A vehicle abnormal position correction method, system, device and medium based on road network position information

Abstract

The application relates to a vehicle abnormal position correction method, system, device and medium based on road network position information, which comprises the following steps: collecting and processing road network map information, tracking vehicle position, and storing as a historical position point set; when the number of historical position points exceeds a set threshold, judging whether the vehicle is in an abnormal deviation state according to the scene where the vehicle is located and the relative position relationship with the road and the road section range; if the vehicle is in the abnormal deviation state, obtaining the latest position point from the historical position point set, predicting and covering the vehicle position; if the vehicle is not in the abnormal deviation state, identifying the front and rear position abnormal states; if the front and rear positions are identified as abnormal, obtaining the latest position point from the historical position point set, predicting and covering the vehicle position. The application fully utilizes and fuses various data sources, designs innovative judgment rules, and adopts a refined abnormal processing mode, so that the accuracy of vehicle position judgment and the refinement of abnormal processing are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, and in particular to a vehicle abnormal position correction method and system based on road network position information, a device and a medium. BACKGROUND

[0002] With the continuous progress of intelligent transportation systems, accurate monitoring and analysis of vehicle position information has become increasingly critical. Under the framework of digital twin technology, accurate display of vehicle position and precise calculation of trajectory indicators play an irreplaceable role in improving traffic management level, optimizing traffic planning and ensuring traffic safety. However, due to the complex and changeable actual traffic conditions, vehicle position data is often disturbed and abnormal, such as position deviation, trajectory reversal, data flashing, etc., which undoubtedly increases the difficulty of accurate monitoring and trajectory analysis.

[0003] Traditional solutions rely heavily on basic vehicle positioning technology and data analysis methods. These solutions often focus on real-time data processing, but fail to fully utilize historical data and geographic information, thereby limiting the accuracy and comprehensiveness of position determination. Although some solutions attempt to incorporate road information, due to their simple decision logic, they are difficult to handle diverse abnormal conditions. When dealing with abnormal data, these solutions usually choose to delete directly or perform simple data correction, which may result in loss or false reporting of key position information, thereby affecting the authenticity of the digital twin platform display and the accuracy of trajectory analysis.

[0004] In recent years, although some solutions have adopted artificial intelligence technologies such as deep learning, these models usually have high complexity, not only in implementation and maintenance, but also in high requirements for data quality and quantity. This leads to the limitations of such solutions in practical applications, such as high consumption of computing resources, long model training period, and strict dependence on data quality, making it difficult to be widely promoted and applied in actual traffic management. SUMMARY

[0005] (I) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present application provides a vehicle abnormal position correction method and system based on road network position information, a device and a medium, which solves the technical problems of insufficient data processing, simple abnormality identification, rough abnormality processing and limited application of artificial intelligence in vehicle position monitoring and analysis in the prior art.

[0007] (II) Technical solutions

[0008] In order to achieve the above-mentioned purposes, the main technical solutions adopted by the present application include:

[0009] In a first aspect, the embodiments of the present application provide a vehicle abnormal position correction method based on road network position information, comprising:

[0010] Collect and pre-process road network map information and store it in a database;

[0011] Track the vehicle position using a detection device and store it as a set of historical position points of the vehicle;

[0012] When the number of historical position points of the vehicle exceeds a set threshold, determine whether the vehicle is in an abnormal deviation state according to the scene in which the vehicle is located and the relative position relationship with the road and the road segment range obtained from the road network map information;

[0013] If the vehicle is in an abnormal deviation state, obtain the latest position point from the set of historical position points, and predict and cover the vehicle position by calculating the historical longitude speed and latitude speed of the vehicle;

[0014] If the vehicle is not in an abnormal deviation state, perform front and rear position abnormality recognition of the vehicle based on a preset threshold and obtained vehicle driving state data;

[0015] If the vehicle is recognized as having abnormal front and rear positions, obtain the latest position point from the set of historical position points, and predict and cover the vehicle position by calculating the longitude speed and latitude speed of the vehicle.

[0016] Optionally, collecting and pre-processing road network map information and storing it in a database comprises:

[0017] Extract road network map information containing road information, road segment information, lane information, and lane center line information from map data;

[0018] Filter and pre-process the collected road network map information to remove duplicate, invalid, or erroneous data;

[0019] Establish a data table structure for storage in the database, and import the pre-processed road network map information into the database according to the data table structure;

[0020] Among them,

[0021] The road information includes a road number and a road range composed of a set of longitude and latitude coordinate points, the road range includes a motor lane, a non-motor lane, and a green belt, and the road range contains at least one road segment;

[0022] The road segment information includes a road segment number, a road number of the road to which it belongs, and a road segment range composed of a set of longitude and latitude coordinate points, the road segment range is limited to a motor lane, and contains at least one lane;

[0023] Lane information includes lane number, road segment number, and lane range consisting of a set of latitude and longitude coordinates. Each lane range has a unique corresponding lane centerline.

[0024] Lane centerline information includes the lane centerline number, the lane number of the lane to which it belongs, and a set of latitude and longitude coordinates from the start point to the end point of the lane. The lane centerline consists of one or more line segments connected in sequence.

[0025] Optionally, the vehicle's location is tracked using detection equipment and stored as a set of the vehicle's historical location points, including:

[0026] The detection equipment continuously tracks the position of the target vehicle at set time intervals;

[0027] Whenever a new vehicle location is detected, vehicle location data including the location's longitude, latitude, and the detection time is recorded;

[0028] The vehicle location data is organized into a historical location set of the vehicle according to the detection time and stored in the database.

[0029] Optionally, when the number of historical location points of a vehicle exceeds a set threshold, the system determines whether the vehicle is in an abnormal deviation state based on the vehicle's location and its relative position to roads and road segments obtained from the road network map information.

[0030] When the number of historical location points of a vehicle exceeds a set threshold, the vehicle's current location is obtained.

[0031] Determine whether the vehicle's current location is within the road area;

[0032] If the vehicle is not currently located within the road area, further judgment will be made based on the scene in which the vehicle is located, as determined by the preset scene labels.

[0033] If the vehicle is in a closed road scenario that includes highways and tunnels, the vehicle's position will be marked as abnormal deviation.

[0034] If the scene is an urban road scene, then mark the vehicle position as normal.

[0035] If the vehicle's current location is within the road area, then further determine whether the vehicle's current location is within the road segment area;

[0036] If the vehicle is currently within the road segment, then mark the vehicle's position as normal.

[0037] If the vehicle's current location is outside the road segment and the vehicle is in a closed road scenario that includes highways and tunnels, then the vehicle's location will be marked as normal.

