Traffic all-domain safety early warning system based on real-time safety information fusion technology

Abstract

Disclosed in the present invention is a traffic all-domain safety early warning system based on real-time safety information fusion technology, comprising a traffic all-domain big data cloud center, an onboard intelligent terminal OBU, an intelligent terminal having a client APP installed thereon, and a roadside unit RSU; the onboard intelligent terminal OBU is used for acquiring vehicle self-collected information serving as a first-layer information source; the roadside unit RSU is used for acquiring RSU information serving as a second-layer information source; the intelligent terminal having a client APP installed thereon is used for acquiring all-domain traffic information serving as a third-layer information source; and the traffic all-domain big data cloud center corrects the accuracy of dynamic traffic data comprising the vehicle self-collected information, an RSU information source and the all-domain traffic information, and fuses the corrected data into a unified traffic electronic map. The present invention ensures that all types of individuals entering the public traffic space can be detected in advance, thereby improving the information transparency and operation efficiency of the traffic system, and travel safety.

Description

Traffic safety early warning system based on real-time safety information fusion technology Technical Field

[0001] This invention relates to the field of traffic safety technology, and in particular to a traffic safety early warning system based on real-time safety information fusion technology. Background Technology

[0002] Advanced intelligent driving and vehicle-road cooperation require abundant multi-source dynamic data. Besides roadside traffic information sources (loop detectors, microwaves, video, radar), it's also necessary to incorporate the dynamic information of all people and vehicles moving within the public transportation environment into the intelligent transportation decision-making environment. Traditionally, traffic information is primarily obtained through direct collection, such as by relying on the active data collection functions of intelligent driving vehicles or roadside units (RSUs). This method forms the basic data foundation for current and future intelligent transportation and intelligent driving. However, to further promote the deepening of intelligent transportation or support the further development of vehicle-road cooperation, it is still necessary to improve the richness and accuracy of traffic information. Only when "all traffic information is under control" can ultimate safety be achieved, thereby supporting the implementation of intelligent transportation and intelligent driving.

[0003] The biggest problem with traditional proactive traffic information collection is the limited variety and scope of information, and the unavoidable identification errors (blind spots, short warning times, and significant impact from severe weather, etc.). This greatly limits the scope and extent of intelligent transportation and intelligent driving applications. By adopting appropriate methods to enable various traffic participants in the public transportation environment to proactively contribute real-time dynamic information and integrate it into the comprehensive traffic information space, the richness, scope, and quality of traditional traffic information sources can be improved, better serving future intelligent transportation application scenarios.

[0004] At present, personal smart devices (mobile phones, smart bracelets, etc.) and on-board units (OBU) are becoming increasingly popular, and have initially met the conditions to cover all mobile transportation individuals. In the future, the breadth and depth of the popularization of smart personal devices will be further enhanced.

[0005] Therefore, how to improve traffic efficiency and travel safety based on intelligent devices has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] In view of the above-mentioned deficiencies of the prior art, the present invention provides a traffic safety early warning system based on real-time security information fusion technology. The purpose is to ensure that all types of individuals (persons and vehicles) entering the public transportation space can be detected in advance and accurately based on the real-time synchronization (access) of mobile information (after de-identification processing) actively activated by intelligent devices. This improves the information transparency and operational efficiency of the traffic system, while also providing corresponding feedback information (real-time information of surrounding mobile traffic bodies and conflict warnings) to actively activated individuals, thereby improving traffic efficiency and travel safety.

[0007] To achieve the above objectives, this invention discloses a traffic safety early warning system based on real-time safety information fusion technology, including a traffic big data cloud center, an on-board unit (OBU), an intelligent terminal with a client APP installed, and a roadside unit (RSU).

[0008] The onboard unit (OBU) is used to acquire information collected by the vehicle itself as the first-layer information source, including traffic information directly acquired through various sensors of the vehicle and the driver's vision.

[0009] The Roadside Unit (RSU) is used to acquire Roadside RSU information as a second-layer information source, including surrounding traffic environment information provided by intelligent information devices within the road environment, specifically including road congestion, signal, and road network geographical environment information collected by roadside monitoring devices.

[0010] The smart terminal with the client APP installed is used to obtain the overall traffic information as the third layer of information source, including non-collected traffic information resources provided by various traffic individuals to the overall traffic environment through the application in the smart terminal.

