Intelligent driving map verification method and system

Abstract

The invention discloses an intelligent driving map verification method and system, relates to the technical field of intelligent driving, and discloses an intelligent driving map verification method comprising the following steps: collecting current road section data in real time according to a selected verification road section model; acquiring geographic information of feature points based on the current road section data; performing differential matching on the geographic information of the feature points in combination with an intelligent driving map to generate a matching result; and verifying the quality of the intelligent driving map based on the matching result. By selecting a representative verification road section model to collect data in real time, testing on irrelevant or repeated road section features is avoided, and the actual condition of a current road is reflected. The matching process is simplified by extracting key feature points, and the test efficiency is improved; and finding the difference between the intelligent driving map and the actual road through difference matching. The quality of the intelligent driving map is verified based on differences, and the accuracy and integrity of map data are efficiently verified.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and particularly to an intelligent driving map verification method and system. Background Art

[0002] With the in-depth transformation of the automotive industry and technology, more and more vehicles are equipped with intelligent driving functions. Maps play an important role in intelligent driving. The geographical information they provide, including detailed road information, traffic signs, etc., enables the intelligent driving system to more accurately judge the road conditions, assist the intelligent driving map verification system in planning the driving route, and improve driving safety.

[0003] Currently, most intelligent driving systems have introduced map data, but there are also problems such as slow update speed and map quality control based on map data. For vehicle manufacturers or manufacturers using intelligent driving maps, how to efficiently verify the accuracy and integrity of map data has become an important task. Summary of the Invention

[0004] The main purpose of this application is to provide an intelligent driving map verification method and system, aiming to solve the technical problem of how to efficiently verify the accuracy and integrity of map data.

[0005] To achieve the above object, this application proposes an intelligent driving map verification method, and the method includes: real-time collecting current road section data according to a selected verification road section model; obtaining geographical information of feature points based on the current road section data; performing differential matching on the geographical information of the feature points in combination with the intelligent driving map to generate a matching result; and verifying the quality of the intelligent driving map based on the matching result.

[0006] In one embodiment, the step of real-time collecting current road section data according to a selected verification road section model includes: collecting road condition data and driving trajectory data according to a selected verification road section model; performing spatio-temporal synchronization on the road condition data and the driving trajectory data to obtain spatio-temporal synchronized data; and generating current road section data based on the road condition data, the driving trajectory data, and the spatio-temporal synchronized data.

[0007] In one embodiment, the step of obtaining geographical information of feature points based on the current road section data includes: preprocessing the current road section data; performing data fusion on the road condition data and the driving trajectory data based on the preprocessed current road section data to generate fusion data; and extracting geographical information of feature points according to the fusion data.

[0008] In one embodiment, the step of performing differential matching on the feature point geographic information in combination with the intelligent driving map to generate a matching result includes: performing differential matching on the feature point geographic information in combination with the intelligent driving map and calculating a deviation value; extracting the feature point geographic information with the deviation value exceeding a preset deviation parameter as the deviation geographic information; and generating a matching result based on the deviation geographic information, where the matching result includes a feature point deviation table and an element change table.

[0009] In one embodiment, before the step of collecting current road section data in real time according to the selected verification road section model, the following steps are further included: calibrating the parameters of the collection device based on different intelligent driving scenarios; setting the collection device based on the calibrated parameters of the collection device and collecting the verification road section data in the intelligent driving scenario; performing feature point recognition on the verification road section data to generate the verification road section feature point geographic information; and building a verification road section model based on the verification road section data after the verification road section feature point geographic information meets the preset accuracy requirements.

[0010] In addition, to achieve the above object, the present application also proposes an intelligent driving map verification system, which applies the steps of the intelligent driving map verification method as described above; the system includes: a collection module and an operation module; the collection module is connected to the operation module; the collection module is used for collecting current road section data in real time according to the selected verification road section model and transmitting it to the operation module; the operation module is used for obtaining the feature point geographic information based on the current road section data; and is also used for performing differential matching on the feature point geographic information in combination with the intelligent driving map to generate a matching result; and is also used for verifying the quality of the intelligent driving map based on the matching result.

[0011] In one embodiment, the system further includes: a power supply module; the power supply module is respectively connected to the collection module and the operation module; the power supply module is used for supplying power to the collection module and the operation module and providing a network; the power supply module includes: an original vehicle battery, a relay, a power switch, a power supply box battery, a power supply control board, a power board, a router, a display screen and an antenna; the power supply control board is used for controlling the access of the original vehicle battery through the relay when the voltage of the power supply box battery and the load current do not meet the requirements; the original vehicle battery and the power supply box battery are used for supplying power to the power board through the power supply control board; the power board is connected to the collection module and the operation module and is used for supplying power to the collection module and the operation module; the power supply control board is further used for detecting the remaining battery power, input voltage, output voltage, load current and load power and controlling the display screen to display; the router and the antenna are used for forming a wireless network and accessing a 4G signal for transmission to the collection module and the operation module.