[0038] If the current time vehicle position is not in the range of the road section, and the vehicle is in an urban road scene, it is further judged whether the last time vehicle position is in the range of the road section;

[0039] If the last time vehicle position is in the range of the road section, the vehicle position is marked as an abnormal deviation state;

[0040] If the last time vehicle position is not in the range of the road section, the vehicle position is marked as a normal state.

[0041] Optionally, if the vehicle is in an abnormal deviation state, the latest position point is obtained from the historical position point set, and the vehicle position is predicted and covered by calculating the historical longitude speed and latitude speed of the vehicle, comprising:

[0042] If the vehicle is in an abnormal deviation state, one or more latest position points are automatically selected from the historical position point set to form a position point sub-set;

[0043] In the position point sub-set, adjacent position point pairs are selected in turn, and the longitude speed and latitude speed between each adjacent position point pair are calculated according to the longitude of the position point, the latitude of the position point and the detection time of the position point in the historical position point set;

[0044] All longitude speeds calculated are averaged to obtain the average value of the longitude speed, and all latitude speeds are averaged to obtain the average value of the latitude speed;

[0045] The obtained average value of the longitude speed and the average value of the latitude speed are used to obtain the predicted longitude and latitude position of the vehicle at the current time, combined with the time difference between the last time of the vehicle position and the current time, and used to cover the original current time vehicle position;

[0046] Wherein, the predicted longitude and latitude position is:

[0047]

[0048]

[0049] In the formula, lon' n+1 , lat' n+1 are the predicted longitude position and latitude position respectively, lon n , lat n are the longitude position and latitude position of the last vehicle position respectively, v lon , v lat are the average value of the longitude speed and the average value of the latitude speed respectively, t n+1 is the current time, and t n is the time of the last vehicle position.

[0050] Optionally, if the vehicle is not in an abnormal deviation state, the front and rear position abnormal state recognition of the vehicle based on the preset threshold and the obtained vehicle driving state data comprises:

[0051] According to the vehicle position at the current time and the vehicle position at the last time, the longitude and latitude of the front and rear positions of the vehicle, the lane center line heading angle of the lane where the vehicle is located are obtained, and the vehicle heading angle and the vehicle driving distance are calculated based on the front and rear position coordinates to form a vehicle driving state data set;

[0052] If the vehicle driving distance does not exceed the distance threshold, the vehicle is considered to be stationary;

[0053] If the vehicle driving distance exceeds the distance threshold, the front and rear position abnormal state recognition of the vehicle is performed according to the vehicle driving state data set as follows:

[0054] When the angle change between the lane center line heading angle of the lane where the vehicle is located at the current time and the lane center line heading angle at the last time exceeds the preset deviation threshold, it is determined that the vehicle has an abnormal deviation;

[0055] When the angle deviation between the lane center line heading angle at the last time and the vehicle heading angle exceeds the preset reverse threshold, it is determined that the vehicle has an abnormal reverse;

[0056] When the vehicle driving distance within the preset time interval exceeds the preset flashing threshold, it is determined that the vehicle has an abnormal flashing.

[0057] Optionally, according to the vehicle position at the current time and the vehicle position at the last time, the longitude and latitude of the front and rear positions of the vehicle, the lane center line heading angle of the lane where the vehicle is located are obtained, and the vehicle heading angle and the vehicle driving distance are calculated based on the front and rear position coordinates to form a vehicle driving state data set, which comprises:

[0058] The vehicle position at the current time containing longitude and latitude is obtained and recorded as the first data item of the vehicle driving state data set;

[0059] According to the road network map information, the lane center line of the lane where the vehicle is located at the current time is determined, and the angle between the lane polyline of the lane center line and the north direction line is calculated to obtain the lane center line heading angle, which is recorded as the second data item of the vehicle driving state data set;

[0060] The vehicle position at the last time containing longitude and latitude is obtained and recorded as the third data item of the vehicle driving state data set;

[0061] According to the road network map information, the lane center line of the lane where the vehicle is located at the last time is determined, and the angle between the lane polyline of the lane center line and the north direction line is calculated to obtain the lane center line heading angle at the last time, which is recorded as the fourth data item of the vehicle driving state data set;

[0062] The vehicle heading angle is obtained by calculating the included angle between the line connecting the vehicle position at the last time and the vehicle position at the current time and the line in the north direction, and recorded as the fifth data item of the vehicle driving state data set;

[0063] The vehicle driving distance is obtained by calculating the straight-line distance between the vehicle position at the last time and the vehicle position at the current time, and recorded as the sixth data item of the vehicle driving state data set.

[0064] In a second aspect, an embodiment of the present application provides a vehicle abnormal position correction system based on road network position information, comprising:

[0065] A collection and processing module is configured to collect and pre-process road network map information and store the information in a database;

[0066] A position tracking module is configured to track the vehicle position by using a detection device and store the position as a historical position point set of the vehicle;

[0067] An abnormal deviation judgment module is configured to, when the number of historical position points of the vehicle exceeds a set threshold, judge whether the vehicle is in an abnormal deviation state according to the scene in which the vehicle is located and the relative position relationship with the road and the road section range obtained from the road network map information;

[0068] An abnormal processing module is configured to, if the vehicle is in an abnormal deviation state, obtain the latest position point from the historical position point set, predict and cover the vehicle position by calculating the historical longitude speed and latitude speed of the vehicle;

[0069] A normal processing module is configured to, if the vehicle is not in an abnormal deviation state, perform front and rear position abnormality identification of the vehicle based on a preset threshold and the obtained vehicle driving state data;

[0070] A front and rear position abnormality processing module is configured to, if the vehicle is identified as having front and rear position abnormality, obtain the latest position point from the historical position point set, predict and cover the vehicle position by calculating the longitude speed and latitude speed of the vehicle.

[0071] In a third aspect, an embodiment of the present application provides a vehicle abnormal position correction device based on road network position information, comprising at least one database and a memory in communication connection with the at least one database; wherein the memory stores instructions executable by the at least one database, and the instructions are executed by the at least one database to enable the at least one database to perform the vehicle abnormal position correction method based on road network position information as described above.

[0072] In a fourth aspect, an embodiment of the present application provides a computer readable medium having computer executable instructions stored thereon, and the executable instructions are executed by a processor to implement the vehicle abnormal position correction method based on road network position information as described above.

[0073] (III) Beneficial Effects

[0074] The beneficial effects of the present application are:

[0075] Firstly, the present application realizes comprehensive and accurate grasp of the vehicle position by collecting and preprocessing road network map information and tracking the vehicle position with detection equipment. This not only relies on real-time vehicle position data, but also integrates rich historical data and geographic information, providing a solid foundation for subsequent anomaly judgment, and effectively avoiding misjudgment caused by insufficient data utilization.

