High-precision map data processing method, driving navigation method and related devices

Abstract

The present disclosure provides a high-precision map data processing method, a driving navigation method and related devices, which involve the fields of artificial intelligence technology such as vehicle networking, smart cockpits, high-precision maps, and autonomous driving, and can be applied to intelligent traffic scenarios. The method includes: obtaining first high-precision map data that describes lane area map information in the form of points and lines; performing curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; performing dimensionality upgrading operations on the second high-precision map data to construct third high-precision map data that describes lane area map information in a surface and / or three-dimensional form. Compared with the three-dimensional map data directly obtained by tilt measurement through aerial photography, the application of this method can significantly reduce the amount of data of the constructed third high-precision map data while ensuring accuracy, thereby better matching the performance of the on-board hardware equipment, and thus providing users driving autonomous vehicles with a more immersive lane-level navigation.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, specifically to the field of artificial intelligence technology such as vehicle networking, smart cockpits, high-precision maps, and autonomous driving, and can be applied to intelligent transportation scenarios. In particular, it relates to a high-precision map data processing method, a driving navigation method, and corresponding devices, electronic devices, computer-readable storage media, and computer program products. Background Art

[0002] With the rapid development of autonomous driving technology, the data products of high-precision maps are also constantly iterating and improving, with the iteration directions mainly towards two aspects: improving accuracy and enhancing three-dimensional perception.

[0003] Since the actual user of high-precision maps is the hardware equipment of autonomous driving vehicles, the high-dimensional high-precision map data conventionally obtained through aerial photography using oblique photogrammetry has a huge amount of data, and the storage capacity and computing performance of the on-board hardware equipment cannot meet the actual autonomous driving requirements. Summary of the invention

[0004] The embodiments of the present disclosure provide a high-precision map data processing method, a driving navigation method, and corresponding devices, electronic devices, computer-readable storage media, and computer program products.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for processing high-precision map data, including: obtaining first high-precision map data that describes lane area map information in the form of points and lines; performing curve smoothing processing on line data in the first high-precision map data to obtain second high-precision map data; performing a dimensionality upgrade operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in the form of surfaces and / or three-dimensional stereoscopic forms.

[0006] In a second aspect, an embodiment of the present disclosure provides another method for processing high-precision map data, including: obtaining first high-precision map data that describes lane area map information in the form of points and lines; performing curve smoothing processing on line data in the first high-precision map data to obtain second high-precision map data; performing a dimensionality upgrade operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in the form of surface and / or three-dimensional form; obtaining first standard map data that describes other area map information in the form of points and lines; wherein the accuracy of the first standard map data is lower than that of the first high-precision map data, and other area map information is map information of other areas except the lane area; performing a dimensionality upgrade operation on the first standard map data to construct second standard map data that describes other area map information in the form of surface and / or three-dimensional form; and fusing the second standard map data and the third high-precision map data to obtain full-area map data.

[0007] In a third aspect, an embodiment of the present disclosure provides a driving navigation method, comprising: determining a current position in response to receiving a driving navigation request; presenting driving navigation information corresponding to the current position based on third high-precision map data or full-area map data; wherein the third high-precision map data is obtained according to the high-precision map data processing method described in any implementation method in the first aspect, and the full-area map data is obtained according to the high-precision map data processing method described in any implementation method in the second aspect.

[0008] In a fourth aspect, an embodiment of the present disclosure provides a high-precision map data processing device, comprising: a first high-precision map data acquisition unit, configured to acquire first high-precision map data that describes lane area map information in the form of points and lines; a curve smoothing processing unit, configured to perform curve smoothing processing on line data in the first high-precision map data to obtain second high-precision map data; and a first dimensionality upgrading operation unit, configured to perform a dimensionality upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in the form of surfaces and / or three-dimensional stereoscopic forms.

[0009] In a fifth aspect, another high-precision map data processing device provided by an embodiment of the present disclosure includes: a first high-precision map data acquisition unit, configured to acquire first high-precision map data that describes lane area map information in the form of points and lines; a curve smoothing processing unit, configured to perform curve smoothing processing on line data in the first high-precision map data to obtain second high-precision map data; a first dimensionality increase operation unit, configured to perform dimensionality increase operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in the form of surface and / or three-dimensional form; a first standard map data acquisition unit, configured to acquire first standard map data that describes other area map information in the form of points and lines; wherein the accuracy of the first standard map data is lower than that of the first high-precision map data, and other area map information is map information of other areas except the lane area; a second dimensionality increase operation unit, configured to perform dimensionality increase operation on the first standard map data to construct second standard map data that describes other area map information in the form of surface and / or three-dimensional form; a map data fusion unit, configured to fuse the second standard map data and the third high-precision map data to obtain full-area map data.

[0010] In the sixth aspect, an embodiment of the present disclosure provides a driving navigation device, comprising: a current position determination unit, configured to determine the current position in response to receiving a driving navigation request; a driving navigation information providing unit, configured to present driving navigation information corresponding to the current position based on third high-precision map data or full-area map data; wherein the third high-precision map data is obtained according to a high-precision map data processing device as described in any implementation method in the fourth aspect, and the full-area map data is obtained according to a high-precision map data processing device as described in any implementation method in the fifth aspect.

[0011] In the seventh aspect, an embodiment of the present disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the high-precision map data processing method described in any implementation manner in the first aspect and / or the high-precision map data processing method described in any implementation manner in the second aspect and / or the driving navigation method described in any implementation manner in the third aspect when executing.

[0012] In the sixth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement a high-precision map data processing method as described in any implementation method in the first aspect and / or a high-precision map data processing method as described in any implementation method in the second aspect and / or a driving navigation method as described in any implementation method in the third aspect when executed.

[0013] In the seventh aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the steps of the high-precision map data processing method described in any implementation manner in the first aspect and / or the high-precision map data processing method described in any implementation manner in the second aspect and / or the driving navigation method described in any implementation manner in the third aspect.

