High-precision map road element live-action model construction method and device

Abstract

The invention discloses a high-precision map road element live-action model construction method and device, and solves the problem of low automation degree of road element live-action model construction in the prior art. The road element live-action model construction method comprises the following steps: acquiring map data of a target road, and determining ground feature element position information and type information; determining real scene model symbols corresponding to the ground feature elements of different types of information; the data cluster of the real scene model symbols comprises name codes, real scene pictures and graphic attribute information; and generating a high-precision map, wherein the high-precision map is a set of real scene model symbols associated according to the position information. The method for rapidly constructing the road total element model is researched on the basis of the characteristics of various elements of the road, rapid batch generation of most of the elements on the road is achieved, and the production efficiency and quality are greatly improved.

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 constructing a real-scene model of road elements in a high-precision map. Background Art

[0002] With the continuous advancement of smart city construction, the demand and application of urban three-dimensional models have also put forward higher development requirements. The traditional basic surveying and mapping, which stays in the two-dimensional plane of geographic data, is far from meeting the requirements of urban smart construction. For urban managers, the realization of visual management of urban infrastructure, visual positioning of urban components, visual monitoring of urban geographic information, and smart visual decision-making of urban emergencies can better meet the high-level applications of management and decision-making. In view of the current concept and demand of refined urban management, intelligent holographic surveying and mapping under the new basic surveying and mapping system has formed the results of full-factor real-scene models. As an important part of the full-factor real-scene model, the road full-factor real-scene model can be applied to intelligent transportation, planning approval and urban refined management. In particular, with the development of intelligent driving technology, the demand for navigation electronic maps continues to increase, and a high-precision map for automatic driving or semi-automatic driving has been derived, which is generally called a high-precision map. For example, the high-precision navigation electronic map of the road contains the geometry, attributes and relationships of the road network, lane network, road markings and road facilities, supports the access of road dynamic data, assists the autonomous intelligent movement of road vehicles and the refined management of road traffic, and is a sub-map or data set that can be used in coordination with the general navigation electronic map. In order to produce high-precision maps, the road full-element real-life model needs to contain many elements, including road surface elements such as motor vehicle lanes, non-motor vehicle lanes, sidewalks, blind paths, and traffic markings, as well as components such as poles, boxes, signs, and probes on both sides of the road. At present, its construction still relies on a large amount of manual labor, with a low degree of automation, which is not conducive to large-scale production, updating, and application of data. Summary of the invention

[0003] This application proposes a method and device for constructing a real-scene model of high-precision map road elements to solve the problem of low efficiency in the high-precision map production process.

[0004] In a first aspect, an embodiment of the present application provides a method for constructing a real scene model of a high-precision map road element, comprising:

[0005] Obtain map data of the target road and determine the location and type information of the ground features;

[0006] Determine the real scene model symbols corresponding to the ground feature elements of different types of information; the data cluster of the real scene model symbol includes name code, real scene picture and graphic attribute information;

[0007] Generate a high-precision map, which is a collection of real-scene model symbols associated according to location information.

[0008] In one embodiment, the ground feature element includes a vector element, which specifically includes the steps of:

[0009] Determine the coordinate information of the vector element positioning point according to the map data;

[0010] Determine the type of the vector element line and a first attribute parameter corresponding to the type; the first attribute includes a size in the horizontal direction;

[0011] Determine the size parameter of the vector element in the direction perpendicular to the horizontal plane as the second attribute parameter;

[0012] The first attribute parameter and the second attribute parameter are assigned to a real scene model symbol according to the positioning point coordinate information to generate a real scene map of the land feature.

[0013] In one embodiment, the method further comprises the steps of:

[0014] Obtain the real scene model symbol of the ground feature on the target road;

[0015] Determine the symbol parameters of the real scene model according to the vector graphics attribute information in the map data of the target road; the symbol parameters of the real scene model include position and size;

[0016] The model is set on the target road real scene image according to the position and the size.

[0017] In one embodiment, the steps include:

[0018] Generate a map of the target road based on the radar image, including vector graphics of the ground features in the target road;

[0019] Identify and determine the location information and shape information of ground features in images collected by radar;

[0020] The real scene model symbol of the land feature element is retrieved, the display position and range of the real scene model symbol are determined according to the position information and shape information, and a real scene map of the land feature element is generated.

[0021] In one embodiment, the steps include:

[0022] Determine the current location information based on the navigation information,

[0023] Determine the ground features within the current position visual volume in the map data of the target road according to the current position information, and display the real scene model symbols of these ground features;

[0024] When the real scene model symbol is displayed, the display position and size of the corresponding real scene model symbol are determined according to the display position and size of the ground feature vector graphic within the range of the viewing volume.

[0025] In one embodiment, the steps include:

[0026] The real scene model symbols are continuously laid out on the vector feature lines according to the preset positioning point spacing parameters.

[0027] In one embodiment, a pattern of surface-like vector elements on a target road is determined;

[0028] The real scene model symbol of the pattern obtained by name coding is set on the planar vector element.

[0029] In the second aspect, the embodiment of the present application further provides a device for constructing a real-scene model of a high-precision map road element, which is used to implement the method for constructing a real-scene model of a high-precision map road element described in any one of the embodiments of the first aspect, and comprises: an acquisition module, which is used to obtain map data of a target road. A determination module, which is used to determine the location information and type information of a land feature element; and is also used to determine the real-scene model symbols corresponding to land features of different types of information. A generation module, which is used to generate a high-precision map.

