CN114705180A

CN114705180A - Data correction method, device and equipment for high-precision map and storage medium

Info

Publication number: CN114705180A
Application number: CN202210627129.XA
Authority: CN
Inventors: 周勋
Original assignee: China Automotive Innovation Corp
Current assignee: China Automotive Innovation Corp
Priority date: 2022-06-06
Filing date: 2022-06-06
Publication date: 2022-07-05
Anticipated expiration: 2042-06-06
Also published as: CN114705180B

Abstract

The application discloses a data correction method, a data correction device, data correction equipment and a storage medium of a high-precision map, relates to the technical field of maps, and can correct data deviation in the high-precision map. The specific scheme comprises the following steps: acquiring object position data of a target object to be corrected in a high-precision map; acquiring central position data of the center line of each lane and boundary position data of the boundary of each lane within a preset range; if the target object is a first type object, correcting the object position data according to the object position data and the center position data to obtain the target position data of the target object, wherein the first type object comprises objects of which the distance from the center line of the lane meets a first preset condition; and if the target object is a second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object, wherein the second type object comprises an object of which the distance from the lane boundary line meets a second preset condition.

Description

Data correction method, device and equipment for high-precision map and storage medium

Technical Field

The present application relates to the field of map technologies, and in particular, to a method, an apparatus, a device, and a storage medium for data correction of a high-precision map.

Background

With the rapid development of the fields of intelligent transportation and automatic driving, the traditional navigation electronic map cannot meet the high-level application requirements in the aspects of content, precision and integrity, and the high-precision map for roads is gradually proposed and widely accepted. The three functions of map matching, auxiliary environment perception and path planning of the high-precision map have rigid requirements and irreplaceable advantages in an automatic driving system.

Currently, high-precision maps are generated from road data, lane data, and data of facilities around roads, which are collected in an actual environment. However, in the data acquisition process, part of the road data, the lane data, and the data of the facilities around the road may not be acquired because of being blocked by vegetation or the like, so that the acquired data is incomplete, and the data in the generated high-precision map has an offset error.

Disclosure of Invention

The application provides a data correction method, a device, equipment and a storage medium for a high-precision map, which can correct data deviation in the high-precision map.

In order to achieve the purpose, the following technical scheme is adopted in the application:

in a first aspect of the embodiments of the present application, a method for correcting data of a high-precision map is provided, where the method includes:

acquiring object position data of a target object to be corrected in a high-precision map;

acquiring center position data of the center line of each lane in a preset range according to the object position data, and acquiring boundary position data of the boundary of each lane in the preset range;

if the target object is a first type object, correcting the object position data according to the object position data and the center position data to obtain the target position data of the target object, wherein the first type object comprises objects of which the distance from the center line of the lane meets a first preset condition;

and if the target object is a second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object, wherein the second type object comprises an object of which the distance from the lane boundary line meets a second preset condition.

In one embodiment, the object position data comprises an object coordinate set of the target object, the center position data comprises a center coordinate set of a lane centerline;

according to the object position data and each center position data, correcting the object position data to obtain the target position data of the target object, comprising the following steps:

for each object coordinate in the set of object coordinates, performing the following operations: calculating the distance value between the object coordinate and each central coordinate in each central coordinate set, and taking the elevation value of the central coordinate corresponding to the minimum distance value in the calculated distance values as the elevation value of the object coordinate to obtain a first object coordinate set, wherein the elevation value is the Z-axis numerical value in the coordinate;

and correcting the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set and target position data of the target object.

In one embodiment, correcting the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set of the target object, includes:

obtaining a first vector according to a first object coordinate corresponding to the minimum elevation value and a second object coordinate corresponding to the maximum elevation value in the first object coordinate set;

calculating the projection distance of the remaining object coordinates in the first object coordinate set in the first vector, and taking the remaining object coordinates corresponding to the minimum projection distance as third object coordinates, wherein the remaining object coordinates are the object coordinates in the first object coordinate set except the first object coordinates and the second object coordinates;

obtaining a second vector according to the first object coordinate and the third object coordinate;

a target object coordinate set is determined from the first vector, the second vector, and the first object coordinate set.

In one embodiment, determining the set of target object coordinates from the first vector, the second vector, and the first set of object coordinates comprises:

determining a reference plane from the first vector and the second vector;

calculating the coordinates of each object coordinate in the first object coordinate set projected on the reference plane to obtain a second object coordinate set;

a set of target object coordinates is determined from the second set of object coordinates.

In one embodiment, determining the target object coordinate set from the second object coordinate set comprises:

determining the second coordinate object set as a target object coordinate set;

or,

determining at least one subset from the second object coordinate set according to the coordinate symmetry relationship in the second object coordinate set, wherein the subset consists of a first reference coordinate and a second reference coordinate which have the coordinate symmetry relationship, and a center coordinate of the first reference coordinate and the second reference coordinate;

and calculating the average value of the elevation values of the first reference coordinate and the second reference coordinate in each subset, and determining the average value as the elevation value of the central coordinate to obtain a target object coordinate set.

