actual traffic data in different preset scenarios. This represents the traffic flow fluctuation cycle in the current scenario. The standard value of the traffic flow fluctuation cycle for the i-th preset scenario is obtained through statistical analysis and experimental calibration of traffic flow fluctuation data for different preset scenarios.

[0009] Furthermore, the parameter iteration subunit of the multi-scene adaptive telemetry parameter dynamic iteration unit realizes dynamic iteration of the telemetry frequency based on the scene recognition result. The core formula of the telemetry parameter dynamic iteration algorithm is: The constraint is 50ms≤ ≤500ms, where, The telemetry frequency after the (t+1)th iteration; Let be the telemetry frequency after the t-th iteration, with initial value . =200ms, this initial value was determined through calibration experiments on telemetry requirements in typical vehicle-road cooperative scenarios; The iteration rate coefficient ranges from 0.1 to 0.3. Its value is based on the requirement of scene adaptability for telemetry frequency adjustment rate and is obtained through multi-scene telemetry iteration experiments. The higher the scene adaptability, the larger the value. For all current preset scenes The maximum value in; This represents the real-time traffic flow in the current vehicle-road cooperative scenario. The traffic flow threshold for the current identification scenario is determined through experimental calibration based on the traffic flow characteristics of different preset scenarios.

[0010] Furthermore, the sensor fusion subunit of the multi-scenario adaptive telemetry parameter dynamic iteration unit dynamically adjusts the multi-sensor fusion weights based on the parameter iteration results. The core formula of the sensor weight iteration algorithm is: ,in, =1, 2, and 3 correspond to LiDAR, millimeter-wave radar, and high-definition camera, respectively, and satisfy the following conditions: =1; Let be the fusion weight of the s-th sensor after the (t+1)-th iteration; Let be the fusion weights of the s-th type of sensor after the t-th iteration. The initial weights are determined through multi-sensor fusion accuracy experiments, and the specific initial values ​​are . (0) = 0.4 (0) = 0.3 (0) = 0.3; This represents the current measured accuracy of the s-th type sensor. The environmental interference influence coefficient is set to 0.5. This value is determined through sensor performance calibration experiments under different environmental interference conditions and is used to quantify the degree of influence of environmental interference on sensor accuracy. The environmental interference coefficient of the s-th type sensor is 0 to 1. Its value is based on the current environmental interference intensity and is obtained by calibrating the data collected in real time by the environmental sensor.

[0011] Furthermore, the parameter caching subunit of the multi-scenario adaptive telemetry parameter dynamic iteration unit is used to store the optimal telemetry parameter combination under different scenarios. When a recurring scenario is identified, the cached parameters can be directly called to assist the parameter iteration subunit in adjusting the telemetry parameters.

[0012] Compared with existing technologies, this vehicle-road cooperative traffic volume dynamic telemetry and real-time communication scheduling system has the following advantages: I. This invention integrates a modular adaptation unit for aging traffic facilities into a roadside telemetry module. Employing a pluggable modular structure coupled with an automatic interface identification algorithm and a data conversion accuracy correction algorithm, it achieves seamless integration between aging traffic facilities and the vehicle-road cooperative telemetry system. This unit can automatically identify the interface type of aging equipment and adapt to power supply requirements, accurately converting non-standardized data into standardized data compatible with the system. This eliminates the need for complete replacement of aging facilities, reducing system deployment costs and modification difficulty. Furthermore, by optimizing algorithm parameters, it improves data conversion accuracy, solving the problem of existing systems being incompatible with aging facilities and having poor adaptability.

[0013] II. This invention achieves accurate identification of road scenes and dynamic optimization of telemetry parameters by setting up a multi-scenario adaptive telemetry parameter dynamic iteration unit in the roadside telemetry module, combined with multi-dimensional scene recognition algorithms, telemetry parameter dynamic iteration algorithms, and sensor weight iteration algorithms. This unit can collect multi-dimensional scene data in real time, automatically match corresponding scenes, and iteratively adjust the telemetry frequency and sensor fusion weights. It can adapt to the telemetry needs of different road scenes without manual intervention, effectively improving the accuracy and efficiency of traffic volume telemetry and solving the problems of fixed telemetry parameters, poor scene adaptability, and weak anti-interference ability in existing systems.