[0076] Further, when the number of historical position points of the vehicle exceeds the set threshold, the present application can accurately judge the abnormal deviation state by combining the scene where the vehicle is located and its relative position relationship with the road and road segment range in the road network map information. This refined judgment logic significantly improves the reliability and stability of the system, effectively overcoming the drawbacks of overly simple judgment rules in the prior art.

[0077] In terms of abnormality processing, the present application also performs outstandingly. Once it detects that the vehicle is in an abnormal deviation state or has abnormal positions before and after, it immediately obtains the latest position point from the historical position point set and predicts and covers the vehicle position by calculating the latitude and longitude speed of the vehicle. This processing method not only avoids information loss and errors caused by directly discarding or simply correcting abnormal data, but also ensures the accuracy of the display effect of the digital twin platform and the calculation of trajectory indicators, and also improves the roughness of existing abnormality processing methods.

[0078] It is worth mentioning that although the present application shows high refinement and intelligence in abnormality judgment and processing, its implementation is relatively simple and practical. This is due to the unique data fusion mechanism and innovative judgment rule design, which enables the present application to avoid the limitations brought by complex artificial intelligence models while still maintaining excellent performance.

[0079] Therefore, the present application proposes to fully utilize and integrate multiple data sources, design innovative judgment rules, and adopt a refined abnormality processing method, which significantly improves the accuracy of vehicle position judgment and the refinement of abnormality processing, providing strong support for the development and application of intelligent transportation systems. BRIEF DESCRIPTION OF DRAWINGS

[0080] Figure 1 A flowchart of a vehicle abnormal position correction method based on road network position information provided for an embodiment of the present application;

[0081] Figure 2 A specific flowchart of step S1 of a vehicle abnormal position correction method based on road network position information provided for an embodiment of the present application;

[0082] Figure 3 A specific flowchart of step S2 of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0083] Figure 4 A specific flowchart of step S3 of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0084] Figure 5 A vehicle abnormal deviation state recognition flowchart of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0085] Figure 6 A specific flowchart of step S4 of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0086] Figure 7 A vehicle abnormal deviation schematic diagram of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0087] Figure 8 A vehicle abnormal reverse schematic diagram of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0088] Figure 9 A vehicle abnormal flashing schematic diagram of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure;

[0089] Figure 10 A whole flowchart of the vehicle abnormal position correction method based on road network position information provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0090] In order to better explain the present application, so as to be understood, the present application is described in detail by specific embodiments in combination with the accompanying drawings.

[0091] Before that, in order to facilitate understanding of the technical solutions provided by the present application, some concepts are introduced first.

[0092] Lane center line heading angle: the angle between the line from the starting point to the ending point of the lane center line and the north direction is the lane center line heading angle;

[0093] Vehicle heading angle: the angle between the line from the front position to the rear position of the vehicle and the north direction is the vehicle heading angle;

[0094] Car following model: a model that predicts the position of a vehicle based on the speed and position data of the preceding and following vehicles.

[0095] As shown in Figure 1 The abnormal position correction method for vehicles based on road network position information provided by the embodiment of the present application includes: collecting and preprocessing road network map information and storing it in a database; tracking the position of a vehicle by using a detection device and storing it as a historical position point set of the vehicle; when the number of historical position points of the vehicle exceeds a set threshold, judging whether the vehicle is in an abnormal deviation state according to the scene in which the vehicle is located and the relative position relationship with the road and section range obtained from the road network map information; if the vehicle is in an abnormal deviation state, obtaining the latest position point from the historical position point set, predicting and covering the position of the vehicle by calculating the historical longitude speed and latitude speed of the vehicle; if the vehicle is not in an abnormal deviation state, identifying the front and rear position abnormal states of the vehicle based on a preset threshold and obtained vehicle driving state data; if the vehicle is identified as having a front and rear position abnormality, obtaining the latest position point from the historical position point set, predicting and covering the position of the vehicle by calculating the longitude speed and latitude speed of the vehicle.

[0096] Firstly, the present application realizes comprehensive and accurate grasp of the position of the vehicle by collecting and preprocessing road network map information and tracking the position of the vehicle by using a detection device. This not only relies on real-time vehicle position data, but also integrates rich historical data and geographic information, providing a solid foundation for subsequent abnormal judgment, and effectively avoiding misjudgment caused by insufficient use of data.

[0097] Further, when the number of historical position points of the vehicle exceeds a set threshold, the present application can accurately judge the abnormal deviation state in combination with the scene in which the vehicle is located and the relative position relationship with the road and section range in the road network map information. This refined judgment logic significantly improves the reliability and stability of the system, effectively overcoming the drawbacks of overly simple judgment rules in the prior art.

[0098] In terms of abnormal processing, the present application also performs well. Once it is detected that the vehicle is in an abnormal deviation state or has a front and rear position abnormality, the latest position point is immediately obtained from the historical position point set, and the position of the vehicle is predicted and covered by calculating the longitude and latitude speed of the vehicle. This processing method not only avoids information loss and errors caused by directly discarding or simply correcting abnormal data, but also ensures the display effect of the digital twin platform and the accuracy of the trajectory index calculation, and also improves the roughness problem of the existing abnormal processing method.

[0099] It is worth mentioning that, although the present application shows high refinement and intelligence in anomaly judgment and processing, its implementation is relatively simple and practical. This is due to the unique data fusion mechanism and innovative decision rule design, which makes the present application avoid the limitations brought by complex artificial intelligence models while still maintaining excellent performance.

[0100] Therefore, the present application proposes to significantly improve the accuracy of vehicle position judgment and the refinement of abnormal processing by fully utilizing and fusing multiple data sources, designing innovative decision rules and adopting refined abnormal processing methods, providing strong support for the development and application of intelligent transportation systems.

[0101] In order to better understand the above technical solutions, the exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer, more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0102] Specifically, the embodiment of the present application provides a vehicle abnormal position correction method based on road network position information, comprising:

[0103] S1, collecting and preprocessing road network map information and storing it in a database.

[0104] Further, as shown in Figure 2 , step S1 includes:

[0105] S11, extracting road network map information containing road information, road segment information, lane information and lane center line information from map data.

[0106] It should be noted that the road network map information containing road information, road segment information, lane information and lane center line information is not only extracted from high-precision maps, but also can be extracted from various sources such as open maps and virtual maps. These map data provides rich road network details, including detailed information of roads, road segments, lanes and lane center lines, providing an important foundation for building a comprehensive and accurate road network map. By comprehensively utilizing these diversified map resources, the required road network map information can be obtained more flexibly to adapt to different application scenarios and needs.

[0107] S12, screening and preprocessing the collected road network map information to remove duplicate, invalid or erroneous data.

[0108] S13, establish a data table structure for storage in the database, and import the pretreated road network map information into the database according to the data table structure.

