Vehicle-road cooperation bus priority system based on multi-source data fusion

Abstract

The invention relates to the field of intelligent traffic systems, in particular to a multi-source data fusion-based vehicle-road collaborative bus priority system, which comprises the following modules: a data acquisition module, which comprises an electronic police, a bayonet device, a monitoring device, a thunder-vision all-in-one machine and a vehicle-road system device and is used for acquiring traffic flow data at an intersection and related road sections thereof; the data processing module comprises a data cleaning unit, a data classification unit and a data analysis unit and is used for cleaning, classifying and analyzing the collected data and extracting traffic flow features, and the data fusion module is used for fusing the traffic flow features through three-level fusion (vehicle data fusion, traffic flow feature fusion and vehicle state fusion). Accurate vehicle position and state information and real-time traffic conditions of the intersection and the vicinity of the intersection are obtained, and the traffic prediction module can accurately predict the traffic flow condition of the whole intersection within a short period of time by combining real-time data and historical data.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation systems, and in particular to a vehicle-road cooperative public transportation priority system based on multi-source data fusion. Background Art

[0002] At present, the bus priority system mainly relies on bus lanes and detectors arranged in the bus lanes to detect vehicles to achieve bus priority control. However, this traditional bus priority system has many limitations.

[0003] First, it has high requirements for channelized roads, and requires specific road design and layout to meet the conditions for setting up bus lanes. This has led to the inability to implement bus lanes in many places due to road conditions or urban planning restrictions, and thus the inability to enjoy the benefits of the bus priority system.

[0004] Secondly, dedicated bus lanes occupy a large amount of urban road resources. In urban areas where road resources are already scarce, the establishment of bus lanes often has a significant impact on the passage of social vehicles, which may lead to traffic congestion and reduced traffic efficiency. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the deficiencies in the prior art, the present invention provides a vehicle-road cooperative public transportation priority system based on multi-source data fusion.

[0007] (II) Technical solution

[0008] To achieve the above purpose, the present invention provides the following technical solution: the present invention.

[0009] Preferably, the traffic flow data collected by the data collection module include traffic parameters such as traffic volume, vehicle speed, traffic flow density and long queues.

[0010] Further preferably, the data fusion module performs three-level fusion of the collected data, including vehicle data fusion, traffic flow feature fusion and vehicle status fusion, to obtain data on the current actual traffic volume at and near the intersection, driving speed, traffic density, queue length, traffic congestion status during driving time, traffic events, bus location and its estimated arrival time at the intersection.

[0011] Again preferably, the traffic prediction module combines real-time data and historical data to predict traffic flow conditions at the entire intersection within a relatively short period of time, including traffic volume, vehicle speed, vehicle density, queue length, congestion and bus estimated arrival time parameters.

[0012] Preferably, the traffic signal control module transmits bus-related information and traffic signal content through the interaction between RSU and OBU, and performs data fusion, feature fusion and state fusion on data sampled by multiple detectors through MEC.

[0013] Further preferably, the bus priority control module optimizes the feasibility of buses passing through intersections on a road section in one go by adjusting early phase duration, early red light switching off, and green light extension.

[0014] Preferably again, the bus priority control module divides the vehicle detection area into three areas: an adjustable area, an area to be adjusted and a confirmed adjustment area. According to traffic flow conditions such as the bus speed, current traffic density and current phase operation conditions, the time it takes for the vehicle to pass the intersection is predicted. If it is predicted to pass, the phase duration is adjusted; if it cannot pass, the corresponding phase duration is not adjusted to ensure that the bus can reduce the number of stops and waiting time.

[0015] Preferably, the bus priority control module includes an optimization algorithm superposition unit, and the optimization algorithm superposition unit is used to optimize the bus priority release scheme several times by classifying the records of each optimization algorithm.

[0016] Preferably again, the optimization algorithm superposition unit forms a bus priority release strategy for different release directions and types through long-term accumulation, analysis and classification.

[0017] (III) Beneficial effects

[0018] Compared with the prior art, the present invention provides a vehicle-road cooperative public transportation priority system based on multi-source data fusion, which has the following beneficial effects:

[0019] Comprehensive data collection and precise analysis:

[0020] Through a variety of collection devices such as electronic police, checkpoint equipment, monitoring equipment, integrated radar and vision devices, and vehicle-road system equipment, the system can comprehensively and real-time collect traffic flow data at intersections and related road sections, including key parameters such as traffic volume, vehicle speed, traffic flow density, and queue lengths.

