Lane matching apparatus and method, and intelligent vehicle

Abstract

A lane matching apparatus and method, and an intelligent vehicle, which relate to the technical field of data processing. The lane matching apparatus may: acquire a first lane group of a first data source and a second lane group of a second data source (S901); obtain N first closed polygons on the basis of the first lane group, and obtain M second closed polygons on the basis of the second lane group (S902); and determine a matching result between the first lane group and the second lane group on the basis of an overlapping relationship between the N first closed polygons and the M second closed polygons (S903). By means of the lane matching apparatus, the correlation between lanes can be determined by means of the relationship between polygons formed by the lanes, thereby realizing accurate matching of heterologous lane data.

Description

Lane matching device, method and intelligent vehicle

[0001] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on August 25, 2023, with application number 202311087019.X and application name “A lane matching device, method and intelligent vehicle,” the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0002] The present application relates to the field of data processing, and in particular to a lane matching device, method and intelligent vehicle. Background Art

[0003] Currently, with the continuous improvement of intelligent driving technology, the demand for lane data is also increasing. At present, lane data can be detected based on the installed sensors in each vehicle. The data detected in this way is crowdsourced data, which is lane data with different accuracy or different sources.

[0004] To evaluate the accuracy of crowdsourced data, lane matching must be performed on lane data from different crowdsourced data sources. Lane matching can then be used to evaluate the accuracy of lane data. Currently, lane matching can be achieved through intersection matching.

[0005] Specifically, intersection matching uses the intersection as a root match. This means that the intersection's associated roads can be matched based on the intersection's shape point location, the number of associated roads, and the names of each road. However, this approach requires that all associated roads are complete; no road can be missing, and each road's attributes and names must be complete. This results in inefficient and inaccurate lane data matching.

[0006] Summary of the Invention

[0007] The present application provides a lane matching device, method and intelligent vehicle to avoid the problem of low matching accuracy caused by lane matching through intersection matching.

[0008] In a first aspect, the present application provides a lane matching device, comprising a processor and a memory, wherein the memory is configured to store a program executable by the processor, and the processor is configured to read the program in the memory and perform the following steps:

[0009] Obtaining a first lane group from a first data source and a second lane group from a second data source, wherein the first lane group and the second lane group include at least two lanes;

[0010] Obtain N first closed polygons based on the first lane group, and obtain M second closed polygons based on the second lane group, wherein the first closed polygons are composed of adjacent lanes in the first lane group, the second closed polygons are composed of adjacent lanes in the second lane group, and M and N are integers greater than or equal to 1;

[0011] A matching result between the first lane group and the second lane group is determined based on an overlapping relationship between the N first closed polygons and the M second closed polygons.

[0012] Through the above-mentioned device, the association between lanes can be determined by the overlapping relationship of the polygons composed of lanes, thereby achieving accurate matching of heterogeneous lane data, thereby avoiding the problem of low matching accuracy caused by lane matching through intersection matching.

[0013] In an optional embodiment, the processor is specifically configured to execute:

[0014] Constructing a bipartite graph based on the N first closed polygons and the M second closed polygons, wherein the N first closed polygons serve as a first vertex set in the bipartite graph, the M second closed polygons serve as a second vertex set in the bipartite graph, a line between the first vertex set and the second vertex set in the bipartite graph represents an overlapping relationship between the first closed polygon and the second closed polygon, and a weight of the line in the bipartite graph is an overlapping area value;

[0015] Calculating a global optimal solution of the bipartite graph, wherein a target bipartite graph corresponding to the global optimal solution includes a one-to-one correspondence between N first closed polygons and M second closed polygons;

[0016] Based on a target bipartite graph corresponding to the global optimal solution, a matching result between the first lane group and the second lane group is determined.

[0017] The above method can determine the accurate matching relationship by calculating the optimal solution of the bipartite graph, thereby ensuring the accuracy of subsequent lane group matching.