In one embodiment, the object position data comprises an object coordinate set of the target object, and the boundary position data comprises a boundary coordinate set of the lane boundary;

correcting the object position data according to the object position data and each boundary position data to obtain target position data of the target object, and the method comprises the following steps:

carrying out interpolation processing on adjacent object coordinates in the object coordinate set according to a first preset threshold value to obtain a discrete object coordinate set;

correcting the discrete object coordinate set according to the boundary node coordinate set to obtain a third object coordinate set;

and correcting the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain a target object coordinate set and target position data.

In one embodiment, the modifying the discrete object coordinate set according to the boundary node coordinate set to obtain a third object coordinate set includes:

calculating the distance value between each boundary coordinate in the boundary coordinate set and each discrete object coordinate in the discrete object coordinate set, and determining the boundary coordinate corresponding to the minimum distance value as a target boundary coordinate;

and taking the elevation value in the target boundary coordinate as the elevation value of each discrete object coordinate in the discrete object coordinate set to obtain a third object coordinate set, wherein the elevation value is a Z-axis numerical value in the coordinate.

In one embodiment, the modifying the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain a target object coordinate set includes:

calculating the distances between the center object coordinate and the object coordinates at two ends in the three adjacent object coordinates of the third object coordinate set;

and deleting the nodes at the two ends corresponding to the distance greater than the second preset threshold value from the third object coordinate set to obtain a target object coordinate set.

In one embodiment, acquiring center position data of the center line of each lane within a preset range includes:

acquiring coordinate sets of all reference lines in a preset range in a high-precision map to obtain all reference coordinate sets, and performing interpolation processing on each reference coordinate set according to a third preset threshold to obtain all interpolation reference coordinate sets;

performing smoothing processing on each interpolation reference coordinate set to obtain each target reference coordinate set;

generating a lane marking line coordinate set and a lane boundary coordinate set according to each target reference coordinate set and the road width of the lane corresponding to each target reference coordinate set;

and obtaining each center coordinate set and center position data according to the lane marking coordinate set and the lane boundary coordinate set.

In a second aspect of the embodiments of the present application, there is provided a data correction apparatus for a high-precision map, the apparatus including:

the first acquisition module is used for acquiring object position data of a target object to be corrected in the high-precision map;

the second acquisition module is used for acquiring the central position data of the center line of each lane in the preset range according to the object position data and acquiring the boundary position data of the boundary of each lane in the preset range;

the first correction module is used for correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object if the target object is a first type object, wherein the first type object comprises an object of which the distance from the lane central line meets a first preset condition;

and the second correction module is used for correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object if the target object is a second type object, wherein the second type object comprises an object of which the distance from the lane boundary line meets a second preset condition.

In a third aspect of the embodiments of the present application, an electronic device is provided, where the electronic device includes a memory and a processor, and the memory stores a computer program, and the computer program is executed by the processor to implement the data correction method for a high-precision map according to the first aspect of the embodiments of the present application.

In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the data correction method for the high-precision map according to any one of the first aspect of the embodiments of the present application.

The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:

according to the data correction method of the high-precision map, the object position data of the target object to be corrected in the high-precision map are obtained, the center position data of the center line of each lane in the preset range are obtained according to the object position data, and the boundary position data of the boundary of each lane in the preset range are obtained. In the process of correcting the target object, if the target object is a first type object, correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object, and if the target object is a second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object, wherein the first type object is an object which is closer to a central line in the high-precision map, and the second type object is an object which is closer to a lane boundary in the high-precision map. Because the data of the center line of the lane and the lane boundary of the high-precision map are accurate, the data accuracy of the high-precision map can be improved by correcting other objects in the high-precision map according to the position data of the center line of the lane and the lane boundary.

Drawings

Fig. 1 is a schematic internal structural diagram of an electronic device according to an embodiment of the present disclosure;

fig. 2 is a first flowchart of a data correction method for a high-precision map according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a reference line before and after smoothing according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of a reference line before and after smoothing in an actual map provided by an embodiment of the present application (left diagram: before smoothing, right diagram: after smoothing);

fig. 5 is a second flowchart of a data correction method for a high-precision map according to an embodiment of the present application;

fig. 6 is a third flowchart of a data correction method for a high-precision map according to an embodiment of the present application;

fig. 7 is a fourth flowchart of a data correction method for a high-precision map according to an embodiment of the present application;

FIG. 8 is a schematic diagram of an actual road crosswalk line before and after correction provided by the embodiment of the application (left diagram: before correction, right diagram: after correction);

FIG. 9 is a schematic diagram of an actual road rod before and after modification according to an embodiment of the present application (left drawing: before modification, right drawing: after modification);

fig. 10 is a structural diagram of a data correction device for a high-precision map according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present disclosure, "a plurality" means two or more unless otherwise specified.

