Simulation scene model representation parameter extraction method and device suitable for cloud platform

Abstract

The invention provides a simulation scene model representation parameter extraction method and device suitable for a cloud platform, and the method correspondingly suitable for the cloud platform comprises the steps: generating a map file of a simulation scene model according to the pre-obtained static attribute data of the simulation scene model, segmenting the road according to the type of the road in the map file to generate a segmentation result; extracting characterization parameters of the simulation scene model according to the structural body data of the map file and the segmentation result; wherein the characterization parameters are used for characterizing a road network center reference line and a road boundary line of the simulation scene model. One aspect. According to the method, accurate extraction of boundary data of the simulation scene model is realized, and the reliability of map modeling is greatly improved; and on the other hand, through data analysis and storage, the modeling efficiency of the cloud platform corresponding to the required high-precision map is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle intelligent automatic driving technology, and in particular to the field of vehicle intelligent driving simulation technology, and specifically to a method and device for extracting characterization parameters of a simulation scene model suitable for a cloud platform. Background Art

[0002] According to statistics and analysis by relevant companies, self-driving cars need to undergo at least 11 billion miles of mileage testing in real or virtual environments to ensure that the self-driving system after testing is more reliable than human drivers; however, mileage-based testing methods have disadvantages such as long testing cycles, low efficiency, and high costs. For self-driving cars to be commercialized, it is obviously unrealistic to rely solely on mileage-based testing methods, so scenario-based simulation testing methods are indispensable.

[0003] On the other hand, since the scenes in the real world are infinitely rich, extremely complex, and unpredictable, it is very difficult to fully reproduce these scenes in a virtual environment; therefore, how to use limited test scenes to map out an infinitely rich world is the key to achieving autonomous driving test verification. Simulation testing based on the scenario library is an important technical route to solve the lack of autonomous driving road test data. The higher the coverage of the test scenes in the scenario library to the real world, the higher the accuracy of the simulation test results.

[0004] For the simulation process of the high-precision map model of the cloud platform autonomous driving system, the cloud platform-based autonomous driving system includes the plane map required for vehicle scheduling and trajectory planning of the system. For the simulation test of the cloud platform autonomous driving system, after the scene model is established on the simulation platform, the corresponding map model needs to be established on the cloud platform. Both use the high-precision map standard, in which the simulation platform three-dimensional model uses a standardized format file, and the cloud platform two-dimensional map modeling requires the boundary data of the simulation scene model. The technicians will first carry out scene modeling on the simulation platform according to the plan. After the simulation platform completes the establishment of hundreds of scene models, how to extract the boundary data of the scene model and quickly apply it to the two-dimensional map modeling of the cloud platform is a difficult point. On the one hand, if the efficiency of the extraction method is low, it will greatly increase the workload of map modeling, resulting in low efficiency of simulation testing; on the other hand, if the accuracy of the extraction method is very low, it will greatly reduce the credibility of map modeling, and even cause the failure of simulation testing. Summary of the invention

[0005] One object of the present invention is to provide a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform. On the one hand, this method realizes the accurate extraction of boundary data of the simulation scene model, greatly improving the credibility of map modeling; on the other hand, through data analysis and preservation, the modeling efficiency of the cloud platform corresponding to the required high-precision map is greatly improved.

[0006] Another object of the present invention is to provide a device for extracting characterization parameters of a simulation scene model suitable for a cloud platform. Another object of the present invention is to provide an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the method for extracting characterization parameters of a simulation scene model suitable for a cloud platform when executing the computer program. Another object of the present invention is to provide a readable medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps of the method for extracting characterization parameters of a simulation scene model suitable for a cloud platform are implemented.

[0007] In order to solve the technical problems in the background technology of this application, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform, comprising:

[0009] Generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model;

[0010] Segmenting the road according to the road type in the map file to generate a segmentation result;

[0011] The characterization parameters of the simulation scene model are extracted according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0012] In one embodiment of the present invention, the step of generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model comprises:

[0013] Generating a schematic diagram of the simulation model scene model according to the static attribute data, wherein the schematic diagram includes relative information of the road;

[0014] The map file is generated according to the schematic diagram.

[0015] In one embodiment of the present invention, the method for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0016] Traversing the map file, and determining the hierarchy type of the current node according to the map file format;

[0017] The structure data is generated according to the hierarchical structure type of all nodes.

[0018] In one embodiment of the present invention, extracting the representation parameters of the simulation scene model according to the structure data of the map file and the segmentation result includes:

[0019] Parsing the structure data to obtain characteristic parameters of the roads in the map file;

[0020] Generate a mathematical model of the road network center reference line and a mathematical model of the road boundary line according to the characteristic parameters;

[0021] The characterization parameters are extracted according to the characteristic parameters, the segmentation results, the mathematical model of the road network center reference line, and the mathematical model of the road boundary line.

[0022] In one embodiment of the present invention, the characteristic parameters are used to characterize the road network logic parameters and the geometric shape of the road in the map file.

[0023] In one embodiment of the present invention, extracting the characterization parameter according to the characteristic parameter, the segmentation result, the mathematical model of the road network center reference line, and the mathematical model of the road boundary line includes:

[0024] According to the characteristic parameters and the mathematical model of the road network center reference line, extract and calculate the characterization parameters of the road network center reference line corresponding to each segmentation result;

[0025] According to the characteristic parameters and the mathematical model of the road boundary line, the characterization parameters of the road boundary line corresponding to each segmentation result are extracted and calculated.

