A lane line vector graphics generation method and device

Abstract

The present application discloses a lane line vector graphics generation method and device, which solves the problem of high efficiency and low cost in drawing lane line vector graphics in the prior art. A lane line vector graphics generation method, used to generate a high-precision map containing lane lines based on point cloud data, includes: obtaining point cloud data of the target road; responding to GUI to capture point cloud data points, determining the plane coordinates of the starting point, turning point and / or end point of any part of the lane line, and connecting adjacent nodes to draw the basic lane line; generating interpolation nodes along the basic lane line according to a preset spacing value; assigning the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the target lane line or target road line. The present application improves the efficiency and accuracy of acquisition production, can bring about a significant efficiency improvement in the production of high-precision map data, and thus can ensure the current demand for high-precision maps in intelligent driving.

Description

Technical Field

[0001] The present application relates to the field of map and graphics processing technology, and in particular to a method and device for generating lane line vector graphics. Background Art

[0002] With the development of intelligent driving technology, the demand for navigation electronic maps continues to increase, which has led to the development of a high-precision map for autonomous or semi-autonomous driving, generally called a high-precision map. For example, a high-precision navigation electronic map of a road contains the geometry, attributes and relationships of the road network, lane network, road markings and road facilities, supports the access of dynamic road data, assists the autonomous intelligent movement of road vehicles and the refined management of road traffic, and is an electronic map or data set that can be used in conjunction with a general navigation electronic map. As a priori data serving autonomous driving, if real-time and dynamic data are not considered, it expresses map elements such as roads, lanes, roadside traffic signs and ground signs, and its geometric accuracy can be down to the centimeter level. And this is only its geometric accuracy. If we want to bring better predictions to intelligent driving, when only considering static data, we also need to know a lot of road and roadside sign information in advance. In addition to adding a large amount of plane and facade element collection work, we also need to fill in complex semantic information. The production of high-precision map data is mainly based on the results of vehicle-mounted point cloud data. Although the collection accuracy and coverage of point cloud data are already very high when it is produced, and there are also related software and hardware equipment for automatic collection or recognition, the complexity, clarity, and standardization of signs in real roads will cause great interference to the original point cloud data results and the automatic collection and recognition based on this. It cannot be completely dependent on automation, or it cannot be solved by automated tools at all. However, completely manual collection is very inefficient, and the timeliness of high-precision map data must be guaranteed. It is conceivable that ground roads are not necessarily straight or flat. Therefore, when drawing road lines, it is generally necessary to move the screen, and the mouse presses a certain interval and a certain interval of points to form a line. The number of mouse operations is too many, and the ups and downs must also be considered. This work is regular and frequent, and the cost of investment is very high. High-precision map data is crucial in intelligent driving technology. Therefore, how to ensure the accuracy of the data and improve the collection efficiency becomes a key issue. Summary of the invention

[0003] The present application proposes a method and device for generating lane line vector graphics, which solves the problem of high efficiency and low cost in the prior art of drawing lane line vector graphics.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a lane line vector graphics, which is used to generate a high-precision map containing lane lines based on point cloud data, including:

[0005] Obtain point cloud data of the target road;

[0006] In response to the GUI capturing point cloud data points, determining the plane coordinates of a starting point, an inflection point, or an end point of any portion of the lane line, and connecting adjacent nodes to draw a basic lane line;

[0007] Generate interpolation nodes along the basic lane line according to the preset spacing value;

[0008] The elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node is assigned to the interpolation node to determine the target lane line or target road line.

[0009] In one embodiment, after drawing the basic lane line, the method further comprises the following steps:

[0010] Compare the point cloud data of the lane line with the basic lane line to determine the deviation;

[0011] Adjust the deviation by adding nodes at the turning points.

[0012] In one embodiment, the target road is a straight road, and the basic lane line is expressed by drawing a straight line connecting the plane coordinates of the start point and the end point.

[0013] In one embodiment, the target road is curved, and a starting point and an inflection point, between two inflection points, and an inflection point and an end point are drawn and expressed by connecting straight lines.

[0014] Furthermore, the inflection point is expressed by drawing a curve or an arc.

