A method and device for generating vector graphics of aerial identification

Abstract

The present application discloses a method and device for generating aerial marker vector graphics, which solves the problem of high efficiency and low cost in generating aerial marker vector graphics in the prior art. A method for generating aerial marker vector graphics, for generating a high-precision map containing aerial markers based on point cloud data, comprising: obtaining point cloud data of a target marker; in response to a GUI instruction, determining at least three points in the point cloud data that are not in a straight line to determine the marking surface of the aerial marker; the marking surface is perpendicular to the horizontal plane; and generating a preset display graphic of an external contour frame of the aerial marker in the high-precision map according to the position information of at least three points. The present application can be compatible with some of the problems of its data and perform specific processing on aerial markers, which can improve the efficiency and accuracy of acquisition and 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 aerial identification 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. It supports the access of dynamic road data, assists the autonomous intelligent movement of road vehicles and the refined management of road traffic, and can be used in conjunction with general navigation electronic maps. Electronic maps or data sets. 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 surface markings, 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 predict 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 and clarity of the actual roads, the standardization of signs, etc., 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 the collection of aerial traffic sign surfaces is actually a collection of facades, and traffic sign surfaces have various shapes, including squares, rectangles, triangles, inverted triangles, diamonds, etc. At the same time, point cloud acquisition is incomplete, and it is difficult to generate completely around the periphery. 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 aerial marker vector graphics, which solves the problem that the generation of aerial marker vector graphics in the prior art is affected by incomplete point cloud collection.

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

[0005] Obtain point cloud data of target identification;

[0006] In response to the GUI instruction, the point cloud data points are located and captured, and at least three points that are not on a straight line are determined in the point cloud data to determine the identification surface of the aerial identification; the identification surface is perpendicular to the horizontal plane;

[0007] A preset display graphic of an outer contour frame of an aerial marker is generated in a high-precision map according to the location information of at least three points.

[0008] In one embodiment, determining the circumscribed contour frame of the aerial marker specifically comprises the steps of:

[0009] Acquire the mark data of the target mark; the mark data includes the preset shape and size of the target mark;

[0010] Determine any point of the aerial marker from the point cloud data as a first point;

[0011] A preset display graphic of an outer contour frame of the aerial marker is generated at a first point with a preset shape and size.

[0012] In one embodiment, determining the circumscribed contour frame of the aerial marker specifically comprises the steps of:

[0013] Determine a middle point of the aerial marker from the point cloud data as a first point;

[0014] Determine a second point on the edge of the aerial marker;

[0015] Draw a perpendicular line from the first point to the line connecting the first point and the second point, and the intersection of the perpendicular line and the aerial marker edge point cloud is the third point;

[0016] Describe the outer contour box between the first point, the second point and the third point according to the point cloud data;

[0017] Taking the line connecting the first point and the second point as an axis, the circumscribed contour frame is symmetrically copied to the opposite side of the line.

[0018] In one embodiment, the marking surfaces of the aerial markings located on the same carrier are parallel to each other.

[0019] In one of the embodiments, the aerial sign is arranged above the road, and the sign surface is perpendicular to the running direction of the road.

[0020] Furthermore, the target mark has a thickness parallel to the horizontal plane, with the opposite direction of the road running as the mark surface.

[0021] In one embodiment, the method further comprises the steps of:

[0022] Acquire point cloud data of the target area, and determine the identification surfaces and identification data of multiple aerial identifications in the target area; the identification data includes the type of the aerial identification;

[0023] Copy the outer contour box of the aerial logo of the target logo to the logo faces of multiple aerial logos of the same type.

[0024] In one of the embodiments, in a data set of a high-precision map, a symbol data cluster associated with the location information is generated, and the symbol data cluster includes data representing the preset display graphic.

[0025] In a second aspect, the embodiments of the present application further provide an aerial marker vector graphics generation device, which is used to implement the high-precision map aerial marker vector graphics generation method based on point cloud data as described in any one of the embodiments of the first aspect, and comprises: an acquisition module, which is used to acquire point cloud data of a target marker. A determination module, which is used to determine the identification surface of the aerial marker by determining at least three points that are not on a straight line in the point cloud data in response to a GUI instruction. A generation module, which is used to generate a display graphic of the circumscribed contour box of the aerial marker in the high-precision map according to the position information of at least three points.

