Electronic map data verification method, electronic map construction method and device

Abstract

The present application provides a method for verifying electronic map data, a method for constructing electronic maps, and a device. In the method for verifying electronic map data, at least two non-point cloud data collected by a collection vehicle for a preset area are obtained, and then the at least two non-point cloud data are converted into point clouds to obtain first point cloud data corresponding to the at least two non-point cloud data. Finally, the verification result of the at least two non-point cloud data is determined based on the difference between the first point cloud data and the second point cloud data collected by a radar unit for the preset area. In this technical solution, by determining various data used for making maps in the preset area collected by the collection vehicle as point cloud data, and comparing them with the point cloud data obtained by the radar that actually fits the preset area, it is determined whether the data used for making maps is accurate. No human intervention is required in the process, thereby saving waste of human resources and improving the accuracy of data verification.

Description

Technical Field

[0001] The present application relates to the technical field of electronic maps, and in particular to an electronic map data verification method, an electronic map construction method and a device. Background Art

[0002] In the development of autonomous driving technology, electronic maps are a very core infrastructure that can provide the most effective and accurate road information, and have a decisive impact on the safety and efficiency of autonomous driving in terms of environmental perception, positioning and path planning. Therefore, it is particularly important to verify the accuracy of the relevant data that constitutes the electronic map.

[0003] In the prior art, the above-mentioned relevant data are generally directly used to generate an electronic map, and then a field test is conducted to use a Global Positioning System (GPS) measuring instrument to mark coordinates at actual road locations, and the spatial accuracy of the measured coordinate points is compared with the electronic map to determine the accuracy of the relevant data.

[0004] However, the above method requires the generation of an electronic map first, which is relatively complicated to implement, and due to manual participation, there is a waste of human resources and insufficient verification accuracy. Summary of the invention

[0005] The present application provides an electronic map data verification method, an electronic map construction method and a device to solve the problems of resource waste, low verification accuracy, and cumbersome implementation in the prior art when verifying electronic map data.

[0006] In a first aspect, an embodiment of the present application provides a method for verifying electronic map data, comprising:

[0007] Acquire at least two non-point cloud data collected by a collection vehicle for a preset area;

[0008] Performing point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data;

[0009] A verification result of the at least two non-point cloud data is determined based on a difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area; the verification result indicates the data quality of the at least two non-point cloud data when used to construct an electronic map.

[0010] In one or more embodiments, the non-point cloud data includes image information collected by a camera unit in the acquisition vehicle, positioning information collected by a position measurement unit in the acquisition vehicle, and vehicle speed information collected by an inertial measurement unit in the acquisition vehicle.

[0011] In one or more embodiments, performing point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data includes:

[0012] Determining the running track information of the collected vehicle according to the positioning information and the vehicle speed information;

[0013] Acquire three-dimensional point cloud information around the acquisition vehicle according to the image information;

[0014] According to the running trajectory information and the viewing angle information of the camera unit, the three-dimensional point cloud information is converted into a global coordinate system to obtain the first point cloud data.

[0015] In one or more embodiments, determining the verification result of the at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area includes:

[0016] Determining third point cloud data corresponding to the environment to be verified from the first point cloud data;

[0017] The verification result of the at least two non-point cloud data is determined according to a difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data.

[0018] In one or more embodiments, determining the verification result of the at least two non-point cloud data according to the difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data includes:

[0019] Determine first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data;

[0020] A verification result of the at least two non-point cloud data is determined according to a difference between the first true value data and the second true value data.

[0021] In one or more embodiments, determining the verification result of the at least two non-point cloud data according to the difference between the first true value data and the second true value data includes:

[0022] Determine a first verification result according to a spatial position difference between a geometric vector in the first true value data and a geometric vector in the second true value data, and a first preset threshold;

[0023] and / or,

[0024] Determine a second verification result according to an attribute difference between an element in the first true value data and an element in the second true value data, and a second preset threshold;

[0025] The verification result includes: the first verification result and / or the second verification result.

[0026] In one or more embodiments, the method further comprises:

[0027] According to the spatial position difference and the attribute difference, the verification result is divided into sub-verification results of different deviation dimensions.

[0028] In one or more embodiments, the method further comprises:

[0029] According to the verification results of the at least two non-point cloud data, parameters of the camera unit, the position measurement unit, and the inertial measurement unit are adjusted.

[0030] In one or more embodiments, the environment to be verified includes at least one of the following: an area to be verified in the preset area, a scene to be verified, an element to be verified, and a sample level to be verified.

[0031] In a second aspect, an embodiment of the present application provides an electronic map construction method, including:

[0032] Based on the electronic map data verification method described in any one of the first aspect and any possible design, determining a verification result of collecting at least two non-point cloud data for a preset area;

[0033] If the data quality indicated by the verification result meets the map data quality requirement, an electronic map corresponding to the preset area is constructed using the at least two non-point cloud data.

[0034] In a third aspect, an embodiment of the present application provides a device for verifying electronic map data, including:

[0035] An acquisition module, used to acquire at least two non-point cloud data collected by a collection vehicle for a preset area;

[0036] A processing module, configured to perform point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data;

[0037] A determination module is used to determine the verification result of the at least two non-point cloud data based on the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area; the verification result indicates the data quality of the at least two non-point cloud data when used to construct an electronic map.

[0038] In one or more embodiments, the non-point cloud data includes image information collected by a camera unit in the acquisition vehicle, positioning information collected by a position measurement unit in the acquisition vehicle, and vehicle speed information collected by an inertial measurement unit in the acquisition vehicle.

[0039] In one or more embodiments, the processing module is specifically used to:

[0040] Determining the running track information of the collected vehicle according to the positioning information and the vehicle speed information;

[0041] Acquire three-dimensional point cloud information around the acquisition vehicle according to the image information;

[0042] According to the running trajectory information and the viewing angle information of the camera unit, the three-dimensional point cloud information is converted into a global coordinate system to obtain the first point cloud data.