[0109] Specifically, the road information includes a road number and a road range composed of a set of longitude and latitude coordinate points, the road range includes a motor vehicle lane, a non-motor vehicle lane and a green belt, and the road range contains at least one road section; the road section information includes a road section number, a road number of the road to which the road section belongs, and a road section range composed of a set of longitude and latitude coordinate points, the road section range is limited to a motor vehicle lane, and contains at least one lane; the lane information includes a lane number, a road section number of the road section to which the lane belongs, and a lane range composed of a set of longitude and latitude coordinate points, each lane range has a unique corresponding lane center line; the lane center line information includes a lane center line number, a lane number of the lane to which the lane center line belongs, and a set of longitude and latitude coordinate points from the starting point to the ending point of the lane, and the lane center line is composed of one or more connected line segments.

[0110] S2, track the position of the vehicle using a detection device, and store as a set of historical position points of the vehicle.

[0111] Further, as shown in Figure 3 , step S2 includes:

[0112] S21, track the position of the target vehicle using the detection device at a set time interval.

[0113] S22, record the vehicle position data containing the longitude of the position point, the latitude of the position point and the detection time of the position point whenever a new position of the vehicle is detected.

[0114] S23, arrange the vehicle position data in sequence according to the detection time to form a set of historical position points of the vehicle, and store in the database.

[0115] In the embodiment of the application, the position of the vehicle is tracked at a time interval Δt using a camera, a radar and the like detection device, and the position history data of the vehicle is stored in the database. The set of historical position points of each vehicle M is P={P0,...P n}.

[0116] S3, when the number of historical position points of the vehicle exceeds a set threshold, determine whether the vehicle is in an abnormal deviation state according to the scene in which the vehicle is located and the relative position relationship with the road and the road section range obtained from the road network map information.

[0117] Further, as shown in Figure 4 , step S3 includes:

[0118] S31, when the number of historical position points of the vehicle exceeds a set threshold, obtain the position of the vehicle at the current time.

[0119] S32, judge whether the vehicle position at the current time is in the road range.

[0120] S33a, if the vehicle position at the current time is not in the road range, further judge according to the scene where the vehicle is located. Specifically, the scene where the vehicle is located is classified according to the project category. If it is a closed road scene such as a tunnel, an elevated road, an expressway, and a national road, it is a closed road scene. If it is a road with intersections in the city, it is a city road scene, and the scene label is set as a parameter in advance.

[0121] If the vehicle is in a closed road scene including a highway and a tunnel, the vehicle position is marked as an abnormal deviation state. If the scene is a city road scene, the vehicle position is marked as a normal state. Wherein, the scene where the vehicle belongs is judged according to the object of the project. If it is a closed road scene such as a tunnel, an elevated road, an expressway, and a national road, it is a closed road scene. If it is a road with intersections in the city, it is a city road scene.

[0122] S33b, if the vehicle position at the current time is in the road range, further judge whether the vehicle position at the current time is in the road section range.

[0123] S34, if the vehicle position at the current time is in the road section range, the vehicle position is marked as a normal state. If the vehicle position at the current time is not in the road section range, and the scene where the vehicle is located is a closed road scene including a highway and a tunnel, the vehicle position is marked as a normal state. If the vehicle position at the current time is not in the road section range, and the scene where the vehicle is located is a city road scene, further judge whether the vehicle position at the last time is in the road section range. If the vehicle position at the last time is in the road section range, the vehicle position is marked as an abnormal deviation state. If the vehicle position at the last time is not in the road section range, the vehicle position is marked as a normal state.

[0124] In an embodiment, referring to Figure 5 , the vehicle abnormal deviation state recognition specifically includes the following steps:

[0125] Judge whether the vehicle position P n+1 at the current time is in the road range.

[0126] If the vehicle position P n+1 at the current time is not in the road range, the vehicle position is marked as an abnormal deviation state under the closed road scene such as a highway and a tunnel.

[0127] If the vehicle position P n+1 at the current time is not in the road range, the vehicle position is marked as a normal state under the city road scene to avoid abnormal road conditions such as left turn and tunnel.

[0128] If the vehicle position P n+1 at the current time is in the road range, judge whether the vehicle position Pn+1 whether the position point P is within the range of the road segment.

[0129] judging the position point P n+1 whether the position point P is within the range of the road segment.

[0130] if the vehicle position P n+1 within the range of the road segment, the vehicle position is marked as normal state.

[0131] if the vehicle position P n+1 not within the range of the road segment, and in the closed road scene such as high speed, tunnel, etc., to avoid the vehicle driving in the emergency lane under the closed road, the vehicle position is marked as normal state.

[0132] if the position point P is not within the range of the road segment, and in the urban road scene, judging the vehicle position point P n whether the position point P is within the range of the road segment.

[0133] judging the vehicle position point P n whether the position point P is within the range of the road segment.

[0134] if the vehicle position point P is within the range of the road segment, the vehicle position is marked as abnormal deviation state.

[0135] if the vehicle position point P is not within the range of the road segment, the vehicle position is marked as normal state.

[0136] S4, if the vehicle is in the abnormal deviation state, the latest position point is obtained from the historical position point set, and the vehicle position is predicted and covered by calculating the historical longitude speed and latitude speed of the vehicle.

[0137] Further, as shown in Figure 6 , step S4 includes:

[0138] S41, if the vehicle is in the abnormal deviation state, one or more latest position points are automatically selected from the historical position point set to form a position point sub-set.

[0139] S42, in the position point sub-set, adjacent position point pairs are selected in turn, and the longitude speed and latitude speed between each pair of adjacent position points are calculated according to the longitude of the position point, the latitude of the position point and the detection time of the position point in the historical position point set.

[0140] S43, all the longitude speeds calculated are averaged to obtain the average value of the longitude speed, and all the latitude speeds are averaged to obtain the average value of the latitude speed.

[0141] S44. Using the obtained average longitude and average latitude speeds, combined with the time difference between the vehicle's previous location and the current time, the predicted longitude and latitude position of the vehicle at the current time is obtained and used to cover the original current vehicle position.

[0142] In another embodiment, the vehicle's latest latitude and longitude position p' is predicted. n+1 The description includes the following steps:

[0143] Obtain the latest m location points from the historical vehicle location set P to form a set PM, where m can be 5.

[0144] Calculate the adjacent points PM in the set PM in sequence. i With PM i+1 Longitude and speed v i,lon With latitude velocity v i,lat That is: v i,lon =(lon) i+1 -lon i ) / (t i+1 -t i ),v i,lat =(lat i+1 -lat i ) / (t i+1 -t i ).

[0145] Calculate the average longitude and velocity at m locations. Average speed at latitude

[0146] Calculate the vehicle's latest latitude and longitude position p' n+1 ,Right now t n+1 For the current time, t n This refers to the time at the vehicle's previous location. n lat n The longitude and latitude of the vehicle's location are given respectively.