[0026] 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.

[0027] 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.

[0028] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0029] This application is able to accommodate some of the issues with its data and perform specific processing on aerial signs, and accurately determine the positions of aerial signs without being affected by ground debris, thereby enabling convenient generation of plan and elevation traffic elements, improving the efficiency and accuracy of acquisition and production, and significantly improving the efficiency of high-precision map data production, thereby ensuring the current demand for high-precision maps in intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] 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:

[0031] Figure 1 A schematic diagram of a commercial server system for the application scenario of this application;

[0032] Figure 2-1 This is a schematic diagram of a traffic sign in the prior art;

[0033] Figure 2-2 This is a schematic diagram of a traffic light in the prior art;

[0034] Figure 2-3 A realistic point cloud data rendering of the existing traffic light installation frame;

[0035] Figure 3 This is a flow chart of a method for generating vector graphics of an aerial marker according to an embodiment of the present application;

[0036] Figure 4-1 This is a schematic diagram of the aerial identification collection effect of the embodiment of the present application;

[0037] Figure 4-2 This is a top view schematic diagram of the aerial identification collection effect of the embodiment of the present application;

[0038] Figure 5 This is a flow chart of another method for generating aerial identification vector graphics according to an embodiment of the present application;

[0039] Figure 6 This is a flow chart of a third method for generating aerial identification vector graphics according to an embodiment of the present application;

[0040] Figure 7 This is a flow chart of a fourth method for generating aerial identification vector graphics according to an embodiment of the present application;

[0041] Figure 8 This is a structural diagram of the aerial identification vector graphics generation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0042] 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.

[0043] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0044] Figure 1 The commercial server system schematic diagram of the application scenario of this application includes: a laser radar 500, a road point cloud database 510, a point cloud data processor 520, a GUI operation interface and operation terminal 530, an on-board application terminal 540, at least one result map data set 550, and a navigation or automatic driving server 560.

[0045] In this application, the vector graphics data of the road signs are generated by the point cloud data processor 520, and a code is set for each type of road sign graphic to represent the type of road sign-like features in the high-precision map data. The vehicle-mounted application terminal 540 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 undulations. 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 550, 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 must identify these data through specific layers.

[0046] 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 sign are all 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.

[0047] The on-board laser radar 500 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 510. The navigation or automatic driving server 560 is used to generate the map displayed during vehicle navigation, and then provide navigation services or automatic 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.

[0048] The aerial signs in this application refer to vertically placed signs in the road system, such as aerial traffic signs, electronic signs, and signs containing geographical, cultural or commercial information. They can be hanging objects or public objects, and can be located on the top of a rack or pole. Figure 2-1 For traffic signs, Figure 2-2 For traffic lights.

[0049] In the present application, in the field of high-precision maps, it is not required to represent the actual graphics of the aerial markers. When production personnel draw maps, they only need to draw the circumscribed contour frame of the aerial markers. The method of drawing the contour frame can be to manually draw a frame in the GUI according to the aerial marker image displayed in the point cloud image, or it can be to automatically identify the aerial marker image in the point cloud data to generate a circumscribed rectangle. If the circumscribed contour frame is drawn manually and depicted one by one according to the point cloud image, the production efficiency is very low, and the operation results are irregular, and even the same markers are of different sizes. The circumscribed contour frame of the aerial marker is obtained with the help of a point cloud recognition tool, but because the marker is unclear due to age, occlusion, etc., the automatic recognition success rate is low, and the recognition results of the same marker are of different sizes.

[0050] It should be noted that the sizes of the aerial signs generally have fixed standards. At the same time, in the actual use of high-precision maps, the iconic facades are more concerned with attributes, and the geometric accuracy is not high. Although the contour lines cannot be accurately generated due to incomplete collection of aerial signs, for the same area or road, the aerial signs are actually divided into different categories, and the shapes of the same category generally have the same standards. Therefore, this application can ignore its true appearance shape, for example, the actual circle is collected into a square that meets the standard.