[0030] 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.

[0031] 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.

[0032] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0033] Based on the characteristics of various road elements, the present invention studies a method for quickly constructing a high-precision map road full-element model. Compared with traditional manual modeling, it can realize the rapid batch generation of most elements on the road, and has greatly improved production efficiency and performance. In the model construction process, program modeling replaces manual modeling, which reduces a lot of manual intervention, effectively guarantees the quality of the results of the road full-element real-life model, and achieves the purpose of improving quality and efficiency. In the high-precision map navigation application, the real-life navigation map generated by this application is a real-life model display associated with the location and updated in real time. It is a three-dimensional stereo image derived from the map, and can display road information in real time.

[0034] The solution of the present application can not only realize the construction of three-dimensional scenes of all road elements, but also realize the expression of all elements underground, above ground and in the air. On the basis of geographic information, for example, as long as the elevation information and three-dimensional information are determined, underground space, landmarks, rooftops, elevated roads, aerial tracks, etc. can all realize the automatic construction of spatially integrated three-dimensional scene data based on vector data. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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:

[0036] Figure 1 A schematic diagram of a commercial server system for the application scenario of this application;

[0037] Figure 2 A flowchart for constructing a real-scene model of road elements according to an embodiment of the present application;

[0038] Figure 3 This is a flow chart of a method for constructing a real-scene model of road elements according to an embodiment of the present application;

[0039] Figure 4 This is a flow chart of another method for constructing a real-scene model of road elements in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of setting the second attribute parameter of a vector element in the GUI of an embodiment of the present application;

[0041] Figure 6 Draw a real-life map of the target road for the vector elements of the embodiment of the present application;

[0042] Figure 7 This is a flow chart of a method for constructing a real-scene model of road elements according to a third embodiment of the present application;

[0043] Figure 8 This is a flow chart of a method for constructing a real-scene model of road elements according to a fourth embodiment of the present application;

[0044] Fig. 9 This is a flow chart of a method for constructing a real-scene model of a fifth road element according to an embodiment of the present application;

[0045] Fig.10 A schematic diagram of setting vector element parameters for the GUI of an embodiment of the present application;

[0046] Fig.11 Draw a real-life map of the target road for the pavement construction elements and component construction elements of the embodiment of the present application;

[0047] Fig.12 This is a flow chart of the method for applying a real scene model symbol for navigation in an embodiment of the present application;

[0048] Fig.13 This is a structural diagram of a device for constructing a real-scene model of road elements according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] 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.

[0050] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0051] Figure 1 The commercial server system schematic diagram of the application scenario of this application includes: a collection terminal 400, a geographic information system database 410, a geographic information data processor 420, an operation terminal 430, a vehicle application terminal 440, at least one vector map result map data set or a real scene map result map data set 450, a real scene model symbol library 460, and a real scene navigation server 470.

[0052] In the present application, the feature map data of the road is generated by the geographic information system database 410 and / or the acquisition terminal 400. The vector graphics data of the feature symbol is generated by the geographic information data processor 420, and a code is set for each type of feature symbol to represent the type of road identification feature in the high-precision map data. The feature data of the high-precision map includes geometric information and attribute information. The vehicle-mounted application terminal 440 retrieves the code of the nearby feature symbol at the spatial position to obtain its geometric information and some attribute information assigned to it, 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 location of the feature. The attribute information includes some spatial topological relationships and association relationships, which represent the adjacent relationship of the drawn line plus other attribute information. In the real scene result map data set 450, these vector graphics data are stored by layers, each type of data belongs to a layer, and each layer has some attribute information. The usage information of the feature element is stored in the attribute.

[0053] Geometric information and attribute information are static data used to describe the terrain features. Scene data is derived from static data, and real-life model symbols are set for the terrain feature data according to location attributes. Features such as vector elements and component elements, such as the height of curbs and the location of road signs, are entered into the attributes. Real-life navigation makes predictions based on the attribute values ​​of location information. For example, when arriving at a certain location, the surrounding terrain features are displayed using real-life model symbols in the high-precision map.

[0054] The operation terminal 430 is used to generate or configure a real scene model symbol data cluster, and edit vector map elements, and associate the vector map elements with the operation interface of the real scene model symbol.

[0055] The real-life navigation server 470 is used to generate a real-life map displayed during vehicle navigation, and then provide navigation services or autonomous driving services on the displayed map. The map displayed in real time during navigation on the road is a map that associates vector graphics data and real-life model symbols together by location and overlays them on the map. 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.

[0056] The collection terminal 400 scans the road to generate radar detection data, and the geographic information data processor 420 generates geographic information data results, which are stored in the geographic information system database 410.

[0057] The real scene in the prior art is a picture collected at a fixed point, while the real scene in the present application is a real scene model display of the combination of local object elements in the visual scene body that is updated in real time and associated with the position. It is a three-dimensional stereo image derived from a vector map.

[0058] This application studies a method for quickly constructing a full-factor model of a high-precision road based on the characteristics of various road elements, which improves the efficiency and quality of constructing a full-factor real-scene model of the road and provides technical support for the production and updating of large-scale full-factor real-scene models of roads.