[0018] In an optional embodiment, the processor is specifically configured to execute:

[0019] Splitting the bipartite graph into a plurality of candidate bipartite graphs, wherein each of the candidate bipartite graphs contains a one-to-one correspondence between N first closed polygons and M second closed polygons;

[0020] Calculate the overlapping area between the first closed polygon and the second closed polygon in each selected bipartite graph, wherein the overlapping area exists between the first closed polygon and the second closed polygon that are in a connected relationship in the selected bipartite graph;

[0021] Calculating the total overlapping area corresponding to each candidate bipartite graph, wherein the total overlapping area is the sum of the overlapping areas of all first closed polygons and second closed polygons in the candidate bipartite graph that have an overlapping relationship;

[0022] The candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

[0023] In an optional embodiment, the processor is specifically configured to execute:

[0024] Determine the area to be measured in the map data;

[0025] taking all lanes in the area to be tested that contain the first data source identifier as the first lane group; and

[0026] All lanes in the area to be detected that contain the second data source identifier are taken as a second lane group.

[0027] In an optional embodiment, the processor is specifically configured to execute:

[0028] sequentially connecting each two adjacent lanes in the first lane group end to end to obtain N first closed polygons with the adjacent lanes as edges; and

[0029] Each two adjacent lanes in the second lane group are sequentially connected end to end to obtain M second closed polygons with the adjacent lanes as edges.

[0030] In a second aspect, the present application provides a lane matching method, the method comprising:

[0031] Obtaining a first lane group from a first data source and a second lane group from a second data source, wherein the first lane group and the second lane group include at least two lanes;

[0032] Obtain N first closed polygons based on the first lane group, and obtain M second closed polygons based on the second lane group, wherein the first closed polygons are composed of adjacent lanes in the first lane group, the second closed polygons are composed of adjacent lanes in the second lane group, and M and N are integers greater than or equal to 1;

[0033] A matching result between the first lane group and the second lane group is determined based on an overlapping relationship between the N first closed polygons and the M second closed polygons.

[0034] In an optional embodiment, determining a matching result between the first lane group and the second lane group based on the N first closed polygons and the M second closed polygons includes:

[0035] Constructing a bipartite graph based on the N first closed polygons and the M second closed polygons, wherein the N first closed polygons serve as a first vertex set in the bipartite graph, the M second closed polygons serve as a second vertex set in the bipartite graph, a line between the first vertex set and the second vertex set in the bipartite graph represents an overlapping relationship between the first closed polygon and the second closed polygon, and a weight of the line in the bipartite graph is an overlapping area value;

[0036] Calculating a global optimal solution of the bipartite graph, wherein a target bipartite graph corresponding to the global optimal solution includes a one-to-one correspondence between N first closed polygons and M second closed polygons;

[0037] Based on a target bipartite graph corresponding to the global optimal solution, a matching result between the first lane group and the second lane group is determined.

[0038] In an optional embodiment, calculating the global optimal solution of the bipartite graph includes:

[0039] Splitting the bipartite graph into a plurality of candidate bipartite graphs, wherein each of the candidate bipartite graphs contains a one-to-one correspondence between N first closed polygons and M second closed polygons;

[0040] Calculate the overlapping area between the first closed polygon and the second closed polygon in each selected bipartite graph, wherein the overlapping area exists between the first closed polygon and the second closed polygon that are in a connected relationship in the selected bipartite graph;

[0041] Calculating the total overlapping area corresponding to each candidate bipartite graph, wherein the total overlapping area is the sum of the overlapping areas of all first closed polygons and second closed polygons in the candidate bipartite graph that have an overlapping relationship;

[0042] The candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

[0043] In a third aspect, the present application provides an intelligent vehicle, which includes any one of the lane matching devices described above.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, any one of the above-mentioned lane matching methods is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic structural diagram of a lane matching device provided in this application;

[0046] FIG2 is a schematic diagram of lanes in the area to be detected provided by this application;

[0047] FIG3 is a schematic diagram of the middle lane of the first lane group provided by this application;

[0048] FIG4 is a schematic diagram of the middle lane of the second lane group provided by this application;

[0049] FIG5 is a schematic diagram of a first closed polygon formed by adjacent lanes in a first lane group provided by the present application;

[0050] FIG6 is a bipartite graph provided by the present application consisting of N first closed polygons and M second closed polygons;

[0051] FIG7 is a bipartite graph formed by the first lane group and the second lane group provided by the present application;