[0051] The specific representation of the aerial signs of the HD map is displayed as line symbols (all the points of the point cloud of the aerial signs are on a straight line from a bird's eye view) or surface symbols. In the built-in data structure of the HD map, the geometric information is the vector graphics data of the outline box, and the attribute information includes the meaning of the aerial sign. For example, the attribute information of a line symbol is "speed limit 60", and its graphic can be a rectangular surface. Or, a line symbol, the attribute information includes features such as "no U-turn", "no honking" or "multiple bends ahead", that is, its use information is stored in the attribute.

[0052] Figure 2-3 This is a point cloud data effect diagram of the traffic light installation frame on the actual road. When the production staff draws the map, they only need to generate the outer frame 41 of the identification surface, such as Figure 4-1 As shown. The method of generating the bounding box can be to manually draw a frame in the GUI based on the aerial identification plane displayed in the point cloud image, or to automatically identify the plane to which the identification surface in the point cloud data belongs to generate the bounding box. If the bounding rectangle is drawn manually and depicted one by one according to the point cloud image, the production efficiency is very low, and the operation results are irregular, and even the same identification has different sizes. The bounding rectangle of the arrow is obtained with the help of the point cloud recognition tool, but the automatic recognition success rate is low because the identification is not clear due to age and occlusion, and the recognition results of the same identification are of different sizes.

[0053] In addition, the existing production method is to fill in the attributes after generating an external frame. Whether it is manual framing or automatic recognition, attribute information is assigned after generating geometric information, which is a large amount of operation work. However, high-precision maps attach importance to attribute information. If the attributes are filled in manually after the rectangular frame is generated, the consistency between the directly recognized attribute value and the true value of the point cloud cannot be guaranteed in the event of an operation error.

[0054] The method described in this application mainly realizes the rapid collection of aerial marking lines on the road based on the vehicle-mounted point cloud data results, determines the attribute information of the aerial markings, retrieves the preset display graphics, locates the position of the aerial markings, and generates the preset display graphics of the aerial markings. 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 collection work in a human-computer interactive manner.

[0055] Figure 3 This is a flow chart of a method for generating aerial marker vector graphics according to an embodiment of the present application, which is used for high-precision maps of point cloud data and specifically includes steps: 110~130.

[0056] Step 110, obtaining point cloud data of the target identification;

[0057] In one embodiment of the present application, the point cloud data of the target identification is obtained by shooting with a point cloud vehicle 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 a 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.

[0058] Then, feedback from the GUI is received to generate vector graphics data of the aerial marker.

[0059] Step 120, in response to the GUI instruction, locate and capture the point cloud data points, and determine at least three points in the point cloud data that are not on a straight line to determine the identification surface of the aerial identification; the identification surface is perpendicular to the horizontal plane;

[0060] Because it is a facade collection, which belongs to the surface of three-dimensional space, at least three points are needed to determine a standard plane.

[0061] Since the aerial signs can be used as air traffic signs to indicate traffic information, the aerial signs should be set perpendicular to the horizontal plane for easy viewing. Figure 2-3 shown.

[0062] In step 120, when the operator sees the image of the traffic sign surface in the point cloud image, he or she selects three points anywhere within the surface to automatically generate the sign surface.

[0063] It should be noted that the three points of the marking surface are not on a straight line, but when viewed from above, the plane coordinates of the three points form a straight line, which is a top-down map graphic representation of the marking surface. Figure 4-2 As shown, there are five hanging signs 42 above the road, and the graphic of each sign is only a straight line.

[0064] The present application obtains the visual effect of the working environment through point cloud data. Step 120 obtains the spatial position information of the aerial mark through the point cloud data. The spatial position information includes the elevation information (Z) and plane coordinate information (X, Y) of at least three nodes. Generate a ground surface symbol of the aerial mark, the display graphic of the surface symbol is selected in the preset symbol library / table, and the three points are captured from the point cloud data.

