A method and device for generating vector graphics of road markings

Abstract

The present application discloses a method and apparatus for generating a vector graph of road markings, which solves the problems of large workload in drawing vector graphs of road markings in the prior art and being affected by incomplete acquisition of point clouds of road markings. A method for generating a vector graph of road markings for generating a high-precision map including road markings based on point cloud data includes: obtaining point cloud data of a target road and attributes of road markings on the target road; a preset display graph corresponding to the attributes; determining position information of the road markings on the target road in response to GUI positioning to capture point cloud data points; retrieving symbol data representing the preset display graph, and generating the preset display graph in the high-precision map according to the position information. The present application also includes an apparatus for implementing the method. The present application can improve the efficiency and accuracy of high-precision map data production.

Description

Technical Field

[0001] The present application relates to the technical fields of map and graphic processing, and particularly relates to a method and device for generating a vector graphic of road markings. Background Art

[0002] With the development of intelligent driving technology, the demand for navigation electronic maps has been increasing continuously, and thus a high-precision map for autonomous driving or semi-autonomous driving has emerged, which is generally called a high-precision map. For example, a road high-precision navigation electronic map contains a road network, a lane network, road markings, and the geometry, attributes, and relationships of road facilities, supports the access of road dynamic data, and assists the autonomous intelligent movement of road traffic tools and the refined management of road traffic. It is a sub-map or data set that can be applied in coordination with a general navigation electronic map. As prior data for serving autonomous driving, if real-time and dynamic data are not considered, it expresses map elements such as roads, lanes, roadside traffic signs, and road markings, and its geometric accuracy can reach the centimeter level. And this is only its geometric accuracy. If we want to bring better prediction for intelligent driving and only consider static data, we also need to predict a lot of marking information on the road surface and roadside in advance. Then, in addition to increasing a large amount of plane and elevation element collection work, we also need to fill in complex semantic information for it. The production of high-precision map data is mainly based on the results of on-vehicle point cloud data. Although the collection accuracy and coverage are already very high during the production of point cloud data, and there are also related software and hardware devices for automatic collection or recognition, the complexity, clarity, and standardization of signs on real roads will all cause great interference to the results of the original point cloud data and the automatic collection and recognition based on it. It cannot rely entirely on automation, or rather, it cannot be solved by automated tools at all. However, completely manual collection is very inefficient, and the currency of high-precision map data must be ensured. Then, it can be imagined that for the arrow surfaces of road markings, there are almost at every intersection, and even many. If they are all hand-drawn, the efficiency is extremely low. Some applications have reduced the requirements for expressing the arrow shape and only require the circumscribed rectangle of the arrow. However, if they are still manually drawn one by one, the workload is still very large. This work is regular and frequent, and the input cost will be very high. And high-precision map data is crucial in intelligent driving technology. Then, how to ensure the accuracy of the data and improve the collection efficiency has become a key problem. Summary of the Invention

[0003] The present application provides a method and device for generating a vector graphic of road markings, which solve the problems in the prior art that the workload of drawing a vector graphic of road markings is large and the accuracy of the attribute information of road markings is affected by incomplete collection of road marking point clouds.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a vector graphic of road markings, which is used to generate a high-precision map containing road markings based on point cloud data, and includes:

[0005] Obtain the point cloud data of the target road and the attributes of the road surface markings on the target road; the attributes correspond to preset display graphics;

[0006] In response to the GUI positioning to capture the point cloud data points, determine the position information of the road surface markings on the target road;

[0007] Retrieve the symbol data representing the preset display graphics, and generate the preset display graphics in the high-precision map according to the position information.

[0008] In one embodiment, determine the circumscribed rectangle of the road surface markings based on the point cloud data as the position information, and fill the circumscribed rectangle with the display graphics.

[0009] In one embodiment, determine the positioning points of the road surface markings based on the point cloud data points as the position information.

[0010] In one embodiment, determining the position information of the road surface markings on the target road specifically further includes the steps of:

[0011] Obtain the lane information of the target road; the lane information includes the number of lanes and the lane spacing;

[0012] Determine the corresponding number of position information according to the number of lanes, and determine the spacing of the position information according to the lane spacing.

[0013] In one embodiment, in response to the road surface marking being a preset arrow pattern, it further includes the steps of:

[0014] Determine the traveling direction of the target road or a single lane on the target road;

[0015] Draw the direction of the arrow pattern to be consistent with the traveling direction of the target road or a single lane on the target road.