[0147] S5a. If the vehicle is not in an abnormal deviation state, identify abnormal states of the vehicle's front and rear positions based on preset thresholds and acquired vehicle driving status data.

[0148] Furthermore, such as Figure 7 As shown, step S5a includes:

[0149] S5a1. Based on the vehicle's current position and the vehicle's position at the previous moment, obtain the longitude, latitude, and lane centerline heading angle of the vehicle's front and rear positions, and calculate the vehicle's heading angle and travel distance by combining the front and rear position coordinates to form a vehicle driving status data set.

[0150] Furthermore, step S5a1 includes: obtaining the current vehicle position, including longitude and latitude, and recording it as a first data item in the vehicle driving state data set; determining the lane centerline of the lane where the vehicle is located at the current time based on road network map information, and calculating the angle between the lane break line of the lane centerline and the due north direction line to obtain the lane centerline heading angle, and recording it as a second data item in the vehicle driving state data set; obtaining the vehicle position at the previous time, including longitude and latitude, and recording it as a third data item in the vehicle driving state data set; determining the previous time... The vehicle's position is located in the lane centerline, and the angle between the lane centerline break and the north direction line is calculated to obtain the lane centerline heading angle at the previous moment, which is recorded as the fourth data item in the vehicle driving status data set; the vehicle heading angle is obtained by calculating the angle between the line connecting the vehicle position at the previous moment and the current moment and the north direction line, which is recorded as the fifth data item in the vehicle driving status data set; the vehicle travel distance is obtained by calculating the straight-line distance between the vehicle position at the previous moment and the current moment, which is recorded as the sixth data item in the vehicle driving status data set.

[0151] In a specific embodiment, each data item is represented as follows:

[0152] 1) Vehicle's current position P at time t n+1 coordinates (lon) n+1 ,lat n+1 (includes longitude and latitude).

[0153] 2) Vehicle's current position P at time t n+1 The lane centerline heading angle of the lane in which it is located n+1 The lane centerline heading angle is the angle between the lane break line and the due north direction, which is calculated from the lane centerline information in the road network map.

[0154] 3) The vehicle's position point P at the previous time t-Δt n coordinates (lon) n ,lat n (includes longitude and latitude).

[0155] 4) The vehicle's position point P at the previous time t-Δt n The lane centerline heading angle of the lane in which it is located n .

[0156] 5) Vehicle heading angle θ n,n+1 Let P be the vehicle's previous position. n With the current position point P n+1 Connect P n Pn+1 The angle with the north direction.

[0157] 6) The vehicle driving distance dis n,n+1 The position point P of the vehicle at the last time n The position point P of the vehicle at the current time n+1 The line P n P n+1 The length.

[0158] S5a2, if the vehicle driving distance does not exceed the distance threshold, it is considered that the vehicle is stationary. If the vehicle driving distance exceeds the distance threshold, according to the vehicle driving state data set, the following vehicle front and rear position abnormal state recognition is performed: when the angle change between the vehicle current time and the last time lane center line heading angle of the lane where the vehicle is located exceeds the preset deviation threshold, it is determined that the vehicle has abnormal deviation. When the angle deviation between the vehicle last time lane center line heading angle and the vehicle heading angle exceeds the preset reverse threshold, it is determined that the vehicle has abnormal reverse. When the vehicle driving distance within the preset time interval exceeds the preset flash threshold, it is determined that the vehicle has abnormal flash.

[0159] In still another embodiment, the vehicle abnormal deviation recognition: the vehicle deviates to the opposite lane or other lane in a short time, the lane where the vehicle is located changes greatly, and the schematic diagram is shown in Figure 7 The angle change between the vehicle last time and the vehicle current time lane center line heading angle exceeds the threshold θ change , which can be 120°, that is, |angle n - angle n+1 | ≥ θ change .

[0160] Vehicle abnormal reverse recognition: the vehicle appears behind the vehicle last time position point in a short time, and the schematic diagram is shown in Figure 8 The angle deviation between the vehicle last time lane center line heading angle angle n and the vehicle heading angle θ n,n+1 exceeds the threshold θ back , which can be 90°, that is, |angle n - θ 01 | > θ back .

[0161] Vehicle abnormal flash recognition: the vehicle appears far ahead of the vehicle last time position point in a short time, and the schematic diagram is shown in Figure 9 The vehicle driving distance exceeds the threshold dis t0 , Δt is 500ms, and the distance dis n,n+1 can be 20m under the time interval, that is, dis t0 ≥ dis .

[0162] S5b, if the vehicle is identified as abnormal in front and rear position, then the latest position point is obtained from the historical position point set, the vehicle position is predicted and covered by calculating the longitude speed and latitude speed of the vehicle. It needs to be known that the flow of steps of step S5b is consistent with step S4.

[0163] In addition, the embodiment of the present application provides a vehicle abnormal position correction system based on road network position information, comprising:

[0164] The acquisition and processing module is used for acquiring and preprocessing road network map information and storing the information in a database.

[0165] The position tracking module is used for tracking the vehicle position by using a detection device and storing the position as a historical position point set of the vehicle.

[0166] The abnormal deviation judgment module is used for judging whether the vehicle is in an abnormal deviation state according to the vehicle scene and the relative position relationship with the road and the road section range obtained from the road network map information when the number of historical position points of the vehicle exceeds a set threshold.

[0167] The abnormal processing module is used for obtaining the latest position point from the historical position point set and predicting and covering the vehicle position by calculating the historical longitude speed and latitude speed of the vehicle if the vehicle is in an abnormal deviation state.

[0168] The normal processing module is used for identifying the front and rear position abnormal state of the vehicle based on a preset threshold and obtained vehicle driving state data if the vehicle is not in an abnormal deviation state.

[0169] The front and rear position abnormal processing module is used for obtaining the latest position point from the historical position point set and predicting and covering the vehicle position by calculating the longitude speed and latitude speed of the vehicle if the vehicle is identified as abnormal in front and rear position.

[0170] In addition, the embodiment of the present application provides a vehicle abnormal position correction system based on road network position information, comprising:

[0171] The embodiment of the present application proposes an innovative device specially used for correcting the vehicle abnormal position based on road network position information. The core components of the device include at least one database and a storage connected in communication with the databases.

[0172] The function of the database is mainly to store, manage and process data related to road network location information, which is the basis for executing vehicle abnormal position correction. The memory is responsible for saving a series of instructions that can be executed by the database.

[0173] When these instructions are executed by the database, the device can automatically run the aforementioned vehicle abnormal position correction method based on road network location information. This method can effectively identify and correct abnormal data of vehicle position, thereby improving the accuracy and reliability of location information.

