Map data matching method and device, electronic equipment, vehicle and storage medium

Abstract

The embodiment of the invention relates to a map data matching method and device, electronic equipment, a vehicle and a storage medium. The method comprises the following steps: acquiring a plurality of first routes in first map data and a plurality of second routes in second map data; matching the plurality of first routes with the plurality of second routes to obtain a plurality of route mapping relationships; for each route mapping relation, acquiring a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relation; matching and combining the plurality of first feature points and the plurality of second feature points according to the sequential relationship of the feature points in the route to obtain a plurality of combination scores; taking the maximum value in the plurality of combined scores as a feature score of the route mapping relationship; and taking the route mapping relationship with the maximum feature score in the plurality of route mapping relationships as a target route mapping relationship required for establishing map mapping.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of map data processing, and in particular to a map data matching method, device, electronic device, vehicle and storage medium. Background Art

[0002] Map data refers to the digital abstraction of real road network information and ground coverage, but map data comes from many sources. When a system accesses multi-source map data, it is often necessary to find similar routes in different maps, and then use this similar route to establish the mapping relationship of multi-source map data. For example, for the same area in different maps, the routes with similar line types are matched by line-to-line matching, so as to use this route matching relationship to determine the mapping relationship of multi-source map data, that is, map data A includes routes 1, 2 and 3, and map data B includes routes a and b. The established route matching relationship is: route 1-route a, route 3-route b; however, in reality, due to the existence of elevated roads, main and auxiliary roads, etc., the two routes in the route matching relationship obtained by line-to-line matching may not be the same route in reality. If the mapping relationship of multi-source map data is determined by using this route matching relationship, it is likely that the mapping relationship of the obtained multi-source map data is biased, which will cause safety hazards when the multi-source map data is used later. Therefore, how to more accurately find the route matching relationship required to determine the mapping relationship of multi-source map data has become an urgent problem to be solved. Summary of the invention

[0003] The embodiments of the present application provide a map data matching method, device, electronic device, vehicle and storage medium, which match feature points in different routes in multi-source map data to obtain a route matching relationship with richer attributes.

[0004] In a first aspect, an embodiment of the present application provides a map data matching method, including: obtaining multiple first routes in first map data and multiple second routes in second map data; matching the multiple first routes with the multiple second routes to obtain multiple route mapping relationships, each route mapping relationship being used to indicate a second route corresponding to a first route; for each route mapping relationship, obtaining multiple first feature points included in the first route and multiple second feature points included in the second route in the route mapping relationship; matching and combining the multiple first feature points with the multiple second feature points according to the order of the feature points in the route to obtain multiple combination scores; using the maximum value of the multiple combination scores as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; and using the route mapping relationship with the largest feature score among the multiple route mapping relationships as the target route mapping relationship required for establishing map mapping.

[0005] In a second aspect, an embodiment of the present application provides a map data matching device, including: an acquisition module, used to acquire multiple first routes in a first map data and multiple second routes in a second map data; a matching module, used to match the multiple first routes with the multiple second routes to obtain multiple route mapping relationships, each route mapping relationship is used to indicate a second route corresponding to a first route; the acquisition module is also used to acquire, for each route mapping relationship, multiple first feature points included in the first route and multiple second feature points included in the second route in the route mapping relationship; match and combine the multiple first feature points with the multiple second feature points according to the order of the feature points in the route to obtain multiple combination scores; use the maximum value of the multiple combination scores as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; the matching module is also used to use the route mapping relationship with the largest feature score among the multiple route mapping relationships as the target route mapping relationship required for establishing map mapping.

[0006] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, the processor being used to execute a computer program stored in a memory, and the computer program, when executed by the processor, implements the steps of the map data matching method provided in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising: the map data matching device of the second aspect, or the electronic device of the third aspect.

[0008] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the map data matching method provided in the first aspect are implemented.

[0009] In the technical solution provided by the embodiment of the present application, a plurality of first routes in the first map data and a plurality of second routes in the second map data are obtained; the plurality of first routes are matched with the plurality of second routes to obtain a plurality of route mapping relationships, each route mapping relationship is used to indicate a second route corresponding to a first route; for each route mapping relationship, a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relationship are obtained; the plurality of first feature points are matched and combined with the plurality of second feature points according to the order of the feature points in the route to obtain a plurality of combination scores; the maximum value among the plurality of combination scores is used as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; the route mapping relationship with the maximum feature score among the plurality of route mapping relationships is used as the target route mapping relationship required for establishing map mapping. In this way, the routes in the multi-source data map are matched more finely, the matching relationship between each feature point in the routes with mapping relationships in different map data is obtained, and the specific feature score is calculated to make the matching more intuitive, and the routes also contain richer features, so that when the multi-source map data needs to be fused later, the fused route obtained has richer features. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0011] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0012] Figure 1 A flowchart of a map data matching method provided in an embodiment of the present application;

[0013] Figure 2 A flowchart of another map data matching method provided in an embodiment of the present application;

[0014] Figure 3 A flowchart of another map data matching method provided in an embodiment of the present application;

[0015] Figure 4 A flowchart of another map data matching method provided in an embodiment of the present application;

[0016] Figure 5 A flowchart of another map data matching method provided in an embodiment of the present application;

[0017] Figure 6 A flowchart of another map data matching method provided in an embodiment of the present application;

[0018] Figure 7 A schematic diagram of multiple track points in a route provided by an embodiment of the present application;

[0019] Figure 8 A schematic diagram of the structure of a map data matching device provided in an embodiment of the present application;

[0020] Fig. 9 A schematic diagram of the hardware structure of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to more clearly understand the above-mentioned purposes, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only part of the embodiments of the present application, rather than all of the embodiments.

