Vehicle positioning data correction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a vehicle positioning data correction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring original historical positioning data; the original historical positioning data comprises a starting station departure time point; converting the original historical positioning data into relative historical positioning data having a corresponding relationship with the departure time point of the starting station; the relative historical positioning data at least comprises relative time; determining the same relative time as target time, and performing aggregation and averaging operation on the multiple pieces of relative historical positioning data based on the target time to generate reference historical positioning data; when the real-time positioning data of the target vehicle is obtained and the real-time positioning data is judged to be abnormal based on the reference historical positioning data, correction operation is executed for the real-time positioning data, and abnormal detection and correction are effectively performed on the real-time positioning data, so that the accuracy of vehicle positioning is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle positioning data correction, and in particular to a vehicle positioning data correction method, a vehicle positioning data correction device, an electronic device and a computer-readable storage medium. Background Art

[0002] The vehicle-mounted intelligent terminal T-Box (Telematics Box) is an intelligent terminal that integrates wireless communication, GPS positioning, sensor and other technologies. It can deeply read various data of the vehicle and transmit it to the cloud in real time through the network. Through T-Box, we can realize a variety of intelligent services such as real-time positioning, remote monitoring, fault diagnosis, emergency rescue, etc. of the vehicle.

[0003] Real-time vehicle positioning is a core function of T-Box. However, due to factors such as weather, satellite signal strength, and the number of satellites, the positioning accuracy of T-Box may be disturbed to a certain extent, and even positioning drift or loss may occur. Summary of the invention

[0004] The embodiments of the present invention provide a vehicle positioning data correction method, device, electronic device and computer-readable storage medium to overcome the above problems or at least partially solve the above problems.

[0005] The embodiment of the present invention discloses a vehicle positioning data correction method, comprising: Obtaining original historical positioning data; the original historical positioning data includes the departure time point and coordinate information of the starting station; Determine the departure time point of the starting station as the time origin, and determine the time point after the time origin as the relative time; determining a relative coordinate corresponding to the relative time based on the coordinate information, and calculating an average vehicle speed for the relative time and the relative coordinate based on the relative coordinate and the relative time; Constructing a relative historical positioning data set using the average vehicle speed, the relative time and the relative coordinates; Determine the same relative time as the target time, and perform aggregation and averaging operations on the plurality of relative historical positioning data based on the target time to generate reference historical positioning data; When the real-time positioning data of the target vehicle is acquired and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data, a correction operation is performed on the real-time positioning data.

[0006] Optionally, before the step of determining the departure time point of the starting station as the time origin and determining the time point after the time origin as the relative time, the step further includes: When it is determined that the original historical positioning data is a faulty shift vehicle, determining the original historical positioning data as abnormal data; Delete the abnormal data.

[0007] Optionally, the step of performing aggregation and averaging operations on a plurality of the relative historical positioning data based on the target time to generate reference historical positioning data includes: Taking the target time as a reference, generating a reference average coordinate for expressing the average value of the relative coordinates of different vehicles and a reference average vehicle speed for expressing the average value of the average vehicle speeds of different vehicles; A tolerance threshold is determined, and when it is determined that the reference average coordinate and the reference average vehicle speed are within the tolerance threshold, the reference average coordinate and the reference average vehicle speed are determined as reference historical positioning data.

[0008] Optionally, the real-time positioning data includes the target vehicle starting station departure time point of the target vehicle, and before the step of performing the correction operation on the real-time positioning data, the step further includes: The real-time positioning data is converted into relative real-time positioning data corresponding to the departure time point of the target vehicle starting station; the real-time positioning data includes real-time relative time, real-time coordinates corresponding to the real-time relative time, and real-time average vehicle speed.

[0009] Optionally, before the step of performing a correction operation on the real-time positioning data, the method further includes: Determine whether the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold; Determining whether a speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold; When it is determined that the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold, and when it is determined that the speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold, the real-time positioning data is determined to be normal.

[0010] Optionally, the step of performing a correction operation on the real-time positioning data includes: Acquiring image information and motion data from a camera and an inertial measurement unit of the target vehicle; Based on the image information, calculating the vehicle motion information of the target vehicle using a visual odometry method; Anomaly detection is performed based on the motion data and the vehicle motion information to optimize the real-time positioning data.

[0011] The embodiment of the present invention also discloses a vehicle positioning data correction device, comprising: The original historical positioning data acquisition module is used to acquire the original historical positioning data; the original historical positioning data includes the departure time point and coordinate information of the starting station; A relative historical positioning data conversion module is used to determine the departure time point of the starting station as the time origin, and determine the time point after the time origin as the relative time; determine the relative coordinates corresponding to the relative time based on the coordinate information, and calculate the average vehicle speed for the relative time and the relative coordinates based on the relative coordinates and the relative time; and construct a relative historical positioning data set using the average vehicle speed, the relative time and the relative coordinates; A reference historical positioning data generating module is used to determine the same relative time as the target time, and perform aggregation and averaging operations on a plurality of the relative historical positioning data based on the target time to generate reference historical positioning data; The correction operation execution module is used to execute a correction operation on the real-time positioning data when the real-time positioning data of the target vehicle is acquired and the real-time positioning data is determined to be abnormal based on the reference historical positioning data.

[0012] The embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0013] The embodiment of the present invention further discloses a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the method described in the embodiment of the present invention.

[0014] The embodiments of the present invention include the following advantages: The embodiment of the present invention obtains original historical positioning data; the original historical positioning data includes the departure time point of the starting station; the original historical positioning data is converted into relative historical positioning data having a corresponding relationship with the departure time point of the starting station; the relative historical positioning data at least includes relative time; the same relative time is determined as a target time, and aggregation and averaging operations are performed on multiple relative historical positioning data based on the target time to generate reference historical positioning data; when the real-time positioning data of the target vehicle is obtained, and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data, a correction operation is performed on the real-time positioning data, and the real-time positioning data is effectively detected and corrected for abnormality, thereby improving the accuracy of vehicle positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the steps of a vehicle positioning data correction method provided in an embodiment of the present invention; Figure 2 is a structural block diagram of a vehicle positioning data correction device provided in an embodiment of the present invention; Figure 3 is a hardware structure block diagram of an electronic device provided in an embodiment of the present invention; Figure 4 is a schematic diagram of a computer-readable medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0017] Reference Figure 1 , shows a flow chart of the steps of a vehicle positioning data correction method provided in an embodiment of the present invention, which may specifically include the following steps: Step 101, obtaining original historical positioning data; the original historical positioning data includes the departure time point of the starting station; Step 102, converting the original historical positioning data into relative historical positioning data corresponding to the departure time point of the starting station; the relative historical positioning data at least includes relative time; Step 103, determining the same relative time as the target time, and performing aggregation and averaging operations on the plurality of relative historical positioning data based on the target time to generate reference historical positioning data; Step 104 : When the real-time positioning data of the target vehicle is acquired and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data, a correction operation is performed on the real-time positioning data.