[0014] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0016] Figure 1 This is a schematic diagram of the overall system architecture and module connection relationships of the present invention; Figure 2 This is a schematic diagram of the internal structure of the roadside telemetry module of the present invention; Figure 3 This is a flowchart illustrating the dynamic iteration process of multi-scenario adaptive telemetry parameters in this invention. Detailed Implementation

[0017] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0018] Example The traffic volume dynamic telemetry and real-time communication dispatch system based on vehicle-road cooperation disclosed in this invention comprises six core modules: an on-board terminal module, a roadside telemetry module, a communication transmission module, a dispatch control module, a data storage module, and an operation and maintenance monitoring module. Figure 1 As shown in the diagram, the modular adaptation unit for old traffic facilities achieves seamless integration between existing facilities and the system through automatic interface identification, data conversion and correction, and wide voltage adaptation technology. The multi-scenario adaptive telemetry parameter dynamic iteration unit automatically adapts to different road scenarios using scene recognition, parameter iteration, and sensor weight adjustment algorithms. The system solves the problems of incompatibility with existing facilities and poor scene adaptation in current systems, improves the accuracy of traffic volume telemetry, and reduces deployment costs.

[0019] The working principle and operation process of each module are as follows: The vehicle-mounted terminal module is the core component for vehicle-side data acquisition, primarily responsible for collecting key information during vehicle operation, providing fundamental data support for the entire system's telemetry and dispatching functions. This module continuously captures data such as vehicle speed, real-time location, operating status, and basic vehicle parameters through various integrated sensors. During data collection, the module prioritizes real-time data and completeness, ensuring that subsequent data analysis and dispatching decisions are based on reliable vehicle data. After data acquisition, the vehicle-mounted terminal module transmits this information to the roadside telemetry module in real time.

[0020] The roadside telemetry module is a key component for realizing the core functions of the system, such as... Figure 2 As shown, it integrates a modular adaptation unit for old transportation facilities and a dynamic iteration unit for multi-scenario adaptive telemetry parameters, which are responsible for solving the two core problems of compatibility with old facilities and multi-scenario adaptation, respectively.

[0021] The modular adaptation unit for aging transportation facilities adopts a pluggable modular structure, which reduces the physical difficulty of connecting aging facilities with new systems, facilitating subsequent installation, maintenance, and upgrades. Its core purpose is to avoid the hassle of replacing the entire aging facility required in traditional systems, reducing deployment costs and construction time. This unit includes an interface adaptation subunit, a data conversion subunit, and a power supply adaptation subunit. These three subunits work together to achieve comprehensive adaptation of aging facilities.

[0022] The core technology of the interface adapter subunit is the automatic interface identification algorithm. Because existing aging transportation infrastructure has a wide variety of interface types and lacks standardized specifications, the number of interfaces, power requirements, and data transmission rates vary significantly between different devices. This directly prevents traditional systems from directly interfacing with these older devices. The formula is: ,in, For compatibility rating, the value ranges from 0 to 1; , , Let be the weighting coefficient, satisfying + + =1, its value is determined based on the adaptation priority of interfaces, power supply, and data formats of old transportation facilities, and is optimized through multiple sets of old equipment adaptation experiments. The specific value is... =0.4、 =0.3、 =0.3; The number of interfaces that can be matched between the old equipment interface and the built-in interface of the adapter unit; This represents the total number of interfaces on the outdated equipment. To accommodate the power supply voltage that the adapter unit can output; The rated power supply voltage for older equipment; The data transmission rate for older equipment; To adapt to the standardized data transmission rate supported by the unit, this value was determined through system compatibility experiments based on the overall data transmission requirements of the vehicle-road cooperative system. The difference between the two values ​​was calculated by... The ratio of these three dimensions, when subtracted from 1, quantifies the compatibility of data transmission rates, preventing data loss or transmission delays caused by rate mismatch. A weighted sum of these three dimensions yields a compatibility score. This score automatically determines the compatibility between the adapter unit and older devices, enabling automatic interface adaptation without manual adjustment of the interface type.