[0011] The traffic big data cloud center corrects the accuracy of dynamic traffic data, including information collected by vehicles themselves, roadside RSU information sources, and traffic information across the entire region, and integrates it into a unified traffic electronic map.

[0012] Preferably, the various sensors of the vehicle itself include radar and / or cameras; the roadside monitoring equipment includes cameras, coils and / or radar; and the smart terminal with a client APP installed includes smartphones, tablets, smartwatches and / or smart bracelets.

[0013] More preferably, the comprehensive traffic information consists of anonymized BeiDou / GPS information, direction of movement information, and speed information uploaded by various traffic individuals, which are then aggregated into the comprehensive traffic information platform.

[0014] Preferably, the traffic big data cloud center includes a processing module, a simulation and prediction module, and an early warning information release module;

[0015] The processing module performs anonymization processing on the information uploaded by various traffic individuals in different regions, and processes the traffic motion data of various traffic individuals, including location, speed, and direction.

[0016] The simulation and prediction module performs short-term conflict simulation and prediction for various types of traffic individuals in different regions;

[0017] The early warning information dissemination module pushes various traffic conflict early warning information by region.

[0018] Preferably, the workflow is as follows:

[0019] Step 1: All the smart terminals with the client APP installed, and all the vehicle-mounted smart terminals (OBUs) upload their own dynamic traffic information to the traffic big data cloud center.

[0020] The intelligent terminal's own dynamic traffic information includes real-time location information, speed information, and direction information collected by the individual's smartphone, smart bracelet, and the vehicle-mounted intelligent terminal OBU;

[0021] The traffic big data cloud center obtains dynamic data on road traffic signals, cycles, and traffic volume from the roadside unit (RSU), and obtains static information related to spatial attributes from the traffic electronic map.

[0022] Step 2: Based on the regions or different blocks of the Roadside Units (RSUs) divided by the traffic big data cloud center, perform correction processing and map coordinate matching on various dynamic real-time traffic information according to the unified traffic electronic map information and coordinate system.

[0023] Step 3: Through the inference and prediction module, the status and risk of various types of traffic data after correction are predicted, and early warning or guidance information is generated.

[0024] Step 4: The warning or guidance information is published through the warning information publishing module to all smart terminals with client APP installed in each area that need to be reminded, as well as all vehicle-mounted smart terminals (OBUs), in the form of sound and graphics.

[0025] Preferably, step 2 is as follows:

[0026] Step 2.1: Obtain the direction vector data of each individual traffic vehicle based on the OBU accelerometer, gyroscope, and magnetometer of the smartphone, smart bracelet, and vehicle-mounted smart terminal OBU;

[0027] Furthermore, the latitude and longitude scatter information of each individual traffic vehicle is obtained based on the OBU satellite positioning signals of the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU.

[0028] Step 2.2: Based on the latitude and longitude scatter information of each traffic individual, determine the speed vector data of the OBU speed sensor of the smartphone, the smart bracelet and the vehicle-mounted smart terminal OBU based on the positioning information;

[0029] At the same time, the accuracy, continuity, and reliability of the latitude and longitude data itself are corrected based on the latitude and longitude scatter information of each individual traffic vehicle.

[0030] Step 2.3: Based on the direction vector data of each traffic individual and the speed vector data obtained by the OBU speed sensor of the smartphone, the smart bracelet and the vehicle-mounted smart terminal OBU, verify the result of correcting the accuracy, continuity and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual.

[0031] Step 2.4: Directly interpolate the verification results into the high-definition electronic map coordinate system;

[0032] Step 2.5: Based on the accurate locations of correction markers or fixed obstacles accumulated and calibrated in the electronic map, and the optimal traffic flow envelope channel fitted according to historical traffic flow statistics, verify the position, direction, and speed of dynamic traffic individuals interpolated into the high-definition electronic map coordinate system.

[0033] Step 2.6: Obtain the optimal position, direction, and speed information of individual traffic vehicles in real time, and then perform collision detection and prediction.