[0059] Figure 2 This is a flow chart of a method for constructing a real-scene model of road elements in a high-precision map according to an embodiment of the present application, including steps 110 to 130.

[0060] Through steps 110 to 130, embedding the real scene model symbol into the ground feature of the geographic information system is achieved.

[0061] Step 110: Obtain map data of the target road and determine the location information and type information of the ground feature.

[0062] In one embodiment of the present application, a radar image of a target road is captured by a collection terminal, and vector map data of ground feature elements is generated and stored in a geographic information system database 410, or further processed by a geographic information data processor 420. When an operator retrieves the radar image or vector map data through an operation terminal 430, the position information and type information of the ground feature elements in the target road are obtained, and an image of the vector map elements is generated on the operation terminal 430 or a GUI connected thereto according to the position information and type information.

[0063] The position information refers to the position of the land feature on the target road.

[0064] The type information refers to the classification of the ground feature on the road, such as probe, pole, sign, pavilion, green vegetation, and box. Different types of ground features have different scene model symbols.

[0065] Step 120: Determine the real scene model symbols corresponding to the ground feature elements of different types of information; the data cluster of the real scene model symbol includes name code, real scene picture and graphic attribute information.

[0066] The real-scene model symbol is a data cluster containing name code, real-scene picture and graphic attribute information. Through the real-scene model symbol data cluster, a simulated real-scene graphic or image of the terrain element displayed in the high-precision map can be obtained.

[0067] In one embodiment, the real scene image further includes color and texture. The graphic attribute information further includes size and positioning point. Through the size and positioning point, the position and range of the real scene model symbol in the high-precision map can be determined.

[0068] Furthermore, the graphic attribute information also includes direction, and the placement orientation of the real scene model symbol in the high-precision map can be determined through the direction attribute.

[0069] It should be noted that the symbols follow the concept of map symbols, but are different from the abstract map symbols of ordinary maps. The real-scene model symbols in this application can be displayed as graphics or images that are similar to the real scene in a high-precision map.

[0070] Step 130: Generate a high-precision map, where the high-precision map is a collection of real-scene model symbols associated according to location information.

[0071] A high-precision map is generated based on the location information of the vector map features and the real-scene model symbols; the high-precision map is a collection of real-scene model symbols associated according to the location information.

[0072] By determining the location information of each geographical feature in the vector map, the real-life model symbol of the geographical feature is adapted to the geometric information of the geographical feature, including position, shape and size, according to the location information, and arranged in three-dimensional space to form a high-precision map.

[0073] In one embodiment, the location information is determined by identifying in images collected by radar; the identification method includes any one of the following:

[0074] selecting in the image data in response to a GUI instruction;

[0075] Automatically identify location information in image data.

[0076] It should be noted that the real scene model symbol is embedded in the feature symbol in the road-related vector map. For example, an attribute value is added to the feature symbol data of the vector map and embedded through coding. The attribute information in the feature symbol includes the identifier of the real scene model symbol, such as the real scene model symbol name code.

[0077] Furthermore, when the real scene model symbol is displayed, the relevant attribute values ​​of the ground feature symbol are adapted.

[0078] For example, when a real-life model symbol is displayed, the attributes of the corresponding ground feature symbol include position and size. Therefore, in a high-precision map, the display of the real-life model symbol needs to take into account its location and the size of the road surface it occupies, and reconstruct the attribute values ​​of the real-life model symbol.

[0079] It should also be noted that a reality model symbol can be nested with several small reality model symbols.

[0080] The present invention forms a solution for quickly constructing a road full-element real-scene model, which divides the construction of the road full-element real-scene model into two parts: road surface construction and component construction. Figure 3 As shown in the figure, the left side is the reconstruction of the road model, i.e. the road construction. The right side is the reconstruction of the component model, i.e. the component assembly.

[0081] It should be noted that the real scene model symbols mainly include two types: pavement construction elements and component construction elements.

[0082] The road construction elements mainly include motor vehicle lanes, non-motor vehicle lanes, flower beds, blind paths and markings, and the component construction elements mainly include urban facilities such as street lights, probes, traffic lights, boxes, signs and roadside trees. The construction of the road surface is mainly based on the characteristic laws of various road surface elements in geometric structure and texture mapping, realizing the automatic construction of motor vehicle lanes, non-motor vehicle lanes, sidewalks, blind paths, flower beds, safety islands, railings and markings.

[0083] The component construction elements are mainly based on the real-life model symbol template library (urban components obtained based on point cloud and image data collected by the vehicle-mounted laser scanning system. Its attributes include size and texture information, realizing a one-to-one restoration of the component model and the actual) and the type, position, and angle information provided in the full-element terrain data to realize the automatic reconstruction of the components. Component elements are usually represented as a point or a surface feature on a vector map, such as a tree, a pavilion, a road sign, etc.

[0084] Figure 4 This is another flow chart of a method for constructing a real-scene model of road elements according to an embodiment of the present application. A high-precision map is constructed by combining vector elements and real-scene model symbols. In one embodiment, step 130 specifically includes steps 130-11 to 130-14.

[0085] Step 130-11: Determine the coordinate information of the vector element positioning point according to the map data.

[0086] The vector element refers to the vector graphics in surveying and mapping. The map graphics in surveying and mapping are divided into vector graphics and raster graphics. The raster graphics, for example, pictures or photos, converting raster graphics into vector graphics is equivalent to converting pictures into several vector graphics. The vector graphics can be a point, a line, or a range surface.

