Test region division method, device, equipment, medium and vehicle

Abstract

The present disclosure relates to a test region division method, device, equipment, medium and vehicle. The test region division method comprises: screening target road segment data of a to-be-tested road segment from a plurality of preset road segment data included in an electronic map; clustering the plurality of preset road segment data to obtain road segment cluster data corresponding to the plurality of preset road segment data; performing a union operation on the target road segment data and the road segment cluster data to obtain union road segment data; determining a plurality of unit grids corresponding to the union road segment data in the electronic map; preprocessing the plurality of unit grids to obtain boundary points, determining a to-be-tested region by using connecting lines of the boundary points, and according to the embodiment of the present disclosure, automatic division of the test region can be realized, and the division efficiency and accuracy of the test region are improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to a test area division method, apparatus, equipment, medium and vehicle. Background Technology

[0002] Currently, autonomous driving road testing is an indispensable and important part of verifying the R&D technology of intelligent connected vehicles. Through road testing, the reliability, intelligence, and safety of autonomous vehicles in different road scenarios can be verified in a comprehensive manner, and the exchange and coordination of real-time traffic information between the vehicle and the outside world can be realized. Without road testing, it is impossible to predict whether the autonomous vehicle's judgment of the surrounding environment in real-world scenarios will meet expectations. Conducting road testing is an essential step for autonomous vehicles.

[0003] Existing methods for delineating autonomous driving road test areas mainly rely on manual analysis and judgment, which is inefficient and cannot accurately delineate based on the density of the road network, making them unsuitable for delineating large-scale autonomous driving road test areas. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a method, apparatus, equipment, medium, and vehicle for dividing a test area.

[0005] A first aspect of this disclosure provides a test region division method, the method comprising:

[0006] Select the target road segment data for the test segment from multiple preset road segment data included in the electronic map;

[0007] Clustering multiple preset road segment data yields road segment cluster data corresponding to the multiple preset road segment data;

[0008] Perform a union operation on the target road segment data and the road segment cluster data to obtain the unioned road segment data;

[0009] Identify multiple cell grids in the electronic map that correspond to the merged road segment data;

[0010] Multiple cell meshes are preprocessed to obtain boundary points, and the test area is determined by connecting the boundary points.

[0011] A second aspect of this disclosure provides a test area division apparatus, the apparatus comprising:

[0012] The road segment filtering module is used to filter target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map;

[0013] The road segment clustering module is used to cluster multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data;

[0014] The union operation module is used to perform a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data;

[0015] The grid determination module is used to determine multiple cell grids in the electronic map that correspond to the merged road segment data;

[0016] The preprocessing module is used to preprocess multiple cell meshes to obtain boundary points, and the test area is determined by connecting the boundary points.

[0017] A third aspect of this disclosure provides an electronic device, the device comprising:

[0018] Memory;

[0019] Processor; and

[0020] A computer program, wherein the computer program is stored in memory and configured to be executed by a processor to implement the test region partitioning method as described in the first aspect above.

[0021] A fourth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the test area division method of the first aspect described above.

[0022] A fifth aspect of this disclosure provides a vehicle that includes the electronic equipment provided in the third aspect.

[0023] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0024] The test area division method, apparatus, device, medium, and vehicle provided in this disclosure can automatically divide the test area by filtering target road segment data of the road segment to be tested from multiple preset road segment data included in an electronic map, clustering the multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data, performing a union operation on the target road segment data and the road segment cluster data to obtain union road segment data, determining multiple cell grids in the electronic map corresponding to the union road segment data after obtaining the union road segment data, preprocessing the multiple cell grids to obtain boundary points, and using the connection of the boundary points to determine the test area. Thus, it is possible to directly filter target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map, and then obtain union road segment data based on the multiple preset road segment data and target road segment data. Furthermore, the multiple cell grids corresponding to the union road segment data in the electronic map are preprocessed to obtain the test area, thereby realizing automatic division of the test area and improving the efficiency and accuracy of test area division. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0026] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a test area division method provided in an embodiment of this disclosure;

[0028] Figure 2 This is a schematic diagram of road segment data clustering provided in an embodiment of this disclosure;

[0029] Figure 3 This is a schematic diagram of a convex hull algorithm provided in an embodiment of this disclosure;

[0030] Figure 4 This is a flowchart of another test area division method provided in this embodiment of the disclosure;

[0031] Figure 5 This is a schematic diagram of the structure of a test area division device provided in an embodiment of this disclosure;

[0032] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0033] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0034] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0035] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0036] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0037] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0038] Existing methods for delineating autonomous driving road test areas typically rely on manual analysis and judgment, which is inefficient, unable to accurately delineate areas based on road network density, and unsuitable for large-scale autonomous driving road test area delineation. To address this issue, this disclosure provides a test area delineation method, which is described below with reference to specific embodiments.