[0015] In one embodiment, the method further comprises the steps of:

[0016] In response to drawing a target road line, determining the number of lanes of the target road;

[0017] According to the number of lanes, a plurality of parallel lines are copied at a preset interval perpendicular to the length direction of the road on one side or both sides of the target road line.

[0018] In one of the embodiments, in response to a change in the slope of consecutive nodes on a section of the target road being less than a set threshold, the number of nodes on the section is reduced.

[0019] In the second aspect, the embodiments of the present application also provide a lane line vector graphics generation device for implementing the lane line vector graphics generation method described in any one of the embodiments of the first aspect, comprising: an acquisition module for acquiring point cloud data of a target road. A determination module for determining the plane coordinates of the starting point, turning point or end point of any part of the lane line in response to capturing point cloud data points in a GUI. A generation module for connecting adjacent nodes to draw a basic lane line; and for generating interpolation nodes along the basic lane line at a preset spacing value, and assigning the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the lane line or the target road line.

[0020] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the embodiments of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the embodiments of the first aspect when executing the computer program.

[0022] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0023] This application can be compatible with some of the problems in its data and perform specific processing on lane lines. There is no need to draw them one by one according to the lane line point cloud map, so it can realize the convenient drawing of plane or elevation traffic elements, improve the efficiency and accuracy of data collection and production, and can bring significant efficiency improvement to the production of high-precision map data, thereby ensuring the current demand for high-precision maps for intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 A schematic diagram of a commercial server system for the application scenario of this application;

[0026] Figure 2 This is a flow chart of a method for generating lane line vector graphics according to an embodiment of the present application;

[0027] Figure 3 This is a flow chart of another method for generating lane line vector graphics according to an embodiment of the present application;

[0028] Figure 4 This is a flow chart of the third lane line vector graphics generation method of the embodiment of the present application;

[0029] Figure 5-1 This is a schematic diagram of a top view of a road line in an embodiment of the present application;

[0030] Figure 5-2 This is a schematic side view of a road line according to an embodiment of the present application;

[0031] Figure 5-3 This is another schematic side view of a road line according to an embodiment of the present application;

[0032] Figure 6 This is a structural diagram of the lane line vector graphics generating device according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0034] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0035] Figure 1 The commercial server system schematic diagram of the application scenario of this application includes: laser radar 300, road point cloud database 310, point cloud data processor 320, GUI operation interface and operation terminal 330, vehicle application terminal 340, at least one result map data set 350, navigation or automatic driving server 360.

[0036] In the present application, the vector graphics data of the road signs are generated by the point cloud data processor 320, and a code is set for each type of road sign graphics to represent the type of road sign-like features in the high-precision map data. The vehicle-mounted application terminal 340 of the intelligent driving device retrieves its geometric information and some attribute information assigned to it at the spatial position, that is, a set of coordinate points and a set of attributes. The set of coordinate points includes the three-dimensional coordinates (XYZ) of each node, reflecting the terrain undulation and slope. The attribute information includes some spatial topological relationships and association relationships, which represent the adjacent relationship of the drawn lines plus other attribute information. In the result map data set 350, these vector graphics data are stored through layers, each type of data belongs to a layer, and each layer has some attribute information. For cars, the vehicle-mounted application terminal needs to identify these data through specific layers. For example, the attribute information of a surface graphic is "no merging", and its graphic can be a solid line. Or, the attribute information of a surface graphic contains "no U-turn", and its graphic can be a double yellow line. A symbol can have various features, that is, the use information of the graphic is stored in the attribute.

[0037] Geometric information and attribute information are static data used to describe the road signs, and intelligent driving is based on these static data. Features such as road equipment and sign information, such as the height, instructions, and warnings of the signs, are entered into the attributes. The intelligent driving system makes predictions based on the attribute values, such as displaying the arrow mark at the intersection in advance and the left turn sign in advance. As long as there is a correlation with the position of the left turn sign, the system will directly warn how many meters ahead you can turn left.

[0038] The navigation or autonomous driving server 360 is used to generate a map displayed during vehicle navigation, and then provide navigation services or autonomous driving services on the displayed map. The map displayed in real time during navigation on the road is a superposition of vector graphics data and map by location. The road data used for navigation and other topographic map data are displayed as its background data to the specific location, and the maps on both sides of the road can also be displayed.