[0052] FIG8 is a schematic diagram of the overlapping area between a first closed polygon and a second closed polygon provided by the present application;

[0053] FIG9a is a schematic diagram of a bipartite graph provided by this application;

[0054] FIG9 b is a schematic diagram of another bipartite graph provided by this application;

[0055] FIG10 is a flow chart of a lane matching method provided in this application. DETAILED DESCRIPTION

[0056] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0057] In embodiments of the present invention, the term "and / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0058] The application scenarios described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Persons skilled in the art will appreciate that as new application scenarios emerge, the technical solutions provided by the embodiments of the present invention will also be applicable to similar technical problems. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0059] Currently, evaluating the accuracy of crowdsourced data requires lane matching across lane data from different crowdsourced sources. This lane matching relies on intersection matching, which matches roads associated with intersections based on the location of intersection shape points, the number of associated roads, and the names of each road. However, intersection matching requires that all associated roads are complete; no road can be missing, and every road's attributes and name must be complete. This results in inefficient and inaccurate lane data matching.

[0060] In order to solve the above-mentioned technical problems, the present application provides a lane matching device, which first obtains a first lane group from a first data source and a second lane group from a second data source, obtains N first closed polygons and M second closed polygons based on the first lane group and the second lane group, and determines the matching result between the first lane group and the second lane group based on the overlapping relationship between the N first closed polygons and the M second closed polygons.

[0061] Through the above-mentioned device, the association between lanes can be determined by the polygons composed of lanes, thereby achieving accurate matching of heterogeneous lane data, thereby avoiding the problem of low matching accuracy caused by lane matching through intersection matching.

[0062] FIG1 shows a lane matching device according to an embodiment of the present application. The device includes a processor 10 and a memory 11. The memory 11 is used to store a program executable by the processor 10. The processor 10 is used to read the program in the memory 10 and execute the following steps:

[0063] Obtain a first lane group from a first data source and a second lane group from a second data source;

[0064] Obtaining N second closed polygons based on the first lane group, and obtaining M second closed polygons based on the second lane group;

[0065] A matching result between the first lane group and the second lane group is determined based on an overlapping relationship between the N first closed polygons and the M second closed polygons.

[0066] Specifically, in an embodiment of the present application, a first lane group from a first data source and a second lane group from a second data source are first obtained. The first data source and the second data source here can be any data source such as a vehicle, a server, a database, etc.

[0067] After receiving the lane data uploaded by the first data source and the second data source, an area to be detected is determined in the map data containing the lane data, and then all lanes uploaded by the first data source are determined in the area to be detected, and all the lanes are used as a first lane group.

[0068] It should be noted here that the first data source includes a first data source identifier, so that all lanes including the first data source identifier can be used as the first lane group.

[0069] Similarly, a second lane group corresponding to the second data source is determined in the area to be detected, that is, all lanes identified by the second data source are included as the second lane group. The first lane group and the second lane group include at least two lanes.

[0070] Additionally, in this embodiment of the present application, the second lane group can also be derived based on the first lane group. Specifically, after determining all lanes in the first lane group, the adjacent lanes from the second data source are determined for each lane in the first data source, and these determined lanes are used as the second lane group. In this embodiment of the present application, the lane closest to the first lane in the second lane group can be determined, and all lanes in the second lane group can be screened using this screening method.

[0071] For example, as shown in Figure 2, the area to be inspected includes lanes from different data sources. The thick lines represent lanes from the first data source, namely, lanes 1, 3, and 5, while the thin lines represent lanes from the second data source, namely, lanes 2, 4, and 6. First, all lanes from the first data source are considered the first lane group. Then, the lanes closest to the lanes in the first lane group and belonging to the second data source are sequentially determined. In Figure 2, lane 2 is the lane closest to lane 1 and belonging to the second data source. Following this approach, lanes 4 and 6 can be determined. Lanes 2, 4, and 6 are then combined to form the second lane group. This results in the first lane group shown in Figure 3 and the second lane group shown in Figure 4.

[0072] Of course, in the embodiment of the present application, the lane group can also be determined directly based on the data source identifier, that is, all lanes in the area to be tested that contain the first data source identifier are used as the first lane group; and all lanes in the area to be tested that contain the second data source identifier are used as the second lane group.