[0065] Regarding the positioning and capturing of the point cloud data points, the display graphics of the aerial marker are positioned through the selected point cloud data points to obtain the position information (X, Y, Z).

[0066] It should be noted that the three points here can be manually captured on the point cloud image or automatically captured. The connection generation identification surface here is manually drawn through the GUI, or the surface graphic of the identification surface is automatically generated according to the three points captured by positioning and displayed through the GUI.

[0067] 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.

[0068] The automatic capture here means automatically searching for any one or more points on the aerial marker in the point cloud image within the range set on the GUI interface and obtaining the coordinate information of the selected point. Or automatically selecting a spatial point of several point cloud data points on the aerial marker, the coordinate information of which is obtained by interpolating the coordinate information of the several point cloud data points.

[0069] In one of the embodiments, a positioning point of an aerial marker is determined based on the point cloud data point as the position information, and the positioning point is a feature point of a displayed graphic corresponding to the position of the point cloud data point.

[0070] Step 130: Generate a preset display graphic of a circumscribed contour frame of an aerial marker at the locations of at least three points, or use the preset display graphic to fill a circumscribed contour frame generated by at least three points.

[0071] The aerial identification of the present application is a surface graphic on the high-precision map. To this end, vector graphics data representing the preset display graphic is generated in the high-precision map data.

[0072] In one embodiment, three positioning points of the aerial marker are determined according to the point cloud data points as the position information to position the display graphic. The position information is assigned to the position attributes of the positioning points preset 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.

[0073] It should be noted that when drawing vertical objects through GUI in the prior art, not only the orthographic view needs to be viewed vertically, but also the view needs to be rotated to view the three-dimensional space to see whether it is perpendicular to the ground surface, which requires a lot of operations. Different from the prior art, the solution of this application can set the size and / or symbol style of the aerial logo external contour frame in advance, select points for positioning and orientation at the specified position, and generate the aerial logo graphic or external contour frame according to the preset style and size, which is simple to operate and has a standardized effect.

[0074] As an optimized embodiment of the present application, the attribute information of the aerial markers in the high-precision map is generated in real time along with the geometric information (that is, the vector graphics data of the target marker). Regarding the acquisition of the attributes of the aerial markers, it can be that the markers on the point cloud data image are automatically identified, and the computer processing program automatically generates the attribute information; or the marker content on the point cloud data image is manually identified, the aerial marker content is manually determined, and the attribute information is input or selected through the GUI; any attribute value corresponds to a specific preset display graphic, so the event of generating a display graphic in the high-precision map is a response to the attribute information.

[0075] Regarding the preset display graphics, the method and device of the present application include a preset symbol library / table, wherein there is a preset display graphic for each type of aerial marker, and these preset display graphics have corresponding attribute information. The preset symbol library / table contains vector graphic data and attribute information used to represent the preset display graphics. The preset symbol library / table is triggered according to the attribute information. That is to say, the present application responds to determining the attribute information, retrieves the corresponding preset display graphic from the preset symbol library / table, and then generates a preset display graphic of the circumscribed contour box of the aerial marker at the position of at least the three points in the high-precision map data.

[0076] A symbol data cluster associated with the location information is generated in the data set of the high-precision map, and the symbol data cluster includes data representing the preset display graphic. The data of the preset display graphic is represented as a point symbol or a surface symbol; the data cluster of the point symbol or surface symbol further includes a graphic element combination, a graphic element position and display attribute value, a symbol size attribute value, a symbol position attribute value, etc.

[0077] In one embodiment, the preset display graphic size is a preset fixed value, that is, the size of its circumscribed outline frame is a preset fixed value. A further optimized technical solution is to preset an adjustment ratio value, which can be manually set to expand or reduce.