[0039] Figure 1 This is a flowchart of a test area division method provided in an embodiment of the present disclosure. The method can be executed by a test area division device, which can be implemented in software and / or hardware. The test area division device can be configured in an electronic device, such as a server, terminal, or server cluster. Specifically, the terminal includes a vehicle terminal, mobile phone, computer, or tablet computer.

[0040] like Figure 1 As shown, the test area division method provided in this embodiment includes the following steps:

[0041] S110. Select the target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map.

[0042] In this embodiment of the disclosure, when the electronic device needs to divide the test area, or when it receives a test area division request or instruction, it selects the target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map.

[0043] In this embodiment of the disclosure, the electronic map can be understood as a digital map, which is a map stored and viewed in digital form using computer technology. The electronic map includes multiple preset road segment data and is pre-stored in an electronic device.

[0044] In this embodiment of the disclosure, the road segment to be tested can be any road segment that needs to be tested. For example, the road segment to be tested can be all road segments included in a certain expressway name, such as all road segments of the expressway named Beijing-Taipei Expressway.

[0045] Specifically, when the electronic device needs to divide the test area, or receives a test area division request or instruction, it retrieves an electronic map from a pre-stored database and filters the target road segment data of the road segment to be tested from the electronic map according to the identification of the road segment to be tested.

[0046] S120. Cluster the data of multiple preset road segments to obtain the road segment cluster data corresponding to the multiple preset road segment data.

[0047] In this embodiment of the disclosure, the electronic device clusters multiple preset road segment data included in the electronic map to obtain road segment cluster data corresponding to the multiple preset road segment data.

[0048] In this embodiment of the disclosure, clustering can be understood as the process of dividing a set of physical or abstract objects into multiple classes composed of similar objects. In this embodiment of the disclosure, clustering refers to the clustering of multiple preset road segment data.

[0049] Furthermore, a cluster refers to a group of data objects generated by clustering.

[0050] In this embodiment of the disclosure, clustering multiple preset road segment data can be understood as clustering multiple preset road segment data according to a preset clustering method.

[0051] The preset clustering method can be density-based clustering, grid-based clustering, model-based clustering, etc., and there are no restrictions here.

[0052] Specifically, the electronic device clusters multiple preset road segment data included in the electronic map according to a preset clustering method to obtain road segment cluster data corresponding to the multiple preset road segment data.

[0053] It should be noted that in this embodiment, S110 and S120 can be executed simultaneously, or S120 can be executed before S110 or after S110. There is no restriction on the execution order of S110 and S120.

[0054] S130. Perform a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data.

[0055] In this embodiment of the disclosure, after obtaining road segment cluster data corresponding to multiple preset road segment data, the electronic device performs a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data.

[0056] In this embodiment of the disclosure, performing a union operation on the target road segment data and the road segment cluster data can be understood as adding the target road segment data to the road segment data in the road segment cluster to obtain the union road segment data.

[0057] Specifically, after obtaining the road segment cluster data corresponding to multiple preset road segment data, the electronic device performs a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data.

[0058] S140. Determine multiple cell grids in the electronic map that correspond to the merged road segment data.

[0059] In this embodiment of the disclosure, after obtaining the union road segment data, the electronic device determines multiple cell grids in the electronic map that correspond to the union road segment data.

[0060] In this embodiment of the disclosure, the electronic map includes multiple cell grids, wherein the cell grids are obtained by gridding the electronic map.

[0061] Specifically, after obtaining the combined road segment data, the electronic device identifies the cell grids in the electronic map that contain the combined road segment data as multiple cell grids in the electronic map that correspond to the combined road segment data.

[0062] Furthermore, the multiple cell grids corresponding to the union road segment data include cell grids that intersect with, overlap with, or contain the union road segment data.