[0039] The vehicle-mounted laser radar 300 scans the road to generate road point cloud data, and the point cloud data processor generates point cloud data results, which are stored in the road point cloud database 310. The method described in this application mainly realizes the rapid acquisition of lane lines based on the vehicle-mounted point cloud data results, and automatically interpolates nodes and matches point cloud elevations at specified intervals. The present invention does not rely solely on computers to identify and collect, but is based on rules, and the operator makes judgments, selects and sets relevant information to achieve rapid acquisition in a human-computer interactive manner. The data is mainly classified from the accuracy requirements of high-precision map data. The ground line elements such as lane lines generally have high geometric accuracy requirements, while the lines or surfaces used for identification have high attribute accuracy requirements. Therefore, the position of the high geometric accuracy requirements must be accurate, and for those with high attribute information, we can slightly reduce the accuracy of its appearance shape to improve the efficiency of acquisition.

[0040] Figure 2 This is a flow chart of a method for generating lane line vector graphics according to an embodiment of the present application, which is used to generate a high-precision map containing lane lines based on point cloud data. It should be noted that the lane lines photographed by the point cloud car may not be clear. For example, some old marking lines have been worn out and the photographed point cloud image cannot be recognized; and the traffic settings on the road or traffic participants block the road surface. Interruptions occur during the automatic recognition of point cloud images or video images, and the workload of data repair is large. The device and method of the present application support the rapid generation of reliable lane line vector graphics data through interactive operation. Specifically comprising steps: 110~140.

[0041] Step 110: Obtain point cloud data of the target road.

[0042] In one embodiment of the present application, the point cloud data of the target road is obtained by shooting with a point cloud car and stored in the road point cloud database 310, or further processed by a point cloud data processor. When the operator retrieves the point cloud data through the production application terminal, the point cloud data of the target road is obtained, and an image of the point cloud data is generated on the production application terminal or a GUI connected thereto, and then feedback from the GUI is received to generate geographic information vector map data.

[0043] Step 120 , in response to the GUI capturing the point cloud data points, determining the coordinates of the starting point, turning point and / or end point of any part of the lane line, and connecting adjacent nodes to draw the basic lane line.

[0044] Here, the starting point, turning point, and end point set on the lane line graph are collectively referred to as nodes. For each of the above nodes, the coordinates include at least plane coordinates (XY). In this application, the plane coordinates, i.e., the coordinates of the point on the horizontal plane, refer to the position of the projection on the horizontal plane.

[0045] It should be noted that the starting point, turning point and end point are manually captured on the point cloud image. The basic lane line for connecting and drawing is manually drawn through the GUI, or a line graphic of the lane line is automatically generated based on the manually captured starting point, turning point and / or end point and displayed through the GUI.

[0046] Manual capture here refers to manually selecting a point cloud data point in the point cloud image on the GUI interface to obtain the position and coordinates of the selected point; or manually selecting a spatial point adjacent to several point cloud data points, and the position and coordinates of the spatial point are obtained by interpolating the coordinates of the several point cloud data points.

[0047] It should be noted that when capturing point clouds, that is, if there is a hole in a certain section of the ground without point clouds, the coordinates of the selected point cannot be directly obtained. Instead, they will be calculated separately here. That is, whether the selected spatial points are one or more, if the point cloud coordinates of the selected points cannot be obtained, the coordinates that can be obtained from several nearby point cloud data points will be used for calculation, in order to make up for the problem that the point cloud data is incomplete and the position and coordinates of the selected points cannot be obtained.

[0048] Preferably, in step 120, the line graphics of the lane lines are drawn in a top view, and only the starting point, turning point and end point of the road need to be considered, without considering the undulations of the ground.

[0049] In one embodiment, the target road is a straight road, and the basic lane line is expressed by a straight line connecting the plane coordinates of the starting point and the end point. A graphic of the basic lane line is generated on the GUI, and / or geometric data representing the basic lane line is generated in the vector graphics data. In the operation, only the starting point and the end point of any lane line need to be set. A straight line graphic displayed on the GUI is automatically generated between the starting point and the end point, and is expressed by drawing a straight line, thereby completing the basic lane line.