[0012] In one embodiment, the acquisition module includes a verification control board, a switch, an integrated navigation system, and an industrial camera; the operation module includes an industrial control computer and a computing power unit; the power supply board is configured to filter, regulate the voltage, and monitor and protect the electrical energy input by the power supply cable, and then output different voltages and powers to supply power to the verification control board, the switch, the integrated navigation system, the industrial camera, the industrial control computer, and the computing power unit; the integrated navigation system is configured to receive GNSS signals and perform positioning and attitude determination in combination with longitude, latitude, altitude, roll, pitch, and heading information, and generate driving trajectory data for transmission to the industrial control computer; the industrial camera takes pictures according to the external trigger signal of the control board and transmits road condition data to the industrial control computer; the verification control board performs data interaction with the power supply control board through the switch; the verification control board accesses the timing pulse and serial port timestamp of the integrated navigation system, tags the camera with a time label when the output pulse triggers the industrial camera to work, and simultaneously outputs spatio-temporal synchronization data to the industrial control computer; the industrial control computer is configured to receive user access in real time and execute user instructions; it is also configured to receive information from the power supply board and the verification control board and issue an alarm when the information from the power supply board and the verification control board is abnormal; the industrial control computer is configured to perform parameter configuration and real-time monitoring of the acquisition status of the acquisition project through acquisition software; it is also configured to fuse the received road condition data, spatio-temporal synchronization data, and driving trajectory data to generate fusion data and output it to the computing power unit; the computing power unit is configured to perform real-time image processing on the fusion data to obtain feature point geographical information; it is also configured to perform differential matching on the feature point geographical information and return the result to the industrial control computer.

[0013] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent driving map verification method as described above are implemented.

[0014] In addition, to achieve the above object, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the intelligent driving map verification method as described above are implemented.

[0015] One or more technical solutions proposed by the present application have at least the following technical effects:

[0016] By selecting a representative verification road section model, testing on irrelevant or duplicate road section features is avoided, saving resources. The actual condition of the current road is reflected by real-time data collection. The matching process is simplified by extracting key feature points, improving the testing efficiency; the differences between the intelligent driving map and the actual road are found through differential matching. The quality of the intelligent driving map is verified through the matching results, and errors or deficiencies in it can be promptly discovered and corrected, thereby improving the accuracy and safety of the intelligent driving map. Brief Description of the Drawings

[0017] The drawings here are incorporated into the description and form a part of this description, showing embodiments consistent with this application, and are used together with the description to explain the principles of this application.

[0018] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart provided for the first embodiment of the intelligent driving map verification method of this application;

[0020] Figure 2 It is a schematic flowchart provided for the second embodiment of the intelligent driving map verification method of this application;

[0021] Figure 3 It is a structural block diagram provided for the third embodiment of the intelligent driving map verification system of this application;

[0022] Figure 4 It is an equipment selection diagram provided for the third embodiment of the intelligent driving map verification system of this application;

[0023] Figure 5 It is an equipment layout diagram provided for the third embodiment of the intelligent driving map verification system of this application.

[0024] The realization of the purpose, functional features and advantages of this application will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0025] It should be understood that the specific embodiments described here are only used to explain the technical solutions of this application and are not used to limit this application.

[0026] In order to better understand the technical solutions of this application, the following will be described in detail in combination with the drawings in the description and the specific embodiments.

[0027] Currently, most intelligent driving systems introduce map data. However, there are also problems such as slow update speed and map quality control based on map data. For vehicle manufacturers or manufacturers using intelligent driving maps, how to efficiently verify the accuracy and integrity of map data has become an important task.

[0028] Most of the existing technical solutions use surveying and mapping equipment such as total stations and RTKs to select certain scenarios of signs, road surfaces, etc. in the map data, manually mark GCP control points, compare the feature point coordinate information in the map data with the GCP points to verify the accuracy of the map data, and extract a section of the road through manual spot-checking to verify the integrity of the map data, and check whether the element information such as signs and street lamp poles is complete. The efficiency is low, and an automated process cannot be achieved.

[0029] Based on this, the embodiments of the present application provide an intelligent driving map verification method, referring to Figure 1 , Figure 1 which is a schematic flowchart provided for the first embodiment of the intelligent driving map verification method of the present application. In this embodiment, the intelligent driving map verification method includes steps S10 to S40:

[0030] Step S10, according to the selected verification road section model, collect the current road section data in real time.

[0031] It should be noted that the selected verification road section model means that one or more specific road sections are selected as verification objects according to the needs of research or projects. These verification road section models may be selected based on various factors such as geographical location, traffic flow, road types such as highways, urban roads, rural roads, etc., and traffic facilities such as traffic lights, zebra crossings, and speed limit signs.