[0016] In one embodiment, it further includes the steps of:

[0017] In response to the target road including multiple lanes, determine a plurality of display graphics corresponding to the number of lanes as a display graphic group;

[0018] Generate the display graphic group according to the position information.

[0019] In one embodiment, the data representation of the display graphics is a point symbol or a face symbol; the data cluster of the point symbol or the face symbol includes primitive combinations, primitive positions, display attribute values, symbol size attribute values, and symbol position attribute values.

[0020] In one embodiment, the display graphics form one road surface marking, or the display graphics form a plurality of road surface markings arranged perpendicular to the traveling direction of the road surface.

[0021] In one embodiment, a symbol data cluster associated with the position information is generated in the dataset of the high-precision map, and the symbol data cluster includes data representing the preset display graphics.

[0022] In a second aspect, an embodiment of the present application further provides a device for generating a vector graphic of a road surface marking, which is used to implement the method for generating a vector graphic of a road surface marking on a high-precision map based on point cloud data according to any one of the embodiments in the first aspect, including: an acquisition module, configured to acquire point cloud data of a target road and attributes of road surface markings on the target road; a determination module, configured to determine the position information of the road surface marking on the target road or determine preset position information; and a generation module, configured to generate the preset display graphics in the high-precision map according to the position information.

[0023] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method according to any one of the embodiments in the first aspect is implemented.

[0024] In a fourth aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method according to any one of the embodiments in the first aspect is implemented.

[0025] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0026] The present application can perform specific processing on road surface markings to be compatible with partial problems of its data, accurately determine the position of road surface markings without being affected by ground debris, that is, it can achieve convenient drawing of traffic elements, improve the efficiency and accuracy of acquisition and production, bring a significant improvement in the efficiency of high-precision map data production, and further ensure the up-to-date demand of intelligent driving for high-precision maps. Description of the Drawings

[0027] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings:

[0028] Figure 1 It is a schematic diagram of a commercial server system for the application scenario of the present application;

[0029] Figure 2 It is the representation of road surface markings in a high-precision map of the prior art;

[0030] Figure 3 This is a flowchart of a method for generating a vector graphic of a road surface marking in an embodiment of the present application;

[0031] Figure 4 This is a schematic diagram of an arrow of a road surface marking in an embodiment of the present application;

[0032] Figure 5 This is a flowchart of another method for generating a vector graphic of a road surface marking in an embodiment of the present application;

[0033] Figure 6 This is a flowchart of another method for generating a vector graphic of a road surface marking in an embodiment of the present application;

[0034] Figure 7 This is a schematic diagram of the positioning point of the display graphic of the road surface marking and the one-point positioning of the point symbol;

[0035] Figure 8 This is a schematic diagram of the positioning of the surface symbol through 3 points;

[0036] Figure 9 This is a schematic diagram of the positioning of the preset display graphic group of the grouped road surface markings;

[0037] Figure 10 This is a structural diagram of a device for generating a lane line vector graphic in an embodiment of the present application. Detailed implementation manners

[0038] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0039] The following details the technical solutions provided by each embodiment of the present application in conjunction with the drawings.

[0040] Figure 1 This is a schematic diagram of a commercial server system for the application scenario of the present application. It includes: a lidar 500, a road point cloud database 510, a point cloud data processor 520, a GUI operation interface and a job terminal 530, a vehicle-mounted application terminal 540, at least one result graph data set 550, and a navigation or autonomous driving server 560.

[0041] In this application, vector graphic data of road signs is generated by the point cloud data processor 520. A code is set for each type of road sign graphic to represent the type of road sign feature in the high-precision map data. The in-vehicle application terminal 540 of the intelligent driving device retrieves its geometric information and some assigned attribute information at the spatial position where it is located, 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 are composed of the adjacent relationships of the drawn lines plus other attribute information. In the result map dataset 550, these vector graphic data are stored through layers. Each type of data belongs to a layer, and there is some attribute information in each layer. For a vehicle, the in-vehicle application terminal needs to identify these data through specific layers.

[0042] The 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, indication, warning, etc. of the signs, are entered into the attributes. The intelligent driving system makes pre-judgments based on the attribute values. For example, it displays the arrow marks at intersections in advance and displays the left-turn signs in advance. As long as there is an association with the position of the left-turn sign, the system directly gives an early warning saying that a left turn can be made at a certain distance ahead.