[0018] In a specific implementation, an embodiment of the present invention can be applied to a supervision platform, which can be used to perform correction operations on the real-time positioning data of an autonomous driving vehicle.

[0019] Specifically, the embodiment of the present invention can obtain original historical positioning data, the purpose of which is to collect and store the positioning data of the vehicle in the past period of time. These original historical positioning data may include the location information of the vehicle, the timestamp when it is at a certain location, and the departure time point of the starting station of each trip.

[0020] Beneficial effects: Establish historical benchmarks: Provide basic data for subsequent relative positioning and anomaly detection.

[0021] Data accumulation: With the continuous accumulation of data, the vehicle's driving trajectory and rules can be more accurately portrayed, improving the robustness of the model.

[0022] After obtaining the original historical positioning data, the present invention can also convert the original historical positioning data into relative historical positioning data. Specifically, the departure time of the starting station can be used as a reference point to convert the timestamp of the original positioning data into a relative time relative to the departure time.

[0023] Relative historical positioning data, including relative time, coordinates corresponding to the relative time, and average vehicle speed. Relative time refers to the time relative to the time point when the vehicle departs from the starting station as the time origin. For example, the departure time point of the starting station is counted as zero time 00:00:00, and the following time is based on the time origin as the starting point, such as the next 1 second, which is 00:00:01.

[0024] Beneficial effects: Eliminate departure time differences: Different trips have different starting times. Converting the time into relative time can eliminate this difference and facilitate comparison and analysis of data from different trips.

[0025] Simplified calculations: Relative times are easier to perform mathematical operations on, and facilitate subsequent aggregation and averaging operations.

[0026] The embodiment of the present invention can also determine the same relative time as the target time, and perform aggregation and averaging operations on multiple relative historical positioning data based on the target time to generate reference historical positioning data. Exemplarily, for multiple data points at the same relative time, the average values ​​of their positions and speeds can be calculated to generate a reference positioning data.

[0027] Beneficial effects: Build a reference model: The reference historical positioning data represents the "normal" state of the vehicle at a specific driving stage and can be used as a standard to determine whether the real-time data is abnormal.

[0028] Smoothing data: Aggregation and averaging operations can smooth out the noise in the data and improve the reliability of the data.

[0029] After generating the reference historical positioning data, the embodiment of the present invention can correct the real-time positioning data based on the reference historical positioning data. For example, when the real-time positioning data differs greatly from the reference historical positioning data, the data is considered abnormal and needs to be corrected.

[0030] Beneficial effects: Improve positioning accuracy: By correcting abnormal data, the accuracy of vehicle positioning can be improved.

[0031] Ensure driving safety: Accurate positioning information is crucial for the vehicle's autonomous driving and assisted driving functions.

[0032] The embodiment of the present invention obtains original historical positioning data; the original historical positioning data includes the departure time point of the starting station; the original historical positioning data is converted into relative historical positioning data having a corresponding relationship with the departure time point of the starting station; the relative historical positioning data at least includes relative time; the same relative time is determined as a target time, and aggregation and averaging operations are performed on multiple relative historical positioning data based on the target time to generate reference historical positioning data; when the real-time positioning data of the target vehicle is obtained, and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data, a correction operation is performed on the real-time positioning data, and the real-time positioning data is effectively detected and corrected for abnormality, thereby improving the accuracy of vehicle positioning.

[0033] Furthermore, the original historical positioning data includes coordinate information, and the step 102 of converting the original historical positioning data into relative historical positioning data having a corresponding relationship with the departure time point of the starting station includes the following sub-steps: Determine the departure time point of the starting station as the time origin; Determine the time point after the time origin as the relative time; Determining a relative coordinate corresponding to the relative time based on the coordinate information; calculating an average vehicle speed for the relative time and the relative coordinates based on the relative coordinates and the relative time; A relative historical positioning data set is constructed using the average vehicle speed, the relative time and the relative coordinates.

[0034] In the specific implementation, the departure time of each shift can be set as the starting point, and all timestamps can be converted into relative times relative to the departure time. At the same time, the original coordinate information can be retained, and the average speed of the vehicle at each relative time point can be calculated. The calculation of the average speed is based on the total driving distance and total driving time of the vehicle from the starting station to the current location, and geographic distance calculation methods such as the Haversine formula can be used.

[0035] Through the above transformation, a new data set can be obtained, which contains: Relative time: starting from the departure time, indicating the distance from the current location to the departure time.

[0036] Relative coordinates: The vehicle position coordinates corresponding to relative time.

[0037] Average speed: The average speed of the vehicle from the starting station to the current location.

[0038] Converting raw data into relative time form has the following advantages: Unified time benchmark: eliminates the impact of differences in departure times of different shifts, making it easier to compare the driving conditions of vehicles on different shifts.

[0039] Simplified calculations: Relative time is easier to perform mathematical operations on, which facilitates subsequent statistical analysis and modeling.

[0040] Highlight the travel characteristics: By analyzing the relative time and average speed, you can more intuitively understand the speed changes, stop and wait conditions of the vehicle throughout the journey.

[0041] Facilitates anomaly detection: Based on relative time and average speed, it is easier to identify abnormal behaviors of vehicles, such as long stops, sudden acceleration, etc.

[0042] Converting raw positioning data into relative historical positioning data not only provides a more convenient data form for subsequent vehicle trajectory analysis, but also helps to deeply explore the vehicle operation rules and provide data support for the optimization of intelligent transportation systems.

[0043] Specifically, the departure time point of the starting station is determined as the time origin, and the departure time of the vehicle at the starting station can be used as the starting point of time, that is, the time is 0.

[0044] The purpose is to use the departure time as a unified time benchmark to facilitate comparison of the driving conditions of different vehicles or the same vehicle on different trips.

[0045] The time point after the time origin is determined as the relative time. The method can be to convert the timestamp in the original data into the relative time relative to the departure time, that is, take the departure time as 0 point and calculate the time elapsed from each data point to the departure time.

[0046] The purpose is to eliminate the impact of differences in departure times between different shifts and make the data of different shifts comparable.

[0047] The relative coordinates corresponding to the relative time are determined based on the coordinate information. The method may be to directly correspond the coordinate information in the original data to the relative time, that is, at each relative time point, the position of the vehicle remains unchanged.