[0023] In order to facilitate the understanding of this scheme, some terms involved in this scheme are explained as follows.

[0024] Map data: refers to the digital abstraction of real road network information and ground cover. The representation of each road in the map can include multiple forms: trajectory points, line segments with geometric information and attribute characteristics, feature points, etc.; points with coordinates can also be used to describe intersection data, and polygons with coordinates and category information can be used to describe ground cover information.

[0025] Line-to-line matching: When a system accesses multi-source map data, it is often necessary to establish a mapping relationship between the multi-source data. The so-called line-to-line matching refers to establishing a mapping relationship between multi-source road data based on an efficient matching algorithm.

[0026] Geometric information: Road data in map data needs to express real-world roads, so it carries geometric information, which is generally expressed in longitude and latitude, but can also be expressed in other coordinate systems. Line segments with geometric information and attribute features are used to indicate the shape and characteristics of roads (such as length, width, etc.).

[0027] Trajectory points: multiple points on a road obtained by sampling.

[0028] Feature points: refers to points on a route in the map data that have obvious characteristics, such as points where the number of lanes changes, representative points of route shapes, representative points of intersections, etc.

[0029] The technical solution of the present application is explained in detail below through several specific embodiments.

[0030] Figure 1 A flowchart of a map data matching method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the process includes the following steps 101 to 104.

[0031] 101. Obtain a plurality of first routes in first map data and a plurality of second routes in second map data.

[0032] Among them, the first map data and the second map data can be map data from different sources, for example, the first map data is standard map data, the second map data is high-precision map data, the first route is an arbitrary route obtained from the first map data, and the second route is an arbitrary route obtained from the second map data. The method of obtaining the route from the map data can be obtained using existing methods, such as randomly selecting a point in the map as the starting point, randomly selecting another point as the end point, and using topology and other methods to obtain the route between the starting point and the end point.

[0033] 102. Match the multiple first routes with the multiple second routes to obtain multiple route mapping relationships.

[0034] Each route mapping relationship is used to indicate a second route corresponding to a first route.

[0035] In the embodiment of the present application, in order to merge map data from two different sources, it is necessary to establish a mapping relationship between routes. Therefore, when establishing the mapping relationship, multiple routes in the same area of ​​interest in the first map data and the second map data are matched, that is, horizontal matching is performed to obtain a mapping relationship between the routes in the two maps, that is, the multiple first routes and the multiple second routes are respectively routes in the same area of ​​interest in the first map data and the second map data. For example: the target area of ​​interest of the first map data includes: route 1, route 2 and route 3; the target area of ​​interest of the second map data includes: route 4 and route 5. After horizontal matching, the determined route mapping relationship is {(route 1-route 4)(route 3-route 5)}, that is, route 1 and route 4 actually represent the same road, and route 3 and route 5 actually represent the same road.

[0036] However, it should be noted that the route mapping relationship does not include the mapping between feature points in the route, that is, when fused, it is impossible to represent richer features in the fused route. Therefore, this solution performs vertical matching after horizontal matching to perform more fine-grained matching of routes in multi-source map data, so that when the two map data are subsequently fused, the fused route includes various feature points, further enriching the route description information of the map data.

[0037] 103. For each route mapping relationship, obtain a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relationship; match and combine the plurality of first feature points with the plurality of second feature points according to the order of the feature points in the route to obtain a plurality of combination scores; and use the maximum value of the plurality of combination scores as the feature score of the route mapping relationship.

[0038] It can be understood that the first route can be a route in the target area of ​​interest of the first map data, and the second route can be a route in the target area of ​​interest of the second map data. Multiple routes in the target area of ​​interest of the first map data and the second map data are matched to determine that the first route matches the second route, that is, the first route and the second route are corresponding routes that have a mapping relationship in the target area of ​​interest in the real world, and then vertical matching of feature points is further required.

[0039] It can be understood that a route includes multiple feature points, and each feature point may include: geometric information (such as longitude and latitude coordinates) and at least one attribute information, and each attribute information is used to indicate a feature at that point in the route. That is to say, each feature point is used to indicate at least one feature in the corresponding route, such as feature point a: {(29°52′28″N, 112°28′20″E), intersection, two lanes-three lanes}, which means that the coordinates of feature point a in the actual road are 29 degrees 52 minutes 28 seconds north latitude and 112 degrees 28 minutes 20 seconds east longitude. Feature point a is used to indicate that the point is an intersection and the number of lanes at the point is changed from two lanes to three lanes.

[0040] In the embodiment of the present application, multiple first feature points and multiple second feature points can be matched and combined according to the order of the feature points in the route to obtain multiple combination scores. Figure 1 ,like Figure 2 As shown, it is achieved through steps 103a to 103c.