[0032] It can be understood that the verification road section model is obtained through algorithm generation and training, and has a guiding role for the road sections in the intelligent driving map to be verified currently. First of all, the verification road section model provides a clear scope and goal for intelligent driving map verification. By selecting specific road sections as verification objects, it can ensure that the verification work is targeted and avoid blindness and randomness.

[0033] It can be understood that the verification road section model usually contains a series of detailed information and requirements on road conditions, traffic facilities, traffic flow, etc. These information and requirements provide clear judgment criteria for intelligent driving map verification, which helps to evaluate the accuracy and integrity of the map.

[0034] It is understandable that during the verification process, it is necessary to collect data of the current road section in real time for comparison with the intelligent driving map. The verification road section model provides specific guidance for data collection, including the types of data to be collected, the collection frequency, the collection location, etc., so as to ensure the comprehensiveness and accuracy of the data.

[0035] It should be noted that collecting data of the current road section in real time means that the data collection is immediate and can reflect the latest situation of the current road section. The collected data may include, but is not limited to, traffic flow (number of vehicles, pedestrian flow), vehicle speed, vehicle type, road congestion, occurrence of traffic accidents, weather conditions (such as rain, snow, haze), visibility, road surface conditions (such as slippery, damaged), etc.

[0036] It should be noted that the data collection can be carried out in various ways, including but not limited to video surveillance, radar speed measurement, sensor detection, GPS positioning, mobile phone base station positioning data, social media data analysis (such as traffic information posted by users), manual observation records, etc.

[0037] Based on this, this embodiment proposes a feasible implementation method. The step of collecting data of the current road section in real time according to the selected verification road section model includes: collecting road condition data and driving trajectory data according to the selected verification road section model; performing spatio-temporal synchronization on the road condition data and the driving trajectory data to obtain spatio-temporal synchronization data; generating data of the current road section based on the road condition data, the driving trajectory data, and the spatio-temporal synchronization data.

[0038] It should be noted that according to the selected verification road section model, we first need to collect the road condition data and the driving trajectory data on this road section. The road condition data may include road conditions (such as slippery road surface, potholes, etc.), traffic flow, traffic signal status, etc.; the driving trajectory data records information such as the driving path, speed, and acceleration of the vehicle on the road section.

[0039] It should be noted that the road condition data is usually collected in real time through devices such as traffic monitoring cameras, sensors, and radars. The driving trajectory data can be obtained through technical means such as GPS positioning, in-vehicle sensors, and vehicle networking.

[0040] It is understandable that in order to ensure that the collected road condition data and driving trajectory data can accurately reflect the traffic conditions at the same time point, we need to perform spatio-temporal synchronization processing on these two types of data. Spatio-temporal synchronization refers to matching data from different sources and different time points through timestamp and geographical location information, so as to obtain a data set within the same time and space range.

[0041] It should be noted that after completing the spatio-temporal synchronization, we can generate the current road segment data based on the road condition data, driving trajectory data, and spatio-temporal synchronization data. Among them, the current road segment data can be understood as a rough model of the current road segment built based on the road condition data, driving trajectory data, and spatio-temporal synchronization data, which can reflect the situation on the road at this moment. These data will serve as the basis for subsequent comparison and verification with the intelligent driving map.

[0042] It should be noted that the current road segment data can be visually displayed in the form of charts, maps, etc. This helps to intuitively understand the traffic conditions of the road segment and provides support for subsequent verification and decision-making. The generated current road segment data will also be stored in the database for subsequent analysis and use to ensure the security and accessibility of the data.

[0043] In this embodiment, by collecting road condition data and driving trajectory data and performing spatio-temporal synchronization processing on them, a data set that comprehensively reflects the traffic conditions of the current road segment can be obtained. This helps to more accurately evaluate the accuracy and integrity of the intelligent driving map. At the same time, the spatio-temporal synchronization processing ensures the consistency of data from different sources in terms of time and space, thereby improving the accuracy of the data. This helps to reduce the deviation of verification results caused by data inconsistency.

[0044] Step S20, obtain the geographical information of the feature points based on the current road segment data.

[0045] It can be understood that after obtaining this rough model of the current road segment data, it is necessary to extract the geographical information of the feature points in it in order to provide an accurate target for the quality verification of the intelligent driving map. Among them, the geographical information of the feature points refers to the geographical location information that has significant features, is easy to identify on the road, and is of great significance for intelligent driving and map verification.

[0046] It should be noted that first, it is necessary to identify the geographical points with significant features from the current road segment data. These feature points may include road intersections, traffic signs, bridges, tunnels, curves, ramps, etc. The identification of feature points usually relies on image recognition, machine learning, or deep learning algorithms, which can analyze the road condition data and driving trajectory data and extract key features from them.

[0047] It should be noted that once the feature points are identified, it is necessary to extract their geographical information. This includes the longitude and latitude coordinates, altitude, relative position relationship, etc. of the feature points. The process of extracting geographical information may need to combine geographic information system (GIS) technology to ensure the accuracy and reliability of the geographical information.