[0087] The vector elements can be points, lines, surfaces, and volumes. They are mainly linear features in vector maps. As a line, a vector element has only length. If you give it width and height, it will form a cube. If you give it radius, it will form a cylinder. Vector elements are mainly used to describe linear features on vector maps.

[0088] The ground model, i.e., vector features, has variable length but is regular in one dimension.

[0089] For example, the length of the lane dashed line varies from road to road, but the line width is fixed, and the style of the same type of line is fixed.

[0090] For example, fast import and optimization of vector elements, including:

[0091] Based on the map data, the coordinate information of the positioning points of the vector elements involved in the model construction is exported;

[0092] Reading of reconstruction information of vector elements involved in model building;

[0093] Reconstruction of vector elements involved in model building;

[0094] Line feature processing and node optimization. Here, the starting point, turning point, and end point set on the line graph are collectively referred to as nodes.

[0095] In one embodiment, in step 130-11, after drawing the vector element line map on the target road, the following steps are further included:

[0096] The nodes are evenly distributed on the vector feature lines according to the preset spacing parameters.

[0097] The closed linear features are automatically processed and the nodes of the line features are optimized according to the set spacing parameters so that the nodes are evenly distributed.

[0098] The closure means that the beginning and end of the linear element are captured at the same coordinate point.

[0099] Step 130-12: Determine the type of the vector element line and the first attribute parameter corresponding to the type; the first attribute includes the size in the horizontal direction.

[0100] The vector elements include points or lines such as lane dividing solid lines, lane dividing dashed lines, speed reduction markings, tidal lane markings, stop lines, speed bumps, and road elevation points.

[0101] The reconstruction of vector elements involved in model construction mainly includes lane dividing solid lines, lane dividing dashed lines, speed reduction markings, tidal lane markings, stop lines, speed bumps and road elevation points.

[0102] It also includes sidewalks, green spaces, blind paths, railings and safety islands.

[0103] The first attribute includes a horizontal size, such as length and width.

[0104] It should be noted that the horizontal dimension refers to the dimension of the vector element extending in the horizontal direction, without considering the extension in the vertical direction. For example, for a road with a slope, the horizontal dimension only considers the width of the road and the length of the road from a bird's-eye view, without considering the additional length of the road caused by the slope.

[0105] Build vector feature renaming.

[0106] For example, rename vector features based on set type, size, and color parameters.

[0107] The renaming refers to assigning semantic information to the vector element. The semantic information, namely the first attribute parameter, at least includes the size of the vector element in the horizontal direction.

[0108] The first attribute value may also include selecting the type, color and material of the vector element, completing the renaming of the vector element, and checking the renaming of the vector element.

[0109] The vector element renaming check checks whether the vector element meets the requirements, mainly checking the correctness of the type, marking line size and element color setting in its naming, and at the same time checking the correctness of the vector closure and the number of sub-spline lines based on its type naming.

[0110] For example, the naming of arrow vector features mainly checks the correctness of the type and feature color settings in its naming, and also checks the closure of the arrow vector.

[0111] It should be noted that the arrow is a closed figure formed by linear elements, so the initial point and the end point of the positioning points forming the arrow are at the same coordinate.

[0112] For another example, the naming of the sidewalk vector elements mainly checks whether the naming of the sidewalk edge line, sidewalk curb and sidewalk boundary is correct, and at the same time checks the correctness of the number and direction of sub-spline lines contained in the sidewalk vector.

[0113] For example, the naming of the blind path and railing vectors mainly checks whether the blind path type setting is correct, and at the same time checks whether the number of sub-spline lines contained in the blind path and railing vectors is one.

[0114] For example, the naming of greening and speed bump vectors mainly checks whether their type settings are correct and whether the vectors are closed; the naming of safety island vectors mainly checks whether the type settings and the corresponding number of spline lines are correct.

[0115] Step 130 - 13 : Determine the size parameter of the vector element in the direction perpendicular to the horizontal plane as the second attribute parameter.

[0116] Set the parameters of the pavement construction elements. For example, for sidewalks, set the curb height and sidewalk curb parameters. For greening, set the curb height and curb width parameters. For blind paths, set the blind path width and texture length parameters. For railings, set the railing height and texture length parameters. For safety islands, set the island stone height and island stone height parameters.

[0117] The GUI program input interface for setting parameters of pavement construction elements, such as sidewalks, greening, blind paths, railings and safety islands, is as follows: Figure 5 shown.

[0118] Step 130-14: assigning the first attribute parameter and the second attribute parameter to a real scene model symbol according to the positioning point coordinate information to generate a real scene map of the land feature.

[0119] Draw a line map of vector elements on the target road based on the coordinate information of the positioning points; the vector elements can be points, lines, surfaces, or volumes.

[0120] The first attribute parameter and the second attribute parameter are assigned to a vector element line drawing to draw a real scene of the target road.

[0121] Pavement element model reconstruction, based on the functional functions of various pavement models, realizes the rapid construction of pavement element models.

[0122] For example, lane lines, dotted lines or mesh lines can be displayed directly by giving them a size value and a color.

[0123] For another example, a road is a whole background with some colored lines on it. It has width but no thickness, which means that a road can be drawn.