[0043] In one or more embodiments, the determination module determines the verification result of the at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area, specifically for:

[0044] Determining third point cloud data corresponding to the environment to be verified from the first point cloud data;

[0045] The verification result of the at least two non-point cloud data is determined according to a difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data.

[0046] In one or more embodiments, the determination module determines the verification result of the at least two non-point cloud data according to the difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data, and is specifically used to:

[0047] Determine first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data;

[0048] A verification result of the at least two non-point cloud data is determined according to a difference between the first true value data and the second true value data.

[0049] In one or more embodiments, the determination module determines the verification result of the at least two non-point cloud data according to the difference between the first true value data and the second true value data, specifically for:

[0050] Determine a first verification result according to a spatial position difference between a geometric vector in the first true value data and a geometric vector in the second true value data, and a first preset threshold;

[0051] and / or,

[0052] Determine a second verification result according to an attribute difference between an element in the first true value data and an element in the second true value data, and a second preset threshold;

[0053] The verification result includes: the first verification result and / or the second verification result.

[0054] In one or more embodiments, the determining module is further configured to:

[0055] According to the spatial position difference and the attribute difference, the verification result is divided into sub-verification results of different deviation dimensions.

[0056] In one or more embodiments, the determining module is further configured to:

[0057] According to the verification results of the at least two non-point cloud data, parameters of the camera unit, the position measurement unit, and the inertial measurement unit are adjusted.

[0058] In one or more embodiments, the environment to be verified includes at least one of the following: an area to be verified in the preset area, a scene to be verified, an element to be verified, and a sample level to be verified.

[0059] In a fourth aspect, an embodiment of the present application provides an electronic map construction device, including:

[0060] A determination module, configured to determine a verification result of collecting at least two non-point cloud data for a preset area based on the verification method for electronic map data described in any one of the first aspect and any possible designs;

[0061] A construction module is used to construct an electronic map corresponding to the preset area by using the at least two non-point cloud data when the data quality indicated by the verification result meets the map data quality requirement.

[0062] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0063] The memory stores computer-executable instructions;

[0064] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first or second aspect or in any one of the above-mentioned methods.

[0065] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first, second or any one of the above aspects.

[0066] In the seventh aspect, an embodiment of the present application provides a computer program, wherein the computer program product includes a computer program, wherein the computer program is stored in a computer-readable storage medium, and at least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, the method described in the first or second aspect or any one of the methods can be implemented.

[0067] The embodiments of the present application provide a method for verifying electronic map data, a method for constructing an electronic map, and a device. In the method for verifying electronic map data, at least two non-point cloud data collected by a collection vehicle for a preset area are obtained, and then the at least two non-point cloud data are converted into point clouds to obtain first point cloud data corresponding to the at least two non-point cloud data. Finally, based on the difference between the first point cloud data and the second point cloud data collected by a radar unit for the preset area, a verification result of the at least two non-point cloud data is determined, and the verification result indicates the data quality of the at least two non-point cloud data when used to construct an electronic map. In this technical solution, the data quality of the relevant data used for making maps in a preset area collected on a collection vehicle is determined by converting the data into point cloud data and comparing it with the point cloud data with high data quality acquired by the radar unit for the preset area. On the one hand, this method does not require human participation, thereby saving waste of human resources and improving the verification efficiency of the relevant data used for electronic map construction. On the other hand, this method converts multiple non-point cloud data collected for the preset area into point cloud data, and verifies the data quality of multiple non-point cloud data used for constructing electronic maps by comparing the difference between the point cloud data with high accuracy acquired by the radar unit, further improving the accuracy of data verification for electronic map construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0069] Figure 1 A schematic diagram of an architecture for producing electronic maps;

[0070] Figure 2 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 1 ;

[0071] Figure 3Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 2 ;

[0072] Figure 4 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 3 ;

[0073] Figure 5 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 4 ;

[0074] Figure 6 A verification schematic diagram provided for an embodiment of the present application;

[0075] Figure 7 A schematic diagram of a process for constructing an electronic map provided in an embodiment of the present application;

[0076] Figure 8 A schematic diagram of the structure of the electronic map data verification device provided in an embodiment of the present application;

[0077] Fig. 9 A schematic diagram of the structure of an electronic map construction device provided in an embodiment of the present application;

[0078] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0079] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0080] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0081] Before introducing the embodiments of the present application, the application background of the embodiments of the present application is first explained:

[0082] In the development of autonomous driving technology, electronic maps are a very core infrastructure that can provide the most effective and accurate road information, and have a decisive impact on the safety and efficiency of autonomous driving in terms of environmental perception, positioning and path planning.

[0083] Figure 1 A schematic diagram of the architecture of an electronic map production, such as Figure 1 As shown, the architecture diagram includes: field collection, data processing, in-house production, quality verification, and data production.

[0084] In a possible implementation, the field collection stage is generally to collect road trajectories, images, spatial positions, and three-dimensional point clouds in one stop through high-precision equipment such as cameras, radars, high-precision global positioning systems (GPS), inertial measurement units (IMUs), and central control machines mounted on the collection vehicles, so as to obtain basic data for generating subsequent electronic maps; data processing is to pre-process the collected basic data to remove smudge data, etc.; in the industry production stage, the processed data is used to generate the initial electronic map; in the quality verification stage, the initial electronic map is verified by actual vehicle testing or field testing. After the verification is passed, the data production stage is entered, and the verified electronic map is put online, etc.

[0085] In the above implementation process, due to the high cost of the Lidar acquisition equipment itself and the large amount of data processing and storage, in the mass production plan of the electronic map, the electronic map collection vehicle does not turn on the Lidar device 80%-90% of the time during the field collection process, and only turns on the Lidar device on 10%-20% of the road sections for laser point cloud collection for precise positioning, matching and production.