[0073] After determining the first and second lane groups, N first closed polygons are generated based on the first lane group. In this embodiment of the present application, the first closed polygons are formed based on two adjacent lane groups within the first lane group. For example, as shown in Figure 5, lanes 1 and 3 are adjacent lanes within the first lane group. Connecting lanes 1 and 3 end-to-end forms a polygon, which serves as the first closed polygon. Similarly, connecting lanes 3 and 5 end-to-end forms another first closed polygon. In this way, adjacent lanes within the first lane group can be combined to form first closed polygons, ultimately resulting in N first closed polygons.

[0074] Similarly, each adjacent pair of lanes in the second lane group is connected end-to-end, resulting in M ​​second closed polygons with adjacent lanes as edges. This process is consistent with the above process and will not be repeated here. It should be noted that N and M can be equal or unequal. In specific application scenarios, the value of N is determined by the number of lanes in the first lane group, and the value of M is determined by the number of lanes in the second lane group.

[0075] After obtaining N first closed polygons based on the lanes in the first lane group and M second closed polygons based on the lanes in the second lane group, a bipartite graph is constructed based on the N first closed polygons and the M second closed polygons. Specifically, the N first closed polygons constitute the first vertex set in the bipartite graph, and the M second closed polygons constitute the second vertex set in the bipartite graph. The lines between the first vertex set and the second vertex set in the bipartite graph represent the overlapping relationship between the first closed polygon and the second closed polygon, and the weight of the lines in the bipartite graph is the overlapping area value. If there is overlap between the two closed polygons, the weight of the line between the two closed polygons is the overlapping area value; if there is no overlap between the two closed polygons, the weight of the line between the two closed polygons is 0.

[0076] Determine whether one of the N first closed polygons overlaps with each of the M second closed polygons. If so, calculate the overlapping area between each first closed polygon and another second closed polygon. Repeat this method for all N first closed polygons and M second closed polygons, and then calculate the overlapping area of ​​all permutations and combinations.

[0077] As shown in Figure 6, in Figure 6, the first vertex set in the bipartite graph is composed of N first closed polygons, namely, a1, a2, a3... aN, where a1, a2, a3... aN each represent a first closed polygon; the second vertex set is composed of M first closed polygons, namely, b1, b2, b3... bM, where b1, b2, b3... bM each represent a second closed polygon. There are multiple connecting lines between the first vertex set and the second vertex set, and these connecting lines represent the overlapping relationship between the first closed polygon and the second closed polygon. The weights on the connecting lines represent the overlapping area of ​​the first polygon and the second polygon.

[0078] For example, based on the inspection area shown in Figure 2, we can obtain the bipartite graph shown in Figure 7. In this bipartite graph, the first vertex set includes a first closed polygon formed by lanes 1 and 3, and another first closed polygon formed by lanes 3 and 5. The second vertex set includes a second closed polygon formed by lanes 2 and 4, and another second closed polygon formed by lanes 4 and 6.

[0079] The relationship between the first vertex set and the second vertex set is as follows:

[0080] The overlapping area between the first closed polygon formed by lanes 1 and 3 and the second closed polygon formed by lanes 2 and 4 is shown in FIG8 ;

[0081] The overlapping area between the first closed polygon formed by lanes 1 and 3 and the second closed polygon formed by lanes 4 and 6;

[0082] The overlapping area between the first closed polygon formed by lanes 3 and 5 and the second closed polygon formed by lanes 2 and 4;

[0083] The overlapping area between the first closed polygon formed by lanes 3 and 5 and the second closed polygon formed by lanes 4 and 6;

[0084] After obtaining the bipartite graph, the global optimal solution of the bipartite graph is calculated. The specific calculation method of the global optimal solution is as follows:

[0085] Split the bipartite graph into multiple candidate bipartite graphs. Each candidate bipartite graph contains a one-to-one correspondence between N first closed polygons and M second closed polygons. Calculate the overlapping area between the first and second closed polygons in each candidate bipartite graph. The sum of the overlapping areas of all first and second polygons in the candidate bipartite graphs needs to be calculated.