[0124] For example, a curb is a two-dimensional vector that is collected as a line close to the ground. By giving it height and width, it can become a volume element.

[0125] The vectors are automatically constructed based on the three-dimensional positioning points and coding information of points, lines and surfaces, and are automatically classified and renamed, providing a vector basis for the rapid construction of models of related elements.

[0126] Finally, the construction results of the target road scene map drawn by vector elements are as follows Figure 6 shown.

[0127] In one of the embodiments, the first attribute parameter is width, the second attribute parameter is height, and a cube is formed by drawing a vector element line drawing.

[0128] In one of the embodiments, the first attribute parameter is width, the second attribute parameter is radius, and the stroke cylinder is drawn by a vector element line drawing.

[0129] Based on the above steps, parameter reconstruction of road pavement construction elements is achieved.

[0130] Figure 7 This is a flow chart of the third method for constructing a real-scene model of road elements in an embodiment of the present application, which is used to construct a high-precision map of component elements. In one of the embodiments, step 130 specifically includes steps 130-21 to 130-23.

[0131] Step 130-21: Obtain the real scene model symbol of the terrain feature on the target road.

[0132] Step 130-22: Determine the symbol parameters of the real scene model according to the vector graphics attribute information in the map data of the target road; the symbol parameters of the real scene model include position and size.

[0133] The component feature model is reconstructed based on the reconstruction attribute information of the component features.

[0134] For example, street trees can be adjusted based on the set rotation angle and scale range.

[0135] It should be noted that the 3D model templates in the component template library are all set to the same size but different colors.

[0136] For example, there are different templates, and the size of the model is not differentiated. The size of the model can be adjusted according to other information, such as image attribute information.

[0137] For example, the component element is a tree. The tree type and age are obtained according to the map information. The type can be distinguished according to the model category, but trees of different ages may belong to the same type, so they are the same model in the component template library, but the difference in tree age will make the height of the tree very different. Therefore, the height of trees of different ages can be preset, and the setting of tree models of different ages can be realized by scaling.

[0138] Step 130-23: setting the model on the target road real scene map according to the position and the size.

[0139] Finally, the construction results of the target road scene map are completed by drawing the road surface elements and component elements. Fig.10 shown.

[0140] This application can realize the rapid extraction and automatic reconstruction of modeling elements in terrain data; rapid processing and optimization of linear elements to evenly distribute the nodes of linear elements; rapid renaming of model construction vector elements to provide semantic information for model construction; rapid construction of models of road surface elements such as motor vehicle lanes, non-motor vehicle lanes, sidewalks, blind paths, safety islands, flower beds, traffic markings, guide arrows and railings; rapid construction of models of component elements such as street lamps, probes, traffic lights, boxes, signs and roadside trees.

[0141] Based on the above steps, parameter reconstruction of component construction elements of the road system is achieved.

[0142] Figure 8 This is a flow chart of a method for constructing a real-scene model of a road element according to a third embodiment of the present application. A map of a target road is determined based on radar point cloud data. In one embodiment, step 130 specifically includes steps 130-31 to 130-33.

[0143] Step 130-31, generating a map of the target road according to the radar image, including vector graphics of the ground features in the target road.

[0144] The radar image of the target road is collected by collecting vehicles and other collecting equipment, and a vector map of the target road is generated based on the radar image. The vector map contains vector graphics of the terrain elements in the target road. The vector map is usually a plane map, which uses lines to reflect the outline of the road and uses abstract symbols to reflect other terrain elements in the road.

[0145] Step 130-32: Identify and determine the location information and shape information of the ground feature in the image collected by the radar.

[0146] The location information and shape information of the features on the target road are collected by image acquisition vehicles / machines, laser radar vehicles / machines and other acquisition equipment. For example, vehicles or drones with point cloud data acquisition functions are used to obtain the actual shape and location of the features on the target road. Further position information and shape information are formed.

[0147] Step 130-33, retrieve the real-scene model symbol of the land feature element, determine the display position and range of the real-scene model symbol according to the position information and shape information, and generate a real-scene map of the land feature element.

[0148] In one embodiment, further, the real scene model symbol is obtained, such as Fig. 9 As shown, the specific steps include:

[0149] Step 130-331, constructing a real scene model symbol template library; the real scene model symbol template library includes the real scene pictures and their corresponding name codes.

[0150] The real-scene model symbol template library can determine the real-scene model of the ground feature on the map by taking photos or drawing.

[0151] For example, trees, electric poles, road signs, etc. can be photographed to obtain real-life pictures, and three-dimensional models can be constructed based on the real-life pictures, which can be used as real-life models of land features.

[0152] Furthermore, the real scene model symbol template library also includes texture material templates, for example, a wall, a road surface or a building, a photo of its appearance is taken, and a picture of a fixed length and width is captured from the photo and used as a texture.

[0153] In the real-scene model symbol template library, each real-scene model symbol template also has an initial name code and initial graphic attribute information, and the graphic attribute information also includes an initial size and an initial positioning point. Through the initial size and initial positioning point, when associated with a specific vector graphic element, the initial size and initial positioning point of the real-scene model symbol template can be reconstructed according to the graphic attribute value of the vector graphic element to determine the position and range of the real-scene model symbol in the high-precision map.