[0048] It should be noted that in addition to extracting geographical information, the feature points also need to be described in detail. This includes the type of feature points (such as intersections, traffic signs, etc.), the physical attributes of feature points (such as the size, color, content of signs, etc.), the traffic functions of feature points (such as indicating directions, speed limits, etc.). The description of feature points helps with subsequent intelligent driving map verification and decision-making of intelligent driving systems. The extracted geographical information of feature points needs to be stored in a database for subsequent analysis and use. The database should have a good data structure and indexing mechanism to ensure fast data retrieval and update.

[0049] Specifically, this embodiment provides a feasible implementation manner. The steps of obtaining the geographical information of feature points based on the current road segment data include: preprocessing the current road segment data; based on the preprocessed current road segment data, fusing the road condition data and the driving trajectory data to generate fused data; extracting the geographical information of feature points according to the fused data.

[0050] It should be noted that before extracting the geographical information of feature points from the current road segment data, data preprocessing needs to be carried out first. The purpose of data preprocessing is mainly to improve data quality, reduce noise and redundant information, and lay a good foundation for subsequent data fusion and feature extraction. The specific operations of data preprocessing include: removing duplicate, abnormal or invalid data to ensure data accuracy and consistency; unifying the data formats from different sources for subsequent data processing and analysis; standardizing the data to eliminate the influence of different dimensions and magnitudes on data fusion and feature extraction.

[0051] It should be noted that after completing data preprocessing, the road condition data and the driving trajectory data need to be fused next. The purpose of data fusion is to integrate data from different sources to form a more comprehensive, accurate and integrated dataset. The specific operations of data fusion include: ensuring the consistency of road condition data and driving trajectory data in terms of time and space for subsequent feature extraction; associating the two by matching the feature points in the road condition data and the driving trajectory data to form fused data; using appropriate data fusion algorithms, such as weighted average, Kalman filter, etc., to fuse the road condition data and the driving trajectory data together to generate fused data.

[0052] It should be noted that after generating the fused data, the last step is to extract the geographic information of feature points based on the fused data. The geographic information of feature points refers to the geographic location information that has significant features, is easy to identify on the road, and is of great significance for intelligent driving and map verification. The methods for extracting the geographic information of feature points include: using image recognition technology to extract feature points from road condition data, such as road intersections, traffic signs, etc.; extracting feature points by analyzing the trajectory changes in the driving trajectory data, such as curves, slopes, etc.; combining geographic information system (GIS) technology to extract the geographic information of feature points from the fused data, including longitude and latitude coordinates, altitude, relative position relationship, etc.

[0053] In this embodiment, through data preprocessing, the data quality can be improved, noise and redundant information can be reduced, and an accurate data basis can be provided for subsequent data fusion and feature extraction. By using appropriate data fusion algorithms, road condition data and driving trajectory data can be effectively fused together to form a more comprehensive, accurate and integrated data set. Combining image recognition technology, trajectory analysis technology and geographic information extraction algorithms, the geographic information of feature points can be accurately extracted, providing strong support for subsequent intelligent driving map verification and intelligent driving assistance.

[0054] Step S30: Combine the intelligent driving map with the geographic information of the feature points for differential matching to generate a matching result.

[0055] Step S40: Based on the matching result, verify the quality of the intelligent driving map.

[0056] It should be noted that the purpose of differential matching is to find the differences between the feature points in the actual road and the feature points in the map, so as to evaluate the accuracy and integrity of the map.

[0057] It should be noted that the specific operations of differential matching include: matching the extracted geographic information of feature points (such as longitude and latitude coordinates, altitude, etc.) with the feature points in the intelligent driving map, which usually involves the calculation of spatial distance to determine the proximity between the actual feature points and the map feature points; comparing the matching results and analyzing the differences between the actual feature points and the map feature points, which may include position deviations, missing or redundant feature points, etc.; generating a matching report according to the results of the difference analysis, and the report should list in detail all the matched feature points, as well as the existing differences and deviation degrees.

[0058] It can be understood that after the matching result is generated, it can be used to verify the quality of the intelligent driving map. The purpose of verification is to evaluate the accuracy and reliability of the map to ensure its effectiveness in actual intelligent driving applications.

[0059] It should be noted that the specific operations for verifying the quality of the intelligent driving map include: analyzing the position deviation in the matching results, evaluating the accuracy of the map. If the deviation exceeds a certain threshold, it is considered that there is an accuracy problem with the map in this area; checking whether there are feature points not included in the map in the matching results. If this is the case, it indicates that the map may be incomplete in this area; comparing the matching results of different feature points, analyzing the internal consistency of the map. If there are inconsistencies between some feature points (such as incorrect relative position relationships), it indicates that the map may have errors or inconsistencies; based on the above analysis, generating a verification report on the quality of the intelligent driving map. The report should detail the evaluation results of the accuracy, integrity, and consistency of the map, as well as the existing problems and proposed improvement measures.