[0063] S150. Preprocess multiple unit meshes to obtain boundary points, and use the lines connecting the boundary points to determine the test area.

[0064] In this embodiment of the disclosure, after determining multiple cell grids in the electronic map that correspond to the union of road segment data, the electronic device preprocesses the multiple cell grids to obtain boundary points, and uses the connection of the boundary points to determine the area to be tested.

[0065] In this embodiment of the disclosure, preprocessing may include smoothing multiple cell meshes, mesh subdivision processing, etc., and is not limited thereto.

[0066] Specifically, after determining multiple cell grids in the electronic map that correspond to the combined road segment data, the electronic device preprocesses the multiple cell grids according to a preset preprocessing method to obtain boundary points, and uses the connection of the boundary points to determine the area to be tested.

[0067] In this embodiment, the target road segment data of the road segment to be tested can be filtered from multiple preset road segment data included in the electronic map. The multiple preset road segment data are clustered to obtain road segment cluster data corresponding to the multiple preset road segment data. The target road segment data and the road segment cluster data are combined to obtain the combined road segment data. After obtaining the combined road segment data, multiple cell grids corresponding to the combined road segment data in the electronic map are determined. The multiple cell grids are preprocessed to obtain boundary points. The test area is determined by connecting the boundary points. Thus, the target road segment data of the road segment to be tested can be directly filtered from multiple preset road segment data included in the electronic map. Then, the combined road segment data is obtained based on the multiple preset road segment data and the target road segment data. The multiple cell grids corresponding to the combined road segment data in the electronic map are further preprocessed to obtain the test area, thereby realizing the automatic division of the test area and improving the efficiency and accuracy of the test area division.

[0068] Based on the above embodiments disclosed herein, S120 may specifically include: acquiring multiple centroids corresponding to multiple preset road segment data respectively; and clustering the multiple centroids according to preset clustering parameters to obtain road segment cluster data corresponding to the multiple preset road segment data.

[0069] In this embodiment of the disclosure, the centroid can be the center point of the preset road segment data, or a point in the preset road segment that is equidistant from both ends of the road segment.

[0070] In this embodiment of the disclosure, obtaining multiple centroids corresponding to multiple preset road segment data may specifically include: selecting the road segment center point corresponding to each preset road segment data in the multiple preset road segment data, and using the road segment center point corresponding to the preset road segment data as the centroid corresponding to the preset road segment data.

[0071] In this embodiment of the disclosure, the preset clustering parameters can be set differently depending on the preset clustering method.

[0072] In some embodiments of this disclosure, when the preset clustering method is to cluster according to density, the preset clustering parameters can be a preset clustering radius and a preset number of clusters.

[0073] In some other embodiments of this disclosure, when the preset clustering method is a grid-based clustering method, the preset clustering parameter can be a preset grid density.

[0074] Specifically, the first step is to perform clustering based on a grid, that is, to divide the data space into a finite number of cells; the second step is to randomly select a target cell from all the cells and calculate the road segment density in the target cell; the third step is to mark the target cell as a new cluster and establish the corresponding cluster if the road segment density in the target cell is greater than the preset grid density, calculate the road segment density in all neighboring cells of the target cell, and if the road segment density in a neighboring cell is greater than the preset grid density, add it to the cluster. The second and third steps are repeated until all cells are traversed.

[0075] In some embodiments of this disclosure, when the preset clustering method is model-based clustering, the preset clustering parameters can be a preset model or a preset density distribution function corresponding to the preset model.

[0076] Specifically, model-based clustering assumes that the distribution of data conforms to a series of probability distributions and uses a preset model or a preset density distribution function corresponding to the preset model to cluster the data.

[0077] In this embodiment of the disclosure, after obtaining multiple centroids corresponding to multiple preset road segment data, the electronic device can cluster the multiple centroids according to preset clustering parameters to obtain road segment cluster data corresponding to the multiple preset road segment data.

[0078] In some embodiments of this disclosure, the electronic device can cluster multiple centroids according to a preset clustering radius and a preset number of clusters, thereby obtaining road segment cluster data corresponding to multiple preset road segment data.

[0079] In other embodiments of this disclosure, the electronic device can cluster the grids corresponding to multiple centroids according to a preset grid density, thereby obtaining road segment cluster data corresponding to multiple preset road segment data.