[0021] The data processing module cleans, classifies and analyzes the collected data, extracts accurate traffic flow characteristics, and provides a solid foundation for subsequent data fusion and traffic prediction.

[0022] High-precision data fusion and real-time traffic prediction:

[0023] The data fusion module obtains accurate vehicle location and status information, as well as real-time traffic conditions at and near intersections through three-level fusion (vehicle data fusion, traffic flow feature fusion, and vehicle status fusion).

[0024] The traffic prediction module combines real-time data with historical data to accurately predict the traffic flow conditions of the entire intersection within a short period of time, including parameters such as traffic volume, vehicle speed, traffic density, queue length, congestion and estimated bus arrival time, providing a scientific basis for traffic signal control and bus priority control.

[0025] Intelligent traffic signal control and bus priority:

[0026] The traffic signal control module realizes intelligent control and adjustment of traffic signals through the collaborative work of RSU, OBU and MEC, reduces the parking and waiting time of buses at intersections, and improves traffic efficiency.

[0027] Based on the data provided by the traffic prediction module, the bus priority control module provides buses with priority right of way by adjusting the phase duration of traffic signals, optimizing algorithm superposition and area division, further reducing the number of stops and waiting time, and improving the travel efficiency and service quality of buses.

[0028] Optimization algorithm superposition and strategy formation:

[0029] The optimization algorithm superposition unit in the bus priority control module classifies the records of each optimization algorithm and uses it to optimize the bus priority release plan several times, thereby achieving continuous improvement and effect enhancement of the optimization algorithm.

[0030] Long-term accumulation, analysis and classification have formed bus priority release strategies with different release directions and types, providing strong support for the long-term operation and continuous optimization of the system.

[0031] Improve overall traffic efficiency and service quality:

[0032] The implementation of this system has significantly improved traffic efficiency at intersections and related road sections, reduced traffic congestion and waiting time, and improved traffic conditions.

[0033] At the same time, the implementation of bus priority control has also improved the travel efficiency and service quality of buses, enhanced the attractiveness and competitiveness of public transportation, and helped promote green travel and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of the structure of the vehicle-road cooperative public transportation priority system of the present invention;

[0035] Figure 2 This is a schematic diagram of the bus priority control structure of the present invention;

[0036] Figure 3 It is a schematic diagram of the data acquisition structure of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0038] See also Figure 1-3 The vehicle-road cooperative public transportation priority system based on multi-source data fusion of the present invention realizes public transportation priority control under vehicle-road cooperative conditions by integrating multiple data sources and advanced data processing technologies. The specific process is as follows:

[0039] Data acquisition module:

[0040] Structure: The data acquisition module includes electronic police, checkpoint equipment, monitoring equipment, radar and vision integrated machine and vehicle-road system equipment.

[0041] Function: These devices are located at major intersections and roads in the city to collect traffic flow data, including traffic volume, vehicle speed, traffic flow density, queue length and other traffic parameters.

[0042] Data processing module:

[0043] Structure: The data processing module includes a data cleaning unit, a data classification unit and a data analysis unit.

[0044] Function: The data cleaning unit cleans the collected data and removes invalid and abnormal data; the data classification unit classifies the data according to parameters such as traffic volume, vehicle speed, traffic flow density, and queue length; the data analysis unit analyzes the classified data and extracts traffic flow characteristics.

[0045] Data fusion module:

[0046] Structure: The data fusion module includes a vehicle data fusion unit, a traffic flow feature fusion unit and a vehicle status fusion unit.

[0047] Function: The vehicle data fusion unit fuses vehicle data from different sources to obtain accurate vehicle location and status information; the traffic flow feature fusion unit fuses traffic flow feature data to obtain information such as the current actual traffic volume, driving speed, traffic density, queue length, etc.; the vehicle status fusion unit fuses vehicle status data to obtain information such as the location of the bus and its estimated arrival time at the intersection.