[0023] The main task of the data conversion subunit is to convert the non-standardized data output by older equipment into standardized data that the system can recognize and process. Because older equipment is produced at different times and uses different technical standards, its output data format lacks uniformity, and the data is prone to noise interference, directly affecting the accuracy of subsequent data processing. To improve conversion accuracy, a data conversion accuracy correction algorithm is needed, the core formula of which is: ,in, This is the corrected, standardized telemetry data; This is the uncorrected, raw transformed data; The error correction coefficient ranges from 0.05 to 0.2. Its value is determined based on the service life of the old equipment. The longer the service life, the larger the value. It is obtained through data conversion experiments of multiple sets of old equipment with different service lives. A compatibility score is given. The amount of noise data in the output data of older equipment; The ratio of the total data output from aging equipment to the total data output directly reflects the purity of the data. The higher the noise percentage, the lower the data reliability, and its impact needs to be mitigated during the correction process. This formula effectively integrates three key factors: compatibility, equipment aging, and data purity, offsetting the impact of various interferences on data conversion and accurately converting non-standardized data into standardized telemetry data usable by the system.

[0024] The power supply adapter subunit is designed to address the issue of inconsistent power supply specifications for older equipment. It supports wide voltage compatibility and can be directly connected to existing power lines of older equipment without requiring additional modifications to the power supply system, significantly reducing deployment difficulty and upgrade costs. Simultaneously, this subunit integrates overvoltage, overcurrent, and short-circuit protection modules, enabling real-time monitoring of power supply voltage, current, and other status parameters. In the event of a power supply anomaly, it promptly relays the abnormal information to the operation and maintenance monitoring module, ensuring the stable operation of older equipment and the adapter unit.

[0025] The core purpose of the multi-scenario adaptive telemetry parameter dynamic iteration unit is to solve the problem that traditional systems have fixed telemetry parameters that cannot adapt to different road scenarios, such as... Figure 3 As shown, this unit automatically identifies road scenes and dynamically adjusts telemetry parameters, enabling the system to maintain high telemetry accuracy and efficiency in various scenarios. This unit comprises a scene recognition subunit, a parameter iteration subunit, a sensor fusion subunit, and a parameter caching subunit, with each subunit operating in the logical sequence of "scene recognition - parameter iteration - data fusion - parameter caching".

[0026] The scene recognition subunit, through the cooperation of roadside multi-sensors and onboard terminal modules, collects multi-dimensional scene data. This data includes four core scene features: traffic flow, vehicle speed, road width, and environmental interference coefficient. These four features were chosen because they reflect the actual road conditions. The number of feature dimensions was determined through demand analysis and experimental verification across the entire vehicle-road cooperative scenario, ensuring coverage of major road scenario differences. The multi-dimensional scene recognition algorithm achieves accurate scene recognition by calculating the fit between the current scene and preset scenes. The core formula is: ,in, The degree of fit between the current scene data and the i-th preset scene ranges from 0 to 1. The number of scene feature dimensions. =4, corresponding to the four core scenario characteristics of traffic flow, vehicle speed, road width, and environmental interference coefficient in the vehicle-road cooperative scenario. Its value was determined through the full-scenario demand analysis and experimental verification of vehicle-road cooperative. The weight of the k-th scene feature is determined based on the influence of each scene feature on the scene recognition result. It is calibrated through multi-scene recognition experiments in vehicle-road cooperative systems, and its specific value is [value missing]. =0.35、 =0.25、 =0.2、 =0.2; This represents the measured value of the k-th scene feature currently collected; The standard threshold for the k-th feature in the i-th preset scenario is obtained through statistical analysis and experimental optimization of actual traffic data in different preset scenarios. This represents the traffic flow fluctuation cycle in the current scenario. The standard value for the traffic flow fluctuation cycle of the i-th preset scenario is obtained through statistical analysis and experimental calibration of traffic flow fluctuation data from different preset scenarios. The traffic flow fluctuation cycle is a key indicator reflecting the dynamic changes of the scenario. For example, the fluctuation cycle differs significantly between peak and off-peak hours. Quantifying the difference between the two using an exponential function can further improve the accuracy of scenario recognition. The calculation process of the formula first obtains the comprehensive fit of each feature dimension through weighted summation, and then corrects it by combining the differences in traffic flow fluctuation cycles. Finally, the fit between the current scenario and each preset scenario is obtained. The preset scenario with the highest fit is the currently identified road scenario, providing a basis for subsequent parameter adjustments.