[0048] Its purpose is to retain the original geographic location information and provide a basis for subsequent trajectory analysis.

[0049] The average vehicle speed for relative time and relative coordinates is calculated based on relative coordinates and relative time. The average speed of the vehicle over a period of time can be calculated based on the coordinates of the vehicle at different time points.

[0050] The purpose is to understand the driving speed of vehicles in different sections or at different time periods through the average vehicle speed, and provide a basis for subsequent traffic flow analysis, anomaly detection, etc.

[0051] The average vehicle speed, relative time and relative coordinates are used to construct a relative historical positioning data set, which can be achieved by combining the calculated relative time, relative coordinates and average vehicle speed into a new data set.

[0052] The purpose is to create a new data set containing key information about vehicle driving, providing a data basis for subsequent in-depth analysis.

[0053] By converting the original historical positioning data into relative historical positioning data, a data set with more analytical value can be obtained. This data set not only retains the spatial information of the original data, but also adds information in the time dimension, which facilitates subsequent in-depth analysis.

[0054] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. It should be noted that in order to make the description concise, only the differences from the above embodiment are described in the variant embodiment.

[0055] In an optional embodiment of the present invention, before the step of determining the departure time point of the starting station as the time origin and determining the time point after the time origin as the relative time, the step further includes: When it is determined that the original historical positioning data is a faulty shift vehicle, determining the original historical positioning data as abnormal data; Delete the abnormal data.

[0056] In practical applications, to ensure data quality, historical positioning data of the same route can be collected and preprocessed. The purpose of preprocessing is to remove abnormal data, such as positioning data during vehicle failure, and to process missing data, duplicate data, and erroneous data. Through preprocessing, high-quality historical positioning data can be obtained, laying a solid foundation for subsequent analysis.

[0057] Currently, there are many mature data cleaning tools available on the market, such as the open source Talend OpenStudio, Knime, and DataLad. These tools integrate a wealth of functions and can efficiently detect and process various abnormal data. For users familiar with programming, Python's Pandas library is also a powerful data analysis tool that provides comprehensive data cleaning and preprocessing functions.

[0058] In a specific implementation, an embodiment of the present invention collects original historical positioning data of a vehicle, which may include information such as a timestamp and coordinates. After obtaining the original historical positioning data, abnormal data of the original historical positioning data may be identified. By analyzing the vehicle operating status, sensor data, etc., it is determined whether the data belongs to a faulty shift, and the positioning data determined to be a faulty shift is deleted from the original historical positioning data. At the same time, the remaining normal data may be cleaned, missing values, duplicate data, erroneous data, etc. may be processed, and the pre-processed original historical positioning data may be used to transform and generate relative historical positioning data.

[0059] The purpose of abnormal data identification is to eliminate abnormal data caused by vehicle failure and other reasons to ensure the quality and reliability of the data.

[0060] Exemplarily, whether the vehicle is in a fault state is determined by analyzing the vehicle's running track, speed changes, sensor data, etc. For example, if the vehicle stays still for a long time or the speed fluctuates abnormally, it can be considered that the vehicle may have a fault.

[0061] Beneficial effects: Improve data quality: Eliminating abnormal data can improve data purity and reduce noise interference.

[0062] Avoid misleading analysis: Abnormal data may mislead subsequent analysis results. Eliminating this data can ensure the accuracy of the analysis results.

[0063] The purpose of removing abnormal data is to delete the identified abnormal data from the original data set.

[0064] Exemplarily, records containing abnormal data may be directly deleted.

[0065] Beneficial effects: Data centralization: Make data more centralized to facilitate subsequent analysis and processing.

[0066] Improve computing efficiency: Reduce the consumption of computing resources by abnormal data.

[0067] The purpose of data cleaning is to process missing values, duplicate values, and erroneous values ​​in the data to further improve data quality.

[0068] Exemplarily, data cleaning may be performed in the following manner.

[0069] Missing value processing: Missing values ​​can be processed by interpolation, deletion and other methods.

[0070] Duplicate value processing: delete duplicate records.

[0071] Error value correction: Correct or delete erroneous data based on actual conditions.

[0072] Beneficial effects: Data integrity: Missing value processing ensures data integrity.

[0073] Data accuracy: The handling of duplicate values ​​and erroneous values ​​ensures the accuracy of the data.

[0074] Data consistency: The cleaned data is more consistent and easier to analyze.

[0075] Summarize: Through the above steps, high-quality, cleaned positioning data can be obtained, providing a reliable basis for subsequent analysis. Eliminating abnormal data and performing data cleaning are important links in data preprocessing, which can effectively improve data quality, reduce noise interference, and ensure the accuracy of analysis results.

[0076] In an optional embodiment of the present invention, the step of performing aggregation and averaging operations on the plurality of relative historical positioning data based on the target time to generate reference historical positioning data includes: Taking the target time as a reference, generating a reference average coordinate for expressing the average value of the relative coordinates of different vehicles and a reference average vehicle speed for expressing the average value of the average vehicle speeds of different vehicles; A tolerance threshold is determined, and when it is determined that the reference average coordinate and the reference average vehicle speed are within the tolerance threshold, the reference average coordinate and the reference average vehicle speed are determined as reference historical positioning data.

[0077] In a specific implementation, the embodiment of the present invention can aggregate and average the coordinates and average vehicle speeds corresponding to the relative time for the relative historical positioning data set, based on the same relative time, and retain a certain tolerance, that is, the coordinate values ​​and average vehicle speeds are set within a certain range, to form reference historical positioning data.

[0078] Specifically: Based on the same relative time: the positioning data of all vehicles at the same driving time point (relative time) are compared. For example, the positioning data of all vehicles at the 10th second after departure will be put together.

[0079] Aggregate and average the coordinates and average speeds corresponding to relative time: average the coordinates and average speeds of all vehicles at the same relative time point to obtain a representative coordinate and average speed.

[0080] Keep some tolerances: Taking into account the uncertainty in vehicle driving (such as road conditions, weather, etc.), the coordinates and average speed are allowed to fluctuate within a certain range. This range is the tolerance.

[0081] Through the above method, the following beneficial effects can be achieved: Improve the accuracy of positioning data: Reducing the impact of noise: By averaging the data of multiple vehicles, the impact of noise and outliers in the positioning data of a single vehicle can be effectively reduced, thereby improving the accuracy of the positioning data.

[0082] Discover abnormal data: If the positioning data of a vehicle differs greatly from the average template, there may be positioning anomalies, which can be checked and handled in a timely manner.