[0050] In one embodiment, the target road is curved, and the starting point and the turning point, between two turning points, and between the turning point and the end point are drawn and expressed by connecting straight lines. It is only necessary to set the starting point, the turning point, and the end point, or select two straight lines with an angle, or select the turning point to be drawn and expressed by a curve or arc. A curve graphic displayed on the GUI is automatically generated between the starting point, the turning point, and the end point, thereby completing the basic lane line.

[0051] In one embodiment, if Figure 3 As shown, in step 120, after drawing the basic lane line, steps 120-1 and 120-2 are also included:

[0052] Step 120 - 1 : Compare the point cloud data of the lane line with the basic lane line to determine the deviation.

[0053] It should be noted that the comparison in step 120-1 can be that the operator observes the point cloud image and the basic lane line displayed on the GUI and visually determines the lane line node at the deviation; or it can be that the point cloud data automatically identifies which point cloud sets belong to the point cloud image of the lane line position, and then automatically identifies the lane line graphics, and compares the generated lane line with the position of the basic lane line generated in step 120.

[0054] Step 120 - 2: Adjust the deviation by adding nodes at the turning point.

[0055] If there is a slight deviation, you can browse the drawing to add nodes for adjustment at the turning point. During the adjustment process, in response to the newly added points or deleted points selected in the point cloud image of the GUI, a line graph connected to the newly added points is automatically generated based on the points of the line graph displayed in the GUI, or a line graph excluding the deleted points is automatically generated.

[0056] Step 130: Generate interpolation nodes along the basic lane line according to a preset spacing value.

[0057] After drawing one or more lane lines, you can interpolate nodes at specified spacing values ​​as needed.

[0058] It should be noted that the interpolation node is automatically generated by the system of the present application during the drawing process of the surface lane line and / or road line. Preferably, in response to any two set points on the basic lane line, an interpolation node is generated on the basic lane line connecting the two set points.

[0059] It should be noted that when manually drawing lane lines along the surface, because the ground is highly undulating, the lines should fit the surface. When drawing through the GUI, not only do you look at the orthographic view vertically, but you also need to rotate the view to view the three-dimensional space to see if the lines fit the surface, and add nodes where they fit, which makes manual drawing difficult. Therefore, in order to avoid this problem and improve work efficiency, this application first considers only the orthographic view, which means vertical projection.

[0060] In step 130, when the operator sees a traffic sign line in the point cloud image, he selects any point upstream and downstream in the line, and automatically generates a line between the two points. As long as the line between the two points does not turn in the horizontal direction, it is a straight lane line. Alternatively, when the lane line turns, multiple points are set at the turning point, and the curved lane line is obtained by the set of lines between any two adjacent upstream and downstream nodes. Furthermore, a curved lane line can be generated by selecting multiple upstream and downstream points for curve interpolation. Then, by interpolating nodes (that is, interpolating on the line), for example, according to a certain preset spacing, such as a prescribed one-meter spacing, a point is interpolated to form a line. In this way, drawing two points forms a straight line feature, and any point on the straight line can determine the horizontal position, that is, the XY coordinate. When only the orthographic view is considered, the XY (or XYZ) coordinates of the interpolated node are obtained by interpolating the XY (or XYZ) coordinates of the upstream and downstream nodes. Although it matches the actual lane line in the horizontal direction, the straight line segment formed by connecting the points may not fit the ground surface because there may be undulating terrain between the upstream and downstream nodes. In other words, part of the straight line segment may be inserted below the ground surface, and part of it may be suspended above the ground surface.

[0061] It should also be noted that when determining the interpolation node, if there is a hole in a certain section of the ground without point cloud, the point cloud elevation cannot be obtained, and it will be calculated separately here, that is, whether there is one or more interpolated nodes, if the point cloud elevation of this node cannot be obtained, the elevation of the two end nodes that can be obtained will be calculated (for example, the elevation values ​​of the two end nodes with elevations are z1 and z2 respectively, and the distance is s, then the elevation of the first interpolated point is z=z1+(z2-z1) (s1 / s), where s1 is the distance from the first interpolated node to the previous node), which is used to make up for the problem that the elevation cannot be obtained due to incomplete point cloud data.