[0027] The parameter iteration subunit dynamically iterates the telemetry frequency based on scene recognition results. The telemetry frequency directly affects the real-time performance of telemetry data and the consumption of system resources. In situations with high traffic volume and complex scenarios, the frequency needs to be increased to ensure real-time data performance; conversely, in situations with low traffic volume and simple scenarios, the frequency can be appropriately reduced to conserve system resources. The core formula of the dynamic iteration algorithm for telemetry parameters is: The constraint is 50ms≤ ≤500ms, where, The telemetry frequency after the (t+1)th iteration; Let be the telemetry frequency after the t-th iteration, with initial value . =200ms, this initial value was determined through calibration experiments on telemetry requirements in typical vehicle-road cooperative scenarios; The iteration rate coefficient ranges from 0.1 to 0.3. Its value is based on the requirement of scene adaptability for telemetry frequency adjustment rate and is obtained through multi-scene telemetry iteration experiments. The higher the scene adaptability, the larger the value. For all current preset scenes The maximum value in; This represents the real-time traffic flow in the current vehicle-road cooperative scenario. The traffic flow threshold for the current identification scenario is determined through experimental calibration based on the traffic flow characteristics of different preset scenarios. The difference between the two is... The ratio is used to quantify the deviation of the current traffic flow from the scene threshold, for example, when... Much larger This indicates that the traffic situation is more complex than the preset scenario, requiring a significant increase in telemetry frequency; constraint 50ms ≤ The ≤500ms setting is to avoid excessive system resource consumption due to excessively high frequencies, or to prevent telemetry accuracy from being affected by excessively low frequencies, thus ensuring stable and efficient system operation. This formula allows for dynamic adjustment of the telemetry frequency based on scene recognition accuracy and real-time traffic flow, ensuring that the telemetry parameters always adapt to the current scene requirements.

[0028] The sensor fusion subunit dynamically adjusts the fusion weights of multiple sensors based on parameter iteration results. The system uses three types of sensors—LiDAR, millimeter-wave radar, and high-definition cameras—to collect roadside data. Different sensors exhibit varying performance under different environments and scenarios. For example, LiDAR has high ranging accuracy but is susceptible to adverse weather conditions; high-definition cameras excel in image recognition, but their performance may decline at night. Therefore, dynamic adjustment of the fusion weights is necessary to improve the accuracy of data fusion. The core formula of the sensor weight iteration algorithm is: ,in, =1, 2, and 3 correspond to LiDAR, millimeter-wave radar, and high-definition camera, respectively, and satisfy the following conditions: =1; Let be the fusion weight of the s-th sensor after the (t+1)-th iteration; Let be the fusion weights of the s-th type of sensor after the t-th iteration. The initial weights are determined through multi-sensor fusion accuracy experiments, and the specific initial values ​​are . (0) = 0.4 (0) = 0.3 (0) = 0.3; This represents the current measured accuracy of the s-th type sensor. The environmental interference influence coefficient is set to 0.5. This value is determined through sensor performance calibration experiments under different environmental interference conditions and is used to quantify the degree of influence of environmental interference on sensor accuracy. Let be the environmental interference coefficient of the s-th type sensor, ranging from 0 to 1. Its value is based on the current environmental interference intensity and is obtained through real-time data collection and calibration from environmental sensors. A larger interference coefficient indicates a more severe impact of the environment on the sensor, and its weight should be reduced accordingly. The design logic of the formula is to adjust the original weights based on the current accuracy performance of the sensors and the environmental interference situation. Simultaneously, through summation and normalization of the denominator, it ensures that the sum of the weights of the three types of sensors is always 1, guaranteeing the rationality of the fusion calculation, achieving complementary advantages of multi-sensor data, and improving the accuracy of telemetry data.