[0083] Establish a reliable reference benchmark: Provide a reference for subsequent data comparison: The reference historical positioning data obtained can be used as a benchmark to compare the real-time positioning data and determine the accuracy of the real-time positioning data.

[0084] Optimize vehicle scheduling and route planning: Improve prediction accuracy: Based on accurate positioning data, the vehicle's arrival time, remaining mileage, etc. can be predicted more accurately, providing more reliable data support for vehicle scheduling and route planning.

[0085] Improve user experience: Improving the stability of positioning services: By improving the accuracy of positioning data, users’ trust in positioning services can be enhanced, improving user experience.

[0086] The target time may be used to select a specific time point as a reference benchmark, and the time may be the same relative time.

[0087] The reference average coordinate may be obtained by averaging the relative coordinates of all vehicles at the target time point to obtain a coordinate representing the average position of all vehicles.

[0088] The reference average vehicle speed may be obtained by averaging the average speeds of all vehicles at a target time point to obtain a speed value representing the average speed of all vehicles.

[0089] The tolerance threshold may be a tolerance set to determine whether the actual driving state of the vehicle deviates from the average state.

[0090] If the coordinates and speeds of all vehicles at the target time point fall within a range near the reference average value (i.e. within the tolerance threshold), the running status of these vehicles is considered normal, and the reference average value can be used as the reference historical positioning data. By setting the tolerance threshold, the data that meets the normal driving status can be screened out to build a reference model.

[0091] By calculating the average position and average speed of multiple vehicles at a specific time point, a reference model is constructed. This reference model can reflect the average behavior of vehicles under normal driving conditions and provide an important reference for subsequent anomaly detection and trajectory prediction.

[0092] In an optional embodiment of the present invention, the real-time positioning data includes the target vehicle starting station departure time point of the target vehicle, and before the step of performing the correction operation on the real-time positioning data, it also includes: The real-time positioning data is converted into relative real-time positioning data corresponding to the departure time point of the target vehicle starting station; the real-time positioning data includes real-time relative time, real-time coordinates corresponding to the real-time relative time, and real-time average vehicle speed.

[0093] In a specific implementation, the real-time positioning data not only includes the current vehicle location information, but also includes the start time of the vehicle's current trip, providing a benchmark for subsequent relative time conversion.

[0094] The embodiment of the present invention can also convert the real-time positioning data acquired in real time into relative time, relative coordinates and average speed relative to the departure time in the same manner as the historical data. The purpose is to make the real-time data and the historical data have a unified time base to facilitate comparison and analysis.

[0095] Real-time relative time can be used to indicate the distance from the current moment to the departure time.

[0096] Real-time coordinates can be used to represent the geographic location of the vehicle at the current moment.

[0097] The real-time average speed can be used to indicate the average speed of the vehicle from the start to the current moment.

[0098] In an embodiment of the present invention, the real-time positioning data is converted into relative real-time positioning data having a corresponding relationship with the departure time point of the target vehicle starting station; the real-time positioning data includes real-time relative time, real-time coordinates corresponding to the real-time relative time, and real-time average vehicle speed, and the real-time positioning data is constructed into a real-time data structure consistent with the relative historical positioning data structure to facilitate subsequent correction operations.

[0099] In an optional embodiment of the present invention, before the step of performing a correction operation on the real-time positioning data, the method further includes: Determine whether the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold; Determining whether a speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold; When it is determined that the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold, and when it is determined that the speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold, the real-time positioning data is determined to be normal.

[0100] Optionally, the vehicle is equipped with a T-Box vehicle-mounted terminal, a camera and an IMU sensor, and the step of performing a correction operation on the real-time positioning data includes: Acquiring image information and motion data from a camera and an inertial measurement unit of the target vehicle; Based on the image information, calculating the vehicle motion information of the target vehicle using a visual odometry method; Anomaly detection is performed based on the motion data and the vehicle motion information to optimize the real-time positioning data.

[0101] In a specific implementation, the embodiment of the present invention can determine whether the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold, thereby comparing the real-time acquired vehicle position with the average position in the reference model to determine whether the distance difference between the two exceeds the set threshold. By comparing with the reference model, the rationality of the vehicle position is preliminarily determined.

[0102] In the embodiment of the present invention, it is also possible to determine whether the speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold, thereby comparing the real-time calculated vehicle average speed with the average speed in the reference model to determine whether the speed difference between the two exceeds a set threshold. By comparing with the reference model, the rationality of the vehicle speed is preliminarily determined.

[0103] When it is determined that the distance difference between the real-time coordinates and the reference average coordinates is lower than the preset distance threshold, and the speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than the preset speed difference threshold, the real-time positioning data is determined to be normal, that is, if the position and speed of the vehicle meet the constraints of the reference model, the real-time positioning data is considered to be normal. Through double judgment, the accuracy of the judgment on the reliability of the real-time positioning data is improved.

[0104] Intelligent connected vehicle supervision system, including T-Box vehicle terminal, data aggregation platform and supervision platform.

[0105] The vehicle terminal is installed on the intelligent connected car, and collects the vehicle's operating data and the perception information of the vehicle's sensors through CAN (Controller Area Network) and vehicle Ethernet. That is, the vehicle terminal is used to call the camera and inertial measurement unit to obtain image information and motion data, and store the collected image information and motion data locally and upload them to the remote data aggregation platform through the wireless network. The vehicle terminal can include a positioning module, support Beidou / GPS and other positioning, to achieve the positioning function; the vehicle terminal can be configured with a corresponding cloud platform, which can be a cloud server.

[0106] The data aggregation platform is deployed on the cloud platform. It is responsible for receiving image information and motion data uploaded by the vehicle terminal, and storing, analyzing and processing the data. The data aggregation platform provides an API (Application Programming Interface) to the outside world and provides data services to the outside world through the API.

[0107] The supervision platform is deployed on the cloud platform. It obtains data from vehicles and on-board sensors by accessing the API interface of the data aggregation platform, and stores, analyzes and displays the data, as well as realizes the interaction with users. The specific functions of the supervision platform include vehicle management, real-time vehicle monitoring, accident warning and alarm, electronic fence management, data statistics and analysis, operation management, process approval, site management, route management, shift management, etc. to realize the supervision and operation of intelligent networked vehicles. Specifically, the supervision platform can use the visual information and motion data obtained by the camera and IMU sensor on the vehicle to correct the GPS positioning data.