[0014] The high-precision map data processing method provided by the embodiment of the present disclosure obtains the first high-precision map data describing the lane area map information in the form of points and lines, performs curve smoothing processing to improve the smoothness of the line data, and then performs dimension upgrading on the zero-dimensional points and one-dimensional lines to obtain the third high-precision map data represented by two-dimensional surfaces and three-dimensional solid forms. Since the first high-precision map data only contains low-dimensional map information of the lane area and removes other useless details for lane-level navigation, the amount of data of the third high-precision map data finally obtained can be significantly reduced even through the dimension upgrading operation, thereby better matching the performance of the on-board hardware equipment, and thus providing users driving autonomous vehicles with a more immersive lane-level navigation.

[0015] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0017] Figure 1 is an exemplary system architecture in which the present disclosure may be applied;

[0018] Figure 2 A flowchart of a high-precision map data processing method provided in an embodiment of the present disclosure;

[0019] Figure 3 A flowchart of a method for performing a dimensionality-upgrading operation on a lane guardrail line provided in an embodiment of the present disclosure;

[0020] Figure 4 A schematic diagram of a process for performing a dimensional upgrade operation on a lane guardrail line provided in an embodiment of the present disclosure;

[0021] Figure 5 A flowchart of a method for performing a dimensionality-upgrading operation on a lane dividing line provided in an embodiment of the present disclosure;

[0022] Figure 6 A flowchart of another high-precision map data processing method provided in an embodiment of the present disclosure;

[0023] Figure 7 A structural block diagram of a high-precision map data processing device provided in an embodiment of the present disclosure;

[0024] Figure 8 A structural block diagram of another high-precision map data processing device provided in an embodiment of the present disclosure;

[0025] Fig. 9 A structural block diagram of a driving navigation device provided by an embodiment of the present disclosure;

[0026] Fig.10 A schematic diagram of the structure of an electronic device suitable for executing a high-precision map data processing method and / or a driving navigation method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments may be combined with each other without conflict.

[0028] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0029] Figure 1 An exemplary system architecture 100 is shown to which the high-precision map data processing method, driving navigation method, and corresponding devices, electronic devices, and computer-readable storage media of the present disclosure can be applied.

[0030] like Figure 1 As shown, the system architecture 100 may include a ground measurement vehicle 101, a map server 102, and an autonomous driving vehicle 103. A data transmission path is established between the ground measurement vehicle 101, the map server 102, and the autonomous driving vehicle 103, such as a wireless network or other types.

[0031] The ground survey vehicle 101 is equipped with a variety of map data measurement equipment such as millimeter wave radar, laser scanner, and camera, so as to collect high-precision map data of the driving area through continuous driving; the map server 102 is used to process the original map data collected by the map survey vehicle 101, so as to ultimately obtain target high-precision map data that can provide a more visual and immersive feeling to the drivers of a large number of autonomous driving vehicles 103 and match the performance of the on-board hardware equipment, thereby providing driving navigation based on the target high-precision map data.

[0032] The ground survey vehicle 101, the map server 102, and the autonomous driving vehicle 103 may be installed with various applications for realizing information communication between the two, such as original map data collection applications, high-precision map generation applications, driving navigation applications, etc.

[0033] The map server 102 can provide various services through various built-in applications. Taking a high-precision map generation application that can generate high-dimensional high-precision map data based on low-dimensional high-precision map data as an example, the map server 102 can achieve the following effects when running the high-precision map generation application: first, receive the original high-precision map data of the lane area collected by the ground measurement vehicle 101; then, extract the first high-precision map data represented by points and lines related to the key information of lane navigation from the original high-precision map data; then, perform curve smoothing on the line data in the first high-precision map data to obtain second high-precision map data; finally, perform dimensionality upgrade operation on the second high-precision map data to construct third high-precision map data that describes the lane area map information in a surface and / or three-dimensional form.

[0034] It should be noted that, in addition to being obtained in real time from the ground survey vehicle 101, the original high-precision map data can also be pre-stored in a local storage unit of the map server 102 in various ways. Therefore, when the map server 102 detects that the data has been stored locally (for example, when starting to process a previously stored map generation task), it can choose to directly obtain the data locally. In this case, the exemplary system architecture 100 may also not include the ground survey vehicle 101.

[0035] After the map server 102 generates the third high-precision map data through the built-in high-precision map application, it can transmit the third high-precision map data to each autonomous driving vehicle 103 that needs the map for driving navigation through the built-in data transmission application.

[0036] Furthermore, in order to optimize the viewing experience of passengers, standard map data of map information of other areas except the lane area can be integrated on the basis of the third high-precision map data to fill in the surrounding background information of lane-level navigation, and finally obtain full-area map data.

[0037] It should be understood that Figure 1 The number of ground survey vehicles, map servers, and autonomous driving vehicles in the embodiment is only illustrative. Any number of ground survey vehicles, map servers, and autonomous driving vehicles may be provided according to implementation requirements.

[0038] Please refer to Figure 2 , Figure 2 A flowchart of a high-precision map data processing method provided in an embodiment of the present disclosure, wherein process 200 includes the following steps:

[0039] Step 201: Acquire first high-precision map data describing lane area map information in the form of points and lines;

[0040] This step is intended to be performed by the execution subject of the high-precision map data processing method (such as Figure 1 The map server 102 shown in the figure obtains the first high-precision map data that describes the lane area map information in the form of points and lines, that is, the first high-precision map data is composed of low-dimensional data such as point data and line data, and the low dimension is relative to the high-dimensional data composed of surface data and three-dimensional data.

[0041] Among them, the first high-precision map data can be extracted from the original high-precision map data obtained by collecting lane areas related to the driving road surface using various collection devices installed on the ground measuring vehicle. The point data in the first high-precision map data can be point cloud data obtained by scanning the lane area with a laser scanner installed on the ground measuring vehicle, or certain specific points in the complete point cloud data, or certain data points sensed by a millimeter-wave radar, or even certain key points extracted from images taken by a vehicle-mounted camera, such as certain points representing lane signs, front and rear vehicles, and obstacles. The line data in the first high-precision map data can also be obtained by connecting or fitting multiple points representing the same object in the point cloud data, or can be extracted or separated from the edge of an object (such as the boundary line of a lane, etc.) recorded in the image taken by the vehicle-mounted camera.