[0026] In one embodiment of the present invention, segmenting the road according to the type of the road in the map file to generate a segmentation result includes:

[0027] Dividing the road into a straight segment and a curved segment;

[0028] When extracting the road boundary line of the simulation scene model, the straight line segment and the curve segment are segmented twice.

[0029] In one embodiment of the present invention, generating a mathematical model of the road boundary line according to the characteristic parameters includes:

[0030] A mathematical model of each segment in the result of the secondary segmentation is generated according to the characteristic parameters.

[0031] In one embodiment of the present invention, based on the characteristic parameters and the mathematical model of the road boundary line, extracting and calculating the characterization parameters of the road boundary line corresponding to each segmentation result includes:

[0032] According to the characteristic parameters and the mathematical model of the road boundary line, the characterization parameters of the road boundary line corresponding to each segment in the result of the secondary segmentation are extracted and calculated.

[0033] In one embodiment of the present invention, before extracting the representation parameters of the simulation scene model according to the structure data of the map file and the segmentation result, the method further includes:

[0034] Convert multiple coordinate systems in the map file into a single coordinate system.

[0035] In one embodiment of the present invention, a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform further includes:

[0036] Determining the traversal direction of the road according to the predecessor and successor relationship of the current road in the road network center reference line and / or the road boundary line;

[0037] At a preset position of the current road, traversing the outermost road of the current road according to the traversal direction;

[0038] When traversing to an intersection, determining whether there is the outermost road behind the intersection;

[0039] If so, continue traversing the outermost road behind the intersection until the outermost road no longer exists behind the intersection;

[0040] The road network center reference line and road boundary line are uploaded to the cloud platform.

[0041] In one embodiment of the present invention, the static attribute data includes: segmented road geometry parameters, segmented road lengths, road quantity, road width, and intersection locations of the road.

[0042] In a second aspect, the present invention provides a device for extracting characterization parameters of a simulation scene model suitable for a cloud platform, the device comprising:

[0043] A map file generating module, used for generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model;

[0044] A road segmentation module, used for segmenting the road according to the type of the road in the map file to generate a segmentation result;

[0045] A characterization parameter extraction module is used to extract the characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0046] In one embodiment of the present invention, the map file generation module includes:

[0047] A schematic diagram generating unit, used for generating a schematic diagram of the simulation model scene model according to the static attribute data, wherein the schematic diagram includes relative information of the road;

[0048] A map file generating unit is used to generate the map file according to the schematic diagram.

[0049] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0050] A structure type determination module, used for traversing the map file and determining the hierarchical structure type of the current node according to the map file format;

[0051] The root structure data generating module is used to generate the structure data according to the hierarchical structure types of all nodes.

[0052] In one embodiment of the present invention, the characterization parameter extraction module includes:

[0053] A structure data parsing unit, used for parsing the structure data to obtain characteristic parameters of the roads in the map file;

[0054] A mathematical model generating unit, used for generating a mathematical model of the road network center reference line and a mathematical model of the road boundary line according to the characteristic parameters;

[0055] A characterization parameter extraction unit is used to extract the characterization parameter according to the characteristic parameter, the segmentation result, the mathematical model of the road network center reference line and the mathematical model of the road boundary line.

[0056] In one embodiment of the present invention, the characteristic parameters are used to characterize the road network logic parameters and the geometric shape of the road in the map file.

[0057] In one embodiment of the present invention, the characterization parameter extraction unit includes:

[0058] A first characterization parameter extraction unit is used to extract and calculate the characterization parameters of the road network center reference line corresponding to each segmentation result according to the characteristic parameters and the mathematical model of the road network center reference line;

[0059] The first characterization parameter extraction unit is used to extract and calculate the characterization parameters of the road boundary line corresponding to each segmentation result based on the characteristic parameters and the mathematical model of the road boundary line.

[0060] In one embodiment of the present invention, the road division module includes:

[0061] A primary segmentation unit, used for dividing the road into straight segments and curved segments;

[0062] The secondary segmentation unit is used to perform secondary segmentation on the straight line segment and the curve segment when extracting the road boundary line of the simulation scene model.

[0063] In one embodiment of the present invention, the mathematical model generating unit includes:

[0064] The first model generation unit is used to generate a mathematical model of each segment in the result of the secondary segmentation according to the characteristic parameters.

[0065] In one embodiment of the present invention, the characterization parameter extraction first unit includes:

[0066] The characterization parameter extraction subunit is used to extract the characterization parameters of the road boundary line corresponding to each segment in the result of calculating the secondary segmentation according to the characteristic parameters and the mathematical model of the road boundary line.

[0067] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0068] The coordinate system conversion module is used to convert multiple coordinate systems in the map file into a single coordinate system.