[0078] For example, the aerial signs may be divided into multiple styles, and the preset display graphic data contained in the symbol data cluster also includes multiple styles, such as circle, rectangle, square, polygon, equilateral triangle, inverted triangle, etc. It may also be four points. The information that can be determined by three points or four points is: two points can determine a sign surface perpendicular to the horizontal plane, three points can determine a sign surface, and three points on the circumscribed contour frame can determine the geometric center space coordinates (XYZ) of its sign surface graphic. Based on the above information, the following embodiments can be implemented:

[0079] In one of the embodiments, a circumscribed contour box generated according to three points of the point cloud data is used as the position information, and the circumscribed contour box is filled with the preset display graphic.

[0080] In one embodiment, if Figure 5 As shown, in step 130, determining the circumscribed contour frame of the aerial marker specifically includes the steps of:

[0081] Step 130-11, obtaining the mark data of the target mark; the mark data includes the preset shape and size of the target mark;

[0082] For example, when the point cloud is not fully acquired, you can choose to obtain the mark data of the target logo from the database. For example, the shape of the aerial logo can be a square, rectangle, triangle, inverted triangle or diamond.

[0083] Step 130-12, determining any point of the identification surface from the point cloud data as the first point;

[0084] Determine any point on the identification surface in the point cloud data of the target identification.

[0085] It should be noted that any point on the identification surface can be determined by manually selecting it through the GUI, or any point on the identification surface can be automatically identified.

[0086] When the point cloud is not fully acquired, it is usually because the periphery of the aerial marker is not fully acquired. Therefore, preferably, the middle point is selected in the point cloud data to locate the preset aerial marker.

[0087] Step 130 - 13 : Generate an outer contour frame of the aerial marker at the first point with a preset shape and size.

[0088] The first point is used as the center of the pattern, and the shape and size of the aerial marker determined by the acquired mark data of the target marker are displayed.

[0089] In another embodiment, Figure 6 As shown, in step 120, three points are determined, specifically including the steps of:

[0090] Step 120-11, determining the middle point of the aerial marker from the point cloud data as the first point;

[0091] Determine the middle point of the aerial marker in the point cloud data of the target marker.

[0092] It should be noted that the middle point of the aerial marker can be determined by manually selecting it through the GUI, or multiple point cloud data points of the aerial marker can be automatically identified to obtain the cluster center.

[0093] Step 120-12, determining a second point on the edge of the aerial mark;

[0094] For example, when the point cloud is not fully acquired, a point is selected from the edge of one side of the relatively complete aerial identification point cloud data to be determined as the second point.

[0095] Step 120-13, draw a perpendicular line from the first point to the second point, and the intersection of the perpendicular line and the aerial marker edge point cloud is the third point;

[0096] A perpendicular line is drawn on the line connecting the first point and the second point. The perpendicular line passes through the first point and is drawn toward a side where the aerial marker point cloud data is relatively complete, and the intersection of the perpendicular line and the edge of the aerial marker is obtained as the third point.

[0097] Determining the circumscribed contour frame of the aerial marker specifically comprises the steps of:

[0098] Step 130-21, drawing an external contour frame between the first point, the second point and the third point according to the point cloud data;

[0099] Since the first point, the second point and the third point are all taken on the relatively complete side of the point cloud acquisition data, the external contour box of the aerial marker can be drawn on the side of these three points.

[0100] Step 130-22: Taking the line connecting the first point and the second point as an axis, symmetrically copy the circumscribed contour frame to the opposite side of the line.

[0101] Since aerial signs are usually regular in shape, the line connecting the first point and the second point is used as the axis, and the circumscribed contour box generated on one side is copied to the opposite side of the axis to form a complete circumscribed contour box.

[0102] In another embodiment, if the standard size and style of the aerial sign graphics are set in advance, by determining the geometric center spatial coordinates (x, y, z), that is, the middle point of the aerial sign, any specified graphic can be generated directly on the sign surface, that is, a vertical facade determined by two points that are not on the same horizontal coordinate, and the geometric center spatial coordinates calculated by three points, any graphic can also be generated on the sign surface determined by three points. If the facade point cloud is not clear, but the graphic has a standard size, the three points do not have to be on the circumscribed contour box, but only need to be evenly distributed, and the geometric center obtained by the three points is also close to the geometric center of the sign image.