In addition, the use of "based on" or "according to" means open and inclusive, as a process, step, calculation, or other action that is "based on" or "according to" one or more conditions or values may, in practice, be based on additional conditions or exceeded values.

With the rapid development of the fields of intelligent transportation and automatic driving, the existing traditional navigation electronic map cannot meet the high-level application requirements in the aspects of content, precision and integrity. High-precision maps for roads are gradually proposed and widely agreed. Compared with the traditional electronic navigation map with a man-made service object, the high-precision map is a special electronic navigation map serving for the intelligent networked automobile, contains more abundant and detailed road surface, road side and road information, needs to be supplemented with real-time dynamic traffic information, and is far higher in manufacturing difficulty and complexity than the traditional electronic navigation map. The three functions of map matching, auxiliary environment perception and path planning of the high-precision map have rigid requirements and irreplaceable advantages in an automatic driving system.

The complete high-precision map expresses real road information through three types of data, wherein the first type is road and lane information and mainly records road information and guiding topological information; the second type is road peripheral facility information, which is auxiliary information such as positioning and obstacles; the third type is a positioning layer used for field matching of an automatic driving system. In the current high-precision map (HDmap) manufacturing process, because the manufacturing mode is semi-automatic or manual drawing, noise exists in the point cloud data acquired and solved or the two sides of the road are shielded by vegetation, the situation that the point cloud capture is not in place is easily caused for the drawing of ground road elements; and the urban road environment is complex, and the rod-shaped object elements are easy to be shielded, so that the bottom point cloud is lost, and a large offset error is caused. The quality of ground road elements affects functions of high-precision map unmanned-based map matching, auxiliary environment perception, path planning and the like, and effective technologies and methods are urgently needed to correct and process relative offset errors of the road elements in order to provide spatial data with detailed contents and continuously improved precision for management, analysis, planning and decision making of different levels.

In order to solve the above problem, an embodiment of the present application provides a data correction method for a high-precision map, which obtains object position data of a target object to be corrected in the high-precision map, and obtains center position data of center lines of lanes within a preset range and obtains boundary position data of boundaries of lanes within the preset range according to the object position data. In the process of correcting the target object, if the target object is a first type object, correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object, and if the target object is a second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object, wherein the first type object is an object which is closer to a central line in the high-precision map, and the second type object is an object which is closer to a lane boundary in the high-precision map. Because the data of the center line of the lane and the lane boundary of the high-precision map are accurate, the data accuracy of the high-precision map can be improved by correcting other objects in the high-precision map according to the position data of the center line of the lane and the lane boundary.

The execution main body of the data correction method for the high-precision map provided by the embodiment of the application can be electronic equipment, and the electronic equipment can be computer equipment, terminal equipment or a server, wherein the terminal equipment can be a vehicle-mounted terminal, various personal computers, a notebook computer, a smart phone, a tablet computer, a portable wearable device and the like, and the application is not particularly limited.

Fig. 1 is a schematic internal structure diagram of an electronic device according to an embodiment of the present application. As shown in fig. 1, the electronic device includes a processor and a memory connected by a system bus. Wherein the processor is configured to provide computational and control capabilities. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by a processor to implement the steps of a high-precision map data correction method provided in the above embodiments. The internal memory provides a cached execution environment for the operating system and computer programs in the non-volatile storage medium.

Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

Based on the execution main body, the embodiment of the application provides a data correction method of a high-precision map. As shown in fig. 2, the method comprises the steps of:

step 201, obtaining object position data of a target object to be corrected in the high-precision map.

The object position data of the target object may be point cloud data forming the target object, and the point cloud data may specifically be coordinate data of at least one node forming the target object.

Step 202, according to the object position data, obtaining center position data of the center line of each lane in a preset range, and obtaining boundary position data of the boundary of each lane in the preset range.

Optionally, the obtaining of the center position data of the center of each lane within the preset range and the obtaining of the boundary position data of each lane boundary within the preset range may include: acquiring coordinate sets of all reference lines in a preset range in a high-precision map to obtain all reference coordinate sets, and performing interpolation processing on each reference coordinate set according to a third preset threshold to obtain all interpolation reference coordinate sets; smoothing each interpolation reference coordinate set to obtain each target reference coordinate set; generating a lane marking line coordinate set and a lane boundary coordinate set according to each target reference coordinate set and the road width of the lane corresponding to each target reference coordinate set; and obtaining each center coordinate set and center position data according to the lane marking coordinate set and the lane boundary coordinate set.

The center position data of the lane center line can be point cloud data forming the lane center line, and the point cloud data can be coordinate data of at least one node forming the lane center line; the boundary position data of the lane boundary may be point cloud data forming the lane boundary, and the point cloud data may be coordinate data of at least one node forming the lane boundary.