[0174] In short, through the cooperation of the database and the memory, this device realizes automatic detection and correction of vehicle abnormal position, providing strong support for various applications that rely on accurate location information.

[0175] Furthermore, the embodiment of the present application provides a computer readable medium having computer executable instructions stored thereon, which, when executed by a processor, implement the vehicle abnormal position correction method based on road network location information as described above.

[0176] When these instructions are executed by the processor, the aforementioned vehicle abnormal position correction method based on road network location information can be implemented. Through this computer readable medium, the correction method can be conveniently deployed on various computing devices. As long as the device is equipped with a corresponding processor and can read and execute the instructions on this medium, it can automatically perform the correction operation of the vehicle abnormal position.

[0177] This computer readable medium not only facilitates the dissemination and application of the method, but also greatly improves the flexibility and universality of the correction operation, so that more devices and systems can benefit from this advanced correction technology.

[0178] In summary, the embodiment of the present application provides a vehicle abnormal position correction method, system, device and medium based on road network location information, which is described in detail with reference to Figure 10 , and the overall process is as follows:

[0179] (1) Collect and obtain road, road segment, lane and other road network map information required for vehicle abnormal position correction. After screening and preprocessing, these data are stored in the database for subsequent use.

[0180] (2) The camera, radar and other detection devices track the vehicle position at time interval Δt, and the historical position data of the tracked vehicle are stored in the database. The historical position point set of each vehicle M is P = {P0,...P n}. When the vehicle obtains the latest real-time position P n+1 at the current time, if the number of historical position points of the vehicle M meets the point requirement, step (3) is entered, otherwise step (8) is entered.

[0181] (3) According to the scene where the vehicle is located, including urban roads, closed roads, calculate P n+1 The relative position relationship with the road range and the section range, the latest position P n+1 of the vehicle is recognized as an abnormal deviation state.

[0182] (4) If the vehicle is recognized as an abnormal deviation state, go to step (7), if the vehicle is in a normal state, according to the latest position P n+1 and the position P n of the last time, get the longitude and latitude of the front and rear positions of the vehicle, the lane center line heading angle of the lane where the vehicle is located, and combine the front and rear coordinates to calculate the vehicle heading angle and the vehicle travel distance, to form a vehicle travel state data set N.

[0183] (5) If the vehicle travel distance does not exceed the distance threshold, the vehicle is considered to be stationary, go to step (8), if the vehicle travel distance exceeds the threshold, according to the data set N calculated in step (4), the front and rear position of the vehicle is recognized as an abnormal state, including vehicle abnormal deviation, vehicle abnormal reverse, vehicle abnormal flash.

[0184] (6) If the vehicle is recognized as an abnormal state of the front and rear positions, go to step (7), if the vehicle is in a normal state, go to step (8).

[0185] (7) According to the latest k position points of the historical position point set P, calculate the historical longitude speed and latitude speed of the vehicle, and predict the latest longitude and latitude position P n ' +1 of the vehicle, which covers the latest vehicle position P n+1 .

[0186] (8) The latest position P n+1 of the vehicle is added to the historical position point set P, P is updated to P0,…,P n ,P n+1 , and the update is completed in the database. Among them, when the vehicle position is marked as an abnormal deviation state of the vehicle and an abnormal state of the front and rear positions of the vehicle, the latest position P n+1 of the vehicle is the position P n ' +1 predicted in step (7); when the vehicle position is in a normal state, the latest position P n+1 of the vehicle is the position point obtained directly by the radar, video and other detection devices in step (2).

[0187] Therefore, the present application aims to provide a more comprehensive, accurate and efficient vehicle abnormal position correction scheme to overcome the shortcomings of the prior art. This scheme fully integrates real-time data, historical data and geographic information of the vehicle position, and designs detailed rule scenarios, thereby achieving more comprehensive and accurate vehicle position judgment and effectively avoiding judgment errors caused by insufficient data utilization.

[0188] The present application uses innovative, geometry-based decision rules that can accurately identify various complex abnormal situations including vehicle deviation, reverse, flashing, etc. This method not only improves the reliability and stability of the system, but also overcomes the defect of the existing simple decision rules.

[0189] In addition, a unique data fusion mechanism is adopted to effectively combine real-time data, historical data and geographic information such as road shape and heading of the vehicle position, providing a solid foundation for accurate judgment of vehicle position and abnormal situations. This mechanism can make detailed judgments according to different road type characteristics and vehicle driving history characteristics, further enhancing its practicality and accuracy.

[0190] It is worth mentioning that the scheme also uses a vehicle position prediction model to accurately process abnormal data, avoiding information loss and errors caused by direct rejection or simple correction. This not only ensures the accuracy of the display effect of the digital twin platform and the trajectory index calculation, but also effectively improves the existing rough abnormal processing problem.

[0191] Although the present application scheme is powerful, it still maintains the characteristics of simplicity and practicality. It avoids the use of complex artificial intelligence models, thereby reducing the application difficulty, popularization difficulty, high computing resource requirement, long training time and strict requirements for data quality.

[0192] In summary, the present application provides an efficient, accurate and practical vehicle abnormal position correction scheme through innovative decision rules, detailed decision scenarios and unique data fusion mechanisms.

[0193] Due to the system / device described in the above embodiments of the present application, the system / device used for the method of the above embodiments of the present application, based on the method described in the above embodiments of the present application, those skilled in the art can understand the specific structure and modification of the system / device, and thus it is not repeated here. Any system / device used in the method of the above embodiments of the present application belongs to the scope of protection of the present application.

[0194] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code thereon for use by or in connection with an instruction execution system. For the purposes of this description, a computer-usable or computer readable storage medium can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The medium can be electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) including a human interface device or computer. Examples of a computer- readable medium include an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) including a human interface device or computer that is an Internet web site, an intranet web site, a telephone line, a cellular telephone

[0195] The present application is described in reference to the drawings using a flowchart intermixed with or followed by block diagrams and / or illustrations. It will be understood that each block of the flowchart, and / or combinations of blocks in the flowchart, can be implemented by computer program instructions. It will also be understood that each block of the flowchart, and / or combinations of blocks in the flowchart, can be implemented by special purpose hardware-based computer systems which perform the specified functions or steps, or combinations of computer hardware and computer program instructions.

[0196] It should be noted that any references made herein to elements or components of the drawings are to be understood in the context of the claims. The word "comprising" does not exclude the presence of elements or steps other than those listed in a claim. The word "a" or "an" preceding the terminology in a claim does not exclude the presence of a plurality of such elements or steps. The application can be implemented by means of both hardware and software, and any combination of hardware and software. In a claim numerated list of several means, several of these means can be embodied by one and the same hardware. The mere fact that different claims depend on a previous claim, refers to a combination of the features of the dependent claim with the features of the previous claim. The use of relative terms like first and second, and the like, does not im- imply any order, but rather these terms are used for naming purposes only. These terms can be regarded as part of the generic term following this term.