[0154] Furthermore, the graphic attribute information also includes an initial direction attribute. By reconstructing the direction attribute, the posture of the real scene model symbol in the high-precision map can be determined.

[0155] Take the setting of pavement construction element parameters as an example. For example, the sidewalk sets the curb height and sidewalk curb parameters. Greening sets the curb height and curb width parameters. Blind path sets the blind path width and texture length parameters. Railing sets the railing height and texture length parameters. Safety island sets the island stone height and island stone height parameters.

[0156] The GUI program input interface for setting parameters of pavement construction elements, such as sidewalks, greening, blind paths, railings and safety islands, is as follows: Figure 5 shown.

[0157] Step 130-332: determine the real scene model of the vector elements on the target road.

[0158] For example, a vector element on a target road is determined to be a tree according to map information. The type information of the tree is obtained through manual identification or automatic recognition. The code corresponding to the real-scene model symbol of the tree is determined according to the real-scene model symbol corresponding to the domain type information.

[0159] Step 130-333, obtain the real scene model symbol through the name code, and set it on the vector element.

[0160] For example, when it is determined that the current tree is a pine tree, the name code corresponding to the pine tree can be input through the GUI command, and the real-scene model symbol of the pine tree is retrieved from the real-scene model symbol template library, and the real-scene model symbol of the pine tree is set on the vector map.

[0161] For example, when it is determined that the material of the vector feature on the target road is a wall, the determined wall texture photo can be used.

[0162] Regarding constructing the renaming of vector elements, the GUI program input interface for renaming vector elements according to the set type, size and color parameters is used for specific settings, such as Fig.10 shown.

[0163] Furthermore, the first attribute parameter also includes color and material. In response to the first attribute parameter including material parameters in the target road real scene image being drawn, texture data of the corresponding material is retrieved.

[0164] In one embodiment, in step 130, to implement linear feature processing, the reality model symbol is arranged on the linear vector feature, including the steps of:

[0165] The real scene model symbols are continuously laid out on the vector feature lines according to the preset positioning point spacing parameters.

[0166] When setting terrain features such as fences and road lines that are arranged along vector features on the lines of linear vector features such as roads and green belts in a vector map, the real-life model symbols of terrain features such as fences and road lines are evenly and continuously arranged according to the preset point spacing parameters, and are displayed as fences and road lines arranged along the vector features.

[0167] In one embodiment, in step 130, to implement the planar element processing, the reality model symbol is arranged on the planar vector element, which includes the steps of:

[0168] Determine the pattern of surface vector elements on the target road;

[0169] Determine the surface vector elements in the vector map, such as lake surface, lawn, etc. When setting the terrain elements on the surface vector elements, first determine the overall scope of the surface vector elements.

[0170] The real scene model symbol of the pattern obtained by name coding is set on the surface vector element. Fig.11 As shown, the code corresponding to the ground feature within the target planar vector feature in the vector map is identified, the real scene model corresponding to the code is obtained from the real scene model symbol library, and the real scene model is set on the planar vector feature.

[0171] Fig.12 In the embodiment of the present application, the real-scene model display of the terrain features is applied to the road navigation flow chart. Based on the high-precision map formed in steps 110 to 130, a road navigation map engine is generated to perform high-precision map "real-scene" navigation, including steps 210 to 230.

[0172] Step 210: determining current location information according to navigation information;

[0173] The vehicle-mounted application terminal is connected to the vehicle-mounted navigation service, and the current location information of the target vehicle is determined through satellite positioning and other means. The location information here refers to the real-time location of the vehicle while it is driving.

[0174] Step 220: Determine the current position of the target vehicle using navigation on the vector map according to the navigation information.

[0175] The location information of the target vehicle is compared with the vector map to determine the display location of the target vehicle on the vector map, trigger the attribute information of the vector graphic element at the location, and retrieve the associated real scene model symbol.

[0176] Step 230: When the real scene model symbol is displayed, the display position and size of the corresponding real scene model symbol are determined according to the display position and size of the ground feature vector graphic within the range of the visual volume.

[0177] The ground features within the current position visual volume in the map data of the target road are determined according to the current position information of the vehicle, and the real scene model symbols of these ground features are displayed.

[0178] The surrounding land feature graphics are displayed on the vector map in the form of real scene model symbols.

[0179] It should be noted that the solution of the present application determines the position of the target vehicle on the vector map in real time according to the set time resolution as the position of the vehicle on the road changes continuously, and determines the morphological changes of the ground objects within the visual volume around the current position point in real time based on the position of the target vehicle on the vector map. Since the ground objects are expressed by vector graphics, the size, position and perspective relationship of the displayed graphics of the ground objects change continuously as the position of the vehicle on the road changes continuously. The size, position and perspective relationship of the displayed graphics of the retrieved real-life model symbol also change accordingly due to the adaptation of the attribute information of the associated vector graphics element.

[0180] As the position changes, when some of the graphics of the land features disappear from the viewing volume and new graphics of the land features enter the viewing volume, the attribute information of the new land features is triggered and the associated real scene model symbols are retrieved, so the displayed real scene graphics also change accordingly.

[0181] Fig.13 This is a structural diagram of a device for constructing a real scene model of road elements in an embodiment of the present application, which is used to implement the method for constructing a real scene model of road elements in a high-precision map described in any embodiment of the first aspect, comprising:

[0182] The acquisition module 310 is used to acquire the map data of the target road, and the functions implemented are as described in step 110 of the embodiment.