[0069] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0070] A traversal direction determination module, used to determine the traversal direction of the road according to the predecessor and successor relationship of the current road in the road network center reference line and / or road boundary line;

[0071] A road traversal module, configured to traverse the outermost road of the current road according to the traversal direction at a preset position of the current road;

[0072] An intersection judgment module, used for judging whether there is the outermost road behind the intersection when traversing to the intersection;

[0073] A continuing traversal module, used for continuing to traverse the outermost road behind the intersection until the outermost road does not exist behind the intersection if it exists;

[0074] The data uploading module is used to upload the road network center reference line and road boundary line to the cloud platform.

[0075] In one embodiment of the present invention, the static attribute data includes: segmented road geometry parameters, segmented road lengths, road quantity, road width, and intersection locations of the road.

[0076] In a third aspect, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform.

[0077] In a fourth aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the processor implements the steps of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform.

[0078] In a fifth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform.

[0079] From the above description, it can be seen that an embodiment of the present invention provides a method and device for extracting characterization parameters of a simulation scene model suitable for a cloud platform. The corresponding method for extracting characterization parameters of a simulation scene model suitable for a cloud platform includes: first, generating a map file of the simulation scene model based on the static attribute data of the simulation scene model acquired in advance, then, segmenting the roads according to the types of roads in the map file to generate segmentation results; finally, extracting the characterization parameters of the simulation scene model based on the structure data of the map file and the segmentation results; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0080] The present invention proposes an effective method and device for extracting and calculating road network boundary data from the general scenario model file of the simulation platform. On the one hand, it realizes the accurate extraction of boundary data, greatly improving the credibility of map modeling; on the other hand, through data analysis and preservation, it greatly improves the modeling efficiency of the cloud control platform corresponding to the required high-precision map. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0082] Figure 1 A schematic flow chart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0083] Figure 2 1 is a flow chart of step 100 of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0084] Figure 3 Another schematic flow chart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0085] Figure 4 300 is a flow chart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0086] Figure 5 303 of the method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0087] Figure 6 Schematic diagram of step 200 of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0088] Figure 7 302 of the method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0089] Figure 8 3032 of the method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0090] Fig. 9 It is a third flow chart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0091] Fig.10 It is a fourth flow chart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in an embodiment of the present invention;

[0092] Fig.11 A schematic diagram of a road boundary point traversal method in an embodiment of the present invention;

[0093] Fig.12 It is a flowchart of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in a specific embodiment of the present invention;

[0094] Fig.13 A mind map of a method for extracting characterization parameters of a simulation scene model applicable to a cloud platform in a specific embodiment of the present invention;

[0095] Fig.14 A schematic diagram of a simulation model scene model in a specific embodiment of the present invention;

[0096] Fig.15 It is a schematic diagram of a map file in a specific implementation manner of the present invention;

[0097] Fig.16 A schematic diagram of a process for extracting characteristic parameters of a road network centerline in a specific embodiment of the present invention;

[0098] Fig.17 A schematic diagram of a process for extracting characteristic parameters of road boundary line width, elevation, and superelevation in a specific implementation manner of the present invention;

[0099] Fig.18 It is a block diagram of a device for extracting characterization parameters of a simulation scene model suitable for a cloud platform in a specific embodiment of the present invention;

[0100] Fig.19 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0101] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0102] 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.

[0103] It should be noted that the terms "including" and "having" in the specification and claims of the present application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. In the absence of conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0104] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of laws and regulations.

[0105] Embodiment 1:

[0106] The embodiment of the present invention provides a specific implementation method of a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, see Figure 1 , specifically including the following:

[0107] Step 100: generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model;

[0108] Step 200: Segmenting the road according to the road type in the map file to generate a segmentation result;

[0109] Step 300: extracting characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0110] From the above description, it can be seen that an embodiment of the present invention provides a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, comprising: first, generating a map file of the simulation scene model based on pre-acquired static attribute data of the simulation scene model, then, segmenting the roads according to the types of roads in the map file to generate segmentation results; finally, extracting the characterization parameters of the simulation scene model based on the structure data of the map file and the segmentation results; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0111] In view of the fact that there is no method in the prior art to quickly convert a large number of scene library models into a two-dimensional high-precision map model and improve the efficiency and accuracy of simulation testing, the present invention proposes a method for converting the scene model of a simulation platform to the map model of a cloud control platform of an autonomous driving system, and applies it to actual work to make up for the pain points of the shortcomings of related solutions in the industry.

[0112] Embodiment 2:

[0113] For step 100, firstly, the basic static attributes of the scene model are selected according to the modeling requirements of the scene library. Preferably, the static attribute data include: segmented road geometry parameters, segmented road length, road number, road width and intersection location.

[0114] For step 200, the beneficial effect of segmenting the road is to improve the extraction efficiency of the representation parameters of the simulation scene model while ensuring the accuracy of the representation parameters of the simulation scene model. However, how to segment needs to be selected based on the road type. Furthermore, for the curved road section, the number of segments needs to be determined according to the accuracy and extraction efficiency of the representation parameters to be extracted.

[0115] For step 300, the structure data of the map file refers to the data structure used to represent the map data. A map file usually contains relevant data such as geographic information, location coordinates, road network, and feature markers. A structure is a custom data type used to organize and store a collection of related data. The structure data of a map file may vary according to specific needs. In this application, the structure data of a map file includes the following data fields:

[0116] Geographic information: including the map's name, boundary range, zoom level, etc.

[0117] Location coordinates: indicates the coordinate information of each location on the map, such as longitude and latitude.