[0080] In some embodiments of this disclosure, the electronic device can cluster multiple centroid-corresponding models according to a preset model and a preset density distribution function corresponding to the preset model, thereby obtaining road segment cluster data corresponding to multiple preset road segment data.

[0081] In this embodiment of the disclosure, the electronic device can acquire multiple centroids corresponding to multiple preset road segment data respectively, and cluster the multiple centroids according to preset clustering parameters to obtain road segment cluster data corresponding to multiple preset road segment data. Thus, during the test area division process, multiple preset road segment data can be clustered according to a preset clustering method, further improving the accuracy and consistency of test area division.

[0082] In this embodiment of the disclosure, clustering multiple centroids according to preset clustering parameters to obtain road segment cluster data corresponding to multiple preset road segment data may specifically include: clustering multiple centroids according to preset clustering radius and preset clustering number to obtain multiple non-isolated point centroids; and determining multiple road segment data corresponding to multiple non-isolated point centroids as road segment cluster data corresponding to multiple preset road segment data.

[0083] Figure 2 This is a schematic diagram of road segment data clustering provided in an embodiment of this disclosure. The following will describe it in detail. Figure 2 The embodiments of this disclosure will be described.

[0084] In this embodiment of the disclosure, the centroid of a non-isolated point can be a core point or a boundary point. The core centroid is defined as the first centroid, which is a circle with a predetermined number of other centroids within a predetermined clustering radius. The boundary centroid is defined as the second centroid, which is a circle with a predetermined number of other centroids within a predetermined clustering radius. However, the second centroid is located within a circle with the first centroid as its center and the predetermined clustering radius as its radius. In this case, the second centroid is defined as the boundary centroid.

[0085] like Figure 2 As shown, points A, B, C, and D represent the centroids corresponding to different preset road segment data. Here, we assume the preset cluster size is 3 and the preset cluster radius is r. A circle is drawn with point A as the center and the preset cluster radius r as the radius, resulting in the circle corresponding to point A. We then count whether there are any other centroids within the circle corresponding to point A that satisfy the preset cluster size. We find that the circle corresponding to point A contains 5 centroids, meaning there are enough other centroids to satisfy the preset cluster size. Next, we select point B within the circle corresponding to point A and draw a circle with the same preset cluster radius r, resulting in the circle corresponding to point B. The circle corresponding to point B contains 4 centroids, meaning it also contains the preset cluster size. Next, we select point C within the circle corresponding to point B and draw a circle with the same preset cluster radius r, resulting in the circle corresponding to point C. The circle corresponding to point C contains 2 centroids, meaning there are no other centroids to satisfy the preset cluster size. At this point, we stop clustering. Points A and B are called core centroids, and point C is called a boundary centroid. Figure 2 As shown, point D is neither inside the circle corresponding to points A, B, and C, nor does it meet the preset clustering number requirement for other centroids within the circle centered at point D and with a preset clustering radius r. In this case, point D is called an isolated centroid. Therefore, when clustering multiple centroids, only points A, B, and C, and the multiple other centroids within their respective circles are considered, while point D is not considered. The road segment data corresponding to points A, B, and C, and the multiple other centroids within their respective circles are determined as the road segment cluster data corresponding to multiple preset road segment data.

[0086] In this embodiment of the disclosure, the electronic device can cluster multiple centroids according to a preset clustering radius and a preset number of clusters to obtain multiple non-isolated point centroids. The multiple road segment data corresponding to the multiple non-isolated point centroids are determined as road segment cluster data corresponding to multiple preset road segment data, thereby improving the accuracy of the obtained road segment cluster data.

[0087] In this embodiment of the disclosure, S150, which involves preprocessing multiple cell grids to obtain boundary points and using the connection of the boundary points to determine the test area, may specifically include: obtaining multiple cell centroids corresponding to the multiple cell grids; generating a circle corresponding to each cell centroid, and determining the area where the circle is located in the electronic map as the target buffer area corresponding to the cell centroid; obtaining boundary points based on the target buffer areas corresponding to the multiple cell centroids, and using the connection of the boundary points to determine the test area.

[0088] In this embodiment of the disclosure, the centroid of the mesh can be the center point of the cell mesh, wherein the center point can be the intersection of the two diagonals of the cell mesh.