[0042] Step 202: performing curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data;

[0043] On the basis of step 201, this step aims to perform curve smoothing on the line data in the first high-precision map data by the above-mentioned execution subject. The reason for performing curve smoothing on the line data in the first high-precision map data is that the data dimension is relatively low due to the acquisition method and acquisition height of the ground survey vehicle, which causes some lines directly extracted or fitted to be not smooth. When the unsmooth lines are upgraded to a surface or further upgraded to a three-dimensional stereogram, the errors will be further amplified. Therefore, the purpose of curve smoothing is to eliminate as much as possible the large errors that occur in the subsequent dimensionality upgrade operation of low-dimensional data.

[0044] Step 203: Perform a dimensionality upgrade operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a surface and / or three-dimensional form.

[0045] On the basis of step 202, this step aims to perform a dimensionality-upgrading operation on the second high-precision map data by the above-mentioned execution subject to construct third high-precision map data describing lane area map information in the form of a surface and / or a three-dimensional form. That is, the data dimension of the second high-precision map data is increased by dimensionality-upgrading processing, and the low-dimensional lane area map data originally represented as points and lines is upgraded to high-dimensional lane area map data represented as a surface and / or a three-dimensional form that is more in line with the actual perception of the user.

[0046] In the dimensionality upgrading process with low-dimensional line data as the starting point of the dimensionality upgrading operation and high-dimensional three-dimensional morphological data as the target point of the dimensionality upgrading operation, the entire dimensionality upgrading operation can be divided into two parts that are performed sequentially, namely, first upgrading the line data to surface data, and then upgrading the surface data to three-dimensional morphological data.

[0047] Of course, in the process of dimensionality upgrading, we must also rely on the dimensionality upgrading parameters that correctly upgrade the line data to surface data, such as the plane extension direction, the plane extension amount, etc. Similarly, in the process of upgrading the surface data to three-dimensional morphological data, we also rely on dimensionality upgrading parameters such as the height extension direction, the height extension amount, etc.

[0048] Similarly, dimensionality-increasing operations involving other starting points and other target points can be adaptively adjusted according to the above-mentioned dimensionality-increasing ideas to make the dimensionality-increasing operations targeted and improve the accuracy of the dimensionality-increasing results.

[0049] The high-precision map data processing method provided by the embodiment of the present disclosure obtains the first high-precision map data describing the lane area map information in the form of points and lines, performs curve smoothing processing to improve the smoothness of the line data, and then performs dimension upgrading on the zero-dimensional points and one-dimensional lines to obtain the third high-precision map data represented by two-dimensional surfaces and three-dimensional solid forms. Since the first high-precision map data only contains low-dimensional map information of the lane area and removes other useless details for lane-level navigation, the amount of data of the third high-precision map data finally obtained can be significantly reduced even through the dimension upgrading operation, thereby better matching the performance of the on-board hardware equipment, and thus providing users driving autonomous vehicles with a more immersive lane-level navigation.

[0050] To facilitate understanding of how to perform three-dimensional operations, the present disclosure will also provide a specific implementation method for the following two different dimensional objects:

[0051] First, please refer to Figure 3 , Figure 3 A flowchart of a method for performing a dimensionality upgrade operation on a lane guardrail line provided in an embodiment of the present disclosure, that is, a specific implementation method of a dimensionality upgrade operation provided for a lane guardrail line in the second high-precision map data, wherein the process 300 includes the following steps:

[0052] Step 301: Determine a plane extension direction and a first extension amount of a lane guardrail line;

[0053] Lane guardrail lines are used to refer to the lines of three-dimensional lane guardrails, that is, only the necessary position and direction information of three-dimensional lane guardrails is retained. Therefore, when performing dimensionality upgrade operations on lane guardrail lines, it is necessary to first determine the plane extension direction and the first extension amount of the lane guardrail line to guide how to correctly generate the lane guardrail surface based on the lane guardrail line.

[0054] There are usually three ways to determine the plane extension direction and the first extension amount of the lane guardrail line: 1) When the lane guardrail line is abstracted from the upper edge of the lane guardrail surface to reflect the direction of the lane guardrail, the plane extension direction should only include the downward extension direction, and the first extension amount should be the length from the upper edge to the lower edge; 2) When the lane guardrail line is abstracted from the center line of the lane guardrail surface to reflect the direction of the lane guardrail, the plane extension direction should include both the upward and downward extension directions, and the first extension amount should be the length from the center line to the upper edge or the lower edge respectively; 3) When the lane guardrail line is abstracted from the lower edge of the lane guardrail surface to reflect the direction of the lane guardrail, the plane extension direction should only include the upward extension direction, and the first extension amount should be the length from the lower edge to the upper edge.

[0055] Step 302: Extend the lane guardrail line along the plane extension direction by a first extension amount to obtain a lane guardrail surface;

[0056] Based on step 301, this step aims to extend the lane guardrail line by a first extension amount along the plane extension direction by the above-mentioned execution subject to obtain a lane guardrail surface. That is, by extending the lane guardrail line by a correct extension amount in the correct extension direction, a correct lane guardrail surface is obtained based on the lane guardrail line.

[0057] Step 303: Determine the height extension direction and the second extension amount of the lane guardrail surface;

[0058] Based on the lane guardrail surface obtained in step 302, this step aims to further determine the height extension direction and the second extension amount of the lane guardrail surface by the above-mentioned execution subject. That is, the height extension direction and the second extension amount are the dimension-upgrading parameters used to determine the correct dimension-upgrading of the two-dimensional plane into a three-dimensional stereoscopic form.

[0059] Step 304: Extend the lane guardrail surface by a second extension amount in the height extension direction to obtain a three-dimensional lane guardrail;

[0060] Based on step 303, this step is similar to step 302, and both extend the correct extension amount in the correct extension direction, so as to obtain the correct three-dimensional lane guardrail based on the lane guardrail surface.

[0061] Step 305: Generate third high-precision map data including three-dimensional lane guardrails;

[0062] Based on step 304, this step aims to generate the third high-precision map data including the three-dimensional lane guardrail by the above-mentioned execution subject. It should be noted that the third high-precision map data, in addition to the three-dimensional lane guardrail, usually also includes other lane-related data such as the lane surface. This embodiment only targets the three-dimensional lane guardrail part. When other lane-related data are also included, the corresponding dimensionality increase operation part should also be included.