[0043] The in-vehicle lidar 500 scans the road to generate road point cloud data, which is processed by the point cloud data processor to generate point cloud data results and stored in the road point cloud database 510. The navigation or autonomous driving server 560 is used to generate the 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 obtained by overlaying the vector graphic data and the map according to the position. The road data used for navigation and other topographic map data are displayed as background data at specific positions, and the maps on both sides of the road can also be shown.

[0044] Figure 2 For the representation of road surface signs in the high-precision map of the prior art, a rectangular box is displayed within the lane. In the internal data structure, the geometric information is the vector graphic data of the rectangular box, and the attribute information includes the meaning of the road surface sign. For example, the attribute information of a surface graphic is "left turn plus U-turn", and its graphic can be a rectangular surface. Or, for a point symbol, the attribute information contains features such as "left turn", "left turn plus U-turn", or "straight plus left turn", that is, its usage information is stored in the attributes.

[0045] Such as Figure 2As shown, in the existing technology for drawing road markings, in the field of high-precision maps, it is not required to represent the arrow graphics of road markings. When map production personnel draw the map, they only need to draw the circumscribed rectangle 21 of the road marking. The method of drawing the rectangle can be manually framed in the GUI according to the road marking image shown in the point cloud image, or the circumscribed rectangle can be automatically recognized from the road marking image in the point cloud data. If the circumscribed rectangle is drawn manually, it is traced one by one according to the point cloud image, and the production efficiency is very low, and the operation results are irregular, and even the same markings have different sizes. With the help of a point cloud recognition tool to obtain the circumscribed rectangle of the arrow, due to the unclear point cloud over the years, occlusion, etc., the success rate of automatic recognition is low, and the recognition results of the same markings have different sizes.

[0046] In addition, the existing production method is to draw a rectangle frame first and then fill in the attributes. Whether it is manually framed or automatically recognized, the attribute information is assigned after generating the geometric information, and the operation workload is large.

[0047] High-precision maps attach importance to attribute information. If the attributes are manually filled in after generating the rectangle frame, it is impossible to directly identify the consistency between the attribute value and the point cloud true value in case of operation errors.

[0048] The method described in this application mainly realizes rapid acquisition based on the results of vehicle-mounted point cloud data, determines the attribute information of road markings, retrieves the preset display graphics, locates the positions of road markings, and thus draws the display graphics of road markings. The present invention does not rely solely on the computer for recognition and acquisition, but is based on rules, and the operator makes judgments, selections, and settings of relevant information to achieve rapid acquisition work in a man-machine interaction manner.

[0049] Figure 3 This is a flowchart of a method for generating a vector graphic of road markings according to an embodiment of the present application, which is used to generate a high-precision map including road markings based on point cloud data, and specifically includes steps 110 to 130.

[0050] Step 110: Obtain the point cloud data of the target road and the attributes of the road markings on the target road; the attributes correspond to preset display graphics.

[0051] The point cloud data of the target road includes the point cloud data of the road markings on the road. Through the image of the point cloud data, the position and pattern information of the road marking can be obtained.

[0052] Regarding the acquisition of the point cloud data of the target road, in an embodiment of the present application, the point cloud data of the target road is obtained by a point cloud vehicle shooting and stored in the road point cloud database 510, or further processed by a point cloud data processor. When the operator retrieves the point cloud data through the operation terminal, the point cloud data of the target road is obtained, and an image of the point cloud data is generated on the operation terminal or the GUI connected thereto.

[0053] Then, receive feedback from the GUI and generate attribute information and vector map data of the road surface markings.

[0054] The attributes of the road surface markings include the traveling direction of the road. For example, in a road with multiple lanes, the traveling directions of each lane can be the same or different. The attributes of the road signs also include the specific types of road surface markings, such as: straight arrow, straight arrow with left turn, straight arrow with right turn, left turn with U-turn arrow, U-turn arrow, etc. For another example, if there are three lanes on a road, the middle lane is a straight lane, the left lane is a left turn, left U-turn or straight lane, and the right lane is a straight or right turn lane.

[0055] Regarding the acquisition of the attributes of the road surface markings on the target road, it can be to automatically identify the arrow markings in the point cloud data image, and the computer processing program automatically generates the attribute information; or manually identify the arrow markings in the point cloud data image, manually determine the marking content, and then input or select the attribute information through the GUI.