[0197] Furthermore, it is to be understood that the use of certain terms, such as "one", "another", "certain", "certain ones" or the like, in the description above does not exclude that several elements can be present. The terms "first", "second", "third", and the like, do not imply an ordering but are to be interpreted as names.

[0198] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those skilled in the art once they have the benefit of the present disclosure. It is therefore intended that such additional variations and modifications be included within the scope of the application. The application is to be limited only by the claims.

[0199] It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A vehicle abnormal position correction method based on road network position information, characterized in that, The method comprises the following steps: Collect and pre-process road network map information and store it in a database; Track the vehicle position by using a detection device and store it as a set of historical position points of the vehicle; When the number of historical position points of the vehicle exceeds a set threshold, determine whether the vehicle is in an abnormal deviation state according to the scene where the vehicle is located and the relative position relationship with the road and road section range obtained from the road network map information; If the vehicle is in an abnormal deviation state, obtain the latest position point from the set of historical position points, predict and cover the vehicle position by calculating the historical longitude speed and latitude speed of the vehicle; If the vehicle is not in an abnormal deviation state, perform the following vehicle front and rear position abnormal state recognition based on a preset threshold and obtained vehicle driving state data: obtain the longitude, latitude and lane center line heading angle of the lane where the vehicle is located according to the vehicle position at the current time and the vehicle position at the last time, calculate the vehicle heading angle and vehicle driving distance by combining the front and rear position coordinates, and form a set of vehicle driving state data; if the vehicle driving distance does not exceed the distance threshold, the vehicle is considered to be stationary; if the vehicle driving distance exceeds the distance threshold, perform the following vehicle front and rear position abnormal state recognition according to the set of vehicle driving state data: when the angle change between the lane center line heading angle of the lane where the vehicle is located at the current time and the lane center line heading angle of the lane where the vehicle is located at the last time exceeds a preset deviation threshold, it is determined that the vehicle has deviated abnormally; when the angle deviation between the lane center line heading angle of the lane where the vehicle is located at the last time and the vehicle heading angle exceeds a preset reverse threshold, it is determined that the vehicle has reversed abnormally; when the vehicle driving distance within a preset time interval exceeds a preset flashing threshold, it is determined that the vehicle has flashed abnormally; The method comprises the following steps: obtain the longitude, latitude and lane center line heading angle of the lane where the vehicle is located according to the vehicle position at the current time and the vehicle position at the last time, calculate the vehicle heading angle and vehicle driving distance by combining the front and rear position coordinates, and form a set of vehicle driving state data; obtain the longitude and latitude of the vehicle position at the current time, and record it as the first data item of the set of vehicle driving state data; determine the lane center line of the lane where the vehicle is located at the current time according to the road network map information, calculate the included angle between the lane polyline of the lane center line and the north direction line to obtain the lane center line heading angle, and record it as the second data item of the set of vehicle driving state data; obtain the longitude and latitude of the vehicle position at the last time, and record it as the third data item of the set of vehicle driving state data; determine the lane center line of the lane where the vehicle is located at the last time according to the road network map information, calculate the included angle between the lane polyline of the lane center line and the north direction line to obtain the lane center line heading angle at the last time, and record it as the fourth data item of the set of vehicle driving state data; calculate the included angle between the line connecting the vehicle position at the last time and the vehicle position at the current time and the north direction line to obtain the vehicle heading angle, and record it as the fifth data item of the set of vehicle driving state data; calculate the straight line distance between the vehicle position at the last time and the vehicle position at the current time to obtain the vehicle driving distance, and record it as the sixth data item of the set of vehicle driving state data. If the vehicle is identified as being abnormal in position, the latest position point is obtained from the historical position point set, the longitude speed and latitude speed of the vehicle are calculated, and the position of the vehicle is predicted and covered. 2.The road network location information based vehicle abnormal position correction method according to claim 1, wherein, The road network map information is collected and preprocessed and stored in a database, including: Extracting road network map information including road information, road segment information, lane information, and lane center line information from map data; Filtering and preprocessing the collected road network map information to remove duplicate, invalid, or incorrect data; Establishing a data table structure for storage in the database, and importing the preprocessed road network map information into the database according to the data table structure; wherein, The road information includes road numbers and road ranges composed of a set of latitude and longitude coordinate points, including motor lanes, non-motor lanes, and green belts within the road range, and containing at least one road segment; The road segment information includes road segment numbers, road numbers of the road to which the road segment belongs, and road segment ranges composed of a set of latitude and longitude coordinate points, which are limited to motor lanes and contain at least one lane; The lane information includes lane numbers, road segment numbers of the road to which the lane belongs, and lane ranges composed of a set of latitude and longitude coordinate points, each lane range having a unique corresponding lane center line; The lane center line information includes lane center line numbers, lane numbers of the lane to which the lane center line belongs, and a set of latitude and longitude coordinate points from the starting point to the ending point of the lane, and the lane center line is composed of one or more connected line segments. 3.The road network location information based vehicle abnormal position correction method according to claim 1, wherein, Tracking the position of the vehicle using detection equipment and storing it as a set of historical position points of the vehicle, including: Continuously tracking the position of the target vehicle at a set time interval using the detection equipment; Recording vehicle position data containing the longitude of the position point, the latitude of the position point, and the detection time of the position point whenever a new position of the vehicle is detected; Organizing the vehicle position data in chronological order to form a set of historical position points of the vehicle and storing it in the database. 4.The road network location information based vehicle abnormal position correction method according to claim 2, wherein, When the number of historical position points of the vehicle exceeds a set threshold, determining whether the vehicle is in an abnormal deviation state according to the scene in which the vehicle is located and the relative position relationship with the road and road segment range based on the road network map information, including: When the number of historical position points of the vehicle exceeds a set threshold, obtaining the current position of the vehicle; Determining whether the current position of the vehicle is within the road range; If the current position of the vehicle is not within the road range, further determining the scene in which the vehicle is located according to the pre-set scene label; If the vehicle is in a closed road scene containing highways and tunnels, marking the vehicle position as an abnormal deviation state; If the scene is a city road scene, marking the vehicle position as a normal state; If the current position of the vehicle is within the road range, further determining whether the current position of the vehicle is within the road segment range; If the current position of the vehicle is within the road segment range, marking the vehicle position as a normal state; If the current position of the vehicle is not within the road segment range and the vehicle is in a closed road scene containing highways and tunnels, marking the vehicle position as a normal state; If the current position of the vehicle is not within the road segment range and the vehicle is in a city road scene, further determining whether the previous position of the vehicle is within the road segment range; If the vehicle position at the last time is within the range of the road segment, the vehicle position is marked as an abnormal deviation state; If the vehicle position at the last time is not within the range of the road segment, the vehicle position is marked as a normal state. 5.The road network location information based vehicle abnormal position correction method according to claim 1, wherein, If the vehicle is in the abnormal deviation state, the latest position point is obtained from the historical position point set, the historical longitude speed and latitude speed of the vehicle are calculated, and the vehicle position is predicted and covered, including: If the vehicle is in the abnormal deviation state, the latest one or more position points are automatically selected from the historical position point set to form a position point subset; In the position point subset, adjacent position point pairs are selected in turn, and the longitude speed and latitude speed between each adjacent position point pair are calculated according to the longitude, latitude and detection time of the position point in the historical position point set; All longitude speeds are averaged to obtain the average value of the longitude speed, and all latitude speeds are averaged to obtain the average value of the latitude speed; The obtained average values of the longitude speed and the latitude speed are used to obtain the predicted longitude and latitude position of the vehicle at the current time in combination with the time difference between the time of the last vehicle position and the current time, and are used to cover the original vehicle position at the current time; The predicted longitude and latitude position is: ； ； wherein, respectively a predicted longitude position and a predicted latitude position, respectively a longitude position and a latitude position of a previous position point on the vehicle, respectively an average of the longitudinal speed and an average of the latitudinal speed, is a current time, is a time of a previous position point on the vehicle. 6.The road network location information based vehicle abnormal position correction method according to claim 1, wherein, According to the current vehicle position and the last vehicle position, the longitude, latitude and lane center line heading angle of the lane where the vehicle is located are obtained, the vehicle heading angle and the vehicle driving distance are calculated in combination with the front and rear position coordinates, and a vehicle driving state data set is formed, including: The current vehicle position containing longitude and latitude is obtained and recorded as the first data item of the vehicle driving state data set; According to the road network map information, the lane center line of the lane where the current vehicle position is located is determined, and the included angle between the lane polyline of the lane center line and the north direction line is calculated to obtain the lane center line heading angle, which is recorded as the second data item of the vehicle driving state data set; The last vehicle position containing longitude and latitude is obtained and recorded as the third data item of the vehicle driving state data set; According to the road network map information, the lane center line of the lane where the last vehicle position is located is determined, and the included angle between the lane polyline of the lane center line and the north direction line is calculated to obtain the last lane center line heading angle, which is recorded as the fourth data item of the vehicle driving state data set; The included angle between the line connecting the last vehicle position and the current vehicle position and the north direction line is calculated to obtain the vehicle heading angle, which is recorded as the fifth data item of the vehicle driving state data set; The straight line distance between the last vehicle position and the current vehicle position is calculated to obtain the vehicle driving distance, which is recorded as the sixth data item of the vehicle driving state data set.