[0183] The determination module 320 is used to determine the location information and type information of the ground feature element and also to determine the real scene model symbols corresponding to the ground feature elements of different types of information. The functions implemented are as described in step 120 of the embodiment.

[0184] The generation module 330 is used to generate a high-precision map. The functions implemented are as described in step 130 of the embodiment.

[0185] Furthermore, the acquisition module further includes a first acquisition unit, which is used to acquire map data of the target road.

[0186] Furthermore, the determination module includes a first determination unit, which is used to determine the location information and type information of the ground feature element; and is also used to determine the real scene model symbols corresponding to the ground feature elements of different types of information.

[0187] Furthermore, the generation module includes a first generation unit for generating a high-precision map.

[0188] In one embodiment, the determination module further comprises a second determination unit, which is used to determine the coordinate information of the vector element positioning point according to the map data; is also used to determine the type of the vector element line and the first attribute parameter corresponding to the type; is also used to determine the size parameter of the vector element in the direction perpendicular to the horizontal plane as the second attribute parameter;

[0189] The generation module also includes a second generation unit, which is used to assign the first attribute parameter and the second attribute parameter to the real scene model symbol according to the positioning point coordinate information to generate a real scene map of the land feature.

[0190] The above embodiment is used to implement the method described in steps 130 - 11 to 130 - 14.

[0191] In one of the embodiments, the acquisition module further comprises a second acquisition unit, which is used to acquire the real scene model symbol of the ground feature on the target road;

[0192] The determination module further comprises a third determination unit, which is used to determine the symbol parameters of the real scene model according to the vector graphics attribute information in the map data of the target road;

[0193] The generation module further includes a third generation unit, which is used to set the model on the target road real scene map according to the position and the size.

[0194] The above embodiment is used to implement the method described in steps 130-21 to 130-23.

[0195] In one of the embodiments, the acquisition module further comprises a third acquisition unit, which is used to generate a map of the target road according to the radar image, including vector graphics of the ground features in the target road;

[0196] The determination module further comprises a fourth determination unit, which is used to identify and determine the position information and shape information of the ground object element in the image collected by the radar;

[0197] The generation module further includes a fourth generation unit, which is used to retrieve the real-scene model symbol of the land feature element, determine the display position and range of the real-scene model symbol according to the position information and shape information, and generate a real-scene map of the land feature element.

[0198] The above embodiment is used to implement the method described in steps 130-31 to 130-33.

[0199] In one embodiment, the determination module further includes a fifth determination unit, which is used to determine the current position information based on the navigation information; it is also used to determine the terrain elements within the current position vision volume in the map data of the target road based on the current position information, and display the real-life model symbols of these terrain elements; it is also used to determine the display position and size of the corresponding real-life model symbol based on the display position and size of the terrain element vector graphics within the vision volume when displaying the real-life model symbol.

[0200] The above-mentioned embodiment is used to implement the method of arranging the real scene model symbols on the linear vector elements or the facial makeup vector elements.

[0201] In one of the embodiments, the determination module further comprises a sixth determination unit, configured to determine a pattern of surface-like vector elements on the target road;

[0202] The generation module further comprises a fifth generation unit, which is used to continuously arrange the real scene model symbols on the vector element lines according to the preset point spacing parameters. And / or, the real scene model symbols of the pattern obtained by encoding are arranged on the planar vector elements.

[0203] The above embodiment is used to implement the method described in steps 210 to 230.

[0204] Furthermore, the acquisition module further includes a fourth acquisition unit, which is used to acquire map data of the target road and determine the coordinate information of the vector element positioning point according to the map data.

[0205] Furthermore, the determination module comprises a seventh determination unit, which is used to determine the type of the vector element line and the first attribute parameter corresponding to the type; and is also used to determine the height attribute of the vector element as the second attribute parameter.

[0206] Furthermore, the generation module includes a sixth generation unit, which is used to draw a vector element line map on the target road according to the positioning point coordinate information; and is also used to assign the first attribute parameter and the second attribute parameter to the vector element line map to generate a real scene map of the target road.

[0207] In one of the embodiments, the determination module further includes an eighth determination unit, which is used to determine a preset point spacing and evenly distribute the nodes on the vector element lines.

[0208] In one of the embodiments, the drawing module further includes a seventh generating unit, which is used to draw a corresponding shape according to the acquired first attribute and second attribute.

[0209] In one of the embodiments, the determination module further comprises a ninth determination unit, which is used to determine a texture material template library;

[0210] The acquisition module further includes a fifth acquisition unit, which is used to acquire a template in a texture material template library.

[0211] The drawing module further comprises an eighth generation unit for drawing the material map on the vector element.

[0212] In one of the embodiments, the acquisition module further includes a sixth acquisition unit for acquiring a model of a component element on the target road.

[0213] The determination module further includes a tenth determination unit, which is used to determine the position and angle of the model information.

[0214] The drawing module also includes a ninth generating unit, which is used to draw the model of the component element onto the target road real scene map.

[0215] Furthermore, the determination module also includes an eleventh determination unit, which is used to determine the component template library and is also used to determine the model corresponding to the component element through the component coding.

[0216] 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.