[0056] Regarding the preset display graphics, the method and device of the present application include a preset symbol library / table, in which there is a preset display graphic for each type of road surface marking. The data of the display graphic is represented as a point symbol or a surface symbol; the data cluster of the point symbol or the surface symbol includes graphic element combinations, graphic element positions, display attribute values, symbol size attribute values, symbol position attribute values, etc.

[0057] In one embodiment, the size of the display graphic is a preset fixed value, that is, the length and width of its circumscribed rectangle are preset fixed values. A further optimized technical solution is to preset an adjustment ratio value, which can be manually set to expand or shrink.

[0058] Step 120: Respond to the GUI to locate and capture the point cloud data points, and determine the position information of the road surface markings on the target road.

[0059] The present application obtains the visual effect of the working environment through the point cloud data. If step 110 performs the recognition and / or selection of the shape types of the road surface markings according to the point cloud image, step 120 obtains the position information of the road surface markings through the point cloud data. The position information includes elevation information (Z) and horizontal coordinate information (X, Y). Generate a ground object symbol of the road surface marking class, which is a point symbol or a surface symbol, and the display graphic of the symbol is selected from the preset symbol library / table, and the position coordinates are captured from the point cloud data.

[0060] Regarding the positioning and capturing of the point cloud data points, it is to locate the display graphic of the road surface markings through the selected point cloud data points and obtain the position information XYZ. It can be manually captured or automatically captured.

[0061] In one embodiment, the positioning point of the road surface marking is determined according to the point cloud data points as the position information.

[0062] As an embodiment, the display graphic of the present application is provided with a positioning point. For example, a positioning point is set on any primitive constituting the display graphic, and the positioning point can be directional. For example, one-point positioning and three-point positioning.

[0063] The one-point positioning method captures the position of 1 point in the point cloud data as the position where the positioning point of the display graphic is located. As Figure 7 shown, for example, the display graphic is an arrow, and a point 71 in the middle of the bottom of the arrow is used as the positioning point. The one-point positioning method is generally used for point symbols, and the primitive of the display graphic is composed of point symbols.

[0064] The multi-point positioning method captures the positions of 3 points in the point cloud data. As Figure 8 shown, the first point 81 is used as the position where the positioning point of the display graphic is located, which can be defined at the lower left corner of the circumscribed rectangle; the second point 82 is used to determine the direction of the graphic, which can be any point in front of the first point, and the direction of the graphic is the vector from the first point to the second point and parallel to the lane line direction, and / or, the third point 83 is used as the width of the display graphic, and the component difference of its coordinate value from the first point in the direction perpendicular to the lane is used as the width value. Set the size of the rectangle or the style of the symbol in advance, and click a point at the specified position to position, and another point to orient, and draw a single arrow or the circumscribed rectangle of a single arrow and / or the display graphic. Two-point positioning can be used for point symbols or surface symbols, and the three-point positioning method is generally used for surface symbols.

[0065] Regarding the determination of the position information of the road surface marking on the target road, it includes directly determining the position information of the road surface marking according to the captured point cloud data points or determining the position information of the road surface marking relative to the captured point cloud data points. (1) Through the point cloud data, determine the position of the road surface marking on the target road. For example, determine the drawing position of the road surface marking of the target road in reality through the point cloud data points captured in the point cloud image. Or, (2) Without considering the real position information of the road surface marking in reality, preset a relative position that meets the setting standard of the road surface marking on the road as the preset relative position information. In one embodiment, the road surface marking is set on the target road at a set length from the stop line. In this way, after capturing the position information of the point cloud data points on the stop line, the position information of the road surface marking is determined according to the relative position information.

[0066] In one embodiment, in response to selecting the real position information of the road surface marking as the position information of the road surface marking, if the GUI positioning captures that the point cloud data points belong to a certain road surface marking, then the circumscribed rectangle of the road surface marking pattern is determined according to the point cloud data as the position information.

[0067] Step 130: Retrieve the symbol data representing the preset display graphic, and generate the preset display graphic in the high-precision map according to the position information.

[0068] In one embodiment, the circumscribed rectangle of the road surface marking is determined based on the point cloud data as the position information, and the circumscribed rectangle is filled with the display graphic.