[0029] The parameter caching subunit is used to store the optimal telemetry parameter combination after iterative optimization under different scenarios. When the system identifies the same scenario again, it can directly call the optimal parameters in the cache without having to go through the complete parameter iteration process again. This can effectively shorten the parameter adjustment time, improve the system response speed, and reduce unnecessary computing resource consumption, thus assisting the parameter iteration subunit to efficiently complete the telemetry parameter adjustment.

[0030] The communication transmission module is responsible for data transmission between modules. This module uses a mature and stable communication protocol to ensure accurate and real-time flow of vehicle data collected by the vehicle terminal module, telemetry data processed by the roadside telemetry module, and operational status data monitored by the maintenance monitoring module. Data transmission follows a pre-defined logical path: data collected by the vehicle terminal module is transmitted in real-time to the roadside telemetry module; standardized data processed by the roadside telemetry module is sent to the dispatch control module via the communication transmission module; simultaneously, relevant raw data and processing results are transmitted to the data storage module for storage. The maintenance monitoring module obtains real-time operational data from each module through the communication transmission module, and dispatch instructions generated by the dispatch control module are also fed back to relevant traffic facilities or vehicle terminals through this module, forming a complete data transmission closed loop.

[0031] The dispatch control module is the core of the system's decision-making. It receives standardized telemetry data transmitted from the roadside telemetry module, combines it with real-time traffic flow, road scene information, and historical data, and generates targeted traffic dispatch strategies through preset dispatch algorithms. These strategies are flexibly adjusted according to different scenarios. For example, in scenarios with high traffic volume, congestion can be alleviated by optimizing traffic light timings and guiding vehicle diversion; in special weather scenarios, speed limits can be adjusted and vehicles can be reminded to maintain safe following distances. The generated dispatch instructions are fed back to the relevant execution units in real time via the communication transmission module, achieving real-time dynamic traffic dispatch.

[0032] The data storage module stores various types of data generated during system operation, including vehicle data collection, telemetry processing data, scheduling strategy data, and module operating status data. This module adopts an industry-standard secure and reliable storage architecture, ensuring data integrity and security through encrypted storage, redundant backups, and other conventional methods. It also possesses efficient data retrieval capabilities, providing data support for subsequent data traceability, system optimization, and traffic condition analysis.

[0033] The operation and maintenance monitoring module establishes communication connections with all other modules, primarily monitoring the real-time operational status of each module, including whether data acquisition is normal, data transmission is smooth, parameter adjustments are reasonable, and whether equipment malfunctions exist. When an anomaly is detected, the module will promptly issue an early warning and record key information such as the time, location, and cause of the anomaly, facilitating timely troubleshooting and handling by staff, ensuring the stable and reliable operation of the entire system, and reducing the risk of system downtime.

[0034] In summary, this embodiment addresses the shortcomings of existing systems, such as weak compatibility with outdated traffic facilities and insufficient adaptability to multi-scenario telemetry, through the collaborative operation of six modules. The application of automatic interface identification algorithms and data conversion accuracy correction algorithms enables seamless integration between outdated facilities and the system, eliminating the need for complete equipment replacement and reducing deployment costs and modification difficulty. The combined use of multi-dimensional scene recognition, dynamic iteration of telemetry parameters, and sensor weight iteration algorithms allows the system to accurately identify road scenarios and adaptively optimize telemetry parameters, thereby improving the accuracy and anti-interference capability of traffic volume telemetry.