[0118] Road network: represents the road network on the map, including the starting and ending coordinates of the road, road type, road name, etc.

[0119] Feature markers: represent various feature markers on the map, such as buildings, parks, shops, etc., including the location coordinates, name, category, etc. of the markers.

[0120] These data fields can be represented by member variables of the structure, and each member variable corresponds to a data field. By using the structure, these related data fields can be organized together to facilitate storage, access and processing of map data.

[0121] In some embodiments of the present invention, see Figure 2 , step 100 comprises:

[0122] Step 101: generating a schematic diagram of the simulation model scene model according to the static attribute data, wherein the schematic diagram includes relative information of the road;

[0123] Specifically, a schematic diagram of the simulation model scenario model is generated based on elements such as segmented road geometry, segmented road length, number and width of lanes, and intersections (the schematic diagram only contains relative information, not specific data information).

[0124] Step 102: Generate the map file according to the schematic diagram.

[0125] First, according to the markers or geographic coordinate information on the schematic diagram, determine the coordinate system of the map, such as the latitude and longitude coordinate system or the projection coordinate system. Then, the geographic features on the schematic diagram are calibrated with the actual geographic location, usually using geographic information system (GIS) software or online map services for calibration. The calibration process includes selecting feature points on the map and matching them with the actual geographic location. Finally, create a map file based on the calibrated geographic location information. The format of the map file can be selected according to specific needs, and common formats include Shapefile, GeoJSON, KML, etc. GIS software or programming languages ​​(such as Python) can be used to create map files. According to the geographic features on the schematic diagram, the corresponding geographic data is added to the map file. For example, add data such as location coordinates, road networks, and feature markers. Preferably, the attributes of the map are set as needed, such as the name of the map, boundary range, zoom level, etc.

[0126] In some embodiments of the present invention, see Figure 3 , a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, further comprising:

[0127] Step 400: traverse the map file and determine the hierarchy type of the current node according to the map file format;

[0128] First, read the map file and traverse the nodes in it according to certain rules. Determine the hierarchy type of the current node: During the traversal process, determine which hierarchy type the current node belongs to based on the format of the map file. For example, labels, indents, or other conventions may be used to represent the hierarchical relationship between nodes, and the hierarchy type of the node is determined based on these rules. Record the hierarchy type of the node by creating a data structure, using variables, or other means: Once the hierarchy type of the current node is determined, record the information.

[0129] Step 500: Generate the structure data according to the hierarchical structure types of all nodes.

[0130] According to the hierarchical structure types of all nodes, the hierarchical structure types of all nodes are integrated and analyzed. Specifically, according to the hierarchical structure types of all nodes, the program will generate corresponding structure data. Structure is a data type that can be used to organize and store related data. Define and fill structure data according to the hierarchical structure type of the node.

[0131] In some embodiments of the present invention, see Figure 4 , step 300 comprises:

[0132] Step 301: parsing the structure data to obtain characteristic parameters of the roads in the map file;

[0133] Specifically, the road feature parameters in the structured data are mapped to the pre-generated data template according to the structured data format.

[0134] Step 302: Generate a mathematical model of the road network center reference line and a mathematical model of the road boundary line according to the characteristic parameters;

[0135] In a specific coordinate system, the road network center reference line and the road boundary line can be represented by their respective mathematical models, so multiple feature parameters can be selected for fitting to generate the mathematical model of the road network center reference line and the mathematical model of the road boundary line. In the process of selecting feature parameters for fitting, it is also necessary to consider the accuracy of the feature parameters and the fitting efficiency to select the number of feature parameters and the location of the road where they are located.

[0136] Step 303: extracting the characterization parameters according to the characteristic parameters, the segmentation results, the mathematical model of the road network center reference line, and the mathematical model of the road boundary line.

[0137] In essence, step 303 is the inverse operation of step 302. On the basis of determining the data model, a number of data points are extracted to generate characterization parameters. Similarly, the extraction process needs to consider the accuracy of the characterization parameters and the efficiency of extracting the characterization parameters.

[0138] In some embodiments of the present invention, the characteristic parameters are used to characterize the road network logic parameters and the geometric shape of the road in the map file.

[0139] Feature parameters can describe the road geometry in the map file and affect the road network logic, including basic data information of each road segment (road starting point x (x value of the starting position of a specific curve segment (inertial coordinate system)), y (y value of the starting position of a specific curve segment (inertial coordinate system)), hdg (direction of the starting point of a specific curve segment (inertial heading angle / yaw angle)), length, type, etc.), lanes, intersections.

[0140] In some embodiments of the present invention, see Figure 5 , step 303 includes:

[0141] Step 3031: extracting and calculating the representation parameters of the road network center reference line corresponding to each segmentation result according to the characteristic parameters and the mathematical model of the road network center reference line;

[0142] The mathematical model of the center reference line of the road network is sampled according to the lane type, and the difference calculation is performed to obtain a series of center reference line coordinate points including road elevation (longitudinal slope information).

[0143] Step 3032: According to the characteristic parameters and the mathematical model of the road boundary line, extract and calculate the characterization parameters of the road boundary line corresponding to each segmentation result.

[0144] The specific implementation process refers to step 3031 and will not be repeated here.