[0103] If the graphic has no fixed size but has a standard shape, two points with different horizontal coordinates at the same height on the identification surface are defined as left and right points, and two points at different heights are defined as upper and lower points. The left and right points determine the width of the outline frame, that is, the calculated horizontal distance is used as the width. The upper and lower points can be used to calculate the height difference between the top and bottom of the outline frame, which is the height of the graphic. The rectangular outline frame can be obtained through the height and width. If the left and right points are relatively centered, the standard rectangle can be obtained through the third point, because the other half of the length can be calculated.

[0104] In one embodiment, the aerial signs on the same carrier have their sign faces parallel to each other. The carrier may be, for example, a traffic light mounting frame or a road sign.

[0105] In one of the embodiments, the aerial sign is arranged above the road, and the aerial sign is perpendicular to the running direction of the road.

[0106] Furthermore, the target identification has a thickness parallel to the horizontal plane, and the identification surface is in the opposite direction of the road. For another example, the traffic light mounting frame is erected in the air perpendicular to the direction of the road, and the traffic indication information should be in the opposite direction of the road so that traffic targets (vehicles, pedestrians, etc.) on the road can observe the traffic signs. Unlike road signs, traffic lights are rectangular boxes. When generating the aerial identification of traffic lights, the surface in the opposite direction of the road is selected as the identification surface.

[0107] The innovation of this case lies in the interactive mode and the generation of single symbols or multiple symbols in groups based on prefabricated display graphics. In this way, the generated map contains display graphics of the sign facade, which is consistent with the rules of the sign facade graphics displayed by the point cloud image, and this graphic generation scheme is set in advance, without the need for manual filling of attributes.

[0108] Figure 7 This is a flow chart of another method for generating aerial identification vector graphics according to an embodiment of the present application, which specifically includes steps 210 to 250.

[0109] Step 210: Obtain point cloud data of the target identification;

[0110] Step 220, in response to the GUI instruction, locate and capture the point cloud data points, and determine at least three points in the point cloud data that are not on a straight line to determine the identification surface of the aerial identification; the identification surface is perpendicular to the horizontal plane;

[0111] Step 230: Generate a preset display graphic of a circumscribed contour frame of an aerial marker at the positions of the three points, or use the preset display graphic to fill a circumscribed contour frame generated by at least three points.

[0112] In one embodiment, the method further comprises the steps of:

[0113] Step 240, acquiring point cloud data of the target area, and determining the identification surfaces and identification data of multiple aerial identifications in the target area; the identification data includes the type of the aerial identification;

[0114] The point cloud data of the target area is obtained. The target area may be a road or a collection of several roads, which is not further limited here.

[0115] It should be noted that the target area may include multiple traffic signs.

[0116] Determine the identification surface and sign data of each traffic sign. The type of traffic sign can be determined by the sign data. Determine the traffic signs of the same type.

[0117] Step 250: copy the outer contour frame of the aerial logo of the target logo to the logo surfaces of multiple aerial logos of the same type.

[0118] The copying of the outline of the marked facade includes copying the graphics of the marked facade in the GUI and / or copying the data representing the marked facade in the vector graphics data.

[0119] After determining the circumscribed contour frame of the target sign, determine the traffic sign of the same type as the target sign, and copy and set the circumscribed contour frame of the target sign on the sign surface of the same type of traffic sign according to the position of the sign surface of the same type of traffic sign, so as to quickly generate multiple traffic signs.

[0120] Figure 8 This is a structural diagram of an aerial marker vector graphics generation device according to an embodiment of the present application, which is used to implement the method for generating aerial marker vector graphics of a high-precision map based on point cloud data according to any one of the embodiments of the first aspect, comprising:

[0121] The acquisition module 310 is used to acquire point cloud data of the target identification.

[0122] The determination module 320 is used to determine, in response to a GUI instruction, at least three points in the point cloud data that are not on a straight line to determine a marking surface of the aerial marking.

[0123] The generation module 330 is used to generate a preset display graphic of the circumscribed contour box of the aerial marker at the positions of three points, and generate vector graphics data representing the preset display graphic in the high-precision map data.