[0063] That is, this embodiment, through steps 301 to 305, takes the low-dimensional lane guardrail line as an example, and provides a dimensionality upgrade implementation solution that first upgrades the line to a surface and then upgrades the surface to a three-dimensional shape. On the basis of ensuring the direction of the lane guardrail, by performing dimensionality upgrade operations on low-dimensional data, it is possible to avoid directly collecting useless detail data carried by high-dimensional data, thereby significantly reducing the amount of data while improving the user experience and better matching the performance of the on-board hardware equipment.

[0064] Furthermore, since the lane guardrail is not just a straight line, but usually appears as a broken line at the intersection, that is, two connected lane guardrail lines, when performing the dimension upgrade operation according to the above embodiment, it is easy to cause a connection gap between the lane guardrail surfaces constructed separately, thereby affecting the subsequent dimension upgrade operation. In response to this problem, the present disclosure further provides an improved method:

[0065] In response to a connection gap between two target lane guardrail surfaces, edge lines of the target lane guardrail surfaces are respectively extended to obtain intersection points of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensionality-upgrading operation on two connected target lane guardrail lines;

[0066] Based on the intersection point, the two target lane guardrail surfaces are spliced ​​into a complete new lane guardrail surface.

[0067] To understand the above-mentioned repair operation of the connection gap, you can also refer to Figure 4 A schematic diagram of a process of performing a dimensionality-upgrading operation on a lane guardrail line is shown, namely, Figure 4 Following the arrows, the process of how to perform dimensional operations from the lane guardrail line to finally obtain the three-dimensional lane guardrail is shown step by step:

[0068] 1) The coordinates of the two endpoints of the line segment representing the lane guardrail line are expressed in a pre-constructed three-dimensional space coordinate system, and then the two endpoints are connected to obtain the lane guardrail line;

[0069] 2) According to the coordinates of the midpoint and the two end points of the lane guardrail line, two temporary points on the plumb line of the lane guardrail line are calculated, and the extension direction of the line corresponding to the two temporary points is determined as the plumb line direction, and the plumb line direction is used as the plane extension direction, and finally four new end points for constituting the lane guardrail surface are determined in combination with the first extension amount;

[0070] 3) Connect the four new endpoints in sequence to obtain the lane guardrail surface. At this time, it is found that the lane guardrail surface constructed based on two connected lane guardrail lines in different directions has a connection gap;

[0071] 4) When repairing the connection gap, the angle bisector N of the angle between the extended line A' of the A lane guardrail line and the B lane guardrail line is specifically used, and the line formed by N1 and N2 is the plumb line of N;

[0072] 5) Use the plumb line N1N2 as the connecting line of the two lane surfaces to splice together to obtain a complete new lane guardrail surface. In principle, this is consistent with the above method of using the intersection of the extended edge lines;

[0073] 6) At this time, the new lane guardrail surface is a plane in the spatial rectangular coordinate system. The plumb line of the new lane guardrail plane will be determined in the same way as step 2), and then the plumb plane of the new lane guardrail plane will be determined based on the plumb line, and the plumb plane will be used as the height extension direction. Finally, combined with the second extension amount, the various endpoints used to form the three-dimensional lane guardrail are determined.

[0074] Different from Figure 3-4 The dimensionality increase operation for the lane guardrail line is shown. Figure 5 This is a flow chart of a method for performing a dimensionality upgrade operation on a lane dividing line provided by an embodiment of the present disclosure, and a specific dimensionality upgrade operation provided for a lane dividing line in the second high-precision map data, wherein the process 500 includes the following steps:

[0075] Step 501: Determine two adjacent and parallel target lane dividing lines;

[0076] Lane dividing lines, as the name implies, are the dividing lines between two adjacent lanes, that is, the area from one side of the lane dividing line to the other side of the adjacent lane dividing line belongs to the same lane. It is precisely because of this feature that only using low-dimensional data such as lane dividing lines can actually provide accurate lane-level navigation, but it does not contain details and gives users a poor perception.

[0077] This step is intended to determine two adjacent and parallel target lane dividing lines by the above-mentioned execution subject.

[0078] Step 502: Connecting the upper edge and the lower edge of the two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface;

[0079] On the basis of step 501, this step aims to connect the upper edge and the lower edge of the two target lane dividing lines respectively along the vertical direction of the target lane dividing lines by the above-mentioned execution subject to obtain a closed lane surface.

[0080] That is, by closing the lower edge of the upper edge, a closed lane surface reflecting the lane width is obtained.

[0081] According to the above operation, an independent lane surface can be obtained for each lane. Of course, in order to avoid that multiple lane surfaces actually belong to the same large road surface, a large road plane can be formed based on the outermost lane dividing lines of multiple parallel lanes, and divided into multiple lane surfaces according to other lane dividing lines contained inside.

[0082] Step 503: Generate third high-precision map data including lane surfaces of each lane.

[0083] Based on step 502, this step aims to generate the third high-precision map data containing the lane surface of each lane by the above-mentioned execution subject. It should be noted that, in addition to the lane surface, the third high-precision map data usually also includes other lane-related data such as lane guardrail entities, driving signs, roadside signs, etc., but since this embodiment is aimed at the lane surface part, the other parts are not expanded together.

[0084] That is, this embodiment, through steps 501 to 503, takes the low-dimensional lane dividing line as an example to provide a dimensionality upgrade solution from a line to a surface. By performing dimensionality upgrade operations on low-dimensional data, it is possible to avoid directly collecting useless detail data carried by high-dimensional data, thereby significantly reducing the amount of data while improving the user experience and better matching the performance of the vehicle-mounted hardware equipment.

[0085] The lane area usually also includes other relevant map data such as traffic lights, driving signs, direction signs, roadside signs, etc., which can be upgraded after adaptive adjustment according to the dimensionality upgrading methods embodied in the above two embodiments, and will not be described in detail here.