[0041] 103a. Traverse multiple matching relationships between multiple first feature points and multiple second feature points.

[0042] Since the matching process is to match a first feature point with a second feature point, multiple first feature points and multiple second feature points can be combined in sequence through permutation and combination to obtain all matching relationships between the multiple first feature points and the multiple second feature points.

[0043] 103b. Calculate the feature matching score of each matching relationship according to a preset feature matching score calculation rule.

[0044] The feature matching score obtained according to the preset feature matching score calculation rule can be used to indicate the degree of matching between the feature points of each matching relationship. The higher the feature matching score, the more matching the feature points are. Conversely, the lower the feature matching score, the less matching the feature points are.

[0045] It can be understood that for the matching between the feature points in the first route and the second route, for any feature point a in the first route, matching is performed with any feature point in the second route, and when the distance between feature point a and feature point b among multiple feature points in the second route is less than the distance threshold, and the absolute value of the difference in orientation angles between feature point a and feature point b is less than the difference threshold, the feature matching score x between feature point a and feature point b can be determined; or, when the distance between feature point a and feature point b among multiple feature points in the second route is less than the distance threshold, and the absolute value of the difference in orientation angles between feature point a and feature point b is less than the difference threshold, and the attributes are partially the same, the feature matching score y between feature point a and feature point b can be determined; or, when the distance between feature point a and feature point b among multiple feature points in the second route is less than the distance threshold, and the absolute value of the difference in orientation angles between feature point a and feature point b is less than the difference threshold, and the attributes are completely the same, the feature matching score z between feature point a and feature point b can be determined; there are many specific ways to calculate the feature matching score.

[0046] In some embodiments, the preset feature matching score calculation rule may be as follows:

[0047]

[0048] Among them, x i It can represent the i-th first feature point included in the first feature point set, that is, x 1 、x 2 , …, x i ;y j It can represent the jth second feature point included in the second feature point set, that is, y 1 ,y 2 , …, y j ;hcs(x i y j ) represents the first feature point set x1 to x i and y in the second feature point set 1 To j The optimal match between the two feature points (i.e., the two feature points with the highest matching score), x i =y j Represents the feature point x i and j is the matching feature point, x i ≠y j Represents the feature point x i and j is the unmatched feature point, [x i y j ] represents x i and j feature matching score.

[0049] From this, it can be seen that after determining the first feature point set and the second feature point set, matching can be started from the feature point with the largest number. If the two feature points are matching feature points, then they are matched in order of numbering without overlap; if two feature points are detected to be unmatched feature points, then the feature matching scores of the two groups of feature points are compared and the highest value is taken. The two groups are the total scores of the feature points in the first feature point set that are numbered before the current first feature point, and the total scores of the feature points in the second feature point set that are numbered before the current second feature point.

[0050] For example, the first feature point set is: {x1, x2, x3, x4}, and the second feature point set is: {y1, y2, y3}, where (x4, y3) is the corresponding relationship, x4 and y3 are determined to be matching feature points, and the feature matching score is 10 points; the next set of corresponding relationships is (x3, y2), x3 and y2 are determined to be unmatched feature points, and the hcs(x 3 y 1 ) and hcs(x 2 y 2 ) has a higher total score of feature matching, among which y 1 Indicates that only y is included in the second feature point set 1 A second characteristic point.

[0051] Among them, hcs(x 3 y 1 ) corresponds to the first feature point subset: {x1, x2, x3}, and the second feature point subset: {y1}. x3 and y1 are different feature points. Then continue to determine hcs(x 3 y 0 ) and hcs(x 2 y 1) has a higher total score of feature matching, hcs(x 3 y 0 ) is 0, hcs(x 2 y 1 ) corresponds to the first feature point subset: {x1, x2}, and the second feature point subset: {y1}. x2 and y1 are different feature points. Then continue to determine hcs(x 2 y 0 ) and hcs(x 1 y 1 ) has a higher total score of feature matching, hcs(x 2 y 0 ) is 0, hcs(x 1 y 1 ) corresponds to the first feature point subset: {x1}, the second feature point subset: {y1}, x1 and y1 are the same feature points, and the feature matching score is 10 points, then hcs(x 3 y 1 ) has a total feature matching score of 10 points, where hcs(x 2 y 0 ) can represent the first feature point subset as: {x1, x2}, but there are no feature points in the second feature point subset.

[0052] Among them, hcs(x 2 y 2 ) corresponds to the first feature point subset: {x1, x2}, the second feature point subset: {y1, y2}, x2 and y2 are the same feature points, and the feature matching score is 10 points, x1 and y1 are the same feature points, and the feature matching score is 10 points, then hcs(x 2 y 2 ) has a total feature matching score of 20 points.

[0053] Among them, hcs(x 3 y 1 ) has a total feature matching score less than hcs(x 2 y 2 ), the final feature point correspondence is {(x4, y3)(x2, y2)(x1, y1)}.