[0089] In this embodiment of the disclosure, obtaining the centroids of multiple cell grids corresponding to multiple cell grids may specifically include: obtaining the center point corresponding to each cell grid in the multiple cell grids, and determining the center point corresponding to the cell grid as the centroid of the cell grid.

[0090] Specifically, after acquiring multiple cell grids, the electronic device determines the center point corresponding to each cell grid and defines the center point corresponding to each cell grid as the centroid of the cell grid.

[0091] In this embodiment of the disclosure, generating a circle corresponding to each of the multiple mesh centroids may specifically include: taking each of the multiple mesh centroids as the center of a circle and using a preset distance as the radius to generate a circle corresponding to the mesh centroid.

[0092] In this embodiment of the disclosure, the preset distance can be a pre-set distance, wherein the preset distance can be set differently as needed.

[0093] Specifically, after acquiring multiple grid centroids, the electronic device takes each grid centroid as its center and a preset distance as its radius to form a circle with the grid centroid as its center. This circle is then identified as the circle corresponding to the grid centroid. The area where the circle is located on the electronic map is then identified as the target buffer area corresponding to the grid centroid. Boundary points are obtained based on the target buffer areas corresponding to the multiple grid centroids, and the test area is determined by connecting the boundary points.

[0094] In this embodiment of the disclosure, the electronic device can select the center point of each unit grid in multiple unit grids as the centroid of the unit grid, generate a circle corresponding to the centroid of the grid with a preset distance as the radius, determine the target buffer area corresponding to the centroid of the grid based on the area where the circle is located in the electronic map, and then obtain the boundary points based on the target buffer areas corresponding to multiple centroids respectively. The test area can be determined by connecting the boundary points, thereby further improving the accuracy of the test area division.

[0095] In this embodiment of the disclosure, the boundary points are obtained based on the target buffer regions corresponding to the centroids of multiple meshes, and the test region is determined by connecting the boundary points. Specifically, this includes: for each target buffer region corresponding to the centroids of multiple meshes, equidistant sampling is performed from the circle corresponding to the target buffer region to obtain multiple target sampling points corresponding to the target buffer region; based on the multiple target sampling points corresponding to the target buffer regions corresponding to the centroids of multiple meshes, the outermost point of the target buffer region corresponding to the centroids of multiple meshes is calculated using the convex hull algorithm, and the outermost point is determined as the boundary point; the region formed by connecting the boundary points is determined as the test region.

[0096] In this embodiment of the disclosure, the convex hull algorithm can be the Graham scan convex hull algorithm, and there is no limitation herein.

[0097] Specifically, after acquiring the target buffer regions corresponding to multiple mesh centroids, the electronic device performs equidistant sampling from the circle corresponding to each target buffer region. The sampling distance is preset and can be set differently as needed, thereby obtaining multiple target sampling points corresponding to the target buffer region. The convex hull algorithm is used to calculate the outermost point of the target buffer region corresponding to the multiple mesh centroids, and the outermost point is determined as the boundary point. The region formed by connecting the boundary points is then determined as the test region.

[0098] Figure 3 This is a schematic diagram of a convex hull algorithm provided in an embodiment of this disclosure. The following is in conjunction with... Figure 3 The embodiments of this disclosure will be described in detail.

[0099] like Figure 3As shown, points P0 to P8 represent multiple target sampling points corresponding to the target buffer regions corresponding to multiple mesh centroids. Placing these sampling points in a two-dimensional coordinate system, the point with the smallest ordinate must be a point on the convex hull, as shown by P0 in the figure. Therefore, taking P0 as the origin, the depression angle 'a' of the other sampling points relative to P0 is calculated. When the depression angle 'a' is the same, the points closer to P0 are ranked first. Thus, as shown in the figure, sorting the sampling points according to the order of depression angle 'a' from smallest to largest yields the following results: P1, P2, P3, P4, P5, P6, P7, P8. P1 and P8 are definitely points on the convex hull. Then, the convex hull algorithm is used to solve for P2 to P7 sequentially, ultimately obtaining the outermost points of the target buffer regions corresponding to the multiple mesh centroids as P0, P1, P3, P6, P7, P8. Connecting P0, P1, P3, P6, P7, and P8 sequentially forms a polygonal region, i.e. Figure 3 The area enclosed by the black lines is designated as the testing area.