[0217] Combination Figure 1 The present application also provides a data processing system for realizing the construction of a real-life model of road elements in a high-precision map, which is used to implement the method described in any one of the embodiments of the present application, including: a collection terminal 400, a geographic information system database 410, a geographic information data processor 420, an operation terminal 430, an on-board application terminal 440, at least one real-life result map data set 450, a real-life model symbol database 460, and a real-life navigation server 470.

[0218] The geographic information system 410 is used to generate and save geographic element data of roads.

[0219] The operation terminal 430 is used to read the target road vector map data, input the set vector map element location information and type information, display the data and / or graphics of the real scene model symbol corresponding to the vector map element; and / or trigger the acquisition module, determination module or generation module. It is an operation interface for associating the vector map element with the real scene model symbol.

[0220] The vehicle-mounted application terminal 440 is used to determine the spatial position, obtain the geometric information of nearby land features through symbol coding, and assign some attribute information to it; it is also used to display high-precision maps during vehicle navigation. The high-precision maps displayed in real time during road navigation are superimposed on the map by associating vector graphic data and real-scene model symbols through location information.

[0221] The geographic information data processor 320 and / or the operation terminal 330 are used to respond to the instructions of the GUI, obtain the map data of the target road, determine the location information and type information of the ground feature elements; determine the real-life model symbols corresponding to the ground feature elements of different types of information; the data cluster of the real-life model symbols includes name codes, real-life pictures and graphic attribute information; generate a high-precision map, which is a collection of real-life model symbols associated according to location information. In one embodiment, the geographic information data processor and / or the operation terminal are also used to generate or edit a real-life model symbol template.

[0222] The geographic information data processor 420 is used to obtain road feature element data scanned and generated by the acquisition terminal or feature element data of the geographic information system, obtain and / or generate real-scene model symbol data of road surface construction elements and component construction elements, and generate a high-precision map containing real-scene model symbols.

[0223] The real-life result map data set 450 is used to store high-precision maps, wherein the data includes geometric information and attribute information of the ground feature symbols, and also includes a data set of real-life model symbols and map overlays corresponding to the vector graphics data.

[0224] The real-scene model symbol database 460 includes real-scene model symbol templates.

[0225] 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.

[0226] 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.

[0227] Those skilled in the art will appreciate 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. Moreover, 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0232] 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.

[0233] 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 memory 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. 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 media 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.

[0234] 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.

[0235] 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 constructing a real-scene model of high-precision map road elements, characterized in that: include: Obtain map data of the target road and determine the location and type information of the ground features; Determine the real scene model symbols corresponding to the ground feature elements of different types of information; the data cluster of the real scene model symbol includes name code, real scene picture and graphic attribute information; Generate a high-precision map, which is a collection of real-scene model symbols associated according to location information.

2. The method for constructing a real scene model of road elements in a high-precision map according to claim 1, characterized in that: The ground feature elements include vector elements, which specifically include the following steps: Determine the coordinate information of the vector element positioning point according to the map data; Determine the type of the vector element line and a first attribute parameter corresponding to the type; the first attribute includes a size in the horizontal direction; Determine the size parameter of the vector element in the direction perpendicular to the horizontal plane as the second attribute parameter; The first attribute parameter and the second attribute parameter are assigned to a real scene model symbol according to the positioning point coordinate information to generate a real scene map of the land feature.

3. The method for constructing a real-scene model of high-precision map road elements according to claim 1 is characterized in that: Also includes the steps: Obtain the real scene model symbol of the ground feature on the target road; Determine the symbol parameters of the real scene model according to the vector graphics attribute information in the map data of the target road; the symbol parameters of the real scene model include position and size; The model is set on the target road real scene image according to the position and the size.

4. The method for constructing a real-scene model of road elements in a high-precision map according to claim 1, characterized in that: The following steps are involved: Generate a map of the target road based on the radar image, including vector graphics of the ground features in the target road; Identify and determine the location information and shape information of ground features in images collected by radar; The real scene model symbol of the land feature element is retrieved, the display position and range of the real scene model symbol are determined according to the position information and shape information, and a real scene map of the land feature element is generated.

5. The method for constructing a real scene model of high-precision map road elements according to claim 1, characterized in that: The following steps are involved: Determine the current location information based on the navigation information, Determine the ground features within the current position visual volume in the map data of the target road according to the current position information, and display the real scene model symbols of these ground features; When the real scene model symbol is displayed, the display position and size of the corresponding real scene model symbol are determined according to the display position and size of the ground feature vector graphic within the range of the viewing volume.

6. The method for constructing a real scene model of high-precision map road elements according to claim 1, characterized in that: Contains steps: The real scene model symbols are continuously laid out on the vector feature lines according to the preset positioning point spacing parameters.

7. The method for constructing a real scene model of high-precision map road elements according to claim 1, characterized in that: The specific steps include: Determine the pattern of surface vector elements on the target road; The real scene model symbol of the pattern obtained by name coding is set on the planar vector element.

8. A device for constructing a real-scene model of road elements in a high-precision map, characterized in that: The method for constructing a real scene model of a high-precision map road element based on point cloud data according to any one of claims 1 to 7 comprises: An acquisition module, used to acquire map data of a target road; A determination module is used to determine the location information and type information of the ground feature; and is also used to determine the real scene model symbols corresponding to the ground feature elements of different types of information; Generation module, used to generate high-precision maps.

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

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

Images