[0054] In summary, the first feature point set is represented as {x1, x2, x3}, the second feature point set is represented as {y1, y2}, and the feature matching scores of the corresponding relationships included in each to-be-matched relationship are: (x1, y1), 4 points, (x2, y2), 10 points, and a total score of 14 points; {(x1, y2)}, 0 points, a total score of 0 points; (x1, y1), 4 points, (x3, y2), 2 points, and a total score of 6 points; (x2, y1), 5 points, (x3, y2), 2 points, and a total score of 7 points; (x3, y1), 0 points, a total score of 0 points; (x3, y2), 2 points, and a total score of 2 points. Therefore, the maximum total score is 14 points, and the determined target matching relationship is: {(x1, y1), (x2, y2)}.

[0055] It should be noted that the above-mentioned preset rules are only exemplary descriptions and are not intended to limit the present application. Other feasible rules may be used, such as: randomly combining two feature points in the first feature point set and the second feature point set, determining the feature matching score, and then determining the target matching relationship as the target matching relationship among the multiple matching relationships composed of all combinations that have no cross-combinations and have the highest total score.

[0056] Exemplarily, the multiple first feature points included in the first route are (x1, x2, x3, x4), and the multiple second feature points included in the second route are (y1, y2, y3, y4, y5). Then, the multiple first feature points and the multiple second feature points are matched each other, and a feature matching score can be obtained according to the preset feature matching score calculation rules. For example: (x1, y1) corresponds to 15 points, (x2, y2) corresponds to 16 points, (x3, y4) corresponds to 5 points, (x4, y5) corresponds to 10 points, and so on.

[0057] In the embodiment of the present application, since the feature matching score can indicate the degree of matching between feature points, the matching relationship between feature points can be determined based on the feature matching score. For example, a feature threshold is set, and only feature points with feature matching scores higher than the feature threshold are considered matched, or all feature matching scores are sorted, and the feature points with the highest sorting scores are taken to determine the match, etc. The above only shows some ways to determine the matching relationship, and there may be other ways, which are not specifically limited in this embodiment.

[0058] It can be understood that after the horizontal matching of the routes, this solution needs to further match the feature points vertically to perform a more fine-grained matching of the routes in the multi-source map data, so that when the two map data are subsequently fused, the fused route includes various feature points, further enriching the route description information of the map data.

[0059] 103c. Combining the first feature points in the first route and the second feature points in the second route according to their sequential relationship to obtain multiple combinations, and taking the sum of all feature matching scores in the combination as the combination score.

[0060] It can be understood that a plurality of first feature points constitute a first feature point set, a plurality of second feature points constitute a second feature point set, and each feature point in the first feature point set and the second feature point set is arranged according to a geometric order in an actual road.

[0061] It can be understood that the first feature point set is represented by {x1, x2, ... xm}, the second feature point set is represented by {y1, y2, ... yn}, multiple first feature points and multiple second feature points are combined into a corresponding relationship, and cross-combination is not allowed (for example, if x1 and y3 are a corresponding relationship, then x2 can only be combined with the feature points after y3 (i.e., y4 to yn) into a corresponding relationship, and x2 is not allowed to form a corresponding relationship with any of y1 to y3). If the first feature point set is represented by {x1, x2, x3} and the second feature point set is represented by {y1, y2}, then there are 6 determined relationships to be matched, namely {(x1, y1)(x2, y2)}, {(x1, y2)}, {(x1, y1)(x3, y2)}, {(x2, y1)(x3, y2)}, {(x3, y1)}, {(x3, y2)}.

[0062] Exemplarily, two matching routes obtained by horizontal matching in the first map data and the second map data are: (Route 1-Route 4); for multiple feature points (x1, x2, x3, x4) of Route 1 and multiple feature points (y1, y2, y3, y4, y5) of Route 4; wherein, feature points x1, x2, x3, x4 are arranged in sequence in the first route, and feature points y1, y2, y3, y4, y5 are arranged in sequence in the second route. If x1 and y1 have a matching relationship, according to the sequence relationship of the feature points in the route, x2 can also be matched with any feature point of y2, y3, y4, y5, but if x1 and y2 have a matching relationship, matching relationship, x2 can only be matched with any one of the feature points y3, y4, and y5. Therefore, according to the order of the feature points in the route, there can be multiple combinations between the multiple first feature points and the multiple second feature points, such as combination 1 {(x1, y1)(x2, y2)(x3, y4)(x4, y5)}, combination 2 {(x1, y2)(x2, y3)(x3, y4)}, combination 3 {(x1, y1)(x2, y3)(x3, y4)(x4, y5)}, and so on. Since each feature matching score is available, the sum of all feature matching scores in the combination gives the combined score of the combination.

[0063] Since multiple combination scores can be obtained in each route mapping relationship, and the combination score is obtained by adding multiple feature matching scores, and the feature matching score can represent the degree of matching between feature points, the combination score can also represent the mapping degree of the route mapping relationship. Therefore, the maximum value of multiple combination scores can be used as the feature score of the route mapping relationship.

[0064] 104. Using the route mapping relationship with the largest feature score among the multiple route mapping relationships as the target route mapping relationship required for establishing the map mapping.

[0065] It can be understood that since multiple route mapping relationships have been obtained through step 102, and the corresponding feature scores have been obtained for each route mapping relationship in step 103, the route mapping relationship with the largest feature score can be found by comparing the feature scores, and then used as the target route mapping relationship; when establishing the map mapping later, the first route and the second route in the target route mapping relationship can be used to determine the mapping relationship between the first map data and the second map data through existing methods such as line-to-line matching.