[0060] Based on this, this embodiment proposes a feasible implementation manner. The step of combining the intelligent driving map to perform differential matching on the geographical information of the feature points and generating the matching results includes: combining the intelligent driving map to perform differential matching on the geographical information of the feature points and calculating the deviation value; extracting the geographical information of the feature points whose deviation values exceed the preset deviation parameter as the deviation geographical information; based on the deviation geographical information, generating the matching results, and the matching results include a feature point deviation table and an element change table.

[0061] It should be noted that after the matching is completed, the deviation value of each feature point is calculated. The deviation value usually represents the position difference between the actual feature point and the map feature point, and can be obtained by calculating the spatial distance (such as Euclidean distance) or angle difference between the two.

[0062] It can be understood that after calculating the deviation value, a preset deviation parameter needs to be set to determine which feature points have significant deviations, that is, which feature points' geographical information needs to be particularly concerned. This preset deviation parameter can be set according to the requirements and accuracy requirements of the actual application. Next, we extract the geographical information of all feature points whose deviation values exceed the preset deviation parameter and classify them as deviation geographical information. These deviation geographical information will serve as an important basis for subsequent analysis and improvement.

[0063] It should be noted that after extracting the deviation geographical information, we need to organize and analyze this information to generate detailed matching results. The matching results usually include two main parts: a feature point deviation table and an element change table.

[0064] It should be noted that the feature point deviation table details all feature points whose deviation values exceed the preset deviation parameter, as well as key information such as their deviation values, actual position information, and map position information. Through this table, we can intuitively understand which feature points have significant deviations, as well as the specific degree and direction of the deviations.

[0065] It should be noted that the element change table is used to record the changes in elements in the intelligent driving map. These elements may include road types, number of lanes, traffic signs, etc. By comparing the element information of the actual feature points and the map feature points, we can discover possible missing, incorrect, or updated requirements in the map.

[0066] In this embodiment, through differential matching and calculation of deviation values, we can accurately identify the differences between the actual feature points and the map feature points, providing accurate data support for subsequent map correction and improvement. At the same time, the generated matching results not only include the deviation information of the feature points but also cover the changes in map elements, enabling a comprehensive evaluation of the quality and accuracy of the intelligent driving map.

[0067] In this embodiment, by selecting a representative verification road section model, testing on irrelevant or duplicate road section features is avoided, saving resources. The actual conditions of the current road are reflected by real-time data collection. The matching process is simplified by extracting key feature points, improving the testing efficiency; the differences between the intelligent driving map and the actual road are found through differential matching. The quality of the intelligent driving map can be verified through the matching results, and errors or deficiencies in it can be promptly discovered and corrected, thereby improving the accuracy and safety of the intelligent driving map.

[0068] Furthermore, in order to improve the accuracy and efficiency of intelligent driving map verification, an embodiment of building a verification road section model is proposed in this application. Please refer to Figure 2 , Figure 2 which is the flowchart provided for the second embodiment of the intelligent driving map verification method of this application.

[0069] In this embodiment, before the step of collecting current road section data according to the selected verification road section model, there are also steps A10 to A40:

[0070] Step A10, calibrate the parameters of the acquisition device based on different intelligent driving scenarios.

[0071] It should be noted that first, according to different intelligent driving scenarios, such as highways, urban expressways, tunnels, viaducts, tree-lined roads, water area roads, urban canyons, etc., the parameters of the acquisition device need to be calibrated.

[0072] It should be noted that these parameters may include the resolution, frame rate, focal length of the camera, the detection range, accuracy of the radar, and the positioning accuracy of the GPS, etc. By accurately calibrating these parameters, it can be ensured that the collected data can accurately reflect the actual road conditions, providing a reliable basis for subsequent analysis and verification.

[0073] Step A20: Set the acquisition device based on the calibrated acquisition device parameters and acquire data for the verification section in the intelligent driving scenario.

[0074] It should be noted that next, the acquisition device needs to be set according to these parameters, and the device is started to acquire data for the verification section in the corresponding intelligent driving scenario. These data may include various types such as images, radar point clouds, GPS trajectories, etc., which together constitute a comprehensive description of the road environment.

[0075] Step A30: Identify feature points from the verification section data to generate geographical information of the verification section feature points.

[0076] It can be understood that after acquiring the verification section data, the feature points of these data need to be identified. At this time, the feature point identification method as described in the above embodiment can be used. In this embodiment, feature points refer to those points that can significantly reflect the characteristics of the road environment, such as road edges, traffic signs, obstacles, etc. By identifying these feature points, geographical information of the verification section feature points can be generated, and these information are the key to constructing the verification section model later.

[0077] Step A40: After the geographical information of the verification section feature points meets the preset accuracy requirements, build a verification section model based on the verification section data.

[0078] It can be understood that after generating the geographical information of the verification section feature points, its accuracy needs to be evaluated. Only when this information meets the preset accuracy requirements can a verification section model be built based on the verification section data.