[0086] Based on the above situation, the basic data collected by cameras, GPS, IMU and other units has a certain degree of inaccuracy, which in turn affects the generation of electronic maps and has a decisive impact on the safety and efficiency of autonomous driving. Therefore, how to verify the data quality of basic data has become a technical problem that needs to be solved urgently.

[0087] In the implementation of the above-mentioned existing related technologies, the following verification method for generating basic data related to electronic maps is provided:

[0088] First, real vehicle testing, where the electronic map generated based on the basic data is loaded onto the vehicle for real-time road testing. During the road testing, the map accuracy and precision are verified, which can determine the accuracy of the basic data.

[0089] Second, field measurement uses GPS measuring instruments to mark coordinates at actual road locations, and compares the spatial accuracy of the measured coordinate points with the electronic map generated based on the basic data to determine the accuracy of the basic data.

[0090] However, in the above-mentioned prior art, it is necessary to first generate an electronic map based on the collected data, and this step is cumbersome for data verification; then, field measurements are carried out based on the electronic map, such as the coordinate marking method, which not only requires the participation of human resources, but also involves the verification of a large amount of data, is time-consuming, has limited sample size, and cannot meet the disadvantages of large-scale sample testing.

[0091] In response to the technical problems existing in the prior art, the inventors of the present application have the following idea: before generating an electronic map, the acquired basic data can be verified, and then after the verification, the electronic map can be directly generated based on the basic data with qualified data quality of the verification result, avoiding the cumbersome implementation existing in the prior art; in most scenarios, the basic data is collected based on high-precision equipment such as cameras, GPS, IMU, etc., and then the map is produced, which leads to certain problems in the accuracy of the produced map. At this time, the data measured by measurement units such as cameras, GPS, IMU, etc. are reversed to obtain point cloud data, which is compared with the point cloud data collected by more accurate radar in the area. Then, the accuracy of the data used to generate the map can be verified, which does not require human participation, does not require high costs, and improves the accuracy of verification.

[0092] Furthermore, in subsequent implementations, if the verification result of the data quality is determined to be high, such as meeting the map data quality requirements, an accurate and more realistic electronic map can be generated based on the basic data.

[0093] In one embodiment, the above method can also be used to retrieve basic data corresponding to some areas in the high-precision map for verification after the electronic map is generated to determine the accuracy of the electronic map.

[0094] It should be understood that the electronic map in the embodiment of the present application can be any one of a high-precision map, a standard-precision map, and other precision maps. The following content in the embodiment of the present application is explained using a high-precision map as an example of an electronic map.

[0095] Therefore, an embodiment of the present application proposes a method for verifying electronic map data, and one possible application scenario may be: after the data of an entire road section is collected by high-precision equipment such as a vehicle-based camera, GPS, IMU, etc., the data of a portion of the road can be intercepted for accuracy verification. When the verification result of the data of this portion of the road is accurate, an electronic map can be generated based on the data of the entire road section.

[0096] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0097] Among them, the executor of this application is an electronic device, which can be a vehicle, a server, a computing device, etc.

[0098] Figure 2 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 1 ,like Figure 2 As shown, the method may include the following steps:

[0099] Step 21: Obtain at least two non-point cloud data collected by a collection vehicle for a preset area.

[0100] In this step, in order to generate a more accurate and more realistic electronic map, the data for generating the electronic map needs to be verified. The data for the electronic map may be based on at least two non-point cloud data collected by the collection vehicle.

[0101] Optionally, the non-point cloud data may be data collected based on a non-radar unit in a collection vehicle and used for subsequent drawing of an electronic map, such as the basic data obtained by the collection vehicle collecting a preset area as mentioned above.

[0102] In order to improve the verification efficiency, at least two non-point cloud data in a preset area may be obtained, and the at least two non-point cloud data in the area may be verified.

[0103] Optionally, the preset area can be any designated area in the actual scene corresponding to the electronic map, can be an area within a certain range along a preset road, can be an area measured by radar in some special sections, and in some cases can be the area covered by the entire map.

[0104] Optionally, the non-point cloud data includes image information collected by a camera unit in the acquisition vehicle, positioning information collected by a position measurement unit in the acquisition vehicle, and vehicle speed information collected by an inertial measurement unit in the acquisition vehicle.

[0105] In one possible implementation, the imaging unit for acquiring image information may be a camera or a camera mounted on a collection vehicle; the position measurement unit for acquiring positioning information may be a GPS mounted on the vehicle; and the inertial measurement unit for acquiring vehicle speed information may be composed of at least one or more of an accelerometer, a gyroscope, and a magnetometer.

[0106] In some possible implementations, the image information is the image taken during the actual collection process; the positioning information is the longitude and latitude of the vehicle when it is running; and the vehicle speed information is the speed and direction of the vehicle when it is running.

[0107] In addition, the positioning information may also include: the height of the acquisition vehicle, which may be the altitude or the ground height, which in some implementations may be used to create a three-dimensional model or scene of a geographic entity, such as a building, mountain, river, etc. By combining longitude and latitude with altitude, the vertical position and shape of these geographic elements may be accurately located and presented.

[0108] In a possible subsequent implementation, the "spatial position" of the point cloud mentioned below may be the longitude and latitude information of the point cloud. In some implementations, it may also include the height of the point cloud at the longitude and latitude, that is, it may be a three-dimensional coordinate.

[0109] Step 22: Perform point cloud conversion processing on at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data.

[0110] In this solution, in order to verify the electronic map data, a more accurate radar unit is used to obtain point cloud data for comparison. Therefore, in this step, at least two non-point cloud data need to be converted into point cloud data to obtain point cloud data corresponding to at least two non-point cloud data, which are recorded as the first point cloud data; the aforementioned radar unit can be a radar device installed on the collection vehicle (such as a laser radar or a radar rangefinder, etc.).

[0111] Step 23: Determine the verification result of the at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area.

[0112] The verification result indicates the data quality of at least two non-point cloud data when used to construct the electronic map.