[0069] In one embodiment, the positioning point of the road surface marking is determined based on the point cloud data points as the position information, and the display graphic is positioned. The position information is assigned to the position attribute of the preset positioning point in the display graphic. Preferably, the display graphic is generated according to a preset size, and the display graphic can also be stretched and shrunk through the GUI. Further preferably, the display graphic is generated according to a preset direction, and the display graphic can also be oriented or rotated through the GUI.

[0070] Different from the prior art, the solution of the present application can set the size of the circumscribed rectangle of the road surface marking and / or the style of the symbol in advance, select a point for positioning and orientation at a specified position, and generate a road surface marking graphic (such as a single arrow) or a circumscribed rectangle according to the preset style and size, with simple operation and standard effect.

[0071] For example, when generating map data, an arrow-shaped road surface marking is generated according to the positioning point, which can be the preset display graphic arrow symbol 41, as Figure 4 shown, or it can be a fixed-size rectangular surface set, as Figure 2 shown.

[0072] Further, a symbol data cluster associated with the position information is generated in the dataset of the high-precision map, and the symbol data cluster contains data representing the preset display graphic.

[0073] Further, the attribute information obtained in step 110 is the attribute information determined in advance in order to retrieve the corresponding display graphic according to the attribute before retrieving the symbol data representing the preset display graphic, and the attribute information associated with the road surface marking is also automatically generated in the dataset of the high-precision map.

[0074] It should also be noted that by using the embodiments of steps 110 to 130, the road surface marking arrows of the same lane group can be drawn in groups. When different schemes are selected, such as "left turn and U-turn + left turn + straight + straight + right turn", the preset grouped roadside marking display graphics, sizes, corresponding positioning points or rectangular surfaces can be automatically read to obtain the corresponding geometric information, retrieve different point symbols or rectangular surfaces associated with the high-precision map, and the corresponding attribute information is also assigned in the attribute item, eliminating the need for manual assignment.

[0075] It should be noted that when selecting the circumscribed rectangle of the road surface marking pattern as the position information, relatively complete point cloud acquisition of the road surface marking is required. In the case of incomplete point cloud acquisition, there may be a large error in directly generating the circumscribed rectangle according to the point cloud image. This application uses a preset display graphic to fill the position of the road surface marking to avoid this problem.

[0076] The innovation of this case lies in the interaction method and the drawing of a single symbol or a group of multiple symbols according to the prefabricated display graphic. In this way, the drawn map contains the display graphic of the road surface marking, which is consistent with the rules of the road surface marking graphic displayed by the point cloud image, and this graphic drawing scheme is set in advance without manual filling of attributes.

[0077] Figure 5 This is a flowchart of another method for generating a vector graphic of a road surface marking according to an embodiment of the present application, specifically including steps 210 to 250.

[0078] Step 210: Obtain the point cloud data of the target road and the attributes of the road surface markings on the target road; the attributes have corresponding preset display graphics.

[0079] Step 220: Respond to the GUI to locate and capture the point cloud data points, and determine the position information of the road surface marking on the target road.

[0080] Step 230: Retrieve the symbol data representing the preset display graphic, and generate the preset display graphic in the high-precision map according to the position information.

[0081] In one embodiment, in response to the road surface marking being a preset arrow pattern, it further includes the steps of:

[0082] Step 240: Determine the traveling direction of the target road or a single lane on the target road.

[0083] Step 250: Generate the direction of the arrow pattern to be consistent with the traveling direction of the target road or a single lane on the target road.

[0084] Figure 6 This is a flowchart of another method for generating a vector graphic of a road surface marking according to an embodiment of the present application, specifically including steps 310 to 330.

[0085] Step 310: Obtain the point cloud data of the target road and the attributes of multiple road surface markings on the target road; each of the attributes has a corresponding preset display graphic, forming a display graphic group.

[0086] In one embodiment, in response to the target road including multiple lanes, determine a plurality of display graphics corresponding to the number of lanes as a display graphic group;

[0087] Within the same lane group, the same road surface markings can be replicated and set. For example, if the straight arrows are shown on two side-by-side lanes, after generating the road surface markings on one lane according to steps 110 to 130, the display graphics of the road surface markings on the first lane, including geometric information and attribute information, are located and replicated on the second lane.