[0066] It should be noted that the target route mapping relationship can represent the correspondence between the feature points of a first route and a second route. That is to say, after determining the target route mapping relationship, the mapping relationship between the feature points of the first route and the second route can be determined. Then, after performing the above steps for each first route and the second route, the mapping relationship between the feature points of each first route and the second route can be determined, that is, the mapping relationship between the entire first map data and the second map data can be obtained.

[0067] In the embodiment of the present application, a plurality of first routes in the first map data and a plurality of second routes in the second map data are obtained; the plurality of first routes and the plurality of second routes are matched to obtain a plurality of route mapping relationships, each route mapping relationship is used to indicate a second route corresponding to a first route; for each route mapping relationship, a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relationship are obtained; the plurality of first feature points and the plurality of second feature points are matched and combined according to the order of the feature points in the route to obtain a plurality of combination scores; the maximum value among the plurality of combination scores is used as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; the route mapping relationship with the maximum feature score among the plurality of route mapping relationships is used as the target route mapping relationship required for establishing map mapping. In this way, the routes in the multi-source data map are matched more finely, the matching relationship between each feature point in the routes with mapping relationships in different map data is obtained, and the specific feature score is calculated to make the matching more intuitive, and the routes also contain richer features, so that when the multi-source map data needs to be fused later, the fused route obtained has richer features.

[0068] In some embodiments of the present application, Figure 2 ,like Figure 3 As shown, before the above step 103b, the map data matching method provided by the present application further includes the following steps 103d and 103e, and the above step 103b can be specifically implemented by the following step 103f.

[0069] 103d. Detect whether the first feature point and the second feature point in the target matching relationship match.

[0070] The target matching relationship is any one of the multiple matching relationships.

[0071] 103e. When the distance between the first feature point and the second feature point is greater than or equal to the first distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is greater than or equal to the first angle threshold, it is determined that the first feature point and the second feature point do not match.

[0072] It can be understood that the coordinates of the two feature points are the coordinates in the same coordinate system, such as both expressed in longitude and latitude; the distance between the two feature points is determined based on the coordinates of the first feature point and the coordinates of the second feature point in the two maps. When the distance is greater than the first distance threshold, the two feature points can be determined to be different feature points. Alternatively, based on two adjacent feature points, the orientation angle of feature point A can be determined based on feature point A and its next feature point. In the two maps, when the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is greater than or equal to the first angle threshold, the two feature points can be determined to be different feature points.

[0073] 103f. When the distance between the first feature point and the second feature point is less than the first distance threshold, and the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the first angle threshold, determine the feature matching score of the first feature point and the second feature point according to a preset feature matching score calculation rule.

[0074] In the embodiment of the present application, whether the first feature point and the second feature point in the target matching relationship match is detected, and the target matching relationship is any one of multiple matching relationships; when the distance between the first feature point and the second feature point is greater than or equal to the first distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is greater than or equal to the first angle threshold, it is determined that the first feature point and the second feature point do not match; when the distance between the first feature point and the second feature point is less than the first distance threshold, and the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the first angle threshold, the feature matching score of the first feature point and the second feature point is determined based on the preset feature matching score calculation rule. In this way, before matching two feature points, through the distance and orientation angle, for feature points with a large distance or a large orientation angle deviation, it can be directly judged that they do not match, and there is no need for subsequent matching, which reduces the amount of calculation and improves the matching efficiency.

[0075] In some embodiments of the present application, Figure 3 ,like Figure 4 As shown, the above step 103f can be specifically implemented through the following steps 103g and 103h.

[0076] 103g. When the distance between the first feature point and the second feature point is less than the second distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the second angle threshold, the feature matching score is increased by a first preset point.

[0077] The first distance threshold is greater than the second distance threshold, and the first angle threshold is greater than the second angle threshold.

[0078] 103h. When the first attribute is the same as the second attribute, the feature matching score is increased by a second preset score.

[0079] The first attribute is any one of the at least one attribute corresponding to the first feature point, and the second attribute is any one of the at least one attribute corresponding to the second feature point.

[0080] It can be understood that when the distance between the first feature point and the second feature point is less than the second distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the second angle threshold, it indicates that the two points are more likely to be the same feature point, and therefore, the feature matching score is increased by a first preset point. For example: the first distance threshold is 15 meters, the second distance threshold is 1 meter, the first angle threshold is 90 degrees, and the second angle threshold is 10 degrees. When the distance between the two feature points is less than 15 meters and the absolute value of the difference in the orientation angle is less than 90 degrees, it is determined that the two points may match; further, when the distance between the two feature points is less than 1 meter, the feature matching score is increased by 2 points; when the absolute value of the difference in the orientation angle is less than 90 degrees, the feature matching score is also increased by 2 points. The higher the feature matching score, the more similar the two feature points are.