In the actual execution process, firstly, determining whether a central line set exists in the map sheet of the current editable high-precision map, and if not, quitting the correction of the object position data of the target object; if the lane center line exists in the preset range of the target object, whether the lane center line exists in the preset range of the target object is determined, if the lane center line exists, the median position data of each lane center line in the preset range are acquired, and if the lane center line does not exist, the preset range can be expanded for re-determination, or the correction of the object position data of the target object is quitted.

Specifically, the process of determining whether a center line set exists in the map frame of the currently editable high-precision map may be: and searching the mark of the lane central line in the map sheet of the current editable high-precision map, and determining whether a central line set exists in the map sheet of the current editable high-precision map according to the searching result.

Specifically, the process of determining whether a center line exists within the preset range of the target object may be: and traversing each node of the target object, searching the mark of the lane center line in a preset range by taking each node as a center, and acquiring the center position data of each searched lane center line.

The preset range may be a range formed by centering each node and taking 17 meters as a radius. The radius length of 17 meters is determined according to historical search data, and the radius length may also be set according to specific situations, which is not specifically limited in the embodiment of the present application.

Similarly, in the actual execution process, whether a lane boundary set exists in the map sheet of the current editable high-precision map or not can be determined, and if not, the correction of the object position data of the target object is quitted; if the lane boundary exists, whether the lane boundary exists in the preset range of the target object is determined, if the lane boundary exists, the boundary position data of each lane boundary in the preset range is acquired, and if the lane boundary does not exist, the preset range can be expanded for re-determination, or the correction of the object position data of the target object is quitted.

Specifically, the process of determining whether the lane boundary set exists in the map frame of the currently editable high-precision map may be: and searching the map frame of the current editable high-precision map for the identification of the lane boundary, and determining whether a lane boundary set exists in the map frame of the current editable high-precision map according to the search result.

Specifically, the process of determining whether a lane boundary exists within the preset range of the target object may be: and traversing each node of the target object, searching the lane boundary identification in a preset range by taking each node as a center, and acquiring the boundary position data of each searched lane boundary.

Optionally, the process of acquiring the central position data of the center line of each lane within the preset range includes:

smoothing each interpolation reference coordinate set to obtain each target reference coordinate set;

The acquired center position data of the center line of each lane and the boundary position data of the boundary of each lane are obtained by interpolating and smoothing the reference lines in the acquired high-precision map.

In the actual execution process, all node coordinate sets of the reference line are obtained, and linear interpolation processing is performed according to 5 m limit difference, namely: sequentially traversing coordinates of two adjacent points, judging the distance between the two points, if the distance is greater than 5 meters, performing linear interpolation calculation according to the interval of 5 meters, and adding the interpolation coordinates into a coordinate set; and if the distance is less than or equal to 5 meters, continuing traversing. Then, smoothing treatment is carried out: traversing according to the three adjacent groups, and smoothing if the three-dimensional space distance from the middle point coordinate to the two adjacent coordinates is greater than 0.1 m limit difference. The smoothing method is that the intermediate point coordinate between the current point coordinate and the previous point coordinate is updated to the current point coordinate, and the intermediate point coordinate between the current point coordinate and the next point coordinate is inserted into the intermediate position between the current point and the next point,

and if the three-dimensional space distance from the middle point coordinate to the two adjacent coordinates is not greater than 0.1 m limit difference, continuing traversing until the traversing is finished. As shown in fig. 3, for the reference line after the smoothing processing, by performing interpolation processing on the reference line, a situation that the distance between adjacent nodes of the reference line is long can be avoided, the accuracy of the reference node can be improved, and further, the accuracy of the node of the lane center line and the lane boundary can be improved. As shown in fig. 4, a schematic diagram of a reference line in an actual map provided by the embodiment of the present application before and after smoothing (left diagram: before smoothing, right diagram: after smoothing).

The interpolation according to the length of 5 meters is determined according to the historical interpolation process, and the interpolation length may be set according to specific situations, which is not specifically limited in the embodiment of the present application.

And step 203, if the target object is the first type object, correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object.

And 204, if the target object is the second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object.

It is to be understood that the correction of the object position data may be understood as a correction of the coordinates of the respective object nodes constituting the object. Because the data of the center line of the lane and the lane boundary of the high-precision map are accurate, the other objects in the high-precision map are corrected according to the position data of the center line of the lane and the lane boundary, and the data accuracy of the high-precision map can be improved.

In the data correction process, the object in the high-precision map may determine an object closer to the center line of the lane as a first type object, and determine an object closer to the boundary of the lane as a second type object.