[0086] After calculating the total overlapping area of ​​each candidate bipartite graph, the candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

[0087] For example, if the first lane group is as shown in Figure 3, the second lane group is as shown in Figure 4, and the resulting bipartite graph is as shown in Figure 7, then the bipartite graph in Figure 7 can be split into the candidate bipartite graphs shown in Figures 9a and 9b. Figures 9a and 9b represent the split bipartite graph, where the first vertex set U represents the lanes corresponding to the first closed polygon, and the second vertex set V represents the lanes corresponding to the second closed polygon. The relationship between the elements of sets U and V is represented by connecting lines, and the overlapping area is represented by the values ​​on the connecting lines.

[0088] As shown in Figures 9a and 9b, the total overlapping area corresponding to the candidate bipartite graph in Figure 9a is 3 + 5 = 8, and the total overlapping area corresponding to the candidate bipartite graph in Figure 9b is 4 + 1 = 5. Therefore, the candidate bipartite graph in Figure 9a is selected as the global optimal solution, and the candidate bipartite graph in Figure 9a is selected as the target bipartite graph. Finally, the matching relationships between the lanes in the candidate bipartite graph are used as the matching relationships between the first lane group and the second lane group.

[0089] Through the above approach, the correlation between lanes can be determined by the overlapping area of ​​the polygons composed of the lanes, thereby achieving accurate matching of heterogeneous lane data, thereby avoiding the problem of low matching accuracy caused by lane matching through intersection matching.

[0090] Of course, in the embodiment of the present application, in addition to first establishing a bipartite graph of all correspondences between the N first closed polygons and the M second closed polygons, then splitting it into multiple bipartite graphs of one-to-one correspondences, and then further determining the total overlapping area, it is also possible to directly establish a one-to-one correspondence between the first closed polygons and the second closed polygons.

[0091] Of course, the above example is only an illustration of a simple scenario and does not limit the scenario in which this application is applied. It can be adjusted according to needs during actual application.

[0092] Based on the same inventive concept, an embodiment of the present application further provides a lane matching method. FIG10 is a flow chart of a lane matching method provided by an embodiment of the present application. The method includes:

[0093] S901, obtaining a first lane group from a first data source and a second lane group from a second data source;

[0094] S902, obtaining N first closed polygons based on the first lane group, and obtaining M second closed polygons based on the second lane group;

[0095] S903 : Determine a matching result between the first lane group and the second lane group based on an overlapping relationship between the N first closed polygons and the M second closed polygons.

[0096] Specifically, in an embodiment of the present application, a first lane group from a first data source and a second lane group from a second data source are first obtained. The first data source and the second data source here can be any data source such as a vehicle, a server, a database, etc.

[0097] After receiving the lane data uploaded by the first data source and the second data source, an area to be detected is determined in the map data containing the lane data, and then all lanes uploaded by the first data source are determined in the area to be detected, and all the lanes are used as a first lane group.

[0098] It should be noted here that the first data source includes a first data source identifier, so that all lanes including the first data source identifier can be used as the first lane group.

[0099] Similarly, a second lane group corresponding to the second data source is determined in the area to be detected, that is, all lanes identified by the second data source are included as the second lane group. The first lane group and the second lane group include at least two lanes.

[0100] Additionally, in this embodiment of the present application, the second lane group can also be derived based on the first lane group. Specifically, after determining all lanes in the first lane group, the adjacent lanes from the second data source are determined for each lane in the first data source, and these determined lanes are used as the second lane group. In this embodiment of the present application, the lane closest to the first lane in the second lane group can be determined, and all lanes in the second lane group can be screened using this screening method.

[0101] For example, as shown in Figure 2, the area to be inspected includes lanes from different data sources. The thick lines represent lanes from the first data source, namely, lanes 1, 3, and 5, while the thin lines represent lanes from the second data source, namely, lanes 2, 4, and 6. First, all lanes from the first data source are considered the first lane group. Then, the lanes closest to the lanes in the first lane group and belonging to the second data source are sequentially determined. In Figure 2, lane 2 is the lane closest to lane 1 and belonging to the second data source. Following this approach, lanes 4 and 6 can be determined. Lanes 2, 4, and 6 are then combined to form the second lane group. This results in the first lane group shown in Figure 3 and the second lane group shown in Figure 4.