[0079] It should be noted that this model will be a digital and high-precision representation of the road environment, which can be used for various applications such as simulation testing, path planning, and obstacle detection of the intelligent driving system. Based on this, the verification section model can quickly identify the objects that need to be recognized, and accordingly adjust and optimize the parameters of the recognition device. This helps to improve the recognition accuracy and efficiency of the intelligent driving system.

[0080] In this embodiment, by accurately calibrating the acquisition device parameters, acquiring high-quality road data, identifying feature points and generating geographical information, and finally constructing a high-precision verification section model, we can provide a more reliable and efficient verification platform for the development and testing of intelligent driving map verification.

[0081] It should be noted that the above examples are only for understanding this application and do not constitute a limitation to the intelligent driving map verification method of this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.

[0082] In addition, this application also proposes an intelligent driving map verification system. Please refer toFigure 3 , Figure 3 This is a structural block diagram provided for the third embodiment of the intelligent driving map verification system of the present application. The system applies the steps of the intelligent driving map verification method as described above; the system includes: a collection module 10 and an operation module 20; the collection module 10 is connected to the operation module 20.

[0083] It should be noted that the collection module 10 is used to collect current road section data in real time according to the selected verification road section model and transmit it to the operation module; the operation module 20 is used to obtain the geographical information of feature points based on the current road section data; it is also used to perform differential matching on the geographical information of feature points in combination with the intelligent driving map to generate a matching result; it is also used to verify the quality of the intelligent driving map based on the matching result.

[0084] Furthermore, the system further includes: a power supply module 30; the power supply module 30 is respectively connected to the collection module 10 and the operation module 20; the power supply module 30 is used to supply power to the collection module and the operation module and provide a network.

[0085] Based on this, the specific equipment selection of the intelligent driving map verification system is given in this embodiment. Please refer to Figure 4 , Figure 4 This is the equipment selection diagram provided for the third embodiment of the intelligent driving map verification system of the present application. At the same time, the installation positions of the equipment are also given. Please refer to Figure 5 , Figure 5 This is the equipment layout diagram provided for the third embodiment of the intelligent driving map verification system of the present application.

[0086] It should be noted that the power supply module 30 includes: the original vehicle battery, a relay, a power switch, a power box battery, a power supply control board, a power board, a router, a display screen, and an antenna. The function module 30 is an in-vehicle module, and its equipment selection is an in-vehicle device and is installed in the vehicle. Among them, the power board is set on the roof because it needs to directly supply power to the collection module 10 and the operation module 20.

[0087] It should be noted that the power supply control board is used to control the access of the original vehicle battery through the relay when the voltage of the power box battery and the load current do not meet the requirements; the original vehicle battery and the power box battery are used to supply power to the power board through the power supply control board; the power board is connected to the collection module and the operation module and is used to supply power to the collection module and the operation module; the power supply control board is also used to detect the remaining battery power, input voltage, output voltage, load current, and load power, and control the display screen for display; the router and the antenna are used to form a wireless network and access the 4G signal and transmit it to the collection module and the operation module.

[0088] It should be noted that the acquisition module 10 includes a verification control board, a switch, an integrated navigation system, and an industrial camera; the operation module 20 includes an industrial control computer and a computing power unit. Since the acquisition module 10 and the operation module 20 need to perform acquisition and operation on the road surface, they can be set on the roof as an external vehicle module, and their devices are also set on the roof in sequence as roof devices, which is convenient for acquisition and processing.

[0089] It should be noted that the power supply board is used to output different voltages and powers after filtering, voltage stabilization, and monitoring protection of the electric energy input by the power supply cable, and supply power to the verification control board, the switch, the integrated navigation system, the industrial camera, the industrial control computer, and the computing power unit; the integrated navigation system is used to receive GNSS signals and combine longitude, latitude, altitude, roll, pitch, and heading information for positioning and attitude determination, and generate driving trajectory data to be transmitted to the industrial control computer; the industrial camera takes pictures according to the external trigger signal of the control board and transmits the road condition data to the industrial control computer; the verification control board conducts data interaction with the power supply control board through the switch; the verification control board accesses the timing pulse and serial port timestamp of the integrated navigation system, marks the time tag for the camera when the output pulse triggers the industrial camera to work, and simultaneously outputs the spatio-temporal synchronization data to the industrial control computer; the industrial control computer is used to receive user access in real time and execute user instructions; it is also used to receive information from the power supply board and the verification control board and alarm when the information of the power supply board and the verification control board is abnormal; the industrial control computer is used to configure parameters for the acquisition project and monitor the acquisition status in real time through acquisition software; it is also used to fuse the received road condition data, spatio-temporal synchronization data, and driving trajectory data to generate fused data and output it to the computing power unit; the computing power unit is used to perform real-time image processing on the fused data to obtain feature point geographical information; it is also used to perform differential matching on the feature point geographical information and return the result to the industrial control computer.