[0034] Preferably, in step 2.2, the method for correcting the accuracy, continuity, and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual is as follows: Preliminary data correction processing is performed on the latitude and longitude scatter information of the traffic individual to eliminate noise data and jump / drift points, and then correction is performed using the following formula: T′ i =T i ×A T′ ;

[0035] In the formula, T i It is the original discrete data; T′ i It is predicted data; A T′ It is the prediction transition matrix for discrete data;

[0036] COV lat It is the neighboring data in the dimensional data sequence. i and lat i-1 The covariance represents the predicted increment;

[0037] COV lon It is the neighboring data in the longitude data series.i T″ i and lon i-1 The covariance represents the predicted increment.

[0038] More preferably, in step 2.3, the method for verifying the accuracy, continuity, and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual is as follows: T″ i =T′ i ×A T″ ;

[0039] Among them, T″ i This is a further correction of the original data; A T″ This is the prediction transition matrix after further correction;

[0040] In the formula, foreLat and foreLon are the speeds measured by the software and chips of the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU, and the direction data decomposed into latitude and longitude.

[0041] The specific calculations are shown below.

[0042] Where θ represents the direction vector determined by the individual traffic participant. The angle between the line of latitude and the line of latitude; v represents the speed measured by the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU.

[0043] More preferably, in step 2.5, the method for verifying the position, direction, and speed of dynamic traffic individuals interpolated into the high-definition electronic map coordinate system is as follows: T″′ i =T″ i ×A T″′ +N;

[0044] In the formula, T″′ i This is the result of further correction; A T″′ N is the empirical trajectory transition matrix; N is the repulsion matrix of the accurate coordinate points or obstacles.

[0045] In the formula, ex lat The empirical correction increment is applied to the original dimensional data; ex lon It is the empirical correction increment of the original longitude data; ex lat =(lat i -lat 80％ ) / (lat i -lat mid ex lon =(lon) i-lon 80％ ) / (lon i -lon mid )

[0046] In the formula, lat i lon i It is the original latitude and longitude data; lat 80％ lon 80％ It is the boundary envelope data of latitude and longitude in historical data statistics; lat mid lon mid It is a weighted average of latitude and longitude data from historical data statistics;

[0047] In the formula, N is the influence parameter of the fixed obstacle; 2×10 -8 Errors caused by satellite chips in smartphones and smart bracelets; Lat j Lon j The fixed position of an obstacle j in an electronic map (including latitude and longitude); Let be the latitude and longitude radius boundary of the repulsion range of a fixed object j in an electronic map.

[0048] The beneficial effects of this invention are:

[0049] This invention is based on a real-time synchronization (access) system for mobile information (after de-identification processing) actively activated by intelligent devices, ensuring that all types of individuals (personal and vehicle) entering public transportation spaces can be detected in advance and accurately, improving the information transparency and operational efficiency of the transportation system. At the same time, it provides corresponding feedback information (real-time information on surrounding mobile traffic bodies and conflict warnings) to actively activated individuals, thereby improving traffic efficiency and travel safety.

[0050] The following will further explain the concept, specific structure, and technical effects of the present invention in conjunction with the accompanying drawings, so as to fully understand the purpose, features, and effects of the present invention. Attached Figure Description

[0051] Figure 1 shows a schematic diagram of the logical framework of a system according to an embodiment of the present invention.

[0052] Figure 2 shows the range of vehicle-to-everything (V2X) information collected by the first-layer information source obtained by the vehicle-mounted intelligent terminal (OBU) in an embodiment of the present invention.

[0053] Figure 3 shows the range of roadside RSU information acquired by the second-layer information source from the roadside unit RSU in one embodiment of the present invention.

[0054] Figure 4 shows the range of global traffic information from the third-layer information source obtained by a smart terminal with a client APP installed in one embodiment of the present invention.

[0055] Figure 5 shows a flowchart of step 2 of an embodiment of the present invention, which involves correcting various types of dynamic real-time traffic information and matching map coordinates.

[0056] Figure 6 shows a schematic diagram of an embodiment of the present invention, which corrects the accuracy, continuity and reliability of latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual.

[0057] Figure 7 shows a schematic diagram of the envelope distribution of historical discrete data for a certain road segment according to an embodiment of the present invention.

[0058] Figure 8 shows a schematic diagram of a road section after step 2 is completed according to an embodiment of the present invention. Detailed Implementation

[0059] Example

[0060] As shown in Figures 1 to 4, the traffic safety early warning system based on real-time safety information fusion technology includes a traffic big data cloud center, an on-board unit (OBU), an intelligent terminal with a client APP installed, and a roadside unit (RSU).