[0062] Step 140: assign the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the target lane line or target road line.

[0063] The lane line or road line is a connecting line including an interpolated node and upstream and downstream nodes. The data cluster of the lane line or road line includes the three-dimensional position coordinate data of the upstream and downstream nodes and the interpolated node, which constitutes the geometric information of the road marking objects. When the height coordinate of the interpolated node is the same as the ground elevation value, the interpolated node coincides with the surface of the road, and the generated lane line or road line is the target lane line or target road line.

[0064] The elevation value of each node is obtained from the point cloud data captured vertically at the node. In the vertical direction, the coordinates of the surface scanned point cloud data points are obtained.

[0065] The vertical capture of point cloud data points is to make a perpendicular to the horizontal plane through the interpolation nodes on the line. It can be a downward perpendicular or an upward perpendicular. After capturing the point cloud data points on the surface, the Z value of the point cloud data points is extracted to the interpolation node. Since the XY value of the interpolation node does not change, the Z value can be lowered or raised in the orthographic view. When viewed from the side, the undulating state is adjusted.

[0066] When vertical capture cannot obtain the point cloud data point that is the same as the plane coordinate XY of the interpolation node, but obtains the coordinate values ​​XiYi of several point cloud data points that are close to the XY coordinate distance, preferably, the vertical coordinate Z of the interpolation node can also be obtained by interpolating the coordinate values ​​Zi of multiple surface point cloud data points that are close to the XY horizontal distance.

[0067] In this way, a line feature is generated. This line feature may be a straight line when viewed from the orthographic perspective, but if you look at the direction of the road from the vertical profile, it may have ups and downs, which is consistent with the surface.

[0068] It should be noted that lane lines and road lines are different concepts. Lane lines are the marking lines on the road surface that can be seen on the highway, such as the lines between lanes, which are separated by dotted or solid lines. Lane reference lines are used to indicate the center line of the road and are only one line.

[0069] The determining of the target lane line or the target road line includes determining the graphics of the target lane line or the target road line on the GUI, and / or determining data representing the target lane line or the target lane line graphics in vector graphics data.

[0070] The node coordinates are projected vertically onto the ground point cloud, and the interpolated elevation value is calculated based on the elevation of the point cloud around the node coordinates and assigned to the node, thus forming a match between the lane line and the road surface. At the same time, the relevant slope value can also be calculated based on the coordinates and elevations of the front and rear nodes.

[0071] In the above embodiments, the method of the present application significantly saves labor costs and makes data production operations simple. For example, according to demand, interpolation is performed at one meter. If this road is about one kilometer, about 1000 points may be inserted (set to 1000 for simplicity of description), so that 1000 points are automatically generated from two manually drawn points. However, if these 1000 points are not generated by interpolation but are manually drawn, at least 1000 clicks of the mouse are required. However, through the solution of the present application, the operator only needs to draw twice, that is, click once a point upstream and click a second point downstream, and the lane line or road line drawing operation of a road is completed.

[0072] like Figure 4 As shown, in one embodiment, the method further comprises the steps of:

[0073] Step 150: In response to determining the target lane line or the target road line, determine the number of lanes of the target road.

[0074] By determining the number of lanes, the number of road lines is determined, for example, three lanes require two road lines.

[0075] Step 160: Copy a plurality of parallel lines on one side or both sides of the target lane line or target road line at a preset interval perpendicular to the road length direction according to the number of lanes.

[0076] Since a target road usually includes one or more lanes, when the target road includes multiple lanes, multiple road lines need to be drawn.

[0077] The copying of the plurality of parallel lines includes copying the graphics of the road lines in the GUI and / or copying the data representing the road lines in the vector graphics data.

[0078] According to the position of the target lane line on the road, it is determined to copy a number of parallel lane lines to one side or both sides.

[0079] The copying of the plurality of parallel lane lines includes copying the graphics of the lane lines in the GUI and / or copying the data representing the lane lines in the vector graphics data.

[0080] For example, if the target lane line is located on one side of the road, a parallel lane line is copied toward the center of the road.

[0081] If the target lane line is located in the middle of the road, parallel lane lines are copied to both sides.