[0088] The road surface markings within the same lane group can also be drawn in groups. In this case, the road surface markings generally have fixed sizes, are arranged side by side in their respective lanes, and are very neat. The preset plan name sets a '+' sign in the middle of the attribute values of each road surface marking. When called, it is decomposed with the '+' sign as a special character. Multiple options are set in advance in this application for quick selection, such as the 'Adjust + Left (Adjust) + Straight + Right (Straight)' type and the 'Straight + Straight Right' type.

[0089] The parameters corresponding to the display graphic group can also be encoded with numbers according to their expressed meanings. For example, for the straight-right type, several sets of commonly used numbers are provided, such as 1,1; 2,1; 3,1, etc., which respectively represent that the number of straight arrows is 1, 2, 3, and the number of right-turn arrows is 1.

[0090] Step 320: In response to the GUI locating and capturing the point cloud data points, determine the position information of the multiple road surface markings on the target road.

[0091] The position information can be, for example, determining the positioning points of the multiple road surface markings based on the point cloud data points as the position information. It can also be determining the circumscribed rectangle of the patterns of the multiple road surface markings based on the point cloud data as the position information.

[0092] When determining the positioning points, positioning points can be set for at least a part of the multiple road surface markings to determine the positions of the display graphics of at least a part of the road surface markings. Further, the positions of the display graphics of other road surface markings are determined in combination with the number of lanes and / or the lane spacing.

[0093] In one embodiment, determining the position information of the road surface markings on the target road specifically includes steps 320-1 to 320-2:

[0094] Step 320-1: Obtain the lane information of the target road; the lane information includes the number of lanes and the lane spacing.

[0095] In response to selecting the preset position information as the drawing position of the road surface markings, when the target road contains multiple lanes, it is necessary to determine the number of lanes and the lane spacing.

[0096] Step 320-2: Determine the corresponding number of position information according to the number of lanes, and determine the spacing of the position information according to the lane spacing.

[0097] For example, multiple location information is determined according to the number of lanes and the lane spacing to form a location information group, and multiple road surface markings of the target lane are drawn according to the location information group. In one embodiment, the display graphics are arranged perpendicular to the road surface traveling direction to form multiple road surface markings.

[0098] Step 330: Retrieve symbol data representing the preset display graphics, and generate the display graphics group in the high-precision map according to the location information.

[0099] Draw the display graphics group at the preset location information of the target road.

[0100] For example, when drawing, if a fixed side-by-side spacing is set through the GUI, then only need to select another point in its direction, and it can be automatically generated and placed correctly according to the setting. If the fixed spacing is not set, then each position needs to be clicked one by one to generate a variable spacing automatically.

[0101] For example: The interpolation method is used to realize automatic graphic generation. As Figure 9 shown, a group of road surface markings includes 4 arrow display graphics, and the attributes are left straight straight right respectively. The 4 display graphics are all preset in advance. For example, taking the bottom middle point 91 of the first arrow as the first positioning point, setting the coordinates of this positioning point by capturing point cloud data points in the point cloud image, and then taking the bottom middle point 92 of the rightmost arrow as the second positioning point, and setting the coordinates of this positioning point by capturing point cloud data points in the point cloud image. Then the two positioning points in the middle are generated by equal-spacing interpolation according to the first positioning point and the second positioning point.

[0102] Another example: The extrapolation method is used to realize automatic graphic generation. For example, the 5 display graphics decomposed from the display graphics group correspond to point symbols of different symbol styles. When drawing, if only 2 points are clicked, then the 5 symbols are arranged at equal intervals according to the positioning points, and the point symbol in the middle is flush with the straight line connecting the head and tail points. The program defaults to setting according to the positioning points. The first arrow uses the first point as the positioning point, the second arrow uses the second point as the positioning point, and the latter 3 arrow symbols are set by equal-spacing extrapolation with the spacing between the first point and the second point.

[0103] Further, a set of multiple symbol data clusters associated with the location information is generated in the dataset of the high-precision map, and the set of multiple symbol data clusters contains data representing the display graphics group.

[0104] Further, the attribute information obtained in step 310, that is, in order to retrieve the corresponding display graphics according to the attributes, the attribute information has been determined before retrieving the symbol data representing the preset display graphics, and multiple attribute information associated with the group of road surface markings is also automatically generated in the dataset of the high-precision map. Preferably, it can be a group of attribute information with a + sign set in the middle of the attribute values of each road surface marking.