[0086] In order to match the computing performance of the onboard hardware equipment of the autonomous vehicle, the high-precision map data provided by the above embodiments only includes the lane area, that is, the remaining map information that is useless for lane-level navigation is completely discarded. Although this can minimize the computing performance requirements of the onboard hardware equipment, it will inevitably affect the perception of the user driving the autonomous vehicle. Figure 6 A flowchart of another method for processing high-precision map data is provided, wherein the process 600 includes the following steps:

[0087] Step 601: Acquire first high-precision map data describing lane area map information in the form of points and lines;

[0088] Step 602: performing curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data;

[0089] Step 603: Perform a dimensionality-upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a plane and / or three-dimensional form;

[0090] Step 604: Acquire first standard map data describing map information of other areas in the form of points and lines;

[0091] The map accuracy of the standard map data is lower than that of the first high-precision map data. This is because the key to lane-level navigation is the high-precision map data of the lane area, and the map data of other areas except the lane area is not necessary data. Therefore, the amount of data can be reduced by lowering the accuracy requirements. For example, the accuracy error of the standard map data can be at the meter level, or even at the level of more than ten meters.

[0092] Step 605: Perform a dimensionality-upgrading operation on the first standard map data to construct second standard map data that describes map information of other regions in a plane and / or three-dimensional form;

[0093] The dimension-upgrading operation performed on the first standard map in this step can refer to the dimension-upgrading method given in the above embodiment. However, it should be noted that in some scenarios, the operation of obtaining the second standard map data based on the first standard map data can also be completed by other execution entities. In this case, the above execution entity only needs to execute step 606.

[0094] Step 606: Fuse the second standard map data and the third high-precision map data to obtain full-area map data.

[0095] Step 605 performs a similar dimensionality increase operation on the first standard map data, so that the second standard map data can have a fusion basis with the third high-precision map data due to the same data dimension, and finally obtain the full-area map data through fusion.

[0096] When the fused full-area map data is used to provide lane-level navigation services for autonomous vehicles, the third high-precision map data will serve as the main information source for lane-level navigation, while the second standard map data will be used to supplement other map information near the lane, such as the outline of surrounding buildings, green spaces and water systems, and distant signs, to enhance the user's perception and immersion.

[0097] Furthermore, in order to ensure that the fused full-area map data does not have errors in certain elevated bridges and locations with spatial overlap, the height information of the high-precision map data and the standard map data at the connected positions can also be unified, which can also be simply understood as unified elevation information.

[0098] On the basis of any of the above embodiments, correctly performing the dimension upgrading operation is the basis for ensuring the picture effect that the final third high-precision map data or the full-area map data can present. In order to ensure that the dimension upgrading operation can be correctly performed as much as possible, the present disclosure also provides an implementation scheme for how to obtain the correct dimension upgrading parameters through the following embodiments:

[0099] Acquire a first real scene image corresponding to the lane area and a second real scene image corresponding to other areas;

[0100] Determine the dimension-upgrading parameters when performing the dimension-upgrading operation on the second high-precision map data by using the first real scene image, such as: the plane extension direction, the height extension direction, the first extension amount, and the second extension amount corresponding to the lane guardrail line;

[0101] The second real scene image is used to determine dimension-upgrading parameters when performing a dimension-upgrading operation on the first standard map data.

[0102] That is, the rich image information contained in the real-life image is used to help obtain more accurate dimensionality-enhancing parameters.

[0103] The above embodiments are based on a map server (for example Figure 1 The map server 102 shown in the figure is the execution subject, and the implementation process of how to generate the third high-precision map data and the full-area map data is described in multiple levels. The following description angle is changed to the autonomous driving vehicle (for example Figure 1 The autonomous driving vehicle 103 shown in the figure provides lane-level navigation using a third high-precision map data or a full-area map data on the vehicle side.

[0104] A driving navigation method, comprising:

[0105] In response to receiving the driving navigation request, determining a current location;

[0106] The driving navigation information corresponding to the current location is presented based on the third high-precision map data or the full-area map data.

[0107] That is, when the autonomous driving vehicle receives a driving navigation request, it first determines the current position of the vehicle itself, and then calls the third high-precision map data or the full-area map data to present the driving navigation information corresponding to the current position. That is, the third high-precision map data or the full-area map data is the map data obtained by the solution provided by the above embodiment and matches the performance of the vehicle-mounted hardware device.

[0108] Further references Figure 7-9 As implementations of the above-mentioned method embodiments, the present disclosure provides two different high-precision map data processing devices and a driving navigation device. Figure 2Corresponding to the embodiment of the high-precision map data processing method shown in FIG. 1 , another embodiment of a high-precision map data processing device is Figure 6 The embodiment of the high-precision map data processing method shown corresponds to the embodiment of the driving navigation device and the embodiment of the driving navigation method. The above device can be specifically applied to various electronic devices.

[0109] like Figure 7 As shown, the high-precision map data processing device 700 of this embodiment may include: a first high-precision map data acquisition unit 701, a curve smoothing processing unit 702, and a first dimension upgrading operation unit 703. Among them, the first high-precision map data acquisition unit 701 is configured to acquire first high-precision map data describing lane area map information in the form of points and lines; the curve smoothing processing unit 702 is configured to perform curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; the first dimension upgrading operation unit 703 is configured to perform dimension upgrading operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in the form of surface and / or three-dimensional stereo.

[0110] In this embodiment, in the high-precision map data processing device 700, the specific processing of the first high-precision map data acquisition unit 701, the curve smoothing processing unit 702, and the first dimension upgrading operation unit 703 and the technical effects thereof can be referred to in Figure 2 The relevant descriptions of steps 201 - 203 in the corresponding embodiment are not repeated here.

[0111] In some optional implementations of this embodiment, the first dimension upgrading operation unit 703 may include a first dimension upgrading subunit configured to perform a dimension upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a three-dimensional form. The first dimension upgrading subunit may be further configured as follows:

[0112] For the lane guardrail line in the second high-precision map data, determine a plane extension direction and a first extension amount of the lane guardrail line;

[0113] Extending the lane guardrail line along the plane extension direction by a first extension amount to obtain a lane guardrail surface;

[0114] Determine the height extension direction and second extension amount of the lane guardrail surface;

[0115] Extending the lane guardrail surface by a second extension amount in a height extension direction to obtain a three-dimensional lane guardrail;

[0116] Generate the third high-precision map data including three-dimensional lane guardrails.

[0117] In some optional implementations of this embodiment, the high-precision map data processing device 700 may further include:

[0118] An edge line extension unit is configured to, in response to a connection gap between two target lane guardrail surfaces, extend the edge lines of the target lane guardrail surfaces respectively to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensional upscaling operation on two connected target lane guardrail lines;

[0119] The connection gap repair unit is configured to splice two target lane guardrail surfaces into a complete new lane guardrail surface based on the intersection point.