[0108] The intelligent connected vehicle supervision system of an embodiment of the present invention may include a supervision platform, a T-Box vehicle-mounted terminal that can perform data interaction with the supervision platform, and is installed on a target vehicle; the target vehicle can call a camera and an inertial measurement unit through the T-Box vehicle-mounted terminal to obtain image information and motion data, and send the image information and motion data to the supervision platform through the T-Box vehicle-mounted terminal, so that the supervision platform can use the visual information and motion data obtained by the camera and IMU sensor on the vehicle to correct the GPS positioning data.

[0109] IMU, the full name of Inertial Measurement Unit, is translated into Chinese as inertial measurement unit.

[0110] Simply put, an IMU is a sensor that measures the movement of an object in three-dimensional space. It can measure the object's: Attitude angle (or angular velocity): that is, the rotation angle of an object relative to its initial position, such as the pitch angle and roll angle of an aircraft.

[0111] Acceleration: The acceleration of an object caused by a force, such as the acceleration of a car when it accelerates.

[0112] There are two main types of sensors inside the IMU: Gyroscope: Measures the angular velocity of an object, that is, how fast the object is spinning.

[0113] Accelerometer: Measures the acceleration of an object in all directions.

[0114] How IMUs Work By measuring this data, the IMU can calculate the object's attitude, speed, position and other information. For example, by continuously measuring acceleration and combining it with the initial speed and position information, the displacement of the object over a period of time can be calculated.

[0115] Advantages of IMU Wide measurement range: can measure a variety of motion parameters.

[0116] Fast response speed: motion data can be measured in real time.

[0117] Not affected by external environment: Not affected by external environment such as GPS signals and magnetic fields.

[0118] IMU is a very important sensor that plays an increasingly important role in modern technology. By understanding the working principle and application of IMU, we can better understand its application in various fields.

[0119] The embodiment of the present invention can also calculate the vehicle motion information of the target vehicle based on the image information using the visual odology method; by analyzing the image sequence, the motion trajectory and speed of the vehicle are calculated using the visual odology method, thereby providing a positioning information independent of GPS for verifying and fusing GPS positioning data.

[0120] The embodiments of the present invention can also perform anomaly detection based on the motion data and the vehicle motion information to optimize the real-time positioning data; by fusing the vehicle motion information calculated by the visual odometer with the IMU data and the GPS data, and optimizing the positioning data through filtering or other methods, the positioning accuracy is improved, thereby achieving multi-sensor fusion, improving the robustness of the positioning system, and reducing the impact of GPS signal interference and occlusion.

[0121] By performing correction operations on real-time positioning data in the above manner, the following beneficial effects can be achieved: Improve positioning accuracy: By fusing GPS data with visual information and IMU data, positioning accuracy can be effectively improved, especially when the GPS signal is weak or blocked.

[0122] Enhance system robustness: Multi-sensor fusion can improve the robustness of the system and reduce the impact of single sensor failure.

[0123] Realize autonomous navigation: In the case of complete loss of GPS signals, the visual odometer can provide vehicle motion information and realize autonomous navigation of the vehicle.

[0124] Support for advanced driver assistance systems: High-precision positioning information provides a reliable data foundation for advanced driver assistance systems (ADAS).

[0125] By introducing visual and inertial sensors, multi-sensor fusion positioning is achieved, further improving the accuracy and reliability of the positioning system. This fusion positioning system can be widely used in fields such as autonomous driving and drones.

[0126] Exemplarily, the following steps may be used to perform correction operations on the real-time positioning data.

[0127] Step 1: Data collection and preprocessing Sensor data collection: The monitoring platform can receive image and motion data collected and sent by the T-Box using high-resolution cameras and IMU sensors.

[0128] Image preprocessing: denoise, enhance contrast and convert color space of the acquired images to improve image quality.

[0129] Feature extraction and description: Use the Shi-Tomasi algorithm to detect image feature points, and use the SIFT descriptor to describe the feature points.

[0130] Step 2: Visual Odometry Calculation Feature matching: The FLANN matcher is used to match feature points between consecutive image frames, and the RANSAC algorithm is used to remove false matches.

[0131] Motion estimation: Calculate the homography matrix based on the matched feature points to preliminarily estimate the vehicle's motion.

[0132] Scale estimation: Combined with IMU data, the actual displacement of the vehicle is estimated by integrating acceleration and angular velocity to solve the scale problem of visual odometer.

[0133] Nonlinear optimization: Perform nonlinear optimization within the sliding window to improve the accuracy of local trajectories.

[0134] Loop closure detection: Optimize long-term trajectories by identifying previous locations that the vehicle has passed through.

[0135] Step 3: Positioning data correction Visual odometry correction: Use the vehicle motion information calculated in step 2 to correct the vehicle's real-time positioning data.

[0136] Anomaly detection: Detect abnormalities in vehicle movement by analyzing data such as vehicle speed and acceleration.

[0137] Positioning algorithm optimization: According to the detected abnormal situation, the parameters of the positioning algorithm are dynamically adjusted to improve the positioning accuracy.

[0138] Summarize: The above three steps describe the core process of the entire vehicle positioning system. First, the system collects data through sensors and preprocesses it, then uses visual odometry to calculate the movement of the vehicle, and finally corrects and optimizes the positioning results by combining IMU data and anomaly detection, thereby achieving high-precision and reliable vehicle positioning.

[0139] In order to enable those skilled in the art to better understand the embodiment of the present invention, an example is used below to illustrate the embodiment of the present invention.

[0140] First, based on the historical positioning data, after data processing, the positioning reference of the departure time and coordinate positioning of the route is obtained, and the accuracy of the real-time positioning data of the unmanned minibus is judged by the positioning reference to determine whether the real-time positioning data of the unmanned minibus has a specified error, as follows: S1. Collect original historical positioning data of the same route in advance, and pre-process the original historical positioning data to obtain pre-processed historical positioning data.

[0141] Preprocessing is to ensure data quality and exclude abnormal data, such as eliminating the historical positioning data of the shift where the vehicle broke down. That is, when the original historical positioning data is determined to be a faulty shift vehicle, the original historical positioning data is determined to be abnormal data and deleted.

[0142] In addition, preprocessing may also include processing missing data, removing duplicate records, correcting erroneous data, etc. You can directly use existing public data cleaning tools to clean abnormal data. These tools usually integrate a variety of data cleaning and preprocessing functions, including outlier detection and processing. Using these tools can greatly simplify the data cleaning process and improve efficiency. For example, open source tools include Talend Open Studio, Knime, and DataLad. If you are familiar with programming, you can use Python's Pandas library, which is a powerful data analysis tool that provides a variety of data cleaning and preprocessing functions.