[0061] The onboard unit (OBU) is used to acquire information collected by the vehicle itself as the first-level information source, including traffic information directly obtained through various sensors on the vehicle and the driver's vision.

[0062] The Roadside Unit (RSU) is used to acquire roadside RSU information as a second-layer information source, including surrounding traffic environment information provided by intelligent information devices in the road environment, specifically including road congestion, signal and road network geographical environment information collected by roadside monitoring equipment;

[0063] Smart terminals with client apps installed are used to obtain comprehensive traffic information as a third-layer information source, including non-collected traffic information resources provided by various traffic individuals to the comprehensive traffic environment through applications in the smart terminals.

[0064] The traffic big data cloud center corrects the accuracy of dynamic traffic data, including information collected by vehicles themselves, roadside RSU information sources, and traffic information across the entire region, and integrates it into a unified traffic electronic map.

[0065] As shown in Figure 1, the graphics represent various terminals, the arrows represent data flow, and the text on the arrows represents key function processing.

[0066] By acquiring information such as the location, speed, and direction of pedestrians and motor vehicles through built-in satellite positioning systems (BeiDou / GPS), speed sensors, and direction sensors in devices such as mobile phones, wristbands, and vehicle OBUs, the system collects movement information of various traffic individuals by region to conduct short-term situational simulations and proposes a comprehensive traffic safety early warning system.

[0067] However, due to the relatively poor positioning accuracy of satellite positioning systems (BeiDou / GPS) in ordinary mobile phones and smartwatches, improvements in positioning accuracy, direction accuracy, and speed accuracy are needed when integrating them into intelligent transportation systems. This invention aims to improve data accuracy and reliability through algorithmic correction and map matching without increasing investment in hardware.

[0068] This invention utilizes existing mature satellite positioning information from mobile phones, wristbands, and vehicle OBUs, as well as other information such as acceleration, direction, and speed, to integrate into a unified traffic electronic map platform in an "actively activated" mode. It also enables real-time conflict monitoring and early warning analysis between various types of traffic entities (after anonymization processing), providing beyond-line-of-sight safety early warning services in the form of images and sounds for motor vehicles, non-motor vehicles, and pedestrians, thereby enhancing overall traffic safety.

[0069] For drivers and passengers, it provides information sources on beyond-line-of-sight movement trajectories and direction judgments for various types of traffic individuals. This not only allows for the early prediction of various traffic conflicts and expands the safety warning range of traditional line-of-sight or radar, but also provides a comprehensive dynamic traffic information foundation service for intelligent driving or "autonomous driving" of future vehicles.

[0070] For pedestrians and cyclists, it provides a safety warning service based on sound alerts (predicting the distance, speed, and direction of other traffic vehicles), improving traffic safety at intersections and other conflict points.

[0071] For traffic managers, by "aggregating" information on the movement status (location, speed, direction) of a wide range of individual traffic participants and integrating traffic information from roadside units (RSUs), the dynamic response speed and effectiveness of existing intelligent transportation equipment can be upgraded and expanded. Furthermore, by extending the functionality of software apps, they can further collect travel planning information such as the destinations and routes of drivers, passengers, and pedestrians. This allows them to provide richer and more accurate traffic guidance and intelligent driving services (vehicle-road cooperation, autonomous driving, etc.) to the public from the perspective of travel demand management.

[0072] In some embodiments, the vehicle's own sensors include radar and / or cameras; roadside monitoring equipment includes cameras, coils, and / or radar; and smart terminals with client apps installed include smartphones, tablets, smartwatches, and / or smart bracelets.

[0073] In some embodiments, the global traffic information consists of anonymized BeiDou / GPS information, direction of movement information, and speed information uploaded by various traffic individuals, which are then aggregated into the global traffic information platform.

[0074] In practical applications, the scope of the whole-domain traffic information can cover all public transportation environments, providing the richest and most reliable beyond-line-of-sight traffic information resources for intelligent traffic information decision-making.

[0075] In some embodiments, the traffic big data cloud center includes a processing module, a simulation and prediction module, and an early warning information dissemination module;

[0076] The processing module performs anonymization processing on the information uploaded by various traffic individuals in different regions, and processes the traffic motion data of various traffic individuals, including location, speed, and direction.

[0077] The simulation and prediction module simulates and predicts short-term conflicts for various traffic entities in different regions.