[0048] Traffic prediction module:

[0049] Structure: The traffic prediction module includes a real-time data processing unit and a historical data analysis unit.

[0050] Function: The real-time data processing unit combines real-time data and predicted data to predict the traffic flow at the intersection and its related sections; the historical data analysis unit predicts the traffic flow conditions in the future by analyzing a large amount of historical data, including parameters such as traffic volume, vehicle speed, traffic density, queue length, congestion and estimated arrival time of buses.

[0051] Traffic signal control module:

[0052] Structure: The traffic signal control module includes signal machine, RSU (roadside unit), OBU (on-board unit) and MEC (multi-access edge computing).

[0053] Function: The traffic light intervenes and adjusts the traffic signal in advance according to the data provided by the traffic prediction module; the RSU and OBU exchange data to transmit the relevant information of the bus and its traffic signal content; the MEC performs data fusion, feature fusion and state fusion on the data sampled by various detectors to restore the real situation of the intersection, and predicts the subsequent traffic flow at the intersection through the analysis of a large amount of historical feature data, and improves the traffic efficiency of buses by adjusting the early phase duration, early turning off of red lights, and extending green lights.

[0054] Bus priority control module:

[0055] Structure: The bus priority control module includes a phase adjustment unit, a speed suggestion unit and an information release unit.

[0056] Function: The phase adjustment unit adjusts the phase duration of the traffic signal according to the data provided by the traffic prediction module to reduce the number of stops and waiting time of the bus; the speed suggestion unit provides the driver with reasonable travel speed to the intersection and the remaining time of the subsequent phase switch to the corresponding information, the remaining time of the current green light and other phase-related information through RSU and OBU, so that the driver can increase or decrease the driving speed according to the prompt; the information release unit releases traffic signal information through RSU and OBU to remind drivers and pedestrians to pay attention to traffic conditions.

[0057] How the Optimal Technology Solution Works

[0058] Traffic flow data collected by the data collection module:

[0059] Structure: The traffic flow data collected by the data acquisition module include traffic parameters such as traffic volume, vehicle speed, traffic flow density and queue length.

[0060] Function: These data provide the basis for subsequent data processing and fusion, ensuring the comprehensiveness and accuracy of the data.

[0061] Three-level fusion of data fusion module:

[0062] Structure: The data fusion module performs three-level fusion on the collected data, including vehicle data fusion, traffic flow feature fusion and vehicle status fusion.

[0063] Function: The vehicle data fusion unit fuses vehicle data from different sources to obtain accurate vehicle location and status information; the traffic flow feature fusion unit fuses traffic flow feature data to obtain information such as the current actual traffic volume, driving speed, traffic density, queue length, etc.; the vehicle status fusion unit fuses vehicle status data to obtain information such as the location of the bus and its estimated arrival time at the intersection.

[0064] Traffic prediction module combines real-time data with historical data:

[0065] Structure: The traffic prediction module combines real-time data and historical data to predict the traffic flow conditions of the entire intersection within a short period of time.

[0066] Function: The real-time data processing unit combines real-time data and predicted data to predict the traffic flow at the intersection and its related sections; the historical data analysis unit predicts the traffic flow conditions in the future by analyzing a large amount of historical data, including parameters such as traffic volume, vehicle speed, traffic density, queue length, congestion and estimated arrival time of buses.

[0067] Data interaction and integration of traffic signal control modules:

[0068] Structure: The traffic signal control module transmits the bus-related information and traffic signal content through the interaction between RSU and OBU.

[0069] Function: MEC performs data fusion, feature fusion and state fusion on data sampled by various detectors to restore the real situation at the intersection. Through the analysis of a large amount of historical feature data, it predicts the subsequent traffic flow at the intersection and improves the traffic efficiency of buses by adjusting the early phase duration, early turning off of red lights, and extending green lights.

[0070] Phase adjustment and speed recommendations of the bus priority control module:

[0071] Structure: The bus priority control module optimizes the feasibility of buses passing through intersections at one time on a road section by adjusting the early phase duration, early red light interruption, and green light extension.

[0072] Function: The phase adjustment unit adjusts the phase duration of the traffic signal according to the data provided by the traffic prediction module to reduce the number of stops and waiting time of the bus; the speed suggestion unit provides the driver with reasonable travel speed to the intersection and the remaining time of the subsequent phase switch to the corresponding information, the remaining time of the current green light and other phase-related information through RSU and OBU, so that the driver can increase or decrease the driving speed according to the prompt.