[0120] In some optional implementations of this embodiment, the first dimension-upgrading operation unit 703 may include a second dimension-upgrading operation subunit configured to perform a dimension-upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a surface form, and the second dimension-upgrading operation subunit may be further configured to:

[0121] For the lane dividing lines in the second high-precision map data, two adjacent and parallel target lane dividing lines are determined;

[0122] Connect the upper edge and the lower edge of the two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface;

[0123] Generate third high-precision map data including the lane surface of each lane.

[0124] In some optional implementations of this embodiment, the high-precision map data processing device 700 may further include:

[0125] A first real scene image acquisition unit is configured to acquire a first real scene image corresponding to the lane area;

[0126] The first dimension-upgrading parameter determination unit is configured to use the first real scene image to determine the dimension-upgrading parameters when performing a dimension-upgrading operation on the second high-precision map data.

[0127] like Figure 8As shown, the high-precision map data processing device 800 of this embodiment may include: a first high-precision map data acquisition unit 801, a curve smoothing processing unit 802, a first dimensionality upgrading operation unit 803, a first standard map data acquisition unit 804, a second dimensionality upgrading operation unit 805, and a map data fusion unit 806. Among them, the first high-precision map data acquisition unit 801 is configured to acquire first high-precision map data that describes lane area map information in the form of points and lines; the curve smoothing processing unit 802 is configured to perform curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; the first dimensionality increase operation unit 803 is configured to perform dimensionality increase operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in the form of surface and / or three-dimensional form; the first standard map data acquisition unit 804 is configured to acquire first standard map data that describes other area map information in the form of points and lines; wherein the accuracy of the first standard map data is lower than that of the first high-precision map data, and the other area map information is map information of other areas except the lane area; the second dimensionality increase operation unit 805 is configured to perform dimensionality increase operation on the first standard map data to construct second standard map data that describes other area map information in the form of surface and / or three-dimensional form; the map data fusion unit 806 is configured to fuse the second standard map data and the third high-precision map data to obtain full-area map data.

[0128] In this embodiment, in the high-precision map data processing device 800, the specific processing of the first high-precision map data acquisition unit 801, the curve smoothing processing unit 802, the first dimension upgrading operation unit 803, the first standard map data acquisition unit 804, the second dimension upgrading operation unit 805, and the map data fusion unit 806 and the technical effects thereof can be referred to in detail. Figure 6 The relevant descriptions of steps 601-606 in the corresponding embodiment are not repeated here.

[0129] In some optional implementations of this embodiment, the first dimension upgrading operation unit 803 may include a first dimension upgrading subunit configured to perform a dimension upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a three-dimensional form. The first dimension upgrading subunit may be further configured as follows:

[0130] For the lane guardrail line in the second high-precision map data, determine a plane extension direction and a first extension amount of the lane guardrail line;

[0131] Extending the lane guardrail line along the plane extension direction by a first extension amount to obtain a lane guardrail surface;

[0132] Determine the height extension direction and second extension amount of the lane guardrail surface;

[0133] Extending the lane guardrail surface by a second extension amount in a height extension direction to obtain a three-dimensional lane guardrail;

[0134] Generate the third high-precision map data including three-dimensional lane guardrails.

[0135] In some optional implementations of this embodiment, the high-precision map data processing device 800 may further include:

[0136] An edge line extension unit is configured to, in response to a connection gap between two target lane guardrail surfaces, extend the edge lines of the target lane guardrail surfaces respectively to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensional upscaling operation on two connected target lane guardrail lines;

[0137] The connection gap repair unit is configured to splice two target lane guardrail surfaces into a complete new lane guardrail surface based on the intersection point.

[0138] In some optional implementations of this embodiment, the first dimension-upgrading operation unit 703 may include a second dimension-upgrading operation subunit configured to perform a dimension-upgrading operation on the second high-precision map data to construct third high-precision map data that describes lane area map information in a surface form, and the second dimension-upgrading operation subunit may be further configured to:

[0139] For the lane dividing lines in the second high-precision map data, two adjacent and parallel target lane dividing lines are determined;

[0140] Connect the upper edge and the lower edge of the two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface;

[0141] Generate third high-precision map data including the lane surface of each lane.

[0142] In some optional implementations of this embodiment, the high-precision map data processing device 800 may further include:

[0143] The height information unification unit is configured to unify the height information of the second high-precision map data and the first standard map data at the connecting position before performing a dimensionality upgrade operation on the first standard map data.

[0144] In some optional implementations of this embodiment, the high-precision map data processing device 800 may further include:

[0145] The first and second real scene image acquisition units are configured to acquire a first real scene image corresponding to the lane area and a second real scene image corresponding to other areas;

[0146] A first dimension-upgrading parameter determining unit is configured to determine a dimension-upgrading parameter when performing a dimension-upgrading operation on the second high-precision map data using the first real scene image;

[0147] The second dimension-upgrading parameter determining unit is configured to determine the dimension-upgrading parameter when performing a dimension-upgrading operation on the first standard map data by using the second real scene image.

[0148] like Fig. 9 As shown, the driving navigation device 900 of this embodiment may include: a current position determining unit 901 and a driving navigation information providing unit 902. The current position determining unit 901 is configured to determine the current position in response to receiving a driving navigation request; the driving navigation information providing unit 902 is configured to present driving navigation information corresponding to the current position based on the third high-precision map data or the full-area map data.

[0149] In this embodiment, in the driving navigation device 900, the specific processing of the current position determining unit 901 and the driving navigation information providing unit 902 and the technical effects brought about by them may correspond to the relevant descriptions in the method embodiment respectively, and will not be repeated here.

[0150] This embodiment exists as a device embodiment corresponding to the above method embodiment. The high-precision map data processing device and driving navigation device provided in this embodiment, after obtaining the first high-precision map data describing the lane area map information in the form of points and lines, perform curve smoothing to improve the smoothness of the line data, and then perform dimension upgrade on the zero-dimensional points and one-dimensional lines to obtain the third high-precision map data represented by a two-dimensional surface and a three-dimensional solid form. Since the first high-precision map data only contains low-dimensional map information of the lane area and removes other useless details for lane-level navigation, even through the dimension upgrade operation, the data volume of the third high-precision map data finally obtained can be significantly reduced, thereby better matching the performance of the on-board hardware equipment, and thus providing users driving autonomous vehicles with a more immersive lane-level navigation.