[0078] The early warning information dissemination module pushes various traffic conflict early warning information by region.

[0079] In some embodiments, the workflow is as follows:

[0080] Step 1: All smart terminals with client apps installed, as well as all vehicle-mounted smart terminals (OBUs), upload their own dynamic traffic information to the traffic big data cloud center.

[0081] The intelligent terminal's own dynamic traffic information includes real-time location information, speed information, and direction information collected by the smartphones, smart bracelets, and vehicle-mounted intelligent terminals (OBU) of individuals traveling on slow-moving traffic.

[0082] The traffic big data cloud center obtains dynamic data on road traffic signals, cycles, and traffic volume from roadside units (RSUs), and obtains static information related to spatial attributes from traffic electronic maps.

[0083] Step 2: Based on the regions or different roadside units (RSUs) divided by the traffic big data cloud center, and using a unified traffic electronic map information and coordinate system, perform correction processing and map coordinate matching on various dynamic real-time traffic information.

[0084] Step 3: Through the simulation and prediction module, the status and risk of various types of traffic data after correction are predicted, and early warning or guidance information is generated.

[0085] Step 4: Through the warning information release module, the warning or guidance information is released to all smart terminals with client APP installed in each area that need to be reminded, as well as all vehicle-mounted smart terminals (OBUs), in the form of sound and graphics.

[0086] Since satellite positioning data from mobile phones, smartwatches, and vehicle OBUs is the most basic and reliable data source (although its accuracy is not high), it can be used as the main basis for analysis. Most mobile phone software's built-in speed measurement functions estimate corresponding space travel speeds based on satellite positioning data, and this type of speed data can be extracted for verification.

[0087] In addition, mobile phones, smart bands, and vehicle OBUs also have chips such as accelerometers, gyroscopes, and magnetometers. Their data sources are independent of satellite positioning signals, and their related results can be used to verify and correct satellite positioning information.

[0088] Based on the above ideas, the main idea of ​​this data processing model is:

[0089] First, the system uses satellite positioning data reported by mobile phones, wristbands, and vehicle OBUs to correct the accuracy, continuity, and reliability of the latitude and longitude data itself.

[0090] Then, based on the speed and direction data measured by the mobile phone itself, the correction output is checked, and the check result is directly interpolated into the high-definition electronic map coordinate system.

[0091] Finally, based on the accurate locations of correction markers (or fixed obstacles) accumulated and calibrated in the electronic map, and the "optimal traffic flow envelope" fitted according to historical traffic flow statistics, the position, direction, and speed of the current dynamic traffic individuals are checked a third time. Ultimately, the optimal position, direction, and speed information of real-time traffic individuals are obtained, which is used for "fusion of comprehensive traffic safety information and conflict early warning."

[0092] In practical applications, firstly, various client apps upload their own dynamic traffic information to the traffic big data cloud center, including real-time location, speed, and direction information collected by individual pedestrians' mobile phones, wristbands, and vehicle-mounted OBUs. Simultaneously, the traffic big data cloud center obtains dynamic data on road traffic signals, cycles, and traffic volume from roadside units (RSUs), and static information related to spatial attributes from electronic traffic maps.

[0093] Then, the relevant (regional) big data cloud center or roadside edge system, based on the unified traffic electronic map information and coordinate system, uses the data processing model of this invention to correct and match various dynamic real-time traffic information and map coordinates.

[0094] Secondly, through the short-term simulation module, the status and risk of various types of traffic data after correction are predicted, and early warning or guidance information is generated.

[0095] Finally, the information dissemination module will release regional warnings or guidance information to the individual traffic users' apps in each region that need to be reminded, using sound, graphics, and other means to remind relevant traffic users and improve traffic safety and operational efficiency.

[0096] As shown in Figure 5, step 2 is as follows:

[0097] Step 2.1: Obtain the orientation vector data of each individual traffic vehicle based on the OBU accelerometer, gyroscope, and magnetometer of the smartphone, smart bracelet, and vehicle-mounted intelligent terminal OBU;

[0098] Furthermore, the latitude and longitude scatter information of each individual traffic vehicle is obtained based on the OBU satellite positioning signals from smartphones, smart bracelets, and vehicle-mounted intelligent terminals (OBUs).