[0105] Figure 10 This is a structural diagram of a lane line vector graphic generation device according to an embodiment of the present application, which is used to implement the high-precision map road surface marking vector graphic generation method based on point cloud data described in any one of the embodiments of the first aspect, and includes:

[0106] An acquisition module 410, configured to acquire the point cloud data of the target road and the attributes of the road surface markings on the target road, and implement the functions of steps 110, 210, and 310 of the embodiments of the present application.

[0107] A determination module 420, configured to determine the position information of the road surface marking on the target road or determine the preset position information in response to the GUI positioning to capture the point cloud data points, and implement the functions of steps 120, 220, 240, and 320 of the embodiments of the present application.

[0108] A generation module 430, configured to retrieve the symbol data representing the preset display graphic, and generate the preset display graphic in the high-precision map according to the position information, and implement the functions of steps 130, 230, 250, and 330 of the embodiments of the present application.

[0109] Further, the acquisition module further includes a first acquisition unit, configured to acquire the point cloud data of the target road and / or the attributes of the road surface markings on the target road.

[0110] Further, the generation module includes a first generation unit, configured to generate the preset display graphic in the high-precision map according to the position information.

[0111] Further, the first determination unit uses the circumscribed rectangle of the road surface marking determined by the point cloud data as the position information, and / or determines the positioning point of the road surface marking according to the point cloud data points as the position information.

[0112] In one embodiment, the acquisition module further includes a second acquisition unit, configured to acquire the lane information of the target road.

[0113] The determination module further includes a second determination unit, configured to determine the corresponding number of position information according to the number of lanes.

[0114] In one embodiment, the determination module further includes a third determination unit, configured to determine the traveling direction of the target road or a single lane on the target road.

[0115] The generation module further includes a second generation unit, configured to draw the arrow pattern with the pointing direction consistent with the traveling direction of the target road or a single lane on the target road.

[0116] In one embodiment, the determining module further includes a fourth determining unit configured to determine a plurality of display graphics corresponding to the number of lanes as a display graphics group.

[0117] In one embodiment, the determining module further includes a fifth determining unit configured to determine the length of the road surface marking from the stop line.

[0118] In one embodiment, the determining module further includes a sixth determining unit configured to determine the arrangement rule of a plurality of road surface markings.

[0119] In one embodiment, it further includes a regional information database / result map database 440, and the geographic information database / result map database is used to store the ground object data before and after merging in the target area.

[0120] Combined Figure 1 With the commercial server system of the application scenario of the present application, an embodiment of the present application further provides a schema processing system for geographic information data, which is used to implement the method described in any one of the embodiments of the present application, including: a lidar 500, a regional point cloud database 510, a point cloud data processor 520, a GUI operation interface and a job terminal 530, a vehicle-mounted application terminal 540, at least one result map data set 550, a navigation or autonomous driving server 560.

[0121] The regional point cloud database is used to store the point cloud data of the target area.

[0122] The GUI operation interface and the operation terminal 530 are used to read the target road point cloud data, generate a point cloud image, input the set point cloud data points, the data and / or graphics of the preset symbol library / table for displaying road markings; and / or, trigger the acquisition module, the determination module or the generation module. The vehicle-mounted application terminal 540 is used to determine the spatial position where it is located, retrieve the vector graphic data of road markings, including geometric information and attribute information; and is also used to display a map during vehicle navigation, and the map displayed in real time during navigation on the road is obtained by overlaying the vector graphic data and the map based on the position. The point cloud data processor 520 or the operation terminal 530 is used to respond to the instructions of the GUI, acquire the point cloud data of the target road, acquire the attributes of road markings, determine the position information of road markings on the target road, determine the elevation values of each coordinate point (including positioning points) on the lane line through the point cloud data, and is also used to retrieve the symbol data representing the preset display graphics, and generate the preset display graphics in the high-precision map according to the position information; the point cloud data processor is also used to acquire the road point cloud data scanned by the vehicle-mounted lidar, acquire and / or generate the vector graphic data of road markings, and generate a high-precision map including the display graphics of road markings. The result map data set is used to store the high-precision map, and the data therein includes the lane lines of the target road, the relevant data of road markings, and also includes the data set of the overlay of vector graphic data and the map.

[0123] It should be understood that the specific relevant content listed above is only for illustrative purposes and should not impose any limitation on this application.

[0124] The specific method for implementing the functions of the above modules is as described in the method embodiments of the first aspect of this application, and will not be elaborated here.