[0151] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the high-precision map data processing method or driving navigation method described in any of the above embodiments can be implemented when the at least one processor executes.

[0152] According to an embodiment of the present disclosure, the present disclosure also provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the high-precision map data processing method or driving navigation method described in any of the above embodiments when executed.

[0153] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which, when executed by a processor, can implement the high-precision map data processing method or driving navigation method described in any of the above embodiments.

[0154] Fig.10 A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0155] like Fig.10 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0156] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0157] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1001 performs the various methods and processes described above, such as a high-precision map data processing method or a driving navigation method. For example, in some embodiments, the high-precision map data processing method or the driving navigation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the high-precision map data processing method or the driving navigation method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute a high-precision map data processing method or a driving navigation method in any other appropriate manner (for example, by means of firmware).

[0158] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0159] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0160] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0162] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0163] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0164] According to the technical solution of the disclosed embodiment, the low-dimensional original high-precision map data collected by the ground survey vehicle for the lane area is selected, and after curve smoothing, the high-dimensional high-precision map data that can enhance the sense of immersion is obtained through dimensionality upgrading operation. Since the collection height of the ground survey vehicle is limited, compared with the three-dimensional map data directly obtained by tilt measurement through aerial photography, the amount of data of the constructed target high-precision map data can be significantly reduced while ensuring accuracy, thereby better matching the performance of the on-board hardware equipment, and thus providing users driving autonomous vehicles with more immersive lane-level navigation.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A high-precision map data processing method, comprising: Acquire first high-precision map data describing lane area map information in the form of points and lines; Performing curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; Performing a dimensionality-upgrading operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in a plane and / or three-dimensional form, including: determining a plane extension direction and a first extension amount of a lane guardrail line in the second high-precision map data; Extend the lane guardrail line along the plane extension direction by the first extension amount to obtain a lane guardrail surface; determine the height extension direction and the second extension amount of the lane guardrail surface; extend the lane guardrail surface along the height extension direction by the second extension amount to obtain a three-dimensional lane guardrail; generate third high-precision map data including the three-dimensional lane guardrail.

2. The method according to claim 1, further comprising: In response to the presence of a connection gap between two target lane guardrail surfaces, the edge lines of the target lane guardrail surfaces are respectively extended to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensionality-upgrading operation on two connected target lane guardrail lines; Based on the intersection point, the two target lane guardrail surfaces are spliced ​​into a complete new lane guardrail surface.

3. The method according to claim 1, wherein: Performing a dimensionality-upgrading operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in a surface form, including: For the lane dividing lines in the second high-precision map data, determining two adjacent and parallel target lane dividing lines; Connecting the upper edge and the lower edge of two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface; Generate third high-precision map data including the lane surface of each lane.

4. The method according to any one of claims 1 to 3, further comprising: Acquire a first real-view image corresponding to the lane area; The first real scene image is used to determine dimension-upgrading parameters when performing a dimension-upgrading operation on the second high-precision map data.

5. A high-precision map data processing method, comprising: Acquire first high-precision map data describing lane area map information in the form of points and lines; Performing curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; Performing a dimensionality upgrade operation on the second high-precision map data to construct third high-precision map data that describes the lane area map information in a plane and / or three-dimensional form, including: determining a plane extension direction and a first extension amount of the lane guardrail line in the second high-precision map data; extending the lane guardrail line along the plane extension direction by the first extension amount to obtain a lane guardrail surface; determining a height extension direction and a second extension amount of the lane guardrail surface; extending the lane guardrail surface along the height extension direction by the second extension amount to obtain a three-dimensional lane guardrail; generating third high-precision map data including the three-dimensional lane guardrail; Acquire first standard map data describing other area map information in the form of points and lines; wherein the accuracy of the first standard map data is lower than the accuracy of the first high-precision map data, and the other area map information is map information of other areas except the lane area; Performing a dimensionality-upgrading operation on the first standard map data to construct second standard map data that describes the map information of the other area in a plane and / or three-dimensional form; The second standard map data and the third high-precision map data are integrated to obtain full-area map data.

6. The method according to claim 5, further comprising: In response to the presence of a connection gap between two target lane guardrail surfaces, the edge lines of the target lane guardrail surfaces are respectively extended to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensionality-upgrading operation on two connected target lane guardrail lines; Based on the intersection point, the two target lane guardrail surfaces are spliced ​​into a complete new lane guardrail surface.

7. The method according to claim 5, wherein: Performing a dimensionality-upgrading operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in a surface form, including: For the lane dividing lines in the second high-precision map data, determining two adjacent and parallel target lane dividing lines; Connecting the upper edge and the lower edge of two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface; Generate third high-precision map data including the lane surface of each lane.

8. The method according to claim 5, wherein: Before performing the dimension-upgrading operation on the first standard map data, the method further includes: Unify the height information of the second high-precision map data and the first standard map data at the connecting position.

9. The method according to any one of claims 5 to 8, further comprising: Acquire a first real scene image corresponding to the lane area and a second real scene image corresponding to the other area; Determine, by using the first real scene image, a dimension-upgrading parameter when performing a dimension-upgrading operation on the second high-precision map data; The second real scene image is used to determine dimension-upgrading parameters when performing a dimension-upgrading operation on the first standard map data.

10. A driving navigation method, comprising: In response to receiving the driving navigation request, determining a current location; Driving navigation information corresponding to the current location is presented based on third high-precision map data or full-area map data; wherein, the third high-precision map data is obtained according to the high-precision map data processing method according to any one of claims 1-4, and the full-area map data is obtained according to the high-precision map data processing method according to any one of claims 5-9.