Optionally, the first type of object may be: arrows, characters or symbols on the road surface of the lane. The second type object may be: the system comprises rod-shaped objects, parking spaces, bicycle lanes in intersections, speed bumps, public transportation parking stations, flow guide areas, pedestrian crosswalks, parking positions, warning areas, well covers, intersections and other types of objects.

In the actual implementation process, the identifications of the objects in the high-precision map can be classified and stored in advance, so that whether the target object is the first-type object or the second-type object can be judged according to the identification of the target object. When the distance between the target object and the lane center line is the same as that between the target object and the lane boundary, the target object can be corrected by using the lane center line, and the target object can also be corrected by using the lane boundary. Specifically, the specific modification processes of step 203 and step 204 are explained in detail in the following embodiments.

In an embodiment, there is provided a technical process of obtaining target position data of the target object by correcting the object position data according to the object position data and each piece of center position data in step 203, where the object position data includes an object coordinate set of the target object, and the center position data includes a center coordinate set of a lane center line, and specifically, the process includes:

for each object coordinate in the set of object coordinates, performing the following operations: calculating the distance value between the object coordinate and each central coordinate in each central coordinate set, and taking the elevation value of the central coordinate corresponding to the minimum distance value in the calculated distance values as the elevation value of the object coordinate to obtain a first object coordinate set, wherein the elevation value is the Z-axis numerical value in the coordinate; and correcting the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set and target position data of the target object.

In practical application, all nodes of the current object are traversed, nodes adjacent to the center line set are traversed simultaneously, the center line set closest to the current object nodes is obtained, the elevation value of the center line set is assigned to the elevation value of the node corresponding to the current object, the object coordinate set of the target object is corrected, and the first object coordinate set is obtained. And then, correcting the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set again to obtain a target object coordinate set of the target object, and further obtain target position data. Because the coordinate data of the target object is actually detected data, but data errors may exist in the actual detection process, and the center line is datum data and the data is accurate, the elevation value of the center coordinate corresponding to the minimum distance value in the calculated distance values can be used as the elevation value of the object coordinate, so that all coordinates in the target object are ensured to be located in the same plane, and the rendering of the target object can be clearer.

As shown in fig. 5, an embodiment of the present application provides a technical process for correcting a first object coordinate set according to an elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set of a target object, where the process includes:

step 501, obtaining a first vector according to a first object coordinate corresponding to a minimum elevation value and a second object coordinate corresponding to a maximum elevation value in a first object coordinate set.

Step 502, calculating the projection distance of the remaining object coordinates in the first object coordinate set in the first vector, and taking the remaining object coordinates corresponding to the minimum projection distance as the third object coordinates.

The remaining object coordinates are object coordinates in the first object coordinate set except the first object coordinate and the second object coordinate;

and 503, obtaining a second vector according to the first object coordinate and the third object coordinate.

Step 504, a target object coordinate set is determined according to the first vector, the second vector and the first object coordinate set.

As shown in fig. 6, an embodiment of the present application further provides an implementation process of the foregoing step 504, where the implementation process includes the following steps:

step 601, determining a target object coordinate set according to the first vector, the second vector and the first object coordinate set, including:

step 602, determining a reference plane according to the first vector and the second vector;

603, calculating coordinates of each object coordinate in the first object coordinate set projected onto a reference plane to obtain a second object coordinate set;

and step 604, determining a target object coordinate set according to the second object coordinate set.

In practical application, for a first object coordinate set, traversing all nodes in the first object coordinate set, taking a node PZ1 corresponding to a minimum elevation value as a starting point and a node PZ2 corresponding to a maximum elevation value as an end point, establishing a first vector, sequentially traversing other nodes, taking the minimum value of the sum of two point distances from the other points to the first vector as a basis, obtaining a minimum value corresponding node PZ3, taking the PZ1 as the starting point and the PZ3 as the end point, establishing a second vector, and obtaining a reference plane direction vector by solving the dot product of the two vectors, so as to obtain a plane equation. And then projecting other nodes onto the reference plane, completing forced planarization treatment to obtain a second object coordinate set, and determining to obtain a target object coordinate set according to the second object coordinate set. By carrying out planarization processing on the data of the nodes in the target object, the coordinates in the target object can be further ensured to be positioned in the same plane, and the rendering of the target object can be clearer.

In an embodiment, there is provided a method for determining the target object coordinate set according to the second object coordinate set in step 604, where the method specifically includes:

determining a second coordinate object set as a target object coordinate set;

or determining at least one subset from the second object coordinate set according to the coordinate symmetry relationship in the second object coordinate set, wherein the subset consists of a first reference coordinate and a second reference coordinate which have the coordinate symmetry relationship, and a central coordinate of the first reference coordinate and the second reference coordinate; and calculating the average value of the elevation values of the first reference coordinate and the second reference coordinate in each subset, and determining the average value as the elevation value of the central coordinate to obtain a target object coordinate set.