[0035] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A traffic volume dynamic telemetry and real-time communication dispatch system based on vehicle-road cooperation, characterized in that, The system includes an on-board terminal module, a roadside telemetry module, a communication transmission module, a dispatch control module, a data storage module, and an operation and maintenance monitoring module; The vehicle terminal module is used to collect vehicle-related data, the communication transmission module is used for data transmission between modules, the scheduling control module is used to generate traffic scheduling strategies, the data storage module is used to store system data, and the operation and maintenance monitoring module is used to monitor the operating status of each module. The roadside telemetry module integrates a modular adaptation unit for old traffic facilities and a dynamic iteration unit for multi-scenario adaptive telemetry parameters. The modular adaptation unit for old traffic facilities is used to achieve seamless connection between old traffic facilities and the system, while the dynamic iteration unit for multi-scenario adaptive telemetry parameters is used to automatically identify road scenarios and dynamically iterate telemetry parameters. The modular adaptation unit for old transportation facilities adopts a pluggable modular structure, including an interface adaptation subunit, a data conversion subunit, and a power supply adaptation subunit. The interface adaptation subunit uses an automatic interface identification algorithm to achieve automatic adaptation of the interfaces of old equipment, and the data conversion subunit uses a data conversion accuracy correction algorithm to convert non-standard data into standardized data for system adaptation. The multi-scenario adaptive telemetry parameter dynamic iteration unit includes a scene recognition subunit, a parameter iteration subunit, a sensor fusion subunit, and a parameter caching subunit. The scene recognition subunit uses a multi-dimensional scene recognition algorithm to achieve accurate recognition of road scenes. The parameter iteration subunit uses a telemetry parameter dynamic iteration algorithm to achieve dynamic adjustment of telemetry frequency and sensor fusion weight. The sensor fusion subunit uses a sensor weight iteration algorithm to achieve accurate fusion of multi-sensor data.

2. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The interface adaptation subunit of the modular adaptation unit for aging transportation facilities integrates multiple standardized interfaces and supports interface expansion. The automatic interface identification algorithm quantifies the compatibility between aging equipment and the adaptation unit to achieve automatic identification and adaptation of the interfaces of aging equipment. Its core formula is: ,in, For compatibility rating, the value ranges from 0 to 1; , , Let be the weighting coefficient, satisfying + + =1, its value is determined based on the adaptation priority of interfaces, power supply, and data formats of old transportation facilities, and is optimized through multiple sets of old equipment adaptation experiments. The specific value is... =0.4、 =0.3、 =0.3; The number of interfaces that can be matched between the old equipment interface and the built-in interface of the adapter unit; This represents the total number of interfaces on the outdated equipment. To accommodate the power supply voltage that the adapter unit can output; The rated power supply voltage for older equipment; The data transmission rate for older equipment; To adapt to the standardized data transmission rate supported by the unit, its value is determined based on the data transmission requirements of the vehicle-road cooperative system through system compatibility test calibration, and the default value is 115200bps.

3. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The data conversion subunit of the modular adaptation unit for aging transportation facilities can parse various non-standardized data output by aging equipment. The core formula of the data conversion accuracy correction algorithm is: ,in, This is the corrected, standardized telemetry data; This is the uncorrected, raw transformed data; The error correction coefficient ranges from 0.05 to 0.

2. Its value is determined based on the service life of the old equipment. The longer the service life, the larger the value. It is obtained through data conversion experiments of multiple sets of old equipment with different service lives. A compatibility score is given. The amount of noise data in the output data of older equipment; The total amount of data output by older equipment.

4. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The power supply adaptation subunit of the modular adaptation unit for old transportation facilities supports wide voltage adaptation and can be directly connected to the existing power supply lines of old equipment. It has built-in overvoltage, overcurrent and short circuit protection modules, and can monitor the power supply status in real time and provide feedback on power supply abnormality information.