11. A high-precision map data processing device, comprising: A first high-precision map data acquisition unit is configured to acquire first high-precision map data describing lane area map information in the form of points and lines; a curve smoothing processing unit, configured to perform curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; The first dimension upgrading operation unit is configured to perform a dimension upgrading operation on the second high-precision map data to construct a third high-precision map data that describes the lane area map information in a surface and / or three-dimensional form, including: a first dimension upgrading sub-unit configured to perform a dimension upgrading operation on the second high-precision map data to construct a third high-precision map data that describes the lane area map information in a three-dimensional form, and the first dimension upgrading sub-unit is further configured to: for the lane guardrail line in the second high-precision map data, determine the plane extension direction and the first extension amount of the lane guardrail line; extend the lane guardrail line along the plane extension direction by the first extension amount to obtain a lane guardrail surface; determine the height extension direction and the second extension amount of the lane guardrail surface; extend the lane guardrail surface along the height extension direction by the second extension amount to obtain a three-dimensional lane guardrail; and generate third high-precision map data including the three-dimensional lane guardrail.

12. The apparatus according to claim 11, further comprising: An edge line extension unit is configured to, in response to a connection gap between two target lane guardrail surfaces, extend the edge lines of the target lane guardrail surfaces respectively to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensional upscaling operation on two connected target lane guardrail lines; The connection gap repair unit is configured to splice the two target lane guardrail surfaces into a complete new lane guardrail surface based on the intersection point.

13. The device according to claim 11, wherein: The first dimension-increasing operation unit includes a second dimension-increasing operation subunit configured to perform a dimension-increasing operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in a surface form, and the second dimension-increasing operation subunit is further configured to: For the lane dividing lines in the second high-precision map data, determining two adjacent and parallel target lane dividing lines; Connecting the upper edge and the lower edge of two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface; Generate third high-precision map data including the lane surface of each lane.

14. The device according to any one of claims 11 to 13, further comprising: A first real scene image acquisition unit is configured to acquire a first real scene image corresponding to the lane area; The first dimension-upgrading parameter determination unit is configured to use the first real-scene image to determine the dimension-upgrading parameters when performing a dimension-upgrading operation on the second high-precision map data.

15. A high-precision map data processing device, comprising: A first high-precision map data acquisition unit is configured to acquire first high-precision map data describing lane area map information in the form of points and lines; a curve smoothing processing unit, configured to perform curve smoothing processing on the line data in the first high-precision map data to obtain second high-precision map data; The first dimension-upgrading operation unit is configured to perform a dimension-upgrading operation on the second high-precision map data to construct third high-precision map data that describes the lane area map information in a plane and / or three-dimensional form, including: a first dimension-upgrading subunit configured to perform a dimension-upgrading operation on the second high-precision map data to construct third high-precision map data that describes the lane area map information in a three-dimensional form, the first dimension-upgrading subunit being further configured to: determine the plane extension direction and the first extension amount of the lane guardrail line in the second high-precision map data; extend the lane guardrail line along the plane extension direction by the first extension amount to obtain a lane guardrail surface; determine the height extension direction and the second extension amount of the lane guardrail surface; extend the lane guardrail surface along the height extension direction by the second extension amount to obtain a three-dimensional lane guardrail; generate third high-precision map data including the three-dimensional lane guardrail; A first standard map data acquisition unit is configured to acquire first standard map data describing other area map information in the form of points and lines; wherein the accuracy of the first standard map data is lower than the accuracy of the first high-precision map data, and the other area map information is map information of other areas except the lane area; A second dimension-increasing operation unit is configured to perform a dimension-increasing operation on the first standard map data to construct second standard map data that describes the map information of the other area in a plane and / or three-dimensional form; The map data fusion unit is configured to fuse the second standard map data and the third high-precision map data to obtain full-area map data.

16. The apparatus according to claim 15, further comprising: An edge line extension unit is configured to, in response to a connection gap between two target lane guardrail surfaces, extend the edge lines of the target lane guardrail surfaces respectively to obtain an intersection of the extended edge lines; wherein the two target lane guardrail surfaces are respectively obtained by performing a dimensional upscaling operation on two connected target lane guardrail lines; The connection gap repair unit is configured to splice the two target lane guardrail surfaces into a complete new lane guardrail surface based on the intersection point.

17. The device according to claim 15, wherein: The first dimension-increasing operation unit includes a second dimension-increasing operation subunit configured to perform a dimension-increasing operation on the second high-precision map data to construct third high-precision map data describing the lane area map information in a surface form, and the second dimension-increasing operation subunit is further configured to: For the lane dividing lines in the second high-precision map data, determining two adjacent and parallel target lane dividing lines; Connecting the upper edge and the lower edge of two target lane dividing lines respectively along the vertical direction of the target lane dividing line to obtain a closed lane surface; Generate third high-precision map data including the lane surface of each lane.

18. The apparatus according to claim 15, further comprising: The height information unification unit is configured to unify the height information of the second high-precision map data and the first standard map data at the connecting position before performing a dimensionality upgrade operation on the first standard map data.

19. The device according to any one of claims 15 to 18, further comprising: A first and second real scene image acquisition unit, configured to acquire a first real scene image corresponding to the lane area and a second real scene image corresponding to the other area; A first dimension-upgrading parameter determining unit is configured to determine a dimension-upgrading parameter when performing a dimension-upgrading operation on the second high-precision map data using the first real scene image; The second dimension-upgrading parameter determining unit is configured to determine the dimension-upgrading parameter when performing a dimension-upgrading operation on the first standard map data by using the second real scene image.

20. A driving navigation device, comprising: a current position determination unit, configured to determine a current position in response to receiving a driving navigation request; The driving navigation information providing unit is configured to present the driving navigation information corresponding to the current position based on the third high-precision map data or the full-area map data; wherein the third high-precision map data The high-precision map data processing device according to any one of claims 11-14 is obtained, and the full-area map data is obtained according to the high-precision map data processing device according to any one of claims 15-19.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the high-precision map data processing method described in any one of claims 1-4 and / or the high-precision map data processing method described in any one of claims 5-9 and / or the driving navigation method described in claim 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the high-precision map data processing method described in any one of claims 1 to 4 and / or the high-precision map data processing method described in any one of claims 5 to 9 and / or the driving navigation method described in claim 10.

23. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the high-precision map data processing method according to any one of claims 1-4 and / or the high-precision map data processing method according to any one of claims 5-9 and / or the driving navigation method according to claim 10.

Images