It should be noted that, if there is a symmetric relationship between nodes in the target object, at least one subset is determined from the second object coordinate set according to the coordinate symmetric relationship in the second object coordinate set, where the subset is composed of a first reference coordinate and a second reference coordinate having a coordinate symmetric relationship, and a center coordinate of the first reference coordinate and the second reference coordinate; and calculating an average value of the elevation values of the first reference coordinate and the second reference coordinate in each subset, and determining the average value as the elevation value of the central coordinate to obtain a target object coordinate set. And if the nodes in the target object do not have a symmetrical relation, determining the second object set as a target object coordinate set. The nodes in the target object are further corrected through the symmetrical relation among the nodes in the target object, so that the target object with a symmetrical structure can be ensured to have a better rendering and displaying effect.

In one embodiment, the object position data comprises an object coordinate set of the target object and the boundary position data comprises a boundary coordinate set of the lane boundary.

As shown in fig. 7, an embodiment of the present application provides a technical process for obtaining target position data of a target object by correcting object position data according to the object position data and boundary position data in step 204, where the process specifically includes:

701, performing interpolation processing on adjacent object coordinates in an object coordinate set according to a first preset threshold to obtain a discrete object coordinate set;

step 702, correcting the discrete object coordinate set according to the boundary node coordinate set to obtain a third object coordinate set;

and 703, correcting the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain a target object coordinate set and target position data.

In an embodiment, the step 702 corrects the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set, and obtaining the third object coordinate set includes:

and taking the elevation value in the target boundary coordinate as the elevation value of each discrete object coordinate in the discrete object coordinate set to obtain a third object coordinate set, wherein the elevation value is a Z-axis numerical value in the coordinate. Therefore, the coordinates in the target object are ensured to be positioned in the same plane, and the rendering of the target object can be clearer.

In an embodiment, the modifying the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain the target object coordinate set includes:

In the actual execution process, if the target object is a second type object, traversing any two adjacent nodes in the object coordinate set, if the distance between the two nodes is greater than 0.5 m, performing linear interpolation processing between the two adjacent nodes according to the distance of 0.5 m, and if the distance between the two nodes is less than 0.5 m, not performing interpolation, so as to obtain a third object coordinate set. Then, aiming at a third object coordinate set, calculating a distance value between each boundary coordinate in the boundary coordinate set and each discrete object coordinate in the discrete object coordinate set, and determining the boundary coordinate corresponding to the minimum distance value as a target boundary coordinate; and taking the elevation value in the target boundary coordinate as the elevation value of each discrete object coordinate in the discrete object coordinate set to obtain a third object coordinate set. Then, aiming at a third object coordinate set, calculating the distances between the center object coordinate and the object coordinates at two ends in three adjacent object coordinates of the third object coordinate set; and deleting the nodes at the two ends corresponding to the distance greater than 0.1 meter from the third object coordinate set to obtain a target object coordinate set. Fig. 8 is a schematic diagram of an actual road crosswalk line before and after correction according to the embodiment of the present application (left diagram: before correction, right diagram: after correction). Fig. 9 is a schematic diagram of an actual road rod before and after correction according to an embodiment of the present application (left diagram: before correction, right diagram: after correction).

In order to facilitate understanding of those skilled in the art, the data modification method for a high-precision map provided in the present application is described by taking an execution subject as an electronic device as an example, and specifically, the method includes:

(1) acquiring object position data of a target object to be corrected in a high-precision map;

(2) acquiring coordinate sets of all reference lines in a preset range in the high-precision map according to the object position data to obtain all reference coordinate sets, and performing interpolation processing on all the reference coordinate sets according to a third preset threshold to obtain all the interpolation reference coordinate sets;

(3) performing smoothing processing on each interpolation reference coordinate set to obtain each target reference coordinate set;

(4) generating a lane marking coordinate set and a lane boundary coordinate set according to each target reference coordinate set and the road width of the lane corresponding to each target reference coordinate set;

(5) obtaining each center coordinate set and center position data according to the lane marking coordinate set and the lane boundary coordinate set;

(6) acquiring central position data of the center line of each lane in a preset range, and acquiring boundary position data of the boundary of each lane in the preset range;

(7) if the target object is the first type object, the following operations are executed for each object coordinate in the object coordinate set: calculating the distance value between the object coordinate and each central coordinate in each central coordinate set, and taking the elevation value of the central coordinate corresponding to the minimum distance value in the calculated distance values as the elevation value of the object coordinate to obtain a first object coordinate set, wherein the elevation value is the Z-axis numerical value in the coordinate;

(8) obtaining a first vector according to a first object coordinate corresponding to the minimum elevation value and a second object coordinate corresponding to the maximum elevation value in the first object coordinate set;

(9) calculating the projection distance of the remaining object coordinates in the first object coordinate set in the first vector, and taking the remaining object coordinates corresponding to the minimum projection distance as third object coordinates, wherein the remaining object coordinates are the object coordinates in the first object coordinate set except the first object coordinates and the second object coordinates;