[0100] In this embodiment of the disclosure, the electronic device can use the convex hull algorithm to calculate the outermost point of the target buffer region corresponding to the centroids of multiple grids, and then obtain the test region based on the outermost point. This can improve the accuracy of test region division while also increasing the flexibility of test region division.

[0101] Figure 4 This is a flowchart of another test area division method provided in this embodiment.

[0102] like Figure 4 As shown, the test area division method provided in this embodiment includes the following steps:

[0103] S410. Select the target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map.

[0104] S420. Select the center point of each preset road segment data in multiple preset road segment data, and take the center point of the preset road segment data as the centroid of the preset road segment data.

[0105] S430. Cluster multiple centroids according to the preset cluster radius and preset cluster number to obtain road segment cluster data corresponding to multiple preset road segment data.

[0106] S440. Perform a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data.

[0107] S450. Determine multiple cell grids in the electronic map that correspond to the combined road segment data.

[0108] S460. Obtain the center point of each cell in multiple cell grids, and determine the center point of each cell grid as the centroid of the cell grid.

[0109] S470. Using each of the multiple grid centroids as the center of a circle and a preset distance as the radius, generate a circle corresponding to the grid centroid, and determine the area where the circle is located in the electronic map as the target buffer area corresponding to the grid centroid.

[0110] S480. For each target buffer region corresponding to the centroids of multiple grids, perform equidistant sampling from the circle corresponding to the target buffer region to obtain multiple target sampling points corresponding to the target buffer region.

[0111] S490. Based on the target sampling points corresponding to the target buffer areas corresponding to the centroids of multiple grids, the outermost point of the target buffer area corresponding to the centroids of multiple grids is calculated using the convex hull algorithm, and the outermost point is determined as the boundary point.

[0112] S4010. The area formed by connecting the boundary points is determined as the area to be tested.

[0113] In this embodiment, it should be noted that the specific implementation of S410-S4010 is similar to the above-described implementation, and will not be repeated here.

[0114] In this embodiment, the electronic device can filter target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map, determine the center point of the road segment corresponding to each of the multiple preset road segment data as the centroid of the preset road segment data, and then cluster the multiple centroids according to a preset clustering radius and a preset clustering number to obtain road segment cluster data corresponding to the multiple preset road segment data. It can also determine multiple cell grids corresponding to the union road segment data obtained by performing a union operation on the target road segment data and the road segment cluster data in the electronic map, select the cell centroids of the multiple cell grids, and then determine the target buffer areas corresponding to the multiple cell centroids. Finally, it can use the convex hull algorithm to obtain the area to be tested. Thus, on the basis of realizing the automatic division of the test area, the efficiency and accuracy of the test area division are further improved.

[0115] Figure 5 This is a schematic diagram of a test area division device provided in an embodiment of this disclosure. The test area division device in this embodiment can be installed in an electronic device, which can be a server, a terminal, or a server cluster. Specifically, the terminal includes vehicle-mounted terminals, mobile phones, computers, or tablet computers, etc., and is not limited thereto.

[0116] like Figure 5As shown, the test area division device 500 may include a road segment screening module 510, a road segment clustering module 520, a union operation module 530, a grid determination module 540, and a preprocessing module 550.

[0117] The road segment filtering module 510 can be used to filter target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map.

[0118] The road segment clustering module 520 can be used to cluster multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data.

[0119] The union operation module 530 can be used to perform a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data.

[0120] The grid determination module 540 can be used to determine multiple cell grids in an electronic map that correspond to the combined road segment data.

[0121] The preprocessing module 550 can be used to preprocess multiple cell meshes to obtain boundary points, and use the connection of the boundary points to determine the test area.

[0122] In this embodiment, the target road segment data of the road segment to be tested can be filtered from multiple preset road segment data included in the electronic map. The multiple preset road segment data are clustered to obtain road segment cluster data corresponding to the multiple preset road segment data. The target road segment data and the road segment cluster data are combined to obtain the combined road segment data. After obtaining the combined road segment data, multiple cell grids corresponding to the combined road segment data in the electronic map are determined. The multiple cell grids are preprocessed to obtain boundary points. The test area is determined by connecting the boundary points. Thus, the target road segment data of the road segment to be tested can be directly filtered from multiple preset road segment data included in the electronic map. Then, the combined road segment data is obtained based on the multiple preset road segment data and the target road segment data. The multiple cell grids corresponding to the combined road segment data in the electronic map are further preprocessed to obtain the test area, thereby realizing the automatic division of the test area and improving the efficiency and accuracy of the test area division.