[0102] Of course, in the embodiment of the present application, the lane group can also be determined directly based on the data source identifier, that is, all lanes in the area to be tested that contain the first data source identifier are used as the first lane group; and all lanes in the area to be tested that contain the second data source identifier are used as the second lane group.

[0103] After determining the first and second lane groups, N first closed polygons are generated based on the first lane group. In this embodiment of the present application, the first closed polygons are formed based on two adjacent lane groups within the first lane group. For example, as shown in Figure 5, lanes 1 and 3 are adjacent lanes within the first lane group. Connecting lanes 1 and 3 end-to-end forms a polygon, which serves as the first closed polygon. Similarly, connecting lanes 3 and 5 end-to-end forms another first closed polygon. In this way, adjacent lanes within the first lane group can be combined to form first closed polygons, ultimately resulting in N first closed polygons.

[0104] Similarly, each adjacent pair of lanes in the second lane group is connected end-to-end, resulting in M ​​second closed polygons with adjacent lanes as edges. This process is consistent with the above process and will not be repeated here. It should be noted that N and M can be equal or unequal. In specific application scenarios, the value of N is determined by the number of lanes in the first lane group, and the value of M is determined by the number of lanes in the second lane group.

[0105] After obtaining N first closed polygons based on the lanes in the first lane group and M second closed polygons based on the lanes in the second lane group, a bipartite graph is constructed based on the N first closed polygons and the M second closed polygons, that is, the N first closed polygons constitute the first vertex set in the bipartite graph, and the M second closed polygons constitute the second vertex set in the bipartite graph. The lines between the first vertex set and the second vertex set in the bipartite graph represent the overlapping relationship between the first closed polygons and the second closed polygons, and the weights of the lines in the bipartite graph are the overlapping area values.

[0106] Determine whether one of the N first closed polygons overlaps with each of the M second closed polygons. If so, calculate the overlapping area between each first closed polygon and another second closed polygon. Repeat this method for all N first closed polygons and M second closed polygons, and then calculate the overlapping area of ​​all permutations and combinations.

[0107] As shown in Figure 6, in Figure 6, the first vertex set in the bipartite graph is composed of N first closed polygons, namely, a1, a2, a3... aN, where a1, a2, a3... aN each represent a first closed polygon; the second vertex set is composed of M first closed polygons, namely, b1, b2, b3... bM, where b1, b2, b3... bM each represent a second closed polygon. There are multiple connecting lines between the first vertex set and the second vertex set, and these connecting lines represent the overlapping relationship between the first closed polygon and the second closed polygon. The weights on the connecting lines represent the overlapping area of ​​the first polygon and the second polygon.

[0108] For example, based on the inspection area shown in Figure 2, we can obtain the bipartite graph shown in Figure 7. In this bipartite graph, the first vertex set includes a first closed polygon formed by lanes 1 and 3, and another first closed polygon formed by lanes 3 and 5. The second vertex set includes a second closed polygon formed by lanes 2 and 4, and another second closed polygon formed by lanes 4 and 6.

[0109] The relationship between the first vertex set and the second vertex set is as follows:

[0110] The overlapping area between the first closed polygon formed by lanes 1 and 3 and the second closed polygon formed by lanes 2 and 4 is shown in FIG8 ;

[0111] The overlapping area between the first closed polygon formed by lanes 1 and 3 and the second closed polygon formed by lanes 4 and 6;

[0112] The overlapping area between the first closed polygon formed by lanes 3 and 5 and the second closed polygon formed by lanes 2 and 4;

[0113] The overlapping area between the first closed polygon formed by lanes 3 and 5 and the second closed polygon formed by lanes 4 and 6;

[0114] After obtaining the bipartite graph, the global optimal solution of the bipartite graph is calculated. The specific calculation method of the global optimal solution is as follows:

[0115] Split the bipartite graph into multiple candidate bipartite graphs. Each candidate bipartite graph contains a one-to-one correspondence between N first closed polygons and M second closed polygons. Calculate the overlapping area between the first and second closed polygons in each candidate bipartite graph. The sum of the overlapping areas of all first and second polygons in the candidate bipartite graphs needs to be calculated.