[0090] Based on the intelligent driving map verification system after the above device selection, it can obtain synchronized binocular image data, high-frequency and high-precision position and attitude data, etc. Combining the internal and external calibration parameters of the sensors, through the multi-sensor fusion algorithm, it can output the geographical information data of the feature points in real time, and finally realize the rapid verification of the map data quality. The specific process is as follows:

[0091] First, it is necessary to develop and integrate the acquisition equipment, complete the overall design of the system, the selection of key sensors, the circuit board design, etc., verify the performance, installation position and angle of key sensors such as industrial cameras and integrated navigation systems, and complete the development and integration of the hardware system to provide a hardware foundation for the system. It is also necessary to develop the acquisition, calibration and quality evaluation software. The acquisition software is responsible for the configuration, monitoring and real-time acquisition and storage of engineering data. The calibration software is responsible for the analysis of trajectory, image and synchronization data, the calibration of the internal and external parameters of the camera and the accuracy verification, and obtaining high-precision camera calibration parameters for subsequent algorithms. The quality evaluation software is responsible for performing multi-sensor data fusion processing on the input synchronized image data, position and attitude data, etc., and outputting geographical information such as the coordinates and elevation of feature points. It is also necessary to calibrate the sensors, collect calibration data of cameras, etc. through indoor and outdoor calibration fields, and complete the calibration of the internal and external parameters of the camera through the calibration software, including the distortion parameters of the camera, the rotation and translation parameters of the camera relative to the inertial navigation, etc.

[0092] Secondly, verify the system accuracy, collect data from the calibration field, use the calibrated parameters for feature point image recognition and output, and verify whether the calibration parameters meet the accuracy requirements by comparing with known accurate coordinate points. Then implement the verification section selection. In the POC stage, typical scenarios covering intelligent driving such as highways, urban expressways, tunnels, viaducts, tree-lined roads, water area roads, urban canyons, etc. can be selected for comprehensive verification. In the large-scale acceptance stage, the system verification is carried out according to the project plan.

[0093] Finally, the intelligent driving map verification method can be implemented. According to the selected verification section, use the developed acquisition vehicle and acquisition software to collect image data, integrated navigation data and synchronization data of the measured section in real time, synchronize the images and trajectory data in time and space on the industrial computer, and output them to the computing unit in real time through Gigabit Ethernet. Through the data quality evaluation software running on the computing unit, perform fusion processing on the received multi-source sensor data, output feature point geographical information data, and perform real-time differential matching of these output information with the existing intelligent driving map data. The data quality evaluation software outputs quality determination suggestions of the software according to the output feature point deviation table and element change table, and according to the set deviation parameters, etc., and displays the statistics of data with deviations exceeding the set values, the statistics of changed elements and the determination results in real time, and stores relevant raw data, feature point deviation analysis tables, element change tables and other data for subsequent detailed analysis and positioning.

[0094] The intelligent driving map verification system provided by this application adopts the intelligent driving map verification method in the above-mentioned embodiment, and can solve the technical problem of how to efficiently verify the accuracy and integrity of map data. Compared with the prior art, the beneficial effects of the intelligent driving map verification system provided by this application are the same as those of the intelligent driving map verification method provided by the above-mentioned embodiment, and other technical features in the intelligent driving map verification system are the same as the features disclosed in the method of the above-mentioned embodiment, which will not be elaborated here.

[0095] This application provides a computer-readable storage medium, which has computer-readable program instructions (i.e., computer programs) stored thereon. The computer-readable program instructions are used to execute the intelligent driving map verification method in the above-mentioned embodiment.

[0096] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0097] The above computer-readable storage medium can be included in the intelligent driving map verification system; it can also exist separately without being assembled into the intelligent driving map verification system. The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the intelligent driving map verification system, the intelligent driving map verification system: collects current road segment data in real time according to the selected verification road segment model; obtains the geographical information of feature points based on the current road segment data; performs differential matching on the geographical information of the feature points in combination with the intelligent driving map to generate a matching result; and verifies the quality of the intelligent driving map based on the matching result.

[0098] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0099] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0100] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0101] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned intelligent driving map verification method, and can solve the technical problem of how to efficiently verify the accuracy and integrity of map data. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the intelligent driving map verification method provided by the above embodiments, and will not be elaborated here.

[0102] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the intelligent driving map verification method as described above.

[0103] The computer program product provided by the present application can solve the technical problem of how to efficiently verify the accuracy and integrity of map data. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the intelligent driving map verification method provided by the above embodiments, and will not be elaborated here.

[0104] The above are only some embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. An intelligent driving map verification method, characterized in that, The intelligent driving map verification method includes: According to the selected verification road section model, collect current road section data in real time; Based on the current road section data, obtain the geographical information of feature points; Combine the intelligent driving map to perform differential matching on the geographical information of the feature points, and generate a matching result; Based on the matching result, verify the quality of the intelligent driving map.