[0099] Step 2.2: Based on the latitude and longitude scatter information of each traffic individual, determine the speed vector data of the OBU speed sensor of the smartphone, smart bracelet and vehicle intelligent terminal OBU based on the positioning information;

[0100] At the same time, the accuracy, continuity, and reliability of the latitude and longitude data itself are corrected based on the latitude and longitude scatter information of each individual traffic vehicle.

[0101] Step 2.3: Based on the direction vector data of each traffic individual and the speed vector data obtained from the OBU speed sensor of the smartphone, smart bracelet and vehicle intelligent terminal OBU, verify the result of correcting the accuracy, continuity and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual.

[0102] Step 2.4: Directly interpolate the verification results into the high-definition electronic map coordinate system;

[0103] Step 2.5: Based on the accurate locations of correction markers or fixed obstacles accumulated and calibrated in the electronic map, and the optimal traffic flow envelope channel fitted according to historical traffic flow statistics, verify the position, direction, and speed of dynamic traffic individuals interpolated into the high-definition electronic map coordinate system.

[0104] Step 2.6: Obtain the optimal position, direction, and speed information of individual traffic vehicles in real time, and then perform collision detection and prediction.

[0105] Ordinary civilian satellite positioning systems (such as BeiDou / GPS in mobile phones and smartwatches) have poor positioning accuracy and are prone to position and direction deviations, which can significantly interfere with the fusion and early warning effects. Without increasing investment in existing equipment hardware (which is expensive), the accuracy of various dynamic traffic data needs to be corrected first and then integrated into a unified electronic traffic map, thereby providing an accurate data foundation for traffic early warning.

[0106] In some embodiments, in step 2.2, the method for correcting the accuracy, continuity, and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each individual traffic is as follows: T′ i =T i ×A T′ ;

[0107] In the formula, T i It is the original discrete data; T′ i It is predicted data; A T′ It is the prediction transition matrix for discrete data;

[0108] COV lat It is the neighboring data in the dimensional data sequence. i and lat i-1 The covariance represents the predicted increment;

[0109] COV lon It is the neighboring data in the longitude data series. i T″ i and lon i-1 The covariance represents the predicted increment.

[0110] As shown in Figure 6, in practical applications, the positioning accuracy of ordinary civilian satellite positioning systems (such as Beidou / GPS in mobile phones and wristbands) is poor, and position and direction deviations are prone to occur. This is a discrete data information. By using the above-mentioned technical means for preliminary data correction processing, noise data and jump and drift points can be initially eliminated.

[0111] In some embodiments, the method for verifying the accuracy, continuity, and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual in step 2.3 is as follows: T″ i =T′ i ×A T″ ;

[0112] Among them, T″ i This is a further correction of the original data; A T″ This is the prediction transition matrix after further correction;

[0113] In the formula, foreLat and foreLon are the speeds measured by the software and chips of smartphones, smart bracelets, and in-vehicle smart terminals (OBU), and the direction data decomposed into latitude and longitude.

[0114] The specific calculations are shown below.

[0115] Where θ represents the direction vector determined by the individual traffic participant. The angle between the line of latitude and the line of latitude; v represents the speed measured by the OBU (On-Board Unit) of a smartphone, smart bracelet, or vehicle.

[0116] In practical applications, the accelerometers, gyroscopes, magnetometers, and other chips built into mobile phones, smart bands, and OBUs can independently predict and point the direction of movement of individual traffic vehicles, and therefore can be used to further verify the prediction results.

[0117] In some embodiments, the method for verifying the position, direction, and speed of dynamic traffic individuals interpolated to the high-definition electronic map coordinate system in step 2.5 is as follows: T″′ i =T″ i ×A T″′ +N;

[0118] In the formula, T″′ i This is the result of further correction; A T″′ N is the empirical trajectory transition matrix; N is the repulsion matrix of the accurate coordinate points or obstacles.

[0119] In the formula, ex lat The empirical correction increment is applied to the original dimensional data; ex lon It is the empirical correction increment of the original longitude data; ex lat =(lat i -lat 80％ ) / (lat i -lat mid ex lon =(lon) i -lon 80％ ) / (lon i -lon mid )

[0120] In the formula, lat i lon i It is the original latitude and longitude data; lat 80％ lon 80％ It is the boundary envelope data of latitude and longitude in historical data statistics; lat mid lon mid It is a weighted average of latitude and longitude data from historical data statistics;

[0121] In the formula, N is the influence parameter of the fixed obstacle; 2×10 -8 Errors caused by satellite chips in smartphones and smart bracelets; Lat j Lon jThe fixed position of an obstacle j in an electronic map (including latitude and longitude); Let be the latitude and longitude radius boundary of the repulsion range of a fixed object j in an electronic map.