[0124] Furthermore, the acquisition module also includes a first acquisition unit, which is used to acquire point cloud data of the target identification.

[0125] Further, the determination module includes a first determination unit for determining a marking surface of the aerial marking in response to determining at least three points in the point cloud data that are not on a straight line. Further, the first determination unit is also used to determine a circumscribed contour line of the representation surface according to the coordinates of the three points.

[0126] Furthermore, the generation module includes a first generation unit, which is used to generate a preset display graphic of a circumscribed contour frame of the aerial marker at the positions of three points.

[0127] In one of the embodiments, the first determination unit is further used to determine the middle point of the marking surface.

[0128] The acquisition module further comprises a second acquisition unit, which is used to acquire the mark data of the target identification.

[0129] In one of the embodiments, the first determining unit is further used to determine a second point of the edge of the aerial marker;

[0130] It is also used to draw a vertical line passing through the first point by using the line connecting the first point and the second point, and determine the third point by the intersection of the vertical line and the edge of the aerial mark.

[0131] The generation module further comprises a second generation unit, which is used to copy the circumscribed contour box defined by the first point, the second point and the third point to the opposite side of the axis, taking the line connecting the first point and the second point as the axis.

[0132] In one of the embodiments, the determination module further includes a second determination unit configured to determine that the marking surfaces of the aerial markings on the same carrier are parallel to each other.

[0133] In one of the embodiments, the determination module further includes a third determination unit for determining the direction in which the aerial marker is facing.

[0134] Furthermore, the third determination unit is also used to determine that the target marked road runs in the opposite direction as a marked surface.

[0135] In one of the embodiments, the acquisition module further comprises a third acquisition unit, which is used to acquire point cloud data of the target area;

[0136] The determination module further comprises a fourth determination unit, which is used to determine the identification surface of the aerial identification of the same type as the target identification.

[0137] The generation module further comprises a third generation unit, which is used to generate a circumscribed contour frame at an aerial mark of the same type as the target mark.

[0138] Furthermore, the determination module also includes a fifth determination unit, which is used to determine the attribute information of the aerial marker; the acquisition module also includes a third acquisition unit, which is used for the application to call up the corresponding preset display graphic in the preset symbol library / table in response to the determined attribute information; and then the generation module, such as the first generation unit, is used to generate a preset display graphic of the circumscribed contour box of the aerial marker at the position of at least the three points in the high-precision map data, or to fill the circumscribed contour box generated by at least three points with the preset display graphic.

[0139] In one embodiment, the generation module further includes a fourth generation unit for generating attribute information of aerial markers in a high-precision map, wherein the attribute information is generated in real time along with geometric information (that is, vector graphics data of the target marker).

[0140] In one of the embodiments, it also includes a regional information database / result map database 340, and the geographic information database / result map database is used to store the ground object data before and after the merger in the target area.

[0141] Combination Figure 1 Schematic diagram of a commercial server system for the application scenario of this application.

[0142] An embodiment of the present application also proposes a graphical 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 laser radar 500, a regional point cloud database 510, a point cloud data processor 520, a GUI operation interface and an operation terminal 530, an on-board application terminal 540, at least one result map data set 550, and a navigation or automatic driving server 560.

[0143] The regional point cloud database is used to store the point cloud data of the target area.