[0113] In this step, since the second point cloud data corresponding to the preset area collected by the radar unit is relatively accurate, but the cost is relatively high, in actual implementation, the point cloud data determined by the camera unit, the position measurement unit, and the inertial measurement unit can be used for comparison to determine the accuracy and reliability of the non-point cloud data collected by the camera unit, the position measurement unit, and the inertial measurement unit during actual operation.

[0114] Optionally, the verification result can be either qualified data quality or unqualified data quality, or can be divided according to the size, degree, attributes, etc. of data differences based on actual conditions.

[0115] In one possible implementation, taking the size of data differences as an example, at the same position, the distance between a point in the converted point cloud and a point in the point cloud acquired by the radar unit can be divided according to a preset difference threshold to obtain a corresponding difference range; taking the intensity information of a point in the point cloud as an example, at the same position, the intensity information of the point in the converted point cloud is compared with the intensity information of the point in the point cloud acquired by the radar unit, and different intensity ranges and corresponding materials can be set to detect the material classification corresponding to different points.

[0116] Furthermore, after step 23, it is also possible to: adjust parameters of the camera unit, the position measurement unit, and the inertial measurement unit according to the verification results of the at least two non-point cloud data.

[0117] In this implementation, the verification results corresponding to at least two non-point cloud data can, to a certain extent, reflect the accuracy of each acquisition unit in the acquisition vehicle during the actual map acquisition process. Therefore, based on the verification results, the parameters of the camera unit, position measurement unit, and inertial measurement unit can be adjusted to improve the accuracy of subsequent acquisition operations.

[0118] For example, compare the differences in spatial position (such as three-dimensional coordinates), direction, angle, etc. between two points in the same area, and determine through statistical analysis or visual inspection that the data of the above units are more accurate or consistent in specific situations. When adjusting parameters, carefully record the changes in parameters and their impact on point cloud data to achieve parameter adjustment.

[0119] For the camera unit, you can adjust the intrinsic parameters (such as focal length, distortion coefficient) and extrinsic parameters (camera unit position and attitude) of the camera unit to improve the spatial accuracy of its point cloud data; for the position measurement unit, adjust its accuracy parameters or use differential GPS to improve the accuracy of position measurement; for the inertial measurement unit, adjust the zero bias and scale factor of the gyroscope and accelerometer to reduce drift and errors in the inertial sensor data.

[0120] In one possible implementation, in the same area, the spatial position deviation between the points in the converted point cloud and the points in the point cloud acquired by the radar unit is large. For the camera unit, for example, if the deviation indicates that the point is farther away from the camera unit than the radar unit, increasing the value of the translation vector can push the scene toward the camera; for GPS, for example, if the deviation indicates that the positioning information is significantly different, the update frequency of the GPS in its accuracy parameters can be increased; for the gyroscope and accelerometer, for example, if the deviation indicates that the vehicle's speed information is lower than the actual speed, the scale factor of the gyroscope can be increased.

[0121] The electronic map data verification method provided in the embodiment of the present application obtains at least two non-point cloud data collected by the collection vehicle for a preset area, then performs point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data, and finally determines the verification result of the at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area, and the verification result indicates the data quality of the at least two non-point cloud data when used to construct the electronic map. In this technical solution, the data quality of the relevant data used to make the map is determined by converting various data used to make the map in the preset area collected by the collection vehicle into point cloud data, and comparing them with the point cloud data with high data quality obtained by the radar unit for the preset area. On the one hand, this method does not require human participation, thereby saving waste of human resources and improving the verification efficiency of the relevant data used to construct the electronic map; on the other hand, in this method, multiple non-point cloud data collected for the preset area are converted into point cloud data, and the difference between the point cloud data with high accuracy collected by the radar unit is used to verify the data quality of multiple non-point cloud data used to construct the electronic map, further improving the accuracy of data verification for the construction of the electronic map.

[0122] Based on the above embodiments, Figure 3 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 2 ,like Figure 3 As shown, the above step 22 can be implemented as follows:

[0123] Step 31: Determine and collect the running track information of the vehicle according to the positioning information and the vehicle speed information;

[0124] In this step, the positioning information is combined with the vehicle speed information to more accurately determine the running trajectory of the collected vehicle, including position, direction and speed.

[0125] One possible implementation is to synchronize the timestamps of the positioning information and the vehicle speed information to ensure that they are available at the same time point, and then use a fusion algorithm (such as the Extended Kalman Filter (EKF)) to perform attitude solution on the positioning information and the vehicle speed information after the timestamp synchronization, and calculate the position, speed and direction of the collected vehicle at each time point during the entire operation, so as to construct a running trajectory during the operation.

[0126] The running trajectory may be a path that collects the position of the vehicle in the coordinate system over time, and may reflect the position, speed and direction of the vehicle.

[0127] Step 32: Acquire three-dimensional point cloud information around the acquisition vehicle based on the image information;

[0128] In this step, the image information includes the depth information of each object in the actual acquisition scene, and the three-dimensional point cloud information around the acquisition vehicle can be determined based on the depth information.

[0129] In a possible implementation, taking a stereo camera as an example, the parallax information between the cameras can be used to calculate the depth information of objects in a three-dimensional scene, such as by using a stereo matching algorithm, thereby obtaining a depth estimate of each pixel, that is, three-dimensional point cloud information.

[0130] In another possible implementation, the Simultaneous Localization and Mapping (SLAM) technology can be combined to build a three-dimensional map of the vehicle's surroundings in real time. SLAM can not only estimate the vehicle's position and posture, but also create and update the three-dimensional model of the environment and represent them as three-dimensional point cloud information.

[0131] In another possible implementation, a deep learning model, such as a semantic segmentation model or a depth estimation model based on a convolutional neural network, can be used to infer the depth information of the scene from a single or multiple images. These models can be trained to directly predict the depth or point cloud data of each pixel from the image acquired by the camera, that is, to obtain three-dimensional point cloud information.