[0116] After calculating the total overlapping area of ​​each candidate bipartite graph, the candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

[0117] For example, if the first lane group is as shown in Figure 3, the second lane group is as shown in Figure 4, and the resulting bipartite graph is as shown in Figure 7, then the bipartite graph in Figure 7 can be split into the candidate bipartite graphs shown in Figures 9a and 9b. Figures 9a and 9b represent the split bipartite graph, where the first vertex set U represents the lanes corresponding to the first closed polygon, and the second vertex set V represents the lanes corresponding to the second closed polygon. The relationship between the elements of sets U and V is represented by connecting lines, and the overlapping area is represented by the values ​​on the connecting lines.

[0118] As shown in Figures 9a and 9b, the total overlapping area corresponding to the candidate bipartite graph in Figure 9a is 3 + 5 = 8, and the total overlapping area corresponding to the candidate bipartite graph in Figure 9b is 4 + 1 = 5. Therefore, the candidate bipartite graph in Figure 9a is selected as the global optimal solution, and the candidate bipartite graph in Figure 9a is selected as the target bipartite graph. Finally, the matching relationships between the lanes in the candidate bipartite graph are used as the matching relationships between the first lane group and the second lane group.

[0119] Through the above approach, the correlation between lanes can be determined by the overlapping area of ​​the polygons composed of the lanes, thereby achieving accurate matching of heterogeneous lane data, thereby avoiding the problem of low matching accuracy caused by lane matching through intersection matching.

[0120] Of course, in the embodiment of the present application, in addition to first establishing a bipartite graph of all correspondences between the N first closed polygons and the M second closed polygons, then splitting it into multiple bipartite graphs of one-to-one correspondences, and then further determining the total overlapping area, it is also possible to directly establish a one-to-one correspondence between the first closed polygons and the second closed polygons.

[0121] Based on the same inventive concept, an embodiment of the present application provides an intelligent vehicle, which includes the above-mentioned lane matching device. The two devices here have been described in detail in the above-mentioned embodiments and will not be repeated here.

[0122] Based on the same inventive concept, embodiments of the present disclosure provide a computer storage medium comprising computer program code. When executed on a computer, the computer program code causes the computer to perform any of the lane matching methods discussed above. Because the principles underlying the problem solved by the computer storage medium are similar to those of the lane matching method, the implementation of the computer storage medium can be referenced to the implementation of the method, and any repetitions will be omitted.

[0123] In a specific implementation process, computer storage media may include: Universal Serial Bus Flash Drive (USB), mobile hard disk, Read-Only Memory (ROM), Random Access Memory (RAM), magnetic disk or optical disk, and other storage media that can store program code.

[0124] Based on the same inventive concept, embodiments of the present disclosure also provide a computer program product comprising computer program code. When executed on a computer, the computer program code causes the computer to perform any of the lane matching methods discussed above. Because the principles underlying the problems solved by the computer program product are similar to those of the lane matching method, the implementation of the computer program product can be referenced to the implementation of the method, and any repetitive details will not be repeated.

[0125] The computer program product can employ any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0126] The methods described herein can be implemented in whole or in part using software, hardware, firmware, or any combination thereof. When implemented using software, they can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described herein are performed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, a core network device, an OAM, or other programmable device.

[0127] The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a digital video disk; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0128] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0130] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0132] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A lane matching device, characterized in that: The system comprises a processor and a memory, wherein the memory is used to store a program executable by the processor, and the processor is used to read the program in the memory and perform the following steps: Acquire a first lane group from a first data source and a second lane group from a second data source, wherein the first lane group and the second lane group include at least two lanes; Obtain N first closed polygons according to the first lane group, and obtain M second closed polygons according to the second lane group, wherein the first closed polygons are composed of adjacent lanes in the first lane group, the second closed polygons are composed of adjacent lanes in the second lane group, and M and N are integers greater than or equal to 1; A matching result between the first lane group and the second lane group is determined according to an overlapping relationship between the N first closed polygons and the M second closed polygons.