[0144] The GUI operation interface and 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, display the data and / or graphics of the preset symbol library / table of the aerial mark; and / or trigger the acquisition module, determination module or generation module. The vehicle application terminal 540 is used to determine the spatial position, retrieve the vector graphics data of the aerial mark, including geometric information and attribute information; and is also used to display the map during vehicle navigation. The map displayed in real time during road navigation is the vector graphics data and the map superimposed together by location. The point cloud data processor 520 or the operation terminal 530 is used to respond to the instructions of the GUI, obtain the point cloud data of the target road, obtain the attributes of the aerial signs, determine the location information of the aerial signs on the target road, and determine the location of each point on the aerial signs through the point cloud data; it 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 location information; the point cloud data processor 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 aerial signs, and generate a high-precision map containing the display graphics of the aerial signs. The result map data set is used to store the high-precision map, and the data therein includes the data related to the sign elevation of the target road, and also includes the vector graphics data and the data set of the map overlay.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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 aerial marker vector graphics, for generating a high-precision map containing aerial markers based on point cloud data, characterized in that: include: Obtain point cloud data of target identification; Positioning and capturing point cloud data points in response to GUI instructions, determining at least three points in the point cloud data that are not in a straight line to determine a marking surface of the aerial marking, and the marking surface is perpendicular to the horizontal plane; Determine attribute information of the aerial marker, the attribute information including the meaning of the aerial marker; in response to determining the attribute information, retrieve a corresponding preset display graphic from a preset symbol library / table; According to the position information of the at least three points, the position attributes of the preset positioning points in the display graphic are assigned, and the preset display graphic of the circumscribed contour box of the aerial marker is generated in the high-precision map; the preset display graphic is generated according to the preset size, or the preset display graphic is stretched or shrunk through the GUI.

2. The method for generating aerial marker vector graphics according to claim 1, characterized in that: Determining the circumscribed contour frame of the aerial marker specifically comprises the steps of: Acquire the mark data of the target mark; the mark data includes the preset shape and size of the target mark; Determine any point of the identification surface from the point cloud data as a first point; A preset display graphic of an outer contour frame of the aerial marker is generated at a first point with a preset shape and size.

3. The method for generating aerial marker vector graphics according to claim 1, characterized in that: Determining the circumscribed contour frame of the aerial marker specifically comprises the steps of: Determine a middle point of the aerial marker from the point cloud data as a first point; Determine a second point on the edge of the aerial marker; Draw a perpendicular line from the first point to the line connecting the first point and the second point, and the intersection of the perpendicular line and the aerial marker edge point cloud is the third point; Describe the outer contour box between the first point, the second point and the third point according to the point cloud data; Taking the line connecting the first point and the second point as an axis, the circumscribed contour frame is symmetrically copied to the opposite side of the line.

4. The method for generating aerial marker vector graphics according to claim 1, characterized in that: The aerial signs located on the same carrier have their sign surfaces parallel to each other.

5. The method for generating aerial marker vector graphics according to claim 1, characterized in that: The aerial sign is arranged above the road, and the sign surface is perpendicular to the running direction of the road.

6. The method for generating aerial marker vector graphics according to claim 1, characterized in that: Also includes the steps: Acquire point cloud data of the target area, and determine the identification surfaces and identification data of multiple aerial identifications in the target area; the identification data includes the type of the aerial identification; Copy the outer contour box of the aerial logo of the target logo to the logo faces of multiple aerial logos of the same type.

7. The method for generating aerial marker vector graphics according to claim 5, characterized in that: The target mark has a thickness parallel to the horizontal plane, and the marking surface is the opposite direction of the road running.

8. The method for generating aerial marker vector graphics according to claim 1, characterized in that: In the data set of the high-precision map, a symbol data cluster associated with the location information is generated, and the symbol data cluster includes data representing the preset display graphic.

9. An aerial identification vector graphics generating device, characterized in that: The method for generating an aerial marker vector graphic according to any one of claims 1 to 8 comprises: An acquisition module is used to acquire point cloud data of a target identifier; and is also used to retrieve a corresponding preset display graphic from a preset symbol library / table in response to determining the attribute information; A determination module, for locating and capturing point cloud data points in response to GUI instructions, determining at least three points in the point cloud data that are not in a straight line to determine the identification surface of the aerial marker, and the identification surface is perpendicular to the horizontal plane; and for determining attribute information of the aerial marker, the attribute information including the meaning of the aerial marker; A generation module, used to assign a value to a location attribute of a preset positioning point in a display graphic according to location information of at least three points, and generate a preset display graphic of an external contour frame of an aerial marker in a high-precision map; The preset display graphic is generated according to a preset size, or the preset display graphic is stretched or shrunk through a GUI.

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 according to any one of claims 1 to 8 is implemented.

11. 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 8 is implemented.

Images