[0132] Step 33: According to the running trajectory information and the viewing angle information of the camera unit, the three-dimensional point cloud information is converted into a global coordinate system to obtain first point cloud data.

[0133] The viewing angle information provided by the camera unit refers to the position and direction (posture) of the camera, which can be obtained by calibrating the camera unit.

[0134] In this step, the three-dimensional point cloud information is usually acquired in the coordinate system of the camera unit (eg, the camera coordinate system or the local acquisition vehicle coordinate system), and the position of each point is relative to the coordinate system of the camera or the acquisition vehicle.

[0135] Therefore, the three-dimensional point cloud information is transformed into the global coordinate system in combination with the running trajectory information to obtain the first point cloud data that can be used for accuracy verification.

[0136] In one possible implementation, first, the position and posture of the camera in each frame are interpolated based on the motion trajectory information, and then the position (rotation matrix and translation vector) of the camera coordinate system in each frame relative to the global coordinate system is calculated based on the camera's intrinsic and extrinsic parameters, and each three-dimensional point is transformed from the camera coordinate system (local coordinate system) to the global coordinate system.

[0137] The electronic map data verification method provided in the embodiment of the present application determines the running track information of the collected vehicle based on the positioning information and the vehicle speed information, then obtains the three-dimensional point cloud information around the collected vehicle based on the image information, and finally converts the three-dimensional point cloud information into a global coordinate system based on the running track information and the viewing angle information of the camera unit to obtain the first point cloud data. In this technical solution, the point cloud information corresponding to the image information is arranged in the same coordinate system through the positioning information and the vehicle speed information, which can be more conveniently and accurately compared with the point cloud data obtained by the subsequent radar.

[0138] Based on the above embodiments, Figure 4 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 3 ,like Figure 4 As shown, the above step 23 can be implemented as follows:

[0139] Step 41, determining third point cloud data corresponding to the environment to be verified from the first point cloud data;

[0140] In this step, in order to reduce the amount of data required for accuracy verification to improve verification efficiency, or to verify only part of the data under some requirements, some verification scenarios can be set to limit the comparison and only compare the point cloud data in the verification environment.

[0141] That is, based on the features involved in the environment to be verified, the first point cloud data is region-cut to obtain third point cloud data corresponding to the environment to be verified.

[0142] Optionally, the environment to be verified includes at least one of the following: an area to be verified in a preset area, a scene to be verified, an element to be verified, and a sample level to be verified.

[0143] For example, the area to be verified in the preset area can be an element within a preset distance from point A in the preset area. The preset distance can be set according to actual needs, such as but not limited to setting the preset distance to 1 meter, 1.5 meters or 2 meters, etc.; the scene to be verified can be one or more elements corresponding to scenes such as bridges, ramps, tunnels, main and auxiliary roads; the elements to be verified can be elements in the scene to be verified, or one or more elements in the preset area such as trees and markings in the preset area; the sample size to be verified can be the number of elements being at least a certain preset value, that is, the element scale, etc.

[0144] Step 42: Determine verification results of at least two non-point cloud data according to the difference between the third point cloud data and the fourth point cloud data corresponding to the environment to be verified in the second point cloud data.

[0145] In this step, in order to ensure the rationality and comparability of the verification, it is necessary to obtain the point cloud data corresponding to the environment to be verified in the second point cloud data collected by the radar, recorded as the fourth point cloud data, and then compare the third point cloud data and the fourth point cloud data to determine the verification results corresponding to at least two non-point cloud data.

[0146] The electronic map data verification method provided in the embodiment of the present application determines the third point cloud data corresponding to the environment to be verified from the first point cloud data, and determines the verification result of the at least two non-point cloud data according to the difference between the third point cloud data and the fourth point cloud data corresponding to the environment to be verified in the second point cloud data. In this technical solution, a specific environment to be verified is selected from a preset area to increase the accuracy of the verification, reduce the amount of data to be verified, improve the verification efficiency, and different verification environments can increase the diversity of the verification results.

[0147] Based on the above embodiments, Figure 5 Schematic diagram of the process of verifying the electronic map data provided in the embodiment of the present application Figure 4 ,like Figure 5 As shown, the above step 42 can be implemented as follows:

[0148] Step 51, determining first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data;

[0149] In this step, true value data can be produced for the corresponding point cloud data based on production specification requirements to obtain first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data.

[0150] Optionally, the first true value data is used to describe the attributes and / or geometric vectors of the elements in the third point cloud data; the second true value data is used to describe the attributes and / or geometric vectors of the elements in the fourth point cloud data.

[0151] In a possible implementation, for any point cloud data in the third point cloud data and the fourth point cloud data, computer vision and geometric processing may be used to extract the attributes or geometric vectors of the elements of interest from the point cloud data, which may involve the following:

[0152] 1. Attributes of elements:

[0153] Color attribute: If the point cloud data is output by a color camera or lidar, each point may have red, green, and blue (RGB) or red, green, and blue transparency (RGBA); intensity attribute: a common attribute in lidar point clouds, which indicates the reflection intensity of each point and can reflect the changes in the surface reflection properties; classification attribute: an attribute that marks each point as belonging to different categories or objects, such as ground points, building points, tree points, etc.; timestamp attribute: if the point cloud data is collected from a dynamic scene, the timestamp attribute can identify the collection time of each point; other custom attributes: depending on the specific application scenario, various custom attributes can also be defined and extracted, such as smoothness, surface normal direction, density, etc.

[0154] 2. Geometric vector:

[0155] Position vector: describes the position of each point in three-dimensional space, usually represented by (x, y, z) coordinates; Normal vector: describes the normal direction of each point on the surface, used to characterize the direction and curvature of the surface, and is important geometric information in many point cloud analysis tasks; Curvature: reflects the degree of curvature or curvature of the surface at a certain point, usually calculated by the rate of change of the normal; Bounding box or envelope vector: describes the minimum bounding box or minimum bounding sphere of a point cloud or its subset, used to quickly calculate the shape range of the point cloud; Other local or global descriptors: descriptors used to characterize local or global structures in point clouds; If the point cloud data contains multiple features, segmentation and classification algorithms can be used to identify and distinguish different features, and then extract feature attributes or geometric vectors for each feature.