[0143] S2. Then, all the original historical positioning data are converted to obtain a relative historical positioning data set. As described in the above step 1, the original historical positioning data includes the vehicle's coordinate information, timestamp, and shift departure time.

[0144] After processing, the relative historical positioning data is obtained, including the relative time, the coordinates corresponding to the relative time, and the average vehicle speed. The relative time refers to the time relative to the time point when the intelligent connected vehicle departs from the starting station as the time origin. In simple terms, the time point when the intelligent connected vehicle departs from the starting station is counted as the zero time 00:00:00, and the following time is based on the time origin as the starting point, such as the next 1 second, which is 00:00:01.

[0145] The coordinates corresponding to the relative time, that is, the vehicle coordinate information corresponding to the time in the original positioning data, remain unchanged. The average speed can be calculated by dividing the distance traveled by the vehicle from the starting point to the time by the total travel time from the starting point to the time. In this step, the original historical positioning data is first converted to generate a relative historical positioning data set.

[0146] This process involves comparing the timestamp of each data point with the departure time of the corresponding shift to calculate the relative time, that is, the number of seconds that have passed since the departure time. Next, the vehicle coordinate information corresponding to each relative time point is extracted directly from the original data. To calculate the average speed, the Haversine formula or other geographic distance calculation methods can be used to determine the distance traveled by the vehicle from the starting station to the current data point, and the distance in each time interval is accumulated to obtain the total travel distance. At the same time, the total travel time from the starting point to each data point is calculated. The average speed is obtained by dividing the total travel distance by the total travel time. Finally, the relative time, the coordinates corresponding to the relative time, and the average speed are integrated into a complete relative historical positioning data set, and the data is verified to ensure that all calculations are accurate.

[0147] S3. For the relative historical positioning data set, based on the same relative time, the coordinates and average vehicle speeds corresponding to the relative time are aggregated and averaged, and a certain tolerance is retained, that is, the coordinate values ​​and average vehicle speeds are set within a certain range to form reference historical positioning data.

[0148] S4, the data aggregation platform obtains the real-time positioning data of the intelligent networked vehicle uploaded by the T-Box vehicle terminal in real time. The positioning data includes coordinate information, timestamp, shift departure time, etc. The data aggregation platform converts the uploaded real-time positioning data of the intelligent networked vehicle into relative real-time positioning data. The relative real-time positioning data includes real-time relative time, coordinates corresponding to the real-time relative time, and real-time average vehicle speed.

[0149] S5, by comparing the reference historical positioning data with the relative real-time positioning data, the accuracy of the real-time positioning data of the unmanned minibus is judged to determine whether the real-time positioning data of the unmanned minibus has a specified error. If the coordinate value and average vehicle speed in the relative real-time positioning data are within the range of the coordinate value and average vehicle speed of the reference historical positioning data, the real-time positioning data of the intelligent networked vehicle at that moment is considered to be accurate; if the coordinate value and average vehicle speed in the relative real-time positioning data exceed the range of the coordinate value and average vehicle speed of the reference historical positioning data, the real-time positioning data of the intelligent networked vehicle at that moment is corrected.

[0150] S1-S5 are described in mathematical language as follows: 1. Data preprocessing: Let D original = {d 1 ,d 2 ,...,d n} is the original historical positioning data set, where di = (x i , y i , t i , T 发车_i) Represents the i-th data point, including coordinates (x i ,y i ), timestamp t i and departure time T 发车_i .

[0151] The preprocessing step includes outlier detection and handling, which can use statistical methods (such as box plots) or machine learning methods to identify and remove abnormal data, as mentioned earlier.

[0152] 2. Generate relative historical positioning data: For each d i , calculate the relative time Δt i =t i -T 发车_i .

[0153] Calculate the average vehicle speed v i =Distance i / Δt i , where the distance can be calculated using the Haversine formula:

[0154] Generate a relative historical positioning data set Drelative = {(Δt 1 ,(x 1 ,y 1 ),v 1 ),...,(Δt n ,(x n ,y n ),vn )}.

[0155] 3. Generate reference historical positioning data: Right D 相对 Aggregate, for each relative time Δ t, calculate the average value of the coordinates and the average speed, and set the tolerance range to obtain the reference historical positioning data D 参考 .

[0156] 4. Real-time positioning data processing: Assume d 实时 =(x 实时 ,y 实时 ,t 实时 ,T 发车实时 ) is the real-time positioning data, and the relative real-time positioning data (Δt 实时, (x 实时 ,y 实时 ),v 实时 ).

[0157] 5. Accuracy judgment and correction: For each (Δt 实时 ,(x 实时 ,y 实时 ),v 实时 ), and D 参考 Compare with the corresponding data in .

[0158] If (x 实时 ,y 实时 ) and v 实时 In D 参考 If the positioning data is within the tolerance range, the positioning data is accurate; otherwise, correction is performed.

[0159] A commonly used positioning correction method is a map matching algorithm, but the map matching algorithm relies on high-precision map data that is updated regularly, while road conditions in the real world may change over time, such as construction, temporary closures, etc., which leads to large errors in the accuracy of the map matching algorithm.

[0160] The real-time positioning data of intelligent networked vehicles can be accurately corrected through the visual odometry method. Visual odometry (VO) can effectively correct the real-time positioning data of intelligent networked vehicles and improve the accuracy and reliability of positioning. The details are as follows: The T-Box vehicle terminal can also obtain data from high-resolution cameras and IMU sensors and upload them to the supervision platform in real time. The vehicle camera captures road images at a speed of 30 frames per second, and the captured road image data is uploaded to the supervision platform through the T-Box vehicle terminal. In each frame of the image, image preprocessing is first performed, including denoising, contrast enhancement, and color space conversion to improve the accuracy and robustness of feature detection. Then, 50 corner points with obvious features are detected using the Shi-Tomasi algorithm. After these corner points are extracted, the SIFT descriptor is used to generate a 128-dimensional feature vector for each corner point, which will be used in the subsequent matching process.

[0161] The FLANN matcher is a fast nearest neighbor search algorithm library, which uses the FLANN matcher to find the correspondence between feature vectors between two consecutive frames. For example, corner point A in the second frame matches corner point B in the first frame. However, due to dynamic changes in the environment, some matches may be wrong. The present invention uses the random sampling consensus algorithm RANSAC algorithm to remove these false matches to ensure that we only process those reliable corresponding points. Through these reliable matching points, the homography matrix is ​​calculated to preliminarily estimate the rotation and translation of the vehicle. For example, the vehicle rotated 5 degrees to the right and moved forward 2 meters between the previous frame and the current frame. However, due to the scale uncertainty of the visual odometer, the exact distance of movement cannot be directly known from the visual data. In order to solve this problem, the present invention combines IMU data to estimate the scale. The IMU provides the acceleration and angular velocity data of the vehicle during this period. By integrating these data, the actual displacement of the vehicle can be obtained, thereby solving the scale problem.