[0123] In some embodiments of this disclosure, the road segment clustering module 520 may include a centroid acquisition unit 5201 and a centroid clustering unit 5202.

[0124] The centroid acquisition unit 5201 can be used to acquire multiple centroids corresponding to multiple preset road segment data.

[0125] The centroid clustering unit 5202 can be used to cluster multiple centroids according to preset clustering parameters to obtain road segment cluster data corresponding to multiple preset road segment data.

[0126] In some embodiments of this disclosure, the centroid acquisition unit 5201 may be specifically used to select the center point of each preset road segment data in a plurality of preset road segment data, and use the center point of the road segment corresponding to the preset road segment data as the centroid of the preset road segment data.

[0127] In some embodiments of this disclosure, the preset clustering parameters include a preset clustering radius and a preset number of clusters.

[0128] In some embodiments of this disclosure, the preprocessing module 550 may include a mesh centroid acquisition unit 5501, a mesh centroid processing unit 5502, and a test area determination unit 5503.

[0129] The mesh centroid acquisition unit 5501 can be used to acquire multiple mesh centroids corresponding to multiple unit meshes.

[0130] The grid centroid processing unit 5502 can be used to generate a circle corresponding to each of the multiple grid centroids, and determine the area where the circle is located in the electronic map as the target buffer area corresponding to the grid centroid.

[0131] The test area determination unit 5503 can be used to obtain boundary points based on the target buffer areas corresponding to multiple mesh centroids, and to determine the test area by connecting the boundary points.

[0132] In some embodiments of this disclosure, the mesh centroid acquisition unit 5501 can be specifically used to acquire the center point corresponding to each of the multiple cell meshes, and determine the center point corresponding to the cell mesh as the centroid of the cell mesh.

[0133] In some embodiments of this disclosure, the mesh centroid processing unit 5502 can be specifically used to take each of the multiple mesh centroids as the center of a circle and generate a circle corresponding to the mesh centroid with a preset distance as the radius.

[0134] In some embodiments of this disclosure, the test area determination unit 5503 may include a sampling subunit, a calculation subunit, and a determination subunit.

[0135] This sampling sub-unit can be used to perform equidistant sampling from the circle corresponding to the target buffer region for each target buffer region corresponding to multiple grid centroids, thereby obtaining multiple target sampling points corresponding to the target buffer region.

[0136] This computational subunit can be used to calculate the outermost point of the target buffer region corresponding to the target sampling points in the target buffer region corresponding to the centroids of multiple grids, and determine the outermost point as the boundary point.

[0137] This defined sub-unit can be used to connect boundary points to form a region, which is then defined as the region to be tested.

[0138] It should be noted that, Figure 5 The test area division device 500 shown can execute the various steps in the above method embodiments and realize the various processes and effects in the above method embodiments, which will not be elaborated here.

[0139] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown.

[0140] In this embodiment of the disclosure, Figure 6 The electronic devices shown can be servers, terminals, or server clusters. Terminals specifically include in-vehicle terminals, mobile phones, computers, or tablets, etc., without limitation.

[0141] like Figure 6 As shown, the electronic device may include a processor 610 and a memory 620 storing computer program instructions.

[0142] Specifically, the processor 610 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0143] Memory 620 may include a large-capacity storage for information or instructions. For example, and not limitingly, memory 620 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 620 may include removable or non-removable (or fixed) media. Where appropriate, memory 620 may be internal or external to the integrated gateway device. In a particular embodiment, memory 620 is a non-volatile solid-state memory. In a particular embodiment, memory 620 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0144] The processor 610 reads and executes computer program instructions stored in the memory 620 to perform the steps of the test area division method provided in this embodiment of the disclosure.

[0145] In one example, the electronic device may also include a transceiver 630 and a bus 640. Wherein, as... Figure 6 As shown, the processor 610, memory 620 and transceiver 630 are connected via bus 640 and communicate with each other.

[0146] Bus 640 may include hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 640 may include one or more buses.

[0147] This disclosure also provides a computer-readable storage medium that can store a computer program that, when executed by a processor, enables the processor to implement the test area division method provided in this disclosure.