[0156] Step 52: Determine verification results of at least two non-point cloud data according to the difference between the first true value data and the second true value data.

[0157] In this step, the difference between the first true value data corresponding to the third point cloud data and the second true value data corresponding to the fourth point cloud data is compared, that is, the information involved in the difference is obtained as the verification result corresponding to at least two non-point cloud data. The verification result can also represent the verification result of generating the electronic map corresponding to the preset area.

[0158] Optionally, this step may be implemented as follows (the verification results corresponding to the at least two non-point cloud data include: a first verification result and / or a second verification result):

[0159] First, determining a first verification result according to a spatial position difference between a geometric vector in the first true value data and a geometric vector in the second true value data, and a first preset threshold;

[0160] The spatial position difference may be a difference between geometric vectors in three-dimensional coordinates;

[0161] In this implementation, the geometric vectors are exemplified in the following cases (for illustration only):

[0162] 1. Difference of position vector: The position and posture of the midpoint of the first truth data and the midpoint of the second truth data at the same geographical location can be represented by a position vector in a three-dimensional coordinate respectively, and the difference between the two position vectors, i.e., the distance difference, can be calculated;

[0163] 2. Difference of normal vector: The normal vector describes the direction of the surface of two adjacent points, that is, the normal vectors of the adjacent points corresponding to the same geographical location in the first true value data and the second true value data, and the difference between the two normal vectors is taken as the difference of the normal vector.

[0164] For example, the spatial position difference is compared with a threshold value that can be accommodated (i.e., a first preset threshold value) to determine, at any position, first true value data and second true value data corresponding to a spatial position difference value greater than the first preset threshold value, and first true value data and second true value data corresponding to a spatial position difference value not greater than the first preset threshold value, as a first verification result, that is, the first verification result includes first true value data and second true value data having data quality distinguished based on spatial position.

[0165] In one implementation, the geometry, coordinates, feature representation, and feature magnitude of the elements in the first verification result that are greater than a first preset threshold value may be output.

[0166] For example, taking the spatial position difference including the distance difference as an example, for the same geographical location, the coordinates of point A in the first true value data are (2,2,2), and the coordinates of point B in the second true value data are (2,2,3). Here, the first preset threshold is set to 0.4, and the calculated distance difference between A and B is 1, then A and B are considered to be points in the first verification result with unqualified data quality.

[0167] For another example, taking the spatial position difference including the distance difference as an example, for the same geographical location, the coordinates of point C in the first true value data are (5, 2, 2), and the coordinates of point D in the second true value data are (5.2, 2, 2). Here, the first preset threshold is set to 0.5, and the calculated distance difference between C and D is 0.2, then A and B are considered to be points in the first verification result with qualified data quality.

[0168] It should be understood that for different geometric vectors, the corresponding first preset threshold values ​​may be different and may be adjusted based on actual conditions.

[0169] Second, a second verification result is determined according to an attribute difference between an element in the first true value data and an element in the second true value data, and a second preset threshold.

[0170] In this implementation, the attribute difference is given in the following examples (for example only): the attribute difference may include: the difference in brightness, chroma, contrast, and saturation between two elements.

[0171] That is, the two elements are respectively the attributes / expression elements of the expression points corresponding to the same geographical location in the physical world in the first point cloud data and the second point cloud data.

[0172] Taking the brightness difference as an example, the brightness difference between the two elements at the same geographical location is compared with the threshold that can be accommodated (i.e., the second preset threshold) to determine the first true value data and the second true value data corresponding to the brightness difference being greater than the second preset threshold, and the first true value data and the second true value data corresponding to the brightness difference being not greater than the second preset threshold, as the second verification result, that is, the second verification result includes the first true value data and the second true value data of the data quality distinguished based on the attributes of the elements.

[0173] In one implementation, the geometry, coordinates, feature ID, and feature magnitude of the elements in the second verification result that are inconsistent or have deviations exceeding a threshold value may be output.

[0174] For example, taking the example of attribute differences including brightness differences, for the element H in the first true value data at the same geographical location, the brightness is 15, and the element I in the second true value data has a brightness of 16. The second preset threshold is set to 0.6 here, and the calculated brightness difference between H and I is 1, then H and I are considered to be elements with unqualified data quality in the second verification result.

[0175] For another example, taking the attribute difference including brightness difference as an example, for the element M in the first true value data at the same geographical location, the brightness is 15, and the element N in the second true value data has a brightness of 15.2. Here, the second preset threshold is set to 0.6, and the calculated brightness difference between M and N is 0.2, then M and N are considered to be elements with qualified data quality in the second verification result.

[0176] It should be understood that for different element attributes, the corresponding second preset threshold values ​​may be different and may be adjusted based on actual conditions.

[0177] In one possible implementation, Figure 6 The verification diagram provided for the embodiment of the present application is as follows: Figure 6 As shown, the schematic diagram includes: lane line 1, lane line 2, lane line 3, and lane line 4.

[0178] For example, lane line 1 is the information corresponding to the element in the first true value data, and lane line 2 is the information corresponding to the element in the second true value data. Then, it can be determined that the spatial position difference between the two lane lines is 6, which is greater than the first preset threshold value of 5. Therefore, it is considered that the element in the map, namely, "lane line 1", is inaccurate.

[0179] For another example, lane line 3 is the information corresponding to the element in the first true value data, and lane line 4 is the information corresponding to the element in the second true value data. It can be determined that the attributes between the two lane lines are inconsistent, that is, lane line 3 is a dotted lane line, and lane line 4 is a solid lane line. The degree of attribute inconsistency can correspond to a certain value, such as 30%, which is greater than the second preset threshold of 10%. In this case, it is considered that the element in the map, namely "lane line 3", is inaccurate.