[0073] Division of vehicle detection areas:

[0074] Structure: The bus priority control module divides the vehicle detection area into three areas: adjustable area, adjustment required area and confirmed adjustment area.

[0075] Function: Based on traffic flow conditions such as bus speed, current traffic density and current phase operation, the time it takes for a vehicle to pass through an intersection is predicted. If it is predicted that the vehicle can pass through, the phase duration is adjusted; if it cannot pass through, the corresponding phase duration is not adjusted to ensure that the bus can reduce the number of stops and waiting time.

[0076] Optimization algorithm superposition unit:

[0077] Structure: The bus priority control module includes an optimization algorithm superposition unit, which is used to optimize the bus priority release scheme several times by classifying the records of each optimization algorithm.

[0078] Function: The optimization algorithm superposition unit forms bus priority release strategies for different release directions and types through long-term accumulation, analysis and classification, ensuring the effectiveness and adaptability of the priority control plan.

[0079] Application technologies of each module:

[0080] Application technology of each module

[0081] Data acquisition module application technology: Electronic police, checkpoint equipment and monitoring equipment are road traffic auxiliary equipment set up in urban construction:

[0082] Electronic police: collect information about vehicles passing through intersections through cameras and sensors, and record data such as vehicle speed and license plate number.

[0083] Checkpoint equipment: installed on key roads, records the time and speed of vehicles passing by and provides traffic flow data.

[0084] Monitoring equipment: HD cameras monitor road conditions in real time and provide video streaming data for analyzing traffic density and queue lengths.

[0085] Radar and vision integrated device: Combines radar and vision sensors to provide high-precision vehicle position and speed data.

[0086] Vehicle-road system equipment: Communicates through the on-board unit (OBU) and the roadside unit (RSU) to obtain the vehicle's location and status information in real time.

[0087] Data processing module application technology:

[0088] Data cleaning unit: Use data cleaning algorithms to remove invalid and abnormal data to ensure the accuracy and completeness of data.

[0089] Data classification unit: Classify the data according to parameters such as traffic volume, vehicle speed, traffic flow density, queue length, etc. for subsequent analysis.

[0090] Data Analysis Unit: Use statistical analysis and machine learning algorithms to extract traffic flow characteristics such as traffic volume, vehicle speed, traffic density, queue length, etc.

[0091] Data fusion module application technology:

[0092] Vehicle data fusion unit: Uses data fusion algorithms, such as Kalman filtering or particle filtering, to fuse vehicle data from different sources to obtain accurate vehicle position and speed information.

[0093] Traffic flow feature fusion unit: Use multi-source data fusion technology, such as Bayesian network or neural network, to fuse traffic flow feature data to obtain current actual traffic volume, vehicle speed, traffic density, queue length and other information.

[0094] Vehicle state fusion unit: Combines vehicle data and traffic flow characteristic data, and uses data fusion algorithms such as data association and state estimation to obtain information such as the location of the bus and its estimated arrival time at the intersection.

[0095] Traffic prediction module application technology:

[0096] Real-time data processing unit: Use real-time data processing technologies, such as stream processing frameworks (such as Apache Kafka or Spark Streaming), to process and analyze traffic data in real time.

[0097] Historical data analysis unit: Use big data analysis technologies, such as Hadoop or Spark, to conduct in-depth analysis of historical data, extract traffic flow characteristics and patterns, and use them to predict future traffic conditions.

[0098] Traffic signal control module application technology:

[0099] Traffic signal: Through the intelligent traffic signal control system, the phase duration of the traffic signal is dynamically adjusted according to the data provided by the traffic prediction module.

[0100] RSU (Roadside Unit): It interacts with the on-board unit (OBU) through wireless communication technologies such as DSRC (Dedicated Short Range Communication) or 5G to transmit traffic signal information.

[0101] OBU (On-Board Unit): Installed on the bus, receives traffic signal information sent by RSU and provides it to the driver.

[0102] MEC (Multi-access Edge Computing): Perform data processing and analysis at edge nodes to reduce data transmission delays and improve response speed.