[0162] Then, nonlinear optimization is performed on the most recent keyframes and map points within a sliding window. For example, the data of the past 10 keyframes are considered, and the Levenberg-Marquardt algorithm, a numerical optimization algorithm for nonlinear least squares problems, is used to minimize the reprojection error, thereby improving the accuracy of the local trajectory. In addition, the present invention also considers loop closure detection to correct and optimize the long-term trajectory by identifying the previous positions passed by the vehicle. Loop closure detection not only improves the long-term trajectory accuracy of the visual odometry method, but also optimizes the vehicle navigation and control system to make it more reliable and accurate.

[0163] Through the above steps, the visual odometer calculation method can effectively correct the real-time positioning data of intelligent connected vehicles and improve the accuracy and reliability of positioning.

[0164] In addition, positioning correction can be assisted by adding an algorithm to judge abnormal situations during the driving process of intelligent connected vehicles, such as when the vehicle suddenly changes its route or encounters traffic congestion. In the process of correcting the positioning data of intelligent connected vehicles, real-time monitoring and threshold setting are used to capture sudden changes in speed and direction, and pattern recognition and analysis technology are used to learn normal driving patterns to identify abnormalities. For example, by analyzing neighboring data to compare vehicle behavior differences and integrating traffic information to assist in identifying abnormal situations. After identifying the abnormal situation of the vehicle, the positioning algorithm is dynamically adjusted to ensure that when the vehicle encounters an emergency situation such as a route change or traffic congestion, it can respond in a timely and accurate manner, thereby improving the accuracy of the positioning data. The specific plan is as follows: First, the vehicle abnormality is identified through the pattern recognition algorithm. The real-time data of the vehicle's speed, direction, acceleration, position, etc. are collected in real time through the supervision platform, and the collected data is pre-processed by denoising and normalization to ensure data quality. The specific scheme is as mentioned in the above steps one and two. Then, the historical normal driving data is classified by cluster analysis algorithms (such as K-means, DBSCAN, etc.) to extract several typical driving modes. And each typical driving mode is trained using machine learning algorithms (such as support vector machines, decision trees, etc.) to establish a normal driving mode recognition model. Real-time monitoring of sudden changes in vehicle speed and direction, setting thresholds, and triggering abnormal detection when the threshold is exceeded. Compare the real-time data with the normal driving mode recognition model, calculate the similarity between the vehicle's current driving mode and the normal mode, and if the difference is large, it is judged as abnormal. In addition, traffic information such as road conditions and traffic congestion can be sensed by the T-Box vehicle terminal sensor to assist in identifying abnormal conditions. When the vehicle abnormality is identified, the system will further analyze the cause of the abnormality to confirm whether it is an emergency (such as route change, traffic congestion, etc.).

[0165] After identifying the abnormal situation of the vehicle, the positioning algorithm is dynamically adjusted. For example, if the abnormality is confirmed to be caused by traffic congestion, the positioning algorithm is dynamically adjusted according to the congestion situation to increase the update frequency of the positioning data and ensure the accuracy of the data. Positioning algorithm adjustment method: (1) Adjust the weight factor: According to the current driving state of the vehicle, dynamically adjust the weight of each data source in the positioning algorithm, such as increasing the weight of high-precision sensor data. (2) Fusion of multi-source data: Introduce more data sources, such as on-board cameras, lidar, etc., to improve positioning accuracy. (3) Optimize the filtering algorithm: Optimize the filtering algorithm parameters for different driving scenarios to improve the anti-interference ability of the positioning data. The real-time feedback and adjustment system will monitor the adjusted positioning effect in real time, and continuously optimize the positioning algorithm according to the actual driving conditions to ensure that the accuracy of the vehicle positioning data is improved in emergency situations.

[0166] Through the above technical solutions, the positioning of intelligent connected vehicles can be effectively improved, providing strong guarantees for the safe driving of vehicles.

[0167] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0168] Reference Figure 2 , shows a structural block diagram of a vehicle positioning data correction device provided in an embodiment of the present invention, which may specifically include the following modules: The original historical positioning data acquisition module 201 is used to acquire the original historical positioning data; the original historical positioning data includes the departure time point and coordinate information of the starting station; The relative historical positioning data conversion module 202 is used to determine the departure time point of the starting station as the time origin, and determine the time point after the time origin as the relative time; determine the relative coordinates corresponding to the relative time based on the coordinate information, and calculate the average vehicle speed for the relative time and the relative coordinates based on the relative coordinates and the relative time; and construct a relative historical positioning data set using the average vehicle speed, the relative time and the relative coordinates; A reference historical positioning data generating module 203 is used to determine the same relative time as the target time, and perform aggregation and averaging operations on a plurality of the relative historical positioning data based on the target time to generate reference historical positioning data; The correction operation execution module 204 is used to execute a correction operation on the real-time positioning data when the real-time positioning data of the target vehicle is acquired and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data.

[0169] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0170] In addition, an embodiment of the present invention further provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, each process of the above-mentioned vehicle positioning data correction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0171] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned vehicle positioning data correction method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0172] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0173] The electronic device 300 includes but is not limited to: a radio frequency unit 301, a network module 302, an audio output unit 303, an input unit 304, a sensor 305, a display unit 306, a user input unit 307, an interface unit 308, a memory 309, a processor 310, and a power supply 311. Those skilled in the art will appreciate that Figure 3 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In the embodiments of the present invention, the electronic device includes but is not limited to a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted terminal, a wearable device, and a pedometer.

[0174] It should be understood that in the embodiment of the present invention, the radio frequency unit 301 can be used for receiving and sending signals during information transmission or communication. Specifically, after receiving downlink data from the base station, it is sent to the processor 310 for processing; in addition, uplink data is sent to the base station. Generally, the radio frequency unit 301 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 301 can also communicate with the network and other devices through a wireless communication system.

[0175] The electronic device provides users with wireless broadband Internet access through the network module 302, such as helping users to send and receive emails, browse web pages, and access streaming media.

[0176] The audio output unit 303 can convert the audio data received by the RF unit 301 or the network module 302 or stored in the memory 309 into an audio signal and output it as sound. Moreover, the audio output unit 303 can also provide audio output related to a specific function performed by the electronic device 300 (for example, a call signal reception sound, a message reception sound, etc.). The audio output unit 303 includes a speaker, a buzzer, a receiver, etc.