[0180] Furthermore, after step 52, it is also possible to: divide the verification result into sub-verification results of different deviation dimensions according to the spatial position difference and the attribute difference.

[0181] In this implementation, the accuracy verification level can be analyzed based on the verification results. For example, the sub-verification results can be multi-dimensional evaluation results such as qualified level, unqualified level, unqualified location, unqualified scene, unqualified accuracy deviation threshold, etc.

[0182] That is, different threshold ranges, different scenarios, etc. can be set.

[0183] It should be understood that the number of features such as the environment to be verified involved in the embodiments of the present application is not limited.

[0184] The electronic map data verification method provided in the embodiment of the present application determines the first true value data corresponding to the third point cloud data and the second true value data corresponding to the fourth point cloud data; and determines the verification results of at least two non-point cloud data according to the difference between the first true value data and the second true value data. In this technical solution, based on the comparison between the attributes and / or geometric vectors of the elements in the two point cloud data, the verification results can be determined more concretely and in different dimensions.

[0185] Based on the above embodiments, Figure 7 A schematic diagram of the process of constructing an electronic map provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the method may include the following steps:

[0186] Step 71: Based on the verification method of electronic map data, determine the verification result of collecting at least two non-point cloud data for a preset area.

[0187] In this step, the verification result of verifying at least two non-point cloud data is described in detail in the above embodiment, and the verification result indicates whether the data quality of the at least two non-point cloud data is qualified when used to construct the electronic map.

[0188] Step 72: When the data quality indicated by the verification result meets the map data quality requirement, construct an electronic map corresponding to the preset area using at least two non-point cloud data.

[0189] In this step, if the data quality indicated by the verification result meets the map data quality requirement, it is considered that at least two non-point cloud data can be used to construct an electronic map corresponding to the preset area.

[0190] On the contrary, if the data quality indicated by the verification result does not meet the map data quality requirements, it is considered that at least two non-point cloud data cannot be used to construct the electronic map corresponding to the preset area; then the parameters of the camera unit, position measurement unit, and inertial measurement unit can be adjusted to re-acquire the map data; other more accurate methods can also be used to acquire map data to avoid inaccurate generated electronic maps.

[0191] The implementation of adjusting the parameters in each unit may refer to the relevant content in step 23.

[0192] The electronic map construction method provided in the embodiment of the present application is based on the electronic map data verification method in the above embodiment, determines the verification result of collecting at least two non-point cloud data for a preset area, and when the data quality indicated by the verification result meets the map data quality requirements, constructs an electronic map corresponding to the preset area through at least two non-point cloud data. In this technical solution, the verification result indicates whether the data quality meets the map data quality requirements. If it meets the requirements, the electronic map corresponding to the preset area can be accurately and reliably generated based on the non-point cloud data, thereby improving the safety and efficiency of autonomous driving.

[0193] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0194] Figure 8 This is a schematic diagram of the structure of the electronic map data verification device provided in the embodiment of the present application. Figure 8 As shown, the device comprises:

[0195] An acquisition module 81 is used to acquire at least two non-point cloud data collected by a collection vehicle for a preset area;

[0196] A processing module 82, configured to perform point cloud conversion processing on at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data;

[0197] The determination module 83 is used to determine the verification results of at least two non-point cloud data based on the difference between the first point cloud data and the second point cloud data collected by the radar unit for a preset area; the verification results indicate the data quality of the at least two non-point cloud data when used to construct an electronic map.

[0198] In one or more embodiments, the non-point cloud data includes image information collected by a camera unit in the acquisition vehicle, positioning information collected by a position measurement unit in the acquisition vehicle, and vehicle speed information collected by an inertial measurement unit in the acquisition vehicle.

[0199] In one or more embodiments, the processing module 82 is specifically configured to:

[0200] Determine the running track information of the collected vehicle according to the positioning information and the vehicle speed information;

[0201] According to the image information, three-dimensional point cloud information around the collected vehicle is obtained;

[0202] According to the running trajectory information and the viewing angle information of the camera unit, the three-dimensional point cloud information is converted into a global coordinate system to obtain first point cloud data.

[0203] In one or more embodiments, the determination module 83 determines the verification results of at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area, specifically for:

[0204] Determining third point cloud data corresponding to the environment to be verified from the first point cloud data;

[0205] The verification results of at least two non-point cloud data are determined according to the difference between the third point cloud data and the fourth point cloud data corresponding to the environment to be verified in the second point cloud data.

[0206] In one or more embodiments, the determination module 83 determines the verification results of at least two non-point cloud data according to the difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data, specifically for:

[0207] Determine first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data;

[0208] According to the difference between the first true value data and the second true value data, verification results of at least two non-point cloud data are determined.

[0209] In one or more embodiments, the determination module 83 determines the verification results of at least two non-point cloud data according to the difference between the first true value data and the second true value data, specifically for:

[0210] Determine a first verification result according to a spatial position difference between a geometric vector in the first true value data and a geometric vector in the second true value data, and a first preset threshold;

[0211] and / or,

[0212] Determine a second verification result according to an attribute difference between an element in the first true value data and an element in the second true value data, and a second preset threshold;

[0213] The verification result includes: a first verification result and / or a second verification result.

[0214] In one or more embodiments, the determination module 83 is further configured to:

[0215] According to the spatial position difference and attribute difference, the verification results are divided into sub-verification results with different deviation dimensions.

[0216] In one or more embodiments, the determination module 83 is further configured to:

[0217] According to the verification results of at least two non-point cloud data, parameters of the camera unit, the position measurement unit, and the inertial measurement unit are adjusted.

[0218] In one or more embodiments, the environment to be verified includes at least one of the following: an area to be verified in a preset area, a scene to be verified, an element to be verified, and a sample level to be verified.