[0148] The aforementioned storage medium may, for example, include a memory 620 containing computer program instructions, which can be executed by a processor 610 of an electronic device to complete the test area partitioning method provided in this embodiment. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0149] This disclosure also provides a vehicle that includes electronic devices that can implement the various processes and effects described in the above embodiments of this disclosure, which will not be elaborated here.

[0150] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for dividing a test region, characterized in that, The method includes: Select the target road segment data for the test segment from multiple preset road segment data included in the electronic map; Cluster the multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data; Perform a union operation between the target road segment data and the road segment cluster data to obtain the union road segment data; Determine multiple cell grids in the electronic map that correspond to the unioned road segment data; The multiple unit grids are preprocessed to obtain boundary points, and the test area is determined by connecting the boundary points. The step of preprocessing the multiple cell meshes to obtain boundary points, and using the lines connecting the boundary points to determine the test area, includes: Obtain the centroids of the multiple unit grids respectively; For each of the multiple grid centroids, a circle corresponding to the grid centroid is generated, and the area where the circle is located in the electronic map is determined as the target buffer area corresponding to the grid centroid. For each target buffer region corresponding to the centroids of the plurality of grids, equidistant sampling is performed from the circle corresponding to the target buffer region to obtain a plurality of target sampling points corresponding to the target buffer region; Based on the multiple target sampling points corresponding to the target buffer regions corresponding to the multiple grid centroids respectively, the outermost point of the target buffer region corresponding to the multiple grid centroids is calculated using the convex hull algorithm, and the outermost point is determined as the boundary point; The region formed by connecting the boundary points is defined as the region to be tested.

2. The method according to claim 1, characterized in that, The step of clustering the multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data includes: Obtain the multiple centroids corresponding to the multiple preset road segment data respectively; According to preset clustering parameters, the multiple centroids are clustered to obtain road segment cluster data corresponding to the multiple preset road segment data.

3. The method according to claim 2, characterized in that, The step of obtaining multiple centroids corresponding to the multiple preset road segment data includes: Select the center point of each preset road segment data in the plurality of preset road segment data, and take the center point of the preset road segment data as the centroid of the preset road segment data.

4. The method according to claim 2, characterized in that, The preset clustering parameters include the preset clustering radius and the preset number of clusters.

5. The method according to claim 1, characterized in that, The step of obtaining the multiple centroids corresponding to the multiple unit grids includes: Obtain the center point corresponding to each of the multiple unit grids, and determine the center point corresponding to the unit grid as the centroid of the unit grid.

6. The method according to claim 1, characterized in that, The step of generating a circle corresponding to each of the plurality of mesh centroids includes: Using each of the multiple mesh centroids as the center of a circle, and with a preset distance as the radius, generate a circle corresponding to the mesh centroid.

7. A test area division device, characterized in that, include: The road segment filtering module is used to filter target road segment data of the road segment to be tested from multiple preset road segment data included in the electronic map; The road segment clustering module is used to cluster the multiple preset road segment data to obtain road segment cluster data corresponding to the multiple preset road segment data; The union operation module is used to perform a union operation on the target road segment data and the road segment cluster data to obtain the union road segment data; A grid determination module is used to determine multiple cell grids in the electronic map that correspond to the union road segment data; The preprocessing module is used to preprocess the multiple unit meshes to obtain boundary points, and to determine the test area by connecting the boundary points. The preprocessing module is specifically used to obtain the centroids of the multiple cell grids corresponding to the multiple unit grids; For each of the multiple grid centroids, a circle corresponding to the grid centroid is generated, and the area where the circle is located in the electronic map is determined as the target buffer area corresponding to the grid centroid. For each target buffer region corresponding to the centroids of the plurality of grids, equidistant sampling is performed from the circle corresponding to the target buffer region to obtain a plurality of target sampling points corresponding to the target buffer region; Based on the multiple target sampling points corresponding to the target buffer regions corresponding to the multiple grid centroids respectively, the outermost point of the target buffer region corresponding to the multiple grid centroids is calculated using the convex hull algorithm, and the outermost point is determined as the boundary point; The region formed by connecting the boundary points is defined as the region to be tested.

8. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-6.

10. A vehicle, characterized in that, Including the electronic device as described in claim 8.

Images