[0177] The input unit 304 is used to receive audio or video signals. The input unit 304 may include a graphics processor (GPU) 3041 and a microphone 3042. The graphics processor 3041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 306. The image frame processed by the graphics processor 3041 can be stored in the memory 309 (or other storage medium) or sent via the radio frequency unit 301 or the network module 302. The microphone 3042 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 301 in the case of a telephone call mode.

[0178] The electronic device 300 also includes at least one sensor 305, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 3061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 3061 and / or the backlight when the electronic device 300 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used to identify the posture of the electronic device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; the sensor 305 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be repeated here.

[0179] The display unit 306 is used to display information input by the user or information provided to the user. The display unit 306 may include a display panel 3061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0180] The user input unit 307 can be used to receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 307 includes a touch panel 3071 and other input devices 3072. The touch panel 3071, also known as a touch screen, can collect user touch operations on or near it (such as operations performed by users using fingers, styluses, or any other suitable objects or accessories on or near the touch panel 3071). The touch panel 3071 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact point coordinates, and then sends it to the processor 310, receives the command sent by the processor 310 and executes it. In addition, the touch panel 3071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel 3071, the user input unit 307 may also include other input devices 3072. Specifically, other input devices 3072 may include but are not limited to a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail here.

[0181] Furthermore, the touch panel 3071 may be overlaid on the display panel 3061. When the touch panel 3071 detects a touch operation on or near it, it is transmitted to the processor 310 to determine the type of touch event. Then, the processor 310 provides corresponding visual output on the display panel 3061 according to the type of touch event. Figure 3 In the figure, the touch panel 3071 and the display panel 3061 are used as two independent components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 3071 and the display panel 3061 can be integrated to realize the input and output functions of the electronic device, which is not limited here.

[0182] The interface unit 308 is an interface for connecting an external device to the electronic device 300. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 308 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the electronic device 300 or may be used to transmit data between the electronic device 300 and an external device.

[0183] The memory 309 can be used to store software programs and various data. The memory 309 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 309 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0184] The processor 310 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 309 and calling data stored in the memory 309, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 310 may include one or more processing units; preferably, the processor 310 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 310.

[0185] The electronic device 300 may also include a power source 311 (such as a battery) for supplying power to various components. Preferably, the power source 311 may be logically connected to the processor 310 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system.

[0186] In addition, the electronic device 300 includes some functional modules not shown, which will not be described in detail here.

[0187] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0188] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0189] like Figure 4 As shown, in another embodiment provided by the present invention, a computer-readable storage medium 401 is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the vehicle positioning data correction method described in the above embodiment.

[0190] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

[0191] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0192] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0193] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0196] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0197] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A vehicle positioning data correction method, characterized in that: include: Obtaining original historical positioning data; the original historical positioning data includes the departure time point and coordinate information of the starting station; Determine the departure time point of the starting station as the time origin, and determine the time point after the time origin as the relative time; determining a relative coordinate corresponding to the relative time based on the coordinate information, and calculating an average vehicle speed for the relative time and the relative coordinate based on the relative coordinate and the relative time; Constructing a relative historical positioning data set using the average vehicle speed, the relative time and the relative coordinates; Determine the same relative time as the target time, and perform aggregation and averaging operations on the plurality of relative historical positioning data based on the target time to generate reference historical positioning data; When the real-time positioning data of the target vehicle is acquired and it is determined that the real-time positioning data is abnormal based on the reference historical positioning data, a correction operation is performed on the real-time positioning data.

2. The method according to claim 1, characterized in that Before the step of determining the departure time point of the starting station as the time origin and determining the time point after the time origin as the relative time, the method further includes: When it is determined that the original historical positioning data is a faulty shift vehicle, determining the original historical positioning data as abnormal data; The abnormal data is deleted.

3. The method according to claim 2, characterized in that The step of performing aggregation and averaging operations on the plurality of relative historical positioning data based on the target time to generate reference historical positioning data comprises: Taking the target time as a reference, generating a reference average coordinate for expressing the average value of the relative coordinates of different vehicles and a reference average vehicle speed for expressing the average value of the average vehicle speeds of different vehicles; A tolerance threshold is determined, and when it is determined that the reference average coordinate and the reference average vehicle speed are within the tolerance threshold, the reference average coordinate and the reference average vehicle speed are determined as reference historical positioning data.

4. The method according to claim 3, characterized in that The real-time positioning data includes the departure time point of the target vehicle starting station of the target vehicle, and before the step of performing the correction operation on the real-time positioning data, it also includes: The real-time positioning data is converted into relative real-time positioning data corresponding to the departure time point of the target vehicle starting station; the real-time positioning data includes real-time relative time, real-time coordinates corresponding to the real-time relative time, and real-time average vehicle speed.

5. The method according to claim 4, characterized in that Before the step of performing a correction operation on the real-time positioning data, the method further includes: Determine whether the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold; Determining whether a speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold; When it is determined that the distance difference between the real-time coordinates and the reference average coordinates is lower than a preset distance threshold, and when it is determined that the speed difference between the real-time average vehicle speed and the reference average vehicle speed is lower than a preset speed difference threshold, the real-time positioning data is determined to be normal.

6. The method according to claim 5, characterized in that The step of performing a correction operation on the real-time positioning data comprises: Acquiring image information and motion data from a camera and an inertial measurement unit of the target vehicle; Based on the image information, calculating the vehicle motion information of the target vehicle using a visual odometry method; Anomaly detection is performed based on the motion data and the vehicle motion information to optimize the real-time positioning data.

7. A vehicle positioning data correction device, characterized in that: include: The original historical positioning data acquisition module is used to acquire the original historical positioning data; the original historical positioning data includes the departure time point and coordinate information of the starting station; A relative historical positioning data conversion module is used to determine the departure time point of the starting station as the time origin, and determine the time point after the time origin as the relative time; Determine the relative coordinates corresponding to the relative time based on the coordinate information, and calculate the average vehicle speed for the relative time and the relative coordinates based on the relative coordinates and the relative time; construct a relative historical positioning data set using the average vehicle speed, the relative time and the relative coordinates; A reference historical positioning data generating module is used to determine the same relative time as the target time, and perform aggregation and averaging operations on a plurality of the relative historical positioning data based on the target time to generate reference historical positioning data; The correction operation execution module is used to execute a correction operation on the real-time positioning data when the real-time positioning data of the target vehicle is acquired and the real-time positioning data is determined to be abnormal based on the reference historical positioning data.

8. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 6 when executing the program stored in the memory.

9. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 6.

Images