[0081] It can be understood that at least one attribute corresponding to the first feature point and at least one attribute corresponding to the second feature point are matched in pairs, and when any two attributes are the same, the feature matching score is increased by a second preset score. For example: the attributes of feature point A include {intersection, two lanes-three lanes}, and the attributes of feature point B include {intersection-cross, two lanes-three lanes}, then the intersections are the same, and the feature matching score is increased by 2 points; the characteristics of two lanes becoming three lanes are the same, and the feature matching score is increased by another 2 points. In this way, according to the feature matching score, when feature point A and feature point B are a set of matching relationships, the two routes need to be fused later, and the attributes of the feature points corresponding to feature points A and feature points B in the fused route can be {intersection, two lanes-three lanes}, that is, the intersection of the attributes of feature point A and feature point B, and the fused feature points can more accurately represent the features in the route; or, it can also be {intersection-cross, two lanes-three lanes}, that is, the union of the attributes of feature point A and feature point B, and the fused feature points represent richer features in the route.

[0082] In the embodiment of the present application, when the distance between the first feature point and the second feature point is less than the second distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the second angle threshold, the feature matching score is increased by the first preset score, the first distance threshold is greater than the second distance threshold, and the first angle threshold is greater than the second angle threshold; when the first attribute is the same as the second attribute, the feature matching score is increased by the second preset score, the first attribute is any one of the at least one attribute corresponding to the first feature point, and the second attribute is any one of the at least one attribute corresponding to the second feature point. In this way, the feature matching relationship with the highest matching degree between the feature point sets in the two routes is determined, and the correspondence between the features represented is more accurate, so that the route in the map data obtained by subsequent fusion not only includes rich feature points, but also the features of the route described by the feature points are more accurate.

[0083] In some embodiments of the present application, Figure 1 ,like Figure 5 As shown, the above step 102 can be specifically implemented through the following steps 102a and 102b.

[0084] 102a. Determine, based on a trajectory similarity algorithm, route matching scores of a plurality of trajectory points corresponding to the first route and a plurality of trajectory points corresponding to the second route, and obtain a plurality of route matching scores.

[0085] 102b. Determine a first route and a second route corresponding to a maximum value among a plurality of route matching scores as a route mapping relationship.

[0086] It can be understood that the trajectory similarity algorithm can be any algorithm that measures the similarity between two trajectories, such as: trajectory time series data distance measurement (EDIY Distance On Real Sequence, EDR) algorithm, Longest Common Sub-Sequence (LCSS) algorithm, Dynamic Time Warping (Dynamic Time Warping, DTW) algorithm, etc.

[0087] Exemplarily, the target area of ​​interest in the first map includes 2 routes, namely A1 and A2; the target area of ​​interest in the second map includes 3 routes, namely B1, B2, and B3. According to the trajectory similarity algorithm, the route matching score between A1 and B1 is 5 points, the route matching score between A1 and B2 is 0 point, the route matching score between A1 and B3 is 1 point, the route matching score between A2 and B1 is 1 point, the route matching score between A2 and B2 is 0 point, and the route matching score between A2 and B3 is 8 points. Then, the route mapping relationship in the target areas of interest of the two maps is determined to be: A1-B1, A2-B3.

[0088] In the embodiment of the present application, based on the trajectory similarity algorithm, the route matching scores of multiple trajectory points corresponding to the first route and multiple trajectory points corresponding to the second route are determined to obtain multiple route matching scores; the first route and the second route corresponding to the maximum value of the multiple route matching scores are determined as a route mapping relationship. The corresponding relationship between the routes with the highest route matching scores is determined as a route mapping relationship to ensure that the route mapping relationship between the routes in the two maps is more accurate.

[0089] In some embodiments of the present application, Figure 5 ,like Figure 6 As shown, the above step 102a can be specifically implemented through the following steps 102c to 102e.

[0090] 102c. Determine route matching scores of a plurality of first trajectory points corresponding to the first route and a plurality of second trajectory points corresponding to the second route based on a trajectory similarity algorithm.

[0091] 102d. When an intersection trajectory point among the plurality of first trajectory points matches an intersection trajectory point among the plurality of second trajectory points, increase the route matching score by a third preset score.

[0092] 102e. When an entry trajectory point among the plurality of first trajectory points matches an entry trajectory point among the plurality of second trajectory points, or an exit trajectory point among the plurality of first trajectory points matches an exit trajectory point among the plurality of second trajectory points, the route matching score is increased by a fourth preset score.

[0093] It can be understood that after determining the route matching scores of two routes based on the trajectory similarity algorithm, if the attribute information of the trajectory point sets of the two routes is the same, the route matching scores are increased by a preset score. For example: trajectory point A is a trajectory point of route 1 in the first map data, trajectory point B is a trajectory point of route 2 in the second map data, trajectory point A and trajectory point B are two corresponding trajectory points, trajectory point A is a trajectory point at an intersection in route 1, and trajectory point B is a trajectory point at an intersection in route 2, then the matching score of route 1 and route 2 is increased by a third preset score. According to the preset route direction, such as Figure 7 As shown, the route direction is set from east to west. In route ad, it includes road segments ab and bc. Track point a is the entrance of road segment ab, track point b is the exit of road segment ab, and is also the entrance of road segment bd and the entrance of road segment bc. Track point d is the exit of road segment bd, and track point c is the exit of road segment bc. When the track points included in the two routes are both entrances or both exits, the route matching score is increased by a fourth preset score. The third preset score and the fourth preset score may be the same or different.