2. The device according to claim 1, characterized in that The processor is specifically configured to execute: Constructing a bipartite graph based on the N first closed polygons and the M second closed polygons, wherein the N first closed polygons serve as a first vertex set in the bipartite graph, the M second closed polygons serve as a second vertex set in the bipartite graph, a line between the first vertex set and the second vertex set in the bipartite graph represents an overlapping relationship between the first closed polygon and the second closed polygon, and a weight of the line in the bipartite graph is an overlapping area value; Calculating a global optimal solution of the bipartite graph, wherein the target bipartite graph corresponding to the global optimal solution contains a one-to-one correspondence between the N first closed polygons and the M second closed polygons; Based on the target bipartite graph corresponding to the global optimal solution, a matching result between the first lane group and the second lane group is determined.

3. The device according to claim 2, characterized in that The processor is specifically configured to execute: Splitting the bipartite graph into a plurality of to-be-selected bipartite graphs, wherein each of the to-be-selected bipartite graphs contains a one-to-one correspondence between the N first closed polygons and the M second closed polygons; Calculate the overlapping area between the first closed polygon and the second closed polygon in each bipartite graph to be selected, wherein there is an overlapping area between the first closed polygon and the second closed polygon that are in a connected relationship in the bipartite graph to be selected; Calculate the total overlapping area corresponding to each bipartite graph to be selected, wherein the total overlapping area is the sum of the overlapping areas of all first closed polygons and second closed polygons in the bipartite graph to be selected that have an overlapping relationship; The candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

4. The device according to claim 1, characterized in that The processor is specifically configured to execute: Determine the area to be tested in the map data; taking all lanes in the test area that contain the first data source identifier as the first lane group; and All lanes in the area to be detected that contain the second data source identifier are used as the second lane group.

5. The device according to claim 1, characterized in that The processor is specifically configured to execute: sequentially connecting each two adjacent lanes in the first lane group end to end to obtain N first closed polygons with the adjacent lanes as edges; and Each two adjacent lanes in the second lane group are sequentially connected end to end to obtain M second closed polygons with the adjacent lanes as edges.

6. A lane matching method, characterized in that: The method comprises: Acquire a first lane group from a first data source and a second lane group from a second data source, wherein the first lane group and the second lane group include at least two lanes; Obtain N first closed polygons according to the first lane group, and obtain M second closed polygons according to the second lane group, wherein the first closed polygons are composed of adjacent lanes in the first lane group, the second closed polygons are composed of adjacent lanes in the second lane group, and M and N are integers greater than or equal to 1; A matching result between the first lane group and the second lane group is determined according to an overlapping relationship between the N first closed polygons and the M second closed polygons.

7. The method according to claim 6, characterized in that The determining, according to the N first closed polygons and the M second closed polygons, a matching result between the first lane group and the second lane group includes: Constructing a bipartite graph based on the N first closed polygons and the M second closed polygons, wherein the N first closed polygons serve as a first vertex set in the bipartite graph, the M second closed polygons serve as a second vertex set in the bipartite graph, a line between the first vertex set and the second vertex set in the bipartite graph represents an overlapping relationship between the first closed polygon and the second closed polygon, and a weight of the line in the bipartite graph is an overlapping area value; Calculating a global optimal solution of the bipartite graph, wherein the target bipartite graph corresponding to the global optimal solution contains a one-to-one correspondence between the N first closed polygons and the M second closed polygons; Based on the target bipartite graph corresponding to the global optimal solution, a matching result between the first lane group and the second lane group is determined.

8. The method according to claim 7, characterized in that The calculating the global optimal solution of the bipartite graph includes: Splitting the bipartite graph into a plurality of to-be-selected bipartite graphs, wherein each of the to-be-selected bipartite graphs contains a one-to-one correspondence between the N first closed polygons and the M second closed polygons; Calculate the overlapping area between the first closed polygon and the second closed polygon in each bipartite graph to be selected, wherein there is an overlapping area between the first closed polygon and the second closed polygon that are in a connected relationship in the bipartite graph to be selected; Calculate the total overlapping area corresponding to each bipartite graph to be selected, wherein the total overlapping area is the sum of the overlapping areas of all first closed polygons and second closed polygons in the bipartite graph to be selected that have an overlapping relationship; The candidate bipartite graph with the largest total overlapping area is taken as the global optimal solution.

9. An intelligent vehicle, characterized in that: The intelligent vehicle comprises the device as claimed in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method described in any one of claims 6 to 8 is implemented.

Images