7. A vehicle abnormal position correction system based on road network position information, characterized by, It includes: The acquisition and processing module is used for collecting and preprocessing the road network map information and storing it in the database; The position tracking module is used for tracking the vehicle position by using the detection device and storing it as a historical position point set of the vehicle; The abnormal deviation judgment module is configured to, when the number of historical position points of the vehicle exceeds a set threshold, judge whether the vehicle is in an abnormal deviation state according to a scene in which the vehicle is located and a relative position relationship with a road and a road section range obtained from road network map information. The abnormal processing module is configured to, if the vehicle is in the abnormal deviation state, acquire a latest position point from the set of historical position points, and predict and cover the vehicle position by calculating a historical longitude speed and a historical latitude speed of the vehicle. The normal processing module is configured to, if the vehicle is not in the abnormal deviation state, perform front and rear position abnormal state recognition of the vehicle based on a preset threshold and acquired vehicle driving state data, including: acquiring longitude and latitude of front and rear positions of the vehicle, a lane center line heading angle of a lane in which the vehicle is located, and combining the front and rear position coordinates to calculate a vehicle heading angle and a vehicle driving distance, to form a set of vehicle driving state data; if the vehicle driving distance does not exceed a distance threshold, the vehicle is considered to be stationary; if the vehicle driving distance exceeds the distance threshold, the following front and rear position abnormal state recognition of the vehicle is performed according to the set of vehicle driving state data: when an angle change between the lane center line heading angle of the lane in which the vehicle is located at the current time and the lane center line heading angle of the lane in which the vehicle is located at the last time exceeds a preset deviation threshold, it is determined that the vehicle has deviated abnormally; when an angle deviation between the lane center line heading angle of the lane in which the vehicle is located at the last time and the vehicle heading angle exceeds a preset reverse threshold, it is determined that the vehicle has reversed abnormally; and when a vehicle driving distance in a preset time interval exceeds a preset flashing threshold, it is determined that the vehicle has flashed abnormally. The normal processing module is configured to, if the vehicle is not in the abnormal deviation state, perform front and rear position abnormal state recognition of the vehicle based on a preset threshold and acquired vehicle driving state data, including: acquiring longitude and latitude of front and rear positions of the vehicle, a lane center line heading angle of a lane in which the vehicle is located, and combining the front and rear position coordinates to calculate a vehicle heading angle and a vehicle driving distance, to form a set of vehicle driving state data; if the vehicle driving distance does not exceed a distance threshold, the vehicle is considered to be stationary; if the vehicle driving distance exceeds the distance threshold, the following front and rear position abnormal state recognition of the vehicle is performed according to the set of vehicle driving state data: when an angle change between the lane center line heading angle of the lane in which the vehicle is located at the current time and the lane center line heading angle of the lane in which the vehicle is located at the last time exceeds a preset deviation threshold, it is determined that the vehicle has deviated abnormally; when an angle deviation between the lane center line heading angle of the lane in which the vehicle is located at the last time and the vehicle heading angle exceeds a preset reverse threshold, it is determined that the vehicle has reversed abnormally; and when a vehicle driving distance in a preset time interval exceeds a preset flashing threshold, it is determined that the vehicle has flashed abnormally. The front-rear position abnormality processing module is configured to, when the vehicle is identified as having an abnormal front-rear position, acquire a latest position point from a historical position point set, and predict and cover the position of the vehicle by calculating the longitude speed and latitude speed of the vehicle.

8. A vehicle abnormal position correction device based on road network position information, characterized by, The method comprises: at least one database; and a memory in communication connection with the at least one database; wherein the memory stores instructions executable by the at least one database, and the instructions are executed by the at least one database to enable the at least one database to perform the road network position information-based vehicle abnormal position correction method according to any one of claims 1-6.

9. A computer readable medium having stored thereon computer- executable instructions, characterized in that, The executable instructions, when executed by the processor, implement the road network position information-based vehicle abnormal position correction method according to any one of claims 1-6.

Images