[0145] In some embodiments of the present invention, see Figure 6 , step 200 comprises:

[0146] Step 201: Divide the road into straight segments and curved segments;

[0147] Step 202: When extracting the road boundary line of the simulation scene model, perform secondary segmentation on the straight line segment and the curve segment.

[0148] In step 201 and step 202, the road network center reference line and the road boundary line are segmented along the road direction, including straight road and curve types. Then, the road boundary line is segmented again based on the road width to the road boundary line geometric segmentation, and each segment is assigned a sequence number in turn to obtain an array dsNum[0, 1, 2...m; 0, 1, 2...n; 0, 1, 2...o], until the width of each road segment can be fitted with a set of fixed parameters.

[0149] In some embodiments of the present invention, see Figure 7 The step 302 of generating the mathematical model of the road boundary line according to the characteristic parameters includes:

[0150] Step 3021: Generate a mathematical model of each segment in the result of the secondary segmentation according to the characteristic parameters.

[0151] It can be understood that, in the result of the secondary segmentation, it is extremely important to generate a mathematical model for each segment separately in order to accurately characterize the shape of the curve.

[0152] In some embodiments of the present invention, see Figure 8 , step 3032 includes:

[0153] Step 30321: According to the characteristic parameters and the mathematical model of the road boundary line, extract the characterization parameters of the road boundary line corresponding to each segment in the result of calculating the secondary segmentation.

[0154] In some embodiments of the present invention, see Fig. 9 The method for extracting the characterization parameters of the simulation scene model applicable to the cloud platform may further include, before step 300:

[0155] Step 600: Convert multiple coordinate systems in the map file into a single coordinate system.

[0156] Preferably, the inertial coordinate system, reference line coordinate system and local coordinate system used in the map file are uniformly converted into the inertial coordinate system.

[0157] In some embodiments of the present invention, in order to establish a closed loop storage of the road network center reference line and / or the road boundary line, it is necessary to traverse the road boundary points. Fig.10 , a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, further comprising:

[0158] Step 700: determining the traversal direction of the road according to the predecessor and successor relationship of the current road in the road network center reference line and / or the road boundary line;

[0159] Step 800: at a preset position of the current road, traverse the outermost road of the current road according to the traversal direction;

[0160] Step 900: When traversing to an intersection, determine whether the outermost road exists behind the intersection;

[0161] Step 1000: If it exists, continue to traverse the outermost road behind the intersection until the outermost road does not exist behind the intersection;

[0162] Step 1100: Upload the road network center reference line and road boundary line to the cloud platform.

[0163] For steps 700 to 1100, see Fig.11 There are two main difficulties in the road boundary point traversal and preservation function. One is to establish a closed-loop data preservation function. The solution is to establish a method that can determine the successor relationship of the current road and realize the direction definition of data traversal and preservation; the other is the judgment of the outermost lane line of the intersection. Due to the complex logical relationship of the intersection model stipulated by the map standard, it is necessary to establish a logical judgment function for the outermost lane of the intersection.

[0164] From the above content, it can be seen that since the scene model established by the simulation platform is a three-dimensional solid model based on graphical modeling, the boundary coordinate data of the scene model cannot be calculated by the software itself. Therefore, the present invention proposes a data extraction and analysis method for the high-precision map scene model file of the simulation platform, which can realize the effective extraction and classification of the purpose data of the high-precision map scene model file of the simulation platform (such as straight roads, curves and intersections).

[0165] Embodiment three:

[0166] In a specific embodiment, the present invention also provides a specific embodiment of a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, see Fig.12 as well as Fig.13 , specifically including the following contents.

[0167] S1: Generate a map file according to the pre-acquired static attribute data of the simulation scene model.

[0168] First, according to the modeling requirements of the scenario library, define the basic static properties of the scenario model, including segmented road geometry, segmented road length, number and width of lanes, intersections and other elements, and draw its schematic diagram (the schematic diagram only contains relative information, not specific data information), such as Fig.14 shown.

[0169] Then, according to the schematic information, simulation software is used to carry out scene modeling based on the OpenX high-precision map standard to generate a three-dimensional high-precision map in xodr format, such as Fig.15 shown.

[0170] S2: Analyze the scene model map format.

[0171] Analyze the xodr format high-precision map, analyze its structure according to its hierarchical structure, and extract relevant characteristic parameters that can describe the road geometry and affect the road network logic. Contains basic data information of each road section (road starting point x, y, hdg, length, type, etc.), lanes, and intersections.

[0172] S3: Extract the characteristic parameters of the road network centerline.

[0173] Parameters are extracted and saved according to lane types, and difference calculations are performed to obtain a series of center reference line coordinate points (including road elevation and superelevation). The inertial coordinate system, reference line coordinate system, and local coordinate system used simultaneously in the xodr format are uniformly converted to the inertial coordinate system, and the corresponding coordinate points are saved.