[0094] In the embodiment of the present application, based on the trajectory similarity algorithm, the route matching scores of the multiple first trajectory points corresponding to the first route and the multiple second trajectory points corresponding to the second route are determined; when the intersection trajectory point in the multiple first trajectory points matches the intersection trajectory point in the multiple second trajectory points, the route matching score is increased by a third preset score; when the entry trajectory point in the multiple first trajectory points matches the entry trajectory point in the multiple second trajectory points, or the exit trajectory point in the multiple first trajectory points matches the exit trajectory point in the multiple second trajectory points, the route matching score is increased by a fourth preset score. In this way, for the matching of two routes in the same area of ​​interest in two map data, both the trajectory similarity and the special trajectory points are considered, so that the obtained route mapping relationship is more accurate.

[0095] like Figure 8 As shown, a map data matching device is provided for the present application, including: an acquisition module 801, used to acquire multiple first routes in the first map data and multiple second routes in the second map data; a matching module 802, used to match the multiple first routes with the multiple second routes to obtain multiple route mapping relationships, each route mapping relationship is used to indicate a second route corresponding to a first route; the acquisition module 801 is also used to acquire, for each route mapping relationship, multiple first feature points included in the first route and multiple second feature points included in the second route in the route mapping relationship; match and combine the multiple first feature points with the multiple second feature points according to the order relationship of the feature points in the route to obtain multiple combination scores; use the maximum value of the multiple combination scores as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; the matching module 802 is also used to use the route mapping relationship with the largest feature score among the multiple route mapping relationships as the target route mapping relationship required for establishing map mapping.

[0096] In some embodiments of the present application, the matching module 802 is specifically used to traverse multiple matching relationships between multiple first feature points and multiple second feature points; calculate the feature matching score of each matching relationship according to a preset feature matching score calculation rule; combine the first feature points in the first route according to the sequential relationship and the second feature points in the second route to obtain multiple combinations, and take the sum of all feature matching scores in the combination as the combination score.

[0097] In some embodiments of the present application, the device further includes: a detection module, configured to detect whether a first feature point matches a second feature point in a target matching relationship, where the target matching relationship is any one of a plurality of matching relationships;

[0098] The matching module 802 is specifically used to determine that the first feature point and the second feature point do not match when the distance between the first feature point and the second feature point is greater than or equal to a first distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is greater than or equal to a first angle threshold; when the distance between the first feature point and the second feature point is less than the first distance threshold, and the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the first angle threshold, determine the feature matching score of the first feature point and the second feature point according to a preset feature matching score calculation rule.

[0099] In some embodiments of the present application, the matching module 802 is specifically used to increase the feature matching score by a first preset point when the distance between the first feature point and the second feature point is less than a second distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than a second angle threshold, the first distance threshold is greater than the second distance threshold, and the first angle threshold is greater than the second angle threshold; and to increase the feature matching score by a second preset point when the first attribute is the same as the second attribute, the first attribute is any one of at least one attribute corresponding to the first feature point, and the second attribute is any one of at least one attribute corresponding to the second feature point.

[0100] In some embodiments of the present application, the matching module 802 is specifically used to determine, based on a trajectory similarity algorithm, the route matching scores of multiple trajectory points corresponding to the first route and the multiple trajectory points corresponding to the second route, to obtain multiple route matching scores; and determine the first route and the second route corresponding to the maximum value of the multiple route matching scores as a route mapping relationship.

[0101] In some embodiments of the present application, the matching module 802 is specifically used to determine, based on a trajectory similarity algorithm, a route matching score of a plurality of first trajectory points corresponding to a first route and a plurality of second trajectory points corresponding to a second route; when an intersection trajectory point among the plurality of first trajectory points matches an intersection trajectory point among the plurality of second trajectory points, the route matching score is increased by a third preset score; when an entry trajectory point among the plurality of first trajectory points matches an entry trajectory point among the plurality of second trajectory points, or an exit trajectory point among the plurality of first trajectory points matches an exit trajectory point among the plurality of second trajectory points, the route matching score is increased by a fourth preset score.

[0102] The map data matching device provided in the embodiment of the present application can be used to execute the steps of the above-mentioned map data matching method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0103] It should be noted that the above-mentioned map data matching device can be the electronic device in the above-mentioned method embodiment of the present application, or it can be a functional module and / or functional entity in the electronic device that can realize the functions of the device embodiment, and the embodiment of the present application is not limited.

[0104] In the embodiment of the present application, each module can implement the map data matching method provided in the above method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0105] The beneficial effects of various implementation methods in this embodiment can be specifically referred to the beneficial effects of the corresponding implementation methods in the above map data matching method embodiment. To avoid repetition, they will not be described again here.