[0125] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0126] Therefore, this application also proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the method described in any embodiment of this application.

[0127] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows 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 the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0128] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0129] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or in multiple blocks.

[0130] Furthermore, the present application also proposes an electronic device (or computing device), including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method described in any embodiment of the present application is implemented.

[0131] 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.

[0132] 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.

[0133] 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 method for generating vector graphics of road markings, which is used to generate a high-precision map containing road markings based on point cloud data, characterized in that, Including: Obtain the point cloud data of the target road and the attributes of the road surface markings on the target road; The attributes correspond to preset display graphics; On any primitive that makes up the display graphic, there is a positioning point, and the positioning point has a direction; In response to the GUI positioning to capture a point cloud data point, determine the position information of the road surface marking on the target road; the first point is used as the position where the display graphic positioning point is located, the second point is used to determine that the graphic direction is from the first point to the second point and parallel to the lane line, and the third point is used as the width of the display graphic, and the component difference of its coordinate value from the first point in the direction perpendicular to the lane is used as the width value; In the preset symbol library / table, there is a preset display graphic for each type of road surface marking, and the display graphic includes primitive combinations, primitive positions, and display attribute values; Assign the position information to the position attributes of the preset positioning points in the display graphic; Retrieve the symbol data representing the preset display graphic, and generate the preset display graphic in the high-precision map according to the position information; When the road surface markings in the same lane group are drawn in groups, a '+' sign is set in the middle of the attribute values of each road surface marking, and it is decomposed according to the '+' sign during calling; obtain the lane information of the target road, including the number of lanes and the lane spacing; determine a group of position information composed of multiple position information according to the number of lanes and the lane spacing, and draw multiple road surface markings of the target lane according to the group of position information, and the display graphics are arranged perpendicular to the traveling direction to form multiple road surface markings; when generating a group of display graphics, if another point is selected in its direction, it will be automatically generated and placed correctly according to the setting.

2. The method for generating a pavement marking vector graph according to claim 1, wherein Automatically generating and placing correctly according to the setting includes at least one of the following methods: fixing the side-by-side spacing, generating the positioning points by interpolating equidistantly according to the first positioning point and the second positioning point, and setting the positioning points by extrapolating equidistantly with the spacing between the first positioning point and the second positioning point.

3. The method for generating a vector graph of a road surface marking according to claim 1, wherein Determine the position information of the road surface marking on the target road, specifically including the steps: Obtain the lane information of the target road; the lane information includes the number of lanes and the lane spacing; Determine the corresponding number of position information according to the number of lanes, and determine the spacing of the position information according to the lane spacing.

4. The method for generating a pavement marking vector graphic according to claim 1, wherein In response to the road surface marking being a preset arrow pattern, it further includes the steps: Determine the traveling direction of the target road or a single lane on the target road; Draw the arrow pattern so that its direction is consistent with the traveling direction of the target road or a single lane on the target road.

5. The method for generating a pavement marking vector graphic according to claim 1, characterized in that, It further includes the steps: In response to the target road including multiple lanes, determine a group of multiple display graphics corresponding to the number of lanes as a group of display graphics; Generate the group of display graphics according to the position information.

6. The method for generating a pavement marking vector graph according to claim 1, wherein The data representation of the display graphic is a point symbol or a face symbol; the data cluster of the point symbol or the face symbol includes primitive combinations, primitive positions, display attribute values, symbol size attribute values, and symbol position attribute values.

7. The method for generating a pavement marking vector graphic according to claim 1, characterized in that The display graphic constitutes 1 road surface marking, or the display graphic constitutes multiple road surface markings arranged perpendicular to the road surface traveling direction.

8. The method for generating a pavement marking vector graph according to claim 1, wherein In the dataset of the high-precision map, generate a symbol data cluster associated with the position information, and the symbol data cluster includes the data representing the preset display graphic.

9. A device for generating pavement marking vector graphics, characterized in that, A method for generating a vector graphic of a road surface marking in a high-precision map based on point cloud data according to any one of claims 1-8, comprising: An acquisition module for acquiring point cloud data of a target road and attributes of road surface markings on the target road; A determination module for determining the position information of the road surface marking on the target road or determining preset position information; A generation module for generating the preset display graphic in the high-precision map according to the position information.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, the method described in any one of claims 1-8 is implemented.

11. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method described in any one of claims 1-8 is implemented.

Images