[0219] The electronic map data verification device provided in the embodiment of the present application can be used to execute the electronic map data verification method in any of the above embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0220] Fig. 9 This is a schematic diagram of the structure of the electronic map construction device provided in the embodiment of the present application. Fig. 9 As shown, the device comprises:

[0221] A determination module 91 is used to determine the verification result of collecting at least two non-point cloud data for a preset area based on the above-mentioned electronic map construction method;

[0222] The construction module 92 is used to construct an electronic map corresponding to a preset area by using at least two non-point cloud data when the data quality indicated by the verification result meets the map data quality requirement.

[0223] The electronic map data verification device provided in the embodiment of the present application can be used to execute the electronic map construction method in any of the above embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0224] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0225] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Fig.10 As shown, the electronic device may include: a processor 101, a memory 102, and computer program instructions stored in the memory 102 and executable on the processor 101. When the processor 101 executes the computer program instructions, the electronic map data verification method or the electronic map construction method provided in any of the aforementioned embodiments is implemented.

[0226] Optionally, the above-mentioned components of the electronic device may be connected via a system bus.

[0227] The memory 102 may be a separate storage unit or a storage unit integrated in the processor 101. The number of the processor 101 is one or more.

[0228] It should be understood that the processor 101 may be a central processing unit (CPU), or other general-purpose processors 101, digital signal processors 101 (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor 101 may be a microprocessor 101 or the processor 101 may be any conventional processor 101, etc. The steps of the method disclosed in the present application may be directly embodied as being executed by the hardware processor 101, or may be executed by a combination of hardware and software modules in the processor 101.

[0229] The system bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The memory 102 may include a random access memory 102 (RAM), and may also include a non-volatile memory 102 (NVM), such as at least one disk storage 102.

[0230] All or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions. The above-mentioned program can be stored in a readable memory 102. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the above-mentioned memory 102 (storage medium) includes: read-only memory 102 (ROM), RAM, flash memory 102, hard disk, solid state hard disk, magnetic tape, floppy disk, optical disc and any combination thereof.

[0231] The electronic device provided in the embodiment of the present application can be used to execute the electronic map data verification method or electronic map construction method provided in any of the above method embodiments. The implementation principles and technical effects are similar and will not be repeated here.

[0232] An embodiment of the present application provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the above-mentioned electronic map data verification method or electronic map construction method.

[0233] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0234] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0235] An embodiment of the present application also provides a computer program product, which includes a computer program, which is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the above-mentioned electronic map data verification method or electronic map construction method can be implemented.

[0236] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for verifying electronic map data, characterized in that: include: Acquire at least two non-point cloud data collected by a collection vehicle for a preset area; Performing point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data; A verification result of the at least two non-point cloud data is determined based on a difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area; the verification result indicates the data quality of the at least two non-point cloud data when used to construct an electronic map; if the data quality indicated by the verification result meets the map data quality requirements, an electronic map corresponding to the preset area is constructed using the at least two non-point cloud data.

2. The method according to claim 1, characterized in that The non-point cloud data includes image information collected by a camera unit in the collection vehicle, positioning information collected by a position measurement unit in the collection vehicle, and vehicle speed information collected by an inertial measurement unit in the collection vehicle.

3. The method according to claim 2, characterized in that The performing point cloud conversion processing on the at least two non-point cloud data to obtain first point cloud data corresponding to the at least two non-point cloud data includes: Determining the running track information of the collected vehicle according to the positioning information and the vehicle speed information; Acquire three-dimensional point cloud information around the acquisition vehicle according to the image information; According to the running trajectory information and the viewing angle information of the camera unit, the three-dimensional point cloud information is converted into a global coordinate system to obtain the first point cloud data.

4. The method according to any one of claims 1 to 3, characterized in that: The determining the verification results of the at least two non-point cloud data according to the difference between the first point cloud data and the second point cloud data collected by the radar unit for the preset area includes: Determining third point cloud data corresponding to the environment to be verified from the first point cloud data; The verification result of the at least two non-point cloud data is determined according to a difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data.

5. The method according to claim 4, characterized in that Determining the verification results of the at least two non-point cloud data according to the difference between the fourth point cloud data corresponding to the environment to be verified in the third point cloud data and the second point cloud data includes: Determine first true value data corresponding to the third point cloud data and second true value data corresponding to the fourth point cloud data; A verification result of the at least two non-point cloud data is determined according to a difference between the first true value data and the second true value data.

6. The method according to claim 5, characterized in that The step of determining the verification result of the at least two non-point cloud data according to the difference between the first true value data and the second true value data comprises: Determine a first verification result according to a spatial position difference between a geometric vector in the first true value data and a geometric vector in the second true value data, and a first preset threshold; and / or, Determine a second verification result according to an attribute difference between an element in the first true value data and an element in the second true value data, and a second preset threshold; The verification result includes: the first verification result and / or the second verification result.

7. The method according to claim 6, characterized in that The method further comprises: According to the spatial position difference and the attribute difference, the verification result is divided into sub-verification results of different deviation dimensions.

8. The method according to claim 2, characterized in that: The method further comprises: According to the verification results of the at least two non-point cloud data, parameters of the camera unit, the position measurement unit, and the inertial measurement unit are adjusted.

9. The method according to claim 4, characterized in that The environment to be verified includes at least one of the following: an area to be verified in the preset area, a scene to be verified, an element to be verified, and a sample level to be verified.

10. A method for constructing an electronic map, characterized in that: include: Based on the electronic map data verification method according to any one of claims 1 to 9, determining the verification result of collecting at least two non-point cloud data for a preset area; If the data quality indicated by the verification result meets the map data quality requirement, an electronic map corresponding to the preset area is constructed using the at least two non-point cloud data.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9 or 10 above.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of claims 1 to 9 or 10 above.

13. A computer program product, characterized in that The computer program product comprises a computer program, which is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the method described in any one of claims 1 to 9 or 10 can be implemented.

Images