5. The traffic volume dynamic telemetry and real-time communication dispatching system based on vehicle-road cooperation according to claim 1, characterized in that, The scene recognition subunit of the multi-scene adaptive telemetry parameter dynamic iteration unit collects multi-dimensional scene data through roadside multi-sensors and vehicle-mounted terminal modules. The multi-dimensional scene recognition algorithm is used to quantify the adaptability between the current scene and the preset scene, and its core formula is: ,in, The degree of fit between the current scene data and the i-th preset scene ranges from 0 to 1. The number of scene feature dimensions. =4, corresponding to the four core scenario characteristics of traffic flow, vehicle speed, road width, and environmental interference coefficient in the vehicle-road cooperative scenario. Its value was determined through the full-scenario demand analysis and experimental verification of vehicle-road cooperative. The weight of the k-th scene feature is determined based on the influence of each scene feature on the scene recognition result. It is calibrated through multi-scene recognition experiments in vehicle-road cooperative systems, and its specific value is [value missing]. =0.35、 =0.25、 =0.2、 =0.2; This represents the measured value of the k-th scene feature currently collected; The standard threshold for the k-th feature in the i-th preset scenario is obtained through statistical analysis and experimental optimization of actual traffic data in different preset scenarios. This represents the traffic flow fluctuation cycle in the current scenario. The standard value of the traffic flow fluctuation cycle for the i-th preset scenario is obtained through statistical analysis and experimental calibration of traffic flow fluctuation data for different preset scenarios.

6. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The parameter iteration subunit of the multi-scene adaptive telemetry parameter dynamic iteration unit realizes dynamic iteration of telemetry frequency based on scene recognition results. The core formula of the telemetry parameter dynamic iteration algorithm is: The constraint is 50ms≤ ≤500ms, where, The telemetry frequency after the (t+1)th iteration; Let be the telemetry frequency after the t-th iteration, with initial value . =200ms, this initial value was determined through calibration experiments on telemetry requirements in typical vehicle-road cooperative scenarios; The iteration rate coefficient ranges from 0.1 to 0.

3. Its value is based on the requirement of scene adaptability for telemetry frequency adjustment rate and is obtained through multi-scene telemetry iteration experiments. The higher the scene adaptability, the larger the value. For all current preset scenes The maximum value in; This represents the real-time traffic flow in the current vehicle-road cooperative scenario. The traffic flow threshold for the current identification scenario is determined through experimental calibration based on the traffic flow characteristics of different preset scenarios.

7. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The sensor fusion subunit of the multi-scenario adaptive telemetry parameter dynamic iteration unit dynamically adjusts the multi-sensor fusion weights based on the parameter iteration results. The core formula of the sensor weight iteration algorithm is: ,in, =1, 2, and 3 correspond to LiDAR, millimeter-wave radar, and high-definition camera, respectively, and satisfy the following conditions: =1; Let be the fusion weight of the s-th sensor after the (t+1)-th iteration; Let be the fusion weights of the s-th type of sensor after the t-th iteration. The initial weights are determined through multi-sensor fusion accuracy experiments, and the specific initial values ​​are . (0) = 0.4 (0) = 0.3 (0) = 0.3; This represents the current measured accuracy of the s-th type sensor. The environmental interference influence coefficient is set to 0.

5. This value is determined through sensor performance calibration experiments under different environmental interference conditions and is used to quantify the degree of influence of environmental interference on sensor accuracy. The environmental interference coefficient of the s-th type sensor is 0 to 1. Its value is based on the current environmental interference intensity and is obtained by calibrating the data collected in real time by the environmental sensor.

8. The traffic volume dynamic telemetry and real-time communication scheduling system based on vehicle-road cooperation according to claim 1, characterized in that, The parameter caching subunit of the multi-scenario adaptive telemetry parameter dynamic iteration unit is used to store the optimal telemetry parameter combination under different scenarios. When a recurring scenario is identified, the cached parameters can be directly called to assist the parameter iteration subunit in completing the telemetry parameter adjustment.

Images