[0174] Specifically, see Fig.16 First, segment the center reference line of the road according to the lane type along the road direction, including straight and curved types. Then, according to the segmentation of the center reference line, establish a mathematical model of the center reference line of the road of the relevant lane type. The constant coefficients of the mathematical model are provided by the xodr file, such as L=a+bx+cx^2+dx^3. Sample the center reference line of the road network according to the lane type, and perform difference calculation to obtain a series of center reference line coordinate points including road elevation (longitudinal slope information). First, convert the inertial coordinate system, reference line coordinate system and local coordinate system used simultaneously in the xodr format into an inertial coordinate system. Finally, traverse and save the data from the starting point to the end point of the center reference line. As a global variable, provide the attributes of each point of the center reference line, including the global sorting information of the current point and the sorting information of the current point in the segmented road. Save the current information and apply it to subsequent boundary coordinate calculation and extraction.

[0175] S4: Extract the characteristic parameters of the road boundary line width, elevation, and superelevation.

[0176] Extract the width of each lane and calculate the boundary coordinate points of each lane (including road elevation, superelevation, and lane height).

[0177] Specifically, refer to Fig.17 , based on the number of segments of the central reference line, segment the road boundary line along the road direction, including straight and curved types. Then, based on the road width, re-segment the geometric segments of the road boundary line, and assign serial numbers to each segment in turn to obtain the array dsNum[0, 1, 2...m; 0, 1, 2...n; 0, 1, 2...o], until it is satisfied that the width of each road segment can be fitted to the road width with a set of fixed parameters. Third, in the automatic extraction process, according to the segmentation situation of the road boundary line, based on the following formula dsNum!= 0 && ref_ds[dsNum] < ref_ds[dsNum - 1], judge the length of the current segmentation point of ref_ds[dsNum] from the starting point of the road, which belongs to the geometryNum-th road geometry on this road, that is, which segment of the above dsNum[]. Based on this, establish a mathematical model of the road boundary line. The constant coefficients of the mathematical model are provided by the xodr file. Taking the ground lane adjacent to the central reference line as an example, its road width calculation model is as follows wright = laneswidth[i].a + laneswidth[i].b * s + laneswidth[i].c * S^2 + laneswidth[i].d * S^3.

[0178] Next, according to the above calculation results, sample the road boundary line along the road direction and perform difference calculation to obtain a series of road boundary line width values wright. Establish a road height and superelevation calculation model, take the above segmentation and sampling results as input, and calculate the road height and superelevation of each point. Convert the inertial coordinate system, reference line coordinate system, and local coordinate system used simultaneously in the xodr format into the inertial coordinate system uniformly. Traverse and save the data from the starting point to the end point of the central reference line as global variables, providing the attributes of each point on the central reference line, including the global sorting information of the current point and the sorting information of the current point in the segmented road. Finally, superimpose the above road height, elevation, and superelevation information to calculate the corresponding inertial reference line z coordinate value.

[0179] S5: Traverse and save the data.

[0180] Realize the traversal and saving of the road boundary data from the starting point to the end point according to the agreed rules.

[0181] S6: Compile the map of the unmanned cloud control center.

[0182] According to the unmanned driving cloud control center map production module, the cloud control center map is produced using the above closed-loop saved data as input.

[0183] From the above description, it can be seen that an embodiment of the present invention provides a method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, comprising: first, generating a map file of the simulation scene model based on pre-acquired static attribute data of the simulation scene model, then, segmenting the roads according to the types of roads in the map file to generate segmentation results; finally, extracting the characterization parameters of the simulation scene model based on the structure data of the map file and the segmentation results; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0184] In order to solve the technical problem that the road geometry of the simulation platform scene model is complex and the boundary shape may be irregular, making it difficult to extract irregular data, the present invention proposes a boundary data extraction method and an automatic saving method based on a road geometry segmentation method. The method can achieve accurate calculation and preservation of road boundary coordinate points (three-dimensional coordinate values ​​under a relational reference coordinate system).

[0185] Embodiment 4:

[0186] Based on the same inventive concept, the embodiments of the present application also provide a device for extracting the characterization parameters of a simulation scene model suitable for a cloud platform, which can be used to implement the method described in the above embodiments, such as the following embodiments. Since the principle of solving the problem by the device for extracting the characterization parameters of a simulation scene model suitable for a cloud platform is similar to the method for extracting the characterization parameters of a simulation scene model suitable for a cloud platform, the implementation of the device for extracting the characterization parameters of a simulation scene model suitable for a cloud platform can refer to the implementation of the method for extracting the characterization parameters of a simulation scene model suitable for a cloud platform, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0187] The embodiment of the present invention provides a specific implementation of a simulation scene model characterization parameter extraction device applicable to a cloud platform that can realize a simulation scene model characterization parameter extraction method applicable to a cloud platform. The simulation scene model characterization parameter extraction device applicable to a cloud platform includes: a simulation scene model characterization parameter extraction device applicable to a cloud platform, wherein, see Fig.18 , a device for extracting characterization parameters of a simulation scene model suitable for a cloud platform includes:

[0188] A map file generating module 10 is used to generate a map file of the simulation scene model according to the static attribute data of the simulation scene model acquired in advance,

[0189] A road segmentation module 20, configured to segment the road according to the type of the road in the map file to generate a segmentation result;

[0190] The characterization parameter extraction module 30 is used to extract the characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0191] In one embodiment of the present invention, the map file generation module includes:

[0192] A schematic diagram generating unit, used for generating a schematic diagram of the simulation model scene model according to the static attribute data, wherein the schematic diagram includes relative information of the road;

[0193] A map file generating unit is used to generate the map file according to the schematic diagram.