[0082] Multiple road lines (or target lane lines) are drawn by duplicating the already drawn target road lines (or target lane lines) perpendicular to the road length direction at a preset interval. The preset interval is determined according to the scale of the current map and the point cloud data of the target road.

[0083] In one of the embodiments, in response to a change in the slope of consecutive nodes on a section of the target road being less than a set threshold, the number of nodes on the section is reduced.

[0084] The relevant slope values ​​can be calculated based on the coordinates and elevations of the front and rear nodes. Based on the comprehensive judgment of the plane angle and slope, if the slope change of a section of road is very small, too many nodes are not needed to express the ups and downs of the road surface. Node selection can be made to reduce data coordinate storage redundancy.

[0085] For example, Figure 5-1As shown, looking vertically downward at the road line 41 on the road surface, the road is relatively straight.

[0086] But if Figure 5-2 As shown, when viewed horizontally from the longitudinal section, the thick line 43 below is the horizontal plane, and the thin line 42 above is the undulating slope of the road, that is, the road surface.

[0087] exist Figure 5-2 On the basis of Figure 5-3 The newly drawn thick solid line 44 shown represents that the first and last points of the lane line are drawn. If the road surface is regarded as point cloud data, the drawn line will be interspersed on the upper and lower sides of the point cloud data. Finally, the drawn line is corrected to the road surface to fit the point cloud data by interpolating nodes as required.

[0088] Figure 6 This is a structural diagram of a lane line vector graphics generating device according to an embodiment of the present application, which is used to implement the lane line vector graphics generating method described in any embodiment of the first aspect, including:

[0089] The acquisition module 210 is used to acquire the point cloud data of the target road. The acquisition module can be a vehicle-mounted laser radar device 300, which acquires the road point cloud data in real time; it can also be a software running module in the point cloud data server 320, GUI operation interface or operation terminal 330, which is used to store, read or edit the target road point cloud data.

[0090] The determination module 220 is used to respond to the GUI and determine the plane coordinates of the starting point, turning point and end point of any part of the lane line.

[0091] The generation module 230 is used to draw the basic lane line; or to generate interpolation nodes along the basic lane line according to a preset spacing value, and assign the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the target lane line or target road line.

[0092] Furthermore, the determination module includes a first determination unit for determining the horizontal coordinates of a starting point, a turning point and / or an end point of any part of the lane line.

[0093] Furthermore, the generation module includes a first drawing unit, which is used to connect adjacent nodes to draw basic lane lines; it is also used to generate interpolation nodes along the basic lane lines according to preset spacing values, and assign the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the target lane line or target road line.

[0094] Furthermore, a comparison module is also included for comparing the point cloud data of the lane line with the basic lane line to determine the deviation.

[0095] The determination module further includes a second determination unit, which is used to determine the nodes added at the turning point and the indication information of the response adjustment deviation.

[0096] Furthermore, the generation module also includes a judgment unit, which is used to judge the shape of the target road and determine the shape of the basic lane line according to the point cloud data of the target road.

[0097] Furthermore, the generation module also includes a copying unit for copying a lane line parallel to the target lane line.

[0098] The determination module further includes a position determination unit for determining the position of the target lane line on the target road, and for determining the direction in which the copied lane line is arranged.

[0099] Furthermore, the determination module also includes a third determination unit, which is used to determine the slope of continuous nodes in a section of the target road, and reduce the number of nodes in the section when the slope change is less than a set threshold.

[0100] Furthermore, the determination module further comprises a fourth determination unit, which is used to determine whether the inflection point is expressed by drawing a curve, an arc or an angle between straight lines.

[0101] In one of the embodiments, a road information database / result map database 240 is also included, and the geographic information database / result map database is used to store the ground feature data before and after the merger in the target area.

[0102] Combination Figure 1 Schematic diagram of a commercial server system for the application scenario of this application.

[0103] The embodiments of the present application also propose a processing system for implementing the method described in any one of the embodiments of the present application, including: a laser radar 300, a road point cloud database 310, a point cloud data processor 320, a GUI operation interface and an operation terminal 330, an on-board application terminal 340, at least one result map data set 350, and a navigation or automatic driving server 360.

[0104] The road point cloud database 310 is used to store point cloud data of the target road.