[0122] As shown in Figures 7 and 8, based on the historical data of various traffic individual movement trajectories collected by mobile phones, wristbands, and OBUs for a certain road segment and a certain scenario, the probability envelope distribution of traffic flow in that road segment can be calculated, and then the scatter points of the real-time data can be corrected and optimized.

[0123] In addition, the electronic map coordinate system contains a series of accurate coordinate points (obstacles or reference points), which can be used to correct abnormal nodes in real-time data.

[0124] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A traffic safety early warning system based on real-time safety information fusion technology; characterized in that, This includes a comprehensive traffic big data cloud center, on-board units (OBU), smart terminals with client apps installed, and roadside units (RSU). The onboard unit (OBU) is used to acquire information collected by the vehicle itself as the first-layer information source, including traffic information directly acquired through various sensors of the vehicle and the driver's vision. The Roadside Unit (RSU) is used to acquire Roadside RSU information as a second-layer information source, including surrounding traffic environment information provided by intelligent information devices within the road environment, specifically including road congestion, signal, and road network geographical environment information collected by roadside monitoring devices. The smart terminal with the client APP installed is used to obtain the overall traffic information as the third layer of information source, including non-collected traffic information resources provided by various traffic individuals to the overall traffic environment through the application in the smart terminal. The traffic big data cloud center corrects the accuracy of dynamic traffic data, including information collected by vehicles themselves, roadside RSU information sources, and traffic information across the entire region, and integrates it into a unified traffic electronic map.

2. The traffic safety early warning system based on real-time safety information fusion technology according to claim 1, characterized in that, The vehicle's own sensors include radar and / or cameras; the roadside monitoring equipment includes cameras, coils, and / or radar; the smart terminal with a client APP installed includes smartphones, tablets, smartwatches, and / or smart bracelets.

3. The traffic safety early warning system based on real-time safety information fusion technology according to claim 2, characterized in that, The comprehensive traffic information consists of anonymized BeiDou / GPS information, direction of movement information, and speed information uploaded by various traffic individuals, which are then aggregated into the comprehensive traffic information platform.

4. The traffic safety early warning system based on real-time safety information fusion technology according to claim 1, characterized in that, The traffic big data cloud center includes a processing module, a simulation and prediction module, and an early warning information release module; The processing module performs anonymization processing on the information uploaded by various traffic individuals in different regions, and processes the traffic motion data of various traffic individuals, including location, speed, and direction. The simulation and prediction module performs short-term conflict simulation and prediction for various types of traffic individuals in different regions; The early warning information dissemination module pushes various traffic conflict early warning information by region.

5. The traffic safety early warning system based on real-time safety information fusion technology according to claim 1, characterized in that, The specific workflow is as follows: Step 1: All the smart terminals with the client APP installed, and all the vehicle-mounted smart terminals (OBUs) upload their own dynamic traffic information to the traffic big data cloud center. The intelligent terminal's own dynamic traffic information includes real-time location information, speed information, and direction information collected by the individual's smartphone, smart bracelet, and the vehicle-mounted intelligent terminal OBU; The traffic big data cloud center obtains dynamic data on road traffic signals, cycles, and traffic volume from the roadside unit (RSU), and obtains static information related to spatial attributes from the traffic electronic map. Step 2: Based on the regions or different blocks of the Roadside Units (RSUs) divided by the traffic big data cloud center, perform correction processing and map coordinate matching on various dynamic real-time traffic information according to the unified traffic electronic map information and coordinate system. Step 3: Through the inference and prediction module, the status and risk of various types of traffic data after correction are predicted, and early warning or guidance information is generated. Step 4: The warning or guidance information is published through the warning information publishing module to all smart terminals with client APP installed in each area that need to be reminded, as well as all vehicle-mounted smart terminals (OBUs), in the form of sound and graphics.