(10) obtaining a second vector according to the first object coordinate and the third object coordinate;

(11) determining a reference plane from the first vector and the second vector;

(12) calculating the coordinates of each object coordinate in the first object coordinate set projected on the reference plane to obtain a second object coordinate set;

(13) determining the second coordinate object set as a target object coordinate set;

(14) or determining at least one subset from the second object coordinate set according to the coordinate symmetry relationship in the second object coordinate set, wherein the subset consists of a first reference coordinate and a second reference coordinate which have the coordinate symmetry relationship, and a central coordinate of the first reference coordinate and the second reference coordinate; calculating an average value of the elevation values of the first reference coordinates and the elevation values of the second reference coordinates in each subset, and determining the average value as the elevation value of the center coordinate to obtain a target object coordinate set;

(15) if the target object is a second type object, performing interpolation processing on adjacent object coordinates in the object coordinate set according to a first preset threshold value to obtain a discrete object coordinate set;

(16) calculating the distance value between each boundary coordinate in the boundary coordinate set and each discrete object coordinate in the discrete object coordinate set, and determining the boundary coordinate corresponding to the minimum distance value as a target boundary coordinate;

(17) taking the elevation value in the target boundary coordinate as the elevation value of each discrete object coordinate in the discrete object coordinate set to obtain a third object coordinate set, wherein the elevation value is a Z-axis numerical value in the coordinate;

(18) calculating the distances between the center object coordinate and the object coordinates at two ends in the three adjacent object coordinates of the third object coordinate set;

(19) and deleting the nodes at the two ends corresponding to the distance greater than the second preset threshold value from the third object coordinate set to obtain a target object coordinate set.

For the implementation processes of (1) to (19), reference may be specifically made to the description of the above embodiments, and the implementation principles and technical effects thereof are similar and will not be described herein again.

It should be understood that the steps in the step flow charts in the above embodiments are shown in sequence as indicated by the arrows, but the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps of the above-mentioned flowcharts may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or the stages is not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a part of the steps or the stages in other steps.

As shown in fig. 10, an embodiment of the present application provides a data correction apparatus for a high-precision map, including: a first obtaining module 11, a second obtaining module 12, a first correcting module 13 and a second correcting module 14.

The first obtaining module 11 is configured to obtain object position data of a target object to be corrected in a high-precision map;

the second obtaining module 12 is configured to obtain center position data of a center line of each lane within a preset range according to the object position data, and obtain boundary position data of boundaries of each lane within the preset range;

a first correction module 13, configured to correct the object position data according to the object position data and the center position data if the target object is a first type object, to obtain target position data of the target object, where the first type object includes an object whose distance from a lane center line meets a first preset condition;

and a second correcting module 14, configured to correct the object position data according to the object position data and the boundary position data if the target object is a second type object, so as to obtain target position data of the target object, where the second type object includes an object whose distance from a lane boundary line meets a second preset condition.

the first modification module 13 is specifically configured to:

for each object coordinate in the set of object coordinates, performing the following operations: calculating the distance value between the object coordinate and each center coordinate in each center coordinate set, and taking the elevation value of the center coordinate corresponding to the minimum distance value in the calculated distance values as the elevation value of the object coordinate to obtain a first object coordinate set, wherein the elevation value is the Z-axis numerical value in the coordinate;

In one embodiment, the first modification module 13 is specifically configured to:

determining a reference plane from the first vector and the second vector;

determining the second coordinate object set as a target object coordinate set;

the second modification module 14 is specifically configured to:

In one embodiment, the second modification module 14 is specifically configured to:

In an embodiment, the second obtaining module 12 is specifically configured to:

According to the data correction device for the high-precision map, the object position data of the target object to be corrected in the high-precision map are obtained, the center position data of the center line of each lane in the preset range is obtained according to the object position data, and the boundary position data of the boundary of each lane in the preset range is obtained. In the process of correcting the target object, if the target object is a first type object, correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object, and if the target object is a second type object, correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object, wherein the first type object is an object which is closer to a central line in the high-precision map, and the second type object is an object which is closer to a lane boundary in the high-precision map. Because the data of the center line of the lane and the lane boundary of the high-precision map are accurate, the data accuracy of the high-precision map can be improved by correcting other objects in the high-precision map according to the position data of the center line of the lane and the lane boundary.

The data correction device for a high-precision map provided by this embodiment may implement the data correction method embodiment for a high-precision map, which has similar implementation principles and technical effects, and will not be described herein again.

Specific limitations of the data correction device for the high-precision map can be referred to the above limitations of the data correction method for the high-precision map, and are not described herein again. The modules in the data correction device for high-precision maps may be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the server, and can also be stored in a memory in the server in a software form, so that the processor can call and execute operations corresponding to the modules.