[0105] The GUI operation interface and the operation terminal 330 are used to read the target road point cloud data, generate a point cloud image, input the set point cloud data points, display the data and / or graphics of the interpolated nodes; and / or trigger the acquisition module, determination module or generation module. The vehicle-mounted application terminal 340 is used to determine the spatial position, retrieve the vector graphics data of the road sign, including geometric information and attribute information; and is also used to display the map during vehicle navigation. The map displayed in real time during navigation on the road is the vector graphics data and the map superimposed together by position. The point cloud data processor 320 or the operation terminal 330 is used to respond to the instructions of the GUI, obtain the point cloud data of the target road, determine the basic lane line, and generate the interpolated nodes along the basic lane line, determine the elevation value of each coordinate point on the lane line through the point cloud data, and generate the target lane line or target road line; the point cloud data processor 320 is also used to obtain the point cloud data of the road scanned by the vehicle-mounted laser radar, obtain and / or generate the vector graphics data of the road sign, and generate a high-precision map containing the lane line. The result map data set is used to store high-precision maps, wherein the data includes target lane line or target road line related data, and also includes vector graphics data and map overlay data sets.

[0106] It should be understood that the above-mentioned specific related contents are only used for illustrative purposes and should not impose any limitation on the present application.

[0107] The specific method for implementing the functions of the above-mentioned modules is as described in the various method embodiments of the first aspect of the present application, and will not be repeated here.

[0108] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] Therefore, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present application is implemented.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Furthermore, the present application also proposes an electronic device (or computing device), comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present application when executing the computer program.

[0114] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium. Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0115] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0116] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A lane line vector graphics generation method for generating a high-precision map containing lane lines based on point cloud data, characterized in that: include: Obtain point cloud data of the target road; In a top view, in response to the GUI capturing point cloud data points, a basic lane line is expressed by a straight line connecting the plane coordinates of a start point and an end point; and geometric data representing the basic lane line is generated in the vector graphics data; Generate interpolation nodes along the basic lane line according to the preset spacing value; By making a perpendicular foot to the horizontal plane through the interpolation node, the point cloud data points are captured in the vertical direction, and the elevation value of the ground point cloud data point corresponding to the perpendicular line of each interpolation node is assigned to the interpolation node to determine the target lane line or target road line.

2. The lane line vector graphics generation method according to claim 1, characterized in that: After drawing the basic lane lines, the following steps are also included: Compare the point cloud data of the lane line with the basic lane line to determine the deviation; Adjust the deviation by adding nodes at the turning points.

3. The lane line vector graphics generation method according to claim 1, characterized in that: The target road is curved, and a starting point, a turning point, and an end point are set. A curve graphic displayed on the GUI is automatically generated between the starting point, the turning point, and the end point, thereby completing the basic lane line.

4. The lane line vector graphics generation method according to claim 1, characterized in that: The target road is curved, and the starting point and the turning point, between two turning points, and the turning point and the end point are drawn and expressed by connecting straight lines.

5. The lane line vector graphics generation method according to claim 1, characterized in that: Also includes the steps: In response to drawing a target road line, determining the number of lanes of the target road; According to the number of lanes, a plurality of parallel lines are copied at a preset interval perpendicular to the length direction of the road on one side or both sides of the target road line.

6. The lane line vector graphics generation method according to claim 1, characterized in that: In response to a change in the slopes of consecutive nodes on a section of the target road being less than a set threshold, the number of nodes on the section is reduced.

7. The lane line vector graphics generation method according to claim 4, characterized in that: The inflection point is expressed by drawing a curve or an arc.

8. A lane line vector graphics generating device, characterized in that: The method for generating a lane line vector graphic according to any one of claims 1 to 7 comprises: An acquisition module is used to acquire point cloud data of the target road; A determination module for determining the plane coordinates of a starting point, an inflection point, or an end point of any portion of a lane line in response to capturing a point cloud data point by the GUI; A generation module is used to connect adjacent nodes to draw basic lane lines; it is also used to generate interpolation nodes along the basic lane lines according to preset spacing values, and assign the elevation value of the ground point cloud data point corresponding to the vertical line of each interpolation node to the interpolation node to determine the target lane line or target road line.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images