6. The traffic safety early warning system based on real-time safety information fusion technology according to claim 1, characterized in that, Step 2 is as follows: Step 2.1: Obtain the direction vector data of each individual traffic vehicle based on the OBU accelerometer, gyroscope, and magnetometer of the smartphone, smart bracelet, and vehicle-mounted smart terminal OBU; Furthermore, the latitude and longitude scatter information of each individual traffic vehicle is obtained based on the OBU satellite positioning signals of the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU. Step 2.2: Based on the latitude and longitude scatter information of each traffic individual, determine the speed vector data of the OBU speed sensor of the smartphone, the smart bracelet and the vehicle-mounted smart terminal OBU based on the positioning information; At the same time, the accuracy, continuity, and reliability of the latitude and longitude data itself are corrected based on the latitude and longitude scatter information of each individual traffic vehicle. Step 2.3: Based on the direction vector data of each traffic individual and the speed vector data obtained by the OBU speed sensor of the smartphone, the smart bracelet and the vehicle-mounted smart terminal OBU, verify the result of correcting the accuracy, continuity and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual. Step 2.4: Directly interpolate the verification results into the high-definition electronic map coordinate system; Step 2.5: Based on the accurate locations of correction markers or fixed obstacles accumulated and calibrated in the electronic map, and the optimal traffic flow envelope channel fitted according to historical traffic flow statistics, verify the position, direction, and speed of dynamic traffic individuals interpolated into the high-definition electronic map coordinate system. Step 2.6: Obtain the optimal position, direction, and speed information of individual traffic vehicles in real time, and then perform collision detection and prediction.

7. The traffic safety early warning system based on real-time safety information fusion technology according to claim 1, characterized in that, In step 2.2, the method for correcting the accuracy, continuity, and reliability of the latitude and longitude data based on the latitude and longitude scatter information of each traffic individual is as follows: Preliminary data correction processing is performed on the latitude and longitude scatter information of the traffic individual to eliminate noise data and jump / drift points, and then correction is performed using the following formula: T′ i =T i ×A T′ ; In the formula, T i It is the original discrete data; T′ i It is predicted data; A T′ It is the prediction transition matrix for discrete data; COV lat It is the neighboring data in the dimensional data sequence. i and lat i-1 The covariance represents the predicted increment; COV lon It is the neighboring data in the longitude data series. i T″ i and lon i-1 The covariance represents the predicted increment.

8. The traffic safety early warning system based on real-time safety information fusion technology according to claim 7, characterized in that, In step 2.3, the method for verifying the accuracy, continuity, and reliability of the latitude and longitude data itself based on the latitude and longitude scatter information of each traffic individual is as follows: T″ i =T′ i ×A T″ ; Among them, T″ i This is a further correction of the original data; A T″ This is the prediction transition matrix after further correction; In the formula, foreLat and foreLon are the speeds measured by the software and chips of the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU, and the direction data decomposed into latitude and longitude. The specific calculations are shown below. Where θ represents the direction vector determined by the individual traffic participant. The angle between the line of latitude and the line of latitude; v represents the speed measured by the smartphone, the smart bracelet, and the vehicle-mounted smart terminal OBU.

9. The traffic safety early warning system based on real-time safety information fusion technology according to claim 8, characterized in that, In step 2.5, the method for verifying the position, direction, and speed of dynamic traffic individuals interpolated into the high-definition electronic map coordinate system is as follows: T″′ i =T″ i ×A T″′ +N; In the formula, T″′ i This is the result of further correction; A T″′ N is the empirical trajectory transition matrix; N is the repulsion matrix of the accurate coordinate points or obstacles. In the formula, ex lat The empirical correction increment is applied to the original dimensional data; ex lon It is an empirical correction increment of the original longitude data; ex lat =(years i -years 80％ ) / (years i -years mid ) ex lon =(lon i -lon 80％ ) / (lon i -lon mid ) In the formula, lat i lon i It is the original latitude and longitude data; lat 80％ lon 80％ It is the boundary envelope data of latitude and longitude in historical data statistics; lat mid lon mid It is a weighted average of latitude and longitude data from historical data statistics; In the formula, N is the influence parameter of the fixed obstacle; 2×10 -8 Errors caused by satellite chips in smartphones and smart bracelets; Lat j Lon j The fixed position of an obstacle j in an electronic map (including latitude and longitude); Let be the latitude and longitude radius boundary of the repulsion range of a fixed object j in an electronic map.

Images