[0194] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0195] A structure type determination module, used for traversing the map file and determining the hierarchical structure type of the current node according to the map file format;

[0196] The root structure data generating module is used to generate the structure data according to the hierarchical structure types of all nodes.

[0197] In one embodiment of the present invention, the characterization parameter extraction module includes:

[0198] A structure data parsing unit, used for parsing the structure data to obtain characteristic parameters of the roads in the map file;

[0199] A mathematical model generating unit, used for generating a mathematical model of the road network center reference line and a mathematical model of the road boundary line according to the characteristic parameters;

[0200] A characterization parameter extraction unit is used to extract the characterization parameter according to the characteristic parameter, the segmentation result, the mathematical model of the road network center reference line and the mathematical model of the road boundary line.

[0201] In one embodiment of the present invention, the characteristic parameters are used to characterize the road network logic parameters and the geometric shape of the road in the map file.

[0202] In one embodiment of the present invention, the characterization parameter extraction unit includes:

[0203] A first characterization parameter extraction unit is used to extract and calculate the characterization parameters of the road network center reference line corresponding to each segmentation result according to the characteristic parameters and the mathematical model of the road network center reference line;

[0204] The first characterization parameter extraction unit is used to extract and calculate the characterization parameters of the road boundary line corresponding to each segmentation result based on the characteristic parameters and the mathematical model of the road boundary line.

[0205] In one embodiment of the present invention, the road division module includes:

[0206] A primary segmentation unit, used for dividing the road into straight segments and curved segments;

[0207] The secondary segmentation unit is used to perform secondary segmentation on the straight line segment and the curve segment when extracting the road boundary line of the simulation scene model.

[0208] In one embodiment of the present invention, the mathematical model generating unit includes:

[0209] The first model generation unit is used to generate a mathematical model of each segment in the result of the secondary segmentation according to the characteristic parameters.

[0210] In one embodiment of the present invention, the characterization parameter extraction first unit includes:

[0211] The characterization parameter extraction subunit is used to extract the characterization parameters of the road boundary line corresponding to each segment in the result of calculating the secondary segmentation according to the characteristic parameters and the mathematical model of the road boundary line.

[0212] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0213] The coordinate system conversion module is used to convert multiple coordinate systems in the map file into a single coordinate system.

[0214] In one embodiment of the present invention, the device for extracting the representation parameters of the simulation scene model applicable to the cloud platform further includes:

[0215] A traversal direction determination module, used to determine the traversal direction of the road according to the predecessor and successor relationship of the current road in the road network center reference line and / or road boundary line;

[0216] A road traversal module, configured to traverse the outermost road of the current road according to the traversal direction at a preset position of the current road;

[0217] An intersection judgment module, used for judging whether there is the outermost road behind the intersection when traversing to the intersection;

[0218] A continuing traversal module, used for continuing to traverse the outermost road behind the intersection until the outermost road does not exist behind the intersection if it exists;

[0219] The data uploading module is used to upload the road network center reference line and road boundary line to the cloud platform.

[0220] In one embodiment of the present invention, the static attribute data includes: segmented road geometry parameters, segmented road lengths, road quantity, road width, and intersection locations of the road.

[0221] From the above description, it can be seen that an embodiment of the present invention provides a device for extracting characterization parameters of a simulation scene model suitable for a cloud platform, including: a map file generation module, used to generate a map file of the simulation scene model based on pre-acquired static attribute data of the simulation scene model, a road division module, used to segment roads according to the types of roads in the map file to generate segmentation results; a characterization parameter extraction module, used to extract the characterization parameters of the simulation scene model based on the structure data of the map file and the segmentation results; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0222] The present invention proposes an effective device for extracting and calculating road network boundary data from the general scenario model file of the simulation platform. On the one hand, it realizes the accurate extraction of boundary data, greatly improving the credibility of map modeling; on the other hand, through data analysis and preservation, it greatly improves the modeling efficiency of the cloud control platform corresponding to the required high-precision map.

[0223] Embodiment five:

[0224] The embodiments of the present application also provide a specific implementation of an electronic device that can implement all the steps in the method for extracting the representation parameters of the simulation scene model applicable to the cloud platform in the above embodiment, see Fig.19 , electronic equipment specifically includes the following:

[0225] Processor (processor) 1201, memory (memory) 1202, communication interface (CommunicationsInterface) 1203 and bus 1204;

[0226] The processor 1201, the memory 1202, and the communication interface 1203 communicate with each other through the bus 1204; the communication interface 1203 is used to realize information transmission between the server device and the client device and other related devices;

[0227] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, all the steps in the method for extracting the representation parameters of the simulation scene model applicable to the cloud platform in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0228] Step 100: generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model;

[0229] Step 200: Segmenting the road according to the road type in the map file to generate a segmentation result;

[0230] Step 300: extracting characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0231] Embodiment six:

[0232] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the method for extracting the representation parameters of the simulation scene model applicable to the cloud platform in the above-mentioned embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the method for extracting the representation parameters of the simulation scene model applicable to the cloud platform in the above-mentioned embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0233] Step 100: generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model;

[0234] Step 200: Segmenting the road according to the road type in the map file to generate a segmentation result;

[0235] Step 300: extracting characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

[0236] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0237] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0238] Although the present application provides method operation steps such as embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0239] For the convenience of description, the above devices are described in various modules according to their functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0240] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0241] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0242] The 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. The memory is an example of a computer-readable medium.