[0106] The present application also provides an electronic device, such as Fig. 9 As shown, the electronic device may include: a processor 901, a memory 902, and a program or instruction stored in the memory 902 and executable on the processor 901. When the program or instruction is executed by the processor 901, each process of the map data matching method provided in the above method embodiment can be implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0107] An embodiment of the present application provides a vehicle, which includes the above-mentioned map data matching device or electronic device, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0108] An embodiment of the present application provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the map data matching method provided in the above method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0109] The embodiment of the present application also provides a computer program product, wherein the computer program product includes a computer program or instructions. When the computer program product runs on a processor, the processor executes the computer program or instructions to implement the various processes of the map data matching method provided in the above method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0110] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned map data matching method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0111] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0112] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, servers and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0116] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A map data matching method, It is characterized in that include: Acquire a plurality of first routes in the first map data and a plurality of second routes in the second map data; Matching the multiple first routes with the multiple second routes to obtain multiple route mapping relationships, each route mapping relationship is used to indicate a second route corresponding to a first route; For each route mapping relationship, obtain a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relationship; match and combine the plurality of first feature points with the plurality of second feature points according to the order of the feature points in the route to obtain a plurality of combination scores; use the maximum value of the plurality of combination scores as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; The route mapping relationship with the largest feature score among the multiple route mapping relationships is used as the target route mapping relationship required for establishing map mapping.

2. The method according to claim 1, It is characterized in that The matching and combining the plurality of first feature points with the plurality of second feature points according to the sequence relationship of the feature points in the route to obtain a plurality of combination scores includes: Traversing a plurality of matching relationships between the plurality of first feature points and the plurality of second feature points; According to the preset feature matching score calculation rules, the feature matching score of each matching relationship is calculated respectively; According to the sequence relationship of the first feature points in the first route and the sequence relationship of the second feature points in the second route, multiple combinations are obtained, and the sum of all feature matching scores in the combination is used as the combination score.

3. The method according to claim 2, It is characterized in that Before respectively calculating the feature matching score of each matching relationship according to the preset feature matching score calculation rule, the method further includes: Detecting whether a first feature point matches a second feature point in a target matching relationship, wherein the target matching relationship is any one of the multiple matching relationships; When the distance between the first feature point and the second feature point is greater than or equal to a first distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is greater than or equal to a first angle threshold, it is determined that the first feature point and the second feature point do not match; The step of calculating the feature matching score of each matching relationship according to a preset feature matching score calculation rule includes: When the distance between the first feature point and the second feature point is less than the first distance threshold, and the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than the first angle threshold, the feature matching score of the first feature point and the second feature point is determined according to a preset feature matching score calculation rule.

4. The method according to claim 3, It is characterized in that The determining a feature matching score between the first feature point and the second feature point includes: When the distance between the first feature point and the second feature point is less than a second distance threshold, or the absolute value of the difference between the orientation angle of the first feature point and the orientation angle of the second feature point is less than a second angle threshold, the feature matching score is increased by a first preset point, the first distance threshold is greater than the second distance threshold, and the first angle threshold is greater than the second angle threshold; When a first attribute is the same as a second attribute, the feature matching score is increased by a second preset score, the first attribute is any one of the at least one attribute corresponding to the first feature point, and the second attribute is any one of the at least one attribute corresponding to the second feature point.

5. The method according to claim 1, It is characterized in that The matching of the plurality of first routes with the plurality of second routes to obtain a plurality of route mapping relationships includes: Based on a trajectory similarity algorithm, determining route matching scores of a plurality of trajectory points corresponding to the first route and a plurality of trajectory points corresponding to the second route, to obtain a plurality of route matching scores; The first route and the second route corresponding to the maximum value among the multiple route matching scores are determined as a route mapping relationship.

6. The method according to claim 5, It is characterized in that The determining, based on the trajectory similarity algorithm, route matching scores of a plurality of trajectory points corresponding to the first route and a plurality of trajectory points corresponding to the second route to obtain a plurality of route matching scores comprises: Determining, based on the trajectory similarity algorithm, route matching scores of a plurality of first trajectory points corresponding to the first route and a plurality of second trajectory points corresponding to the second route; In the case where an intersection trajectory point among the plurality of first trajectory points matches an intersection trajectory point among the plurality of second trajectory points, increasing the route matching score by a third preset point; When an entry trajectory point among the plurality of first trajectory points matches an entry trajectory point among the plurality of second trajectory points, or an exit trajectory point among the plurality of first trajectory points matches an exit trajectory point among the plurality of second trajectory points, the route matching score is increased by a fourth preset point.

7. A map data matching device, It is characterized in that include: An acquisition module, configured to acquire a plurality of first routes in the first map data and a plurality of second routes in the second map data; A matching module, used for matching the plurality of first routes with the plurality of second routes to obtain a plurality of route mapping relationships, each route mapping relationship being used for indicating a second route corresponding to a first route; The acquisition module is further used to acquire, for each route mapping relationship, a plurality of first feature points included in the first route and a plurality of second feature points included in the second route in the route mapping relationship; match and combine the plurality of first feature points with the plurality of second feature points according to the order of the feature points in the route to obtain a plurality of combination scores; and use the maximum value of the plurality of combination scores as the feature score of the route mapping relationship; each feature point is used to indicate at least one feature in the corresponding route; The matching module is further configured to use the route mapping relationship with the largest feature score among the multiple route mapping relationships as the target route mapping relationship required for establishing the map mapping.

8. An electronic device, It is characterized in that include: A memory and a processor, the memory is used to store computer programs; The processor is used to execute the map data matching method according to any one of claims 1 to 6 when calling the computer program.

9. A vehicle, It is characterized in that include: The map data matching device according to claim 7, or the electronic device according to claim 8.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the map data matching method according to any one of claims 1 to 6 is implemented.

Images