2. The intelligent driving map verification method according to claim 1, wherein, The step of collecting current road section data in real time according to the selected verification road section model includes: According to the selected verification road section model, collect road condition data and driving trajectory data; Synchronize the road condition data and the driving trajectory data in time and space to obtain time-space synchronized data; Based on the road condition data, the driving trajectory data and the time-space synchronized data, generate current road section data.

3. The intelligent driving map verification method according to claim 2, wherein The step of obtaining the geographical information of feature points based on the current road section data includes: Preprocess the current road section data; Based on the preprocessed current road section data, perform data fusion on the road condition data and the driving trajectory data to generate fusion data; According to the fusion data, extract the geographical information of feature points.

4. The intelligent driving map verification method according to claim 3, wherein The step of combining the intelligent driving map to perform differential matching on the geographical information of the feature points and generating a matching result includes: Combine the intelligent driving map to perform differential matching on the geographical information of the feature points, and calculate the deviation value; Extract the geographical information of feature points with deviation values exceeding the preset deviation parameter as deviation geographical information; Based on the deviation geographical information, generate a matching result, and the matching result includes a feature point deviation table and an element change table.

5. The intelligent driving map verification method according to any one of claims 1 to 4, characterized in that Before the step of collecting current road section data in real time according to the selected verification road section model, it further includes: Based on different intelligent driving scenarios, calibrate the parameters of the collection device; Set the collection device based on the calibrated parameters of the collection device, and collect the verification road section data in the intelligent driving scenario; Perform feature point recognition on the verification road section data to generate the geographical information of the verification road section feature points; After the geographical information of the verification road section feature points meets the preset accuracy requirements, build a verification road section model based on the verification road section data.

6. An intelligent driving map verification system, characterized in that, The system applies the steps of the intelligent driving map verification method described in any one of 1 to 5; The system includes: a collection module and an operation module; the collection module is connected to the operation module; The collection module is used to collect current road section data in real time according to the selected verification road section model and transmit it to the operation module; the operation module is used to obtain the geographical information of feature points based on the current road section data; it is also used to combine the intelligent driving map to perform differential matching on the geographical information of the feature points to generate a matching result; it is also used to verify the quality of the intelligent driving map based on the matching result.

7. The intelligent driving map verification system according to claim 6, wherein The system further includes: a power supply module; The power supply module is respectively connected to the collection module and the operation module; The power supply module is used to supply power to the collection module and the operation module and provide a network; The power supply module includes: the original vehicle battery, a relay, a power switch, a power supply box battery, a power supply control board, a power board, a router, a display screen and an antenna; The power supply control board is used to control the access of the original vehicle battery through the relay when the voltage of the power supply box battery and the load current do not meet the requirements; The original vehicle battery and the power supply box battery are used to supply power to the power supply board through the power supply control board; The power supply board is connected to the acquisition module and the operation module, and is used to supply power to the acquisition module and the operation module; The power supply control board is further used to detect the remaining power, input voltage, output voltage, load current and load power of the battery, and control the display screen to display; The router and the antenna are used to form a wireless network and access the 4G signal for transmission to the acquisition module and the operation module.

8. The intelligent driving map verification system according to claim 7, wherein The acquisition module includes a verification control board, a switch, an integrated navigation system and an industrial camera; the operation module includes an industrial personal computer and a computing power unit; The power supply board is used to output different voltages and powers after filtering, voltage stabilization, monitoring and protection of the electric energy input by the power supply cable, and supply power to the verification control board, the switch, the integrated navigation system, the industrial camera, the industrial personal computer and the computing power unit; The integrated navigation system is used to receive GNSS signals and combine longitude, latitude, elevation, roll, pitch and heading information for positioning and attitude determination, and generate driving trajectory data for transmission to the industrial personal computer; The industrial camera takes pictures according to the external trigger signal of the control board and transmits the road condition data to the industrial personal computer; The verification control board performs data interaction with the power supply control board through the switch; The verification control board accesses the timing pulse and serial port timestamp of the integrated navigation system, tags the camera with a time label when the output pulse triggers the industrial camera to work, and simultaneously outputs the spatio-temporal synchronization data to the industrial personal computer; The industrial personal computer is used to receive user access in real time and execute user instructions; it is also used to receive information from the power supply board and the verification control board, and alarm when the information of the power supply board and the verification control board is abnormal; The industrial personal computer is used to configure parameters for the acquisition project and monitor the real-time acquisition status through the acquisition software; it is also used to fuse the received road condition data, spatio-temporal synchronization data and driving trajectory data to generate fusion data and output it to the computing power unit; The computing power unit is used to perform real-time image processing on the fusion data to obtain feature point geographic information; it is also used to perform differential matching on the feature point geographic information and return the result to the industrial personal computer.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the intelligent driving map verification method according to any one of claims 1 to 5 are implemented.

10. A computer program product, characterized in that, The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the intelligent driving map verification method according to any one of claims 1 to 5 are implemented.

Images