[0103] Bus priority control module application technology:

[0104] Phase adjustment unit: Uses intelligent algorithms, such as genetic algorithms or reinforcement learning, to dynamically adjust the phase duration of traffic signals based on the data provided by the traffic prediction module to optimize the travel efficiency of buses.

[0105] Speed ​​Advisory Unit: Through communication between RSU and OBU, it provides reasonable travel speed advice to the driver to help the driver adjust the driving speed.

[0106] Information release unit: Through RSU and OBU, traffic signal information is released, including the remaining time of the current green light, subsequent phase switching time, etc., to help drivers make reasonable driving decisions.

[0107] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The vehicle-road cooperative public transportation priority system based on multi-source data fusion is characterized by: Includes the following modules: A data collection module, which includes electronic police, checkpoint equipment, monitoring equipment, integrated radar and visual equipment, and vehicle-road system equipment, and is used to collect traffic flow data at intersections and related road sections; A data processing module, comprising a data cleaning unit, a data classification unit and a data analysis unit, for cleaning, classifying and analyzing the collected data and extracting traffic flow characteristics; A data fusion module, the data fusion module includes a vehicle data fusion unit, a traffic flow feature fusion unit and a vehicle status fusion unit, and is used to fuse vehicle data, traffic flow feature data and vehicle status data from different sources to obtain accurate vehicle location and status information; Traffic prediction module, the traffic prediction module includes a real-time data processing unit and a historical data analysis unit, which is used to combine real-time data and historical data to predict the traffic flow conditions and bus arrival time of the intersection and its related sections; Traffic signal control module, which includes a signal machine, RSU (roadside unit), OBU (on-board unit) and MEC (multi-access edge computing), and is used to intervene and adjust traffic signals in advance, reduce the parking and waiting time of buses at intersections, and optimize traffic efficiency; The bus priority control module includes a phase adjustment unit, a speed suggestion unit and an information release unit, which is used to adjust the phase duration of the traffic signal according to the data provided by the traffic prediction module, and provide the driver with a reasonable travel speed for reaching the intersection and the remaining time for subsequent switching to the corresponding information, the remaining time of the current green light and other phase-related information.

2. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 1 is characterized in that: The traffic flow data collected by the data collection module include traffic volume, vehicle speed, traffic flow density and traffic parameters of long queues.

3. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 2 is characterized in that: The data fusion module performs three-level fusion on the collected data, including vehicle data fusion, traffic flow feature fusion and vehicle status fusion, to obtain data on the current actual traffic volume at and near the intersection, driving speed, traffic density, queue length, traffic congestion status during driving time, traffic events, bus location and its estimated arrival time at the intersection.

4. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 3 is characterized in that: The traffic prediction module combines real-time data and historical data to predict the traffic flow conditions of the entire intersection within a short period of time, including traffic volume, vehicle speed, vehicle density, queue length, congestion and bus estimated arrival time parameters.

5. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 4 is characterized in that: The traffic signal control module transmits the relevant information of the bus and its traffic signal content through the interaction between the RSU and the OBU, and performs data fusion, feature fusion and state fusion on the data sampled by various detectors through the MEC.

6. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 5 is characterized in that: The bus priority control module optimizes the feasibility of buses passing through intersections on a road section at one time by adjusting the early phase duration, early red light off, and green light extension.

7. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 6 is characterized in that: The bus priority control module divides the vehicle detection area into three areas: an adjustable area, an area to be adjusted, and a confirmed adjustment area. It predicts the time it takes for a vehicle to pass the intersection based on traffic flow conditions such as the bus speed, current traffic density, and current phase operation conditions. If it is predicted to pass, the phase duration is adjusted; if it cannot pass, the corresponding phase duration is not adjusted to ensure that the bus can reduce the number of stops and waiting time.

8. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 7 is characterized in that: The bus priority control module includes an optimization algorithm superposition unit, which is used to optimize the bus priority release scheme several times by classifying the records of each optimization algorithm.

9. The vehicle-road cooperative public transportation priority system based on multi-source data fusion according to claim 8 is characterized in that: The optimization algorithm superposition unit forms bus priority release strategies of different release directions and types through long-term accumulation, analysis and classification.

Images