In another embodiment of the present application, a computer device is further provided, which includes a memory and a processor, where the memory stores a computer program, and the computer program is executed by the processor to implement the steps of the data correction method for high-precision maps according to the embodiment of the present application.

In another embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the data correction method for high-precision maps according to the embodiment of the present application.

In another embodiment of the present application, a computer program product is further provided, which includes computer instructions, when the computer instructions are run on a data correction apparatus for high-precision maps, the data correction apparatus for high-precision maps executes each step executed by the data correction method for high-precision maps in the method flows shown in the above method embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The processes or functions according to the embodiments of the present application are generated in whole or in part when the computer-executable instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer-readable storage media can be any available media that can be accessed by a computer or data storage device including one or more available media integrated servers, data centers, and the like. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A data correction method of a high-precision map is characterized by comprising the following steps:

acquiring object position data of a target object to be corrected in the high-precision map;

2. The method of claim 1, wherein the object location data comprises a set of object coordinates of the target object, the center location data comprises a set of center coordinates of a lane centerline;

the correcting the object position data according to the object position data and the central position data to obtain the target position data of the target object includes:

performing the following for each object coordinate in the set of object coordinates: calculating a distance value between the object coordinate and each central coordinate in each central coordinate set, and taking an elevation value of the central coordinate corresponding to the minimum distance value in the calculated distance values as an elevation value of the object coordinate to obtain a first object coordinate set, wherein the elevation value is a Z-axis numerical value in the coordinate;

and correcting the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set of the target object and the target position data.

3. The method according to claim 2, wherein the modifying the first object coordinate set according to the elevation value of each object coordinate in the first object coordinate set to obtain a target object coordinate set of the target object comprises:

determining the set of target object coordinates from the first vector, the second vector, and the first set of object coordinates.

4. The method of claim 3, wherein determining the set of target object coordinates from the first vector, the second vector, and the first set of object coordinates comprises:

determining a reference plane according to the first vector and the second vector;

calculating coordinates of each object coordinate in the first object coordinate set projected onto the reference plane to obtain a second object coordinate set;

and determining the target object coordinate set according to the second object coordinate set.

5. The method of claim 4, wherein determining the set of target object coordinates from the second set of object coordinates comprises:

determining the second set of object coordinates as the set of target object coordinates;

or,

and calculating an average value of the elevation values of the first reference coordinate and the second reference coordinate in each subset, and determining the average value as the elevation value of the central coordinate to obtain the target object coordinate set.

6. The method of claim 1, wherein the object position data comprises a set of object coordinates of the target object, and the boundary position data comprises a set of boundary coordinates of a lane boundary;

the correcting the object position data according to the object position data and each boundary position data to obtain the target position data of the target object comprises the following steps:

correcting the discrete object coordinate set according to the boundary coordinate set to obtain a third object coordinate set;

and correcting the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain the target object coordinate set and the target position data.

7. The method of claim 6, wherein modifying the set of discrete object coordinates according to the set of boundary coordinates to obtain a third set of object coordinates comprises:

and taking the elevation value in the target boundary coordinate as the elevation value of each discrete object coordinate in the discrete object coordinate set to obtain the third object coordinate set, wherein the elevation value is a Z-axis numerical value in the coordinate.

8. The method according to claim 6 or 7, wherein the modifying the third object coordinate set according to the distance between two adjacent object coordinates in the third object coordinate set to obtain the target object coordinate set comprises:

and deleting the two end nodes corresponding to the distance larger than a second preset threshold value from the third object coordinate set to obtain the target object coordinate set.

9. The method of claim 1, wherein obtaining center position data of the center line of each lane within a preset range comprises:

acquiring a coordinate set of each reference line in a preset range in a high-precision map to obtain each reference coordinate set, and performing interpolation processing on each reference coordinate set according to a third preset threshold to obtain each interpolation reference coordinate set;

and obtaining each center coordinate set and the center position data according to the lane marking coordinate set and the lane boundary coordinate set.

10. A data correction apparatus for a high-precision map, characterized by comprising:

the second acquisition module is used for acquiring the central position data of the center line of each lane in a preset range according to the object position data and acquiring the boundary position data of the boundary of each lane in the preset range;

the first correction module is used for correcting the object position data according to the object position data and the center position data to obtain target position data of the target object if the target object is a first type object, wherein the first type object comprises an object of which the distance from a lane center line meets a first preset condition;

and the second correction module is used for correcting the object position data according to the object position data and the boundary position data to obtain the target position data of the target object if the target object is a second type object, wherein the second type object comprises an object of which the distance from a lane boundary line meets a second preset condition.

11. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements the data correction method for high-precision maps according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that a computer program is stored thereon, which when executed by a processor implements the data correction method of a high-precision map according to any one of claims 1 to 9.