[0243] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0244] The above is only an example of the embodiment of the present specification and is not intended to limit the embodiment of the present specification. For those skilled in the art, the embodiment of the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiment of the present specification shall be included in the scope of the claims of the embodiment of the present specification.

Claims

1. A method for extracting characterization parameters of a simulation scene model suitable for a cloud platform, characterized in that: include: Generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model; Segmenting the road according to the road type in the map file to generate a segmentation result; The characterization parameters of the simulation scene model are extracted according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

2. The method for extracting the characterization parameters of the simulation scene model according to claim 1, characterized in that: The step of generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model comprises: Generating a schematic diagram of the simulation model scene model according to the static attribute data, wherein the schematic diagram includes relative information of the road; The map file is generated according to the schematic diagram.

3. The method for extracting the characterization parameters of the simulation scene model according to claim 1, characterized in that: Also includes: Traversing the map file, and determining the hierarchy type of the current node according to the map file format; The structure data is generated according to the hierarchical structure type of all nodes.

4. The method for extracting the characterization parameters of the simulation scene model according to any one of claims 1 to 3, characterized in that: Extracting the representation parameters of the simulation scene model according to the structure data of the map file and the segmentation result includes: Parsing the structure data to obtain characteristic parameters of the roads in the map file; Generate a mathematical model of the road network center reference line and a mathematical model of the road boundary line according to the characteristic parameters; The characterization parameters are extracted according to the characteristic parameters, the segmentation results, the mathematical model of the road network center reference line, and the mathematical model of the road boundary line.

5. The method for extracting the characterization parameters of the simulation scene model according to claim 4, characterized in that: The characteristic parameters are used to characterize the road network logic parameters and the geometric shape of the road in the map file.

6. The method for extracting the characterization parameters of the simulation scene model according to claim 4, characterized in that: Extracting the characterization parameter according to the characteristic parameter, the segmentation result, the mathematical model of the road network center reference line and the mathematical model of the road boundary line includes: According to the characteristic parameters and the mathematical model of the road network center reference line, extract and calculate the characterization parameters of the road network center reference line corresponding to each segmentation result; According to the characteristic parameters and the mathematical model of the road boundary line, the characterization parameters of the road boundary line corresponding to each segmentation result are extracted and calculated.

7. The method for extracting the characterization parameters of the simulation scene model according to claim 4, characterized in that: The road is segmented according to the type of the road in the map file to generate a segmentation result, including: Dividing the road into a straight segment and a curved segment; When extracting the road boundary line of the simulation scene model, the straight line segment and the curve segment are segmented twice.

8. The method for extracting the characterization parameters of the simulation scene model according to claim 7, characterized in that: Generating a mathematical model of the road boundary line according to the characteristic parameters includes: A mathematical model of each segment in the result of the secondary segmentation is generated according to the characteristic parameters.

9. The method for extracting the characterization parameters of the simulation scene model according to claim 8, characterized in that: According to the characteristic parameters and the mathematical model of the road boundary line, the characterization parameters of the road boundary line corresponding to each segmentation result are extracted and calculated, including: According to the characteristic parameters and the mathematical model of the road boundary line, the characterization parameters of the road boundary line corresponding to each segment in the result of the secondary segmentation are extracted and calculated.

10. The method for extracting characterization parameters of a simulation scene model according to any one of claims 1 to 3, characterized in that: Before extracting the representation parameters of the simulation scene model according to the structure data of the map file and the segmentation result, the method further includes: Convert multiple coordinate systems in the map file into a single coordinate system.

11. The method for extracting characterization parameters of a simulation scene model according to any one of claims 1 to 3, characterized in that: Also includes: Determining the traversal direction of the road according to the predecessor and successor relationship of the current road in the road network center reference line and / or the road boundary line; At a preset position of the current road, traversing the outermost road of the current road according to the traversal direction; When traversing to an intersection, determining whether there is the outermost road behind the intersection; If so, continue traversing the outermost road behind the intersection until the outermost road no longer exists behind the intersection; The road network center reference line and road boundary line are uploaded to the cloud platform.

12. The method for extracting characterization parameters of a simulation scene model according to any one of claims 1 to 3, characterized in that: The static attribute data includes: segmented road geometry parameters, segmented road length, road quantity, road width, and intersection locations of the road.

13. A device for extracting characterization parameters of a simulation scene model suitable for a cloud platform, characterized in that: include: A map file generating module, used for generating a map file of the simulation scene model according to the pre-acquired static attribute data of the simulation scene model; A road segmentation module, used for segmenting the road according to the type of the road in the map file to generate a segmentation result; A characterization parameter extraction module is used to extract the characterization parameters of the simulation scene model according to the structure data of the map file and the segmentation result; wherein the characterization parameters are used to characterize the road network center reference line and road boundary line of the simulation scene model.

14. 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 program, the steps of the method for extracting characterization parameters of a simulation scene model applicable to a cloud platform as described in any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for extracting characterization parameters of a simulation scene model applicable to a cloud platform as described in any one of claims 1 to 12 are implemented.

Images