A road longitudinal matching method, device, equipment and computer program product

Abstract

This disclosure relates to a road longitudinal matching method, apparatus, device, and computer program product. By acquiring the distance feature points and shape feature points included in both high-precision line segments and candidate standard line segments, the average distance similarity and shape similarity between the high-precision line segments and candidate standard line segments can be determined. The average distance similarity comprehensively considers the average distance from the high-precision line segment to the candidate standard line segment, reducing longitudinal offset caused by positional accuracy errors at the beginning and end points of the standard line segment. The shape similarity enables matching based on shape, reducing longitudinal offset caused by shape differences. Therefore, based on the average distance similarity and shape similarity, a standard line segment that matches the high-precision line segment can be determined, reducing longitudinal offset and improving driving safety.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to a road longitudinal matching method, apparatus, device, and computer program product. Background Technology

[0002] In applications such as autonomous driving or lane-level navigation, the navigation path is planned based on a standard-precision map, while some sections of the navigation path are navigated based on a high-precision map. Therefore, it is necessary to perform longitudinal matching between the standard-precision map and the high-precision map, where longitudinal can be understood as the vehicle's driving direction.

[0003] Currently, the longitudinal matching method for roads combines intersection anchor points with direct projection. Roads near intersections are aligned using intersection anchor points, while non-nearby roads between intersections are directly projected. However, due to longitudinal accuracy errors in high-precision maps, this matching method results in longitudinal offset. Furthermore, if the road has significant curvature, the length of the matched high-precision road differs considerably from the length of the high-precision road, leading to even greater longitudinal offset and potential driving safety hazards. Summary of the Invention

[0004] At least one embodiment of this disclosure provides a road longitudinal matching method, apparatus, device, medium, and computer program product.

[0005] In a first aspect, embodiments of this disclosure propose a road longitudinal matching method, the method comprising:

[0006] Obtain the high-precision line segments to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map;

[0007] Obtain the distance feature points and shape feature points included in the high-precision line segment, and obtain the distance feature points and shape feature points included in each candidate high-precision line segment;

[0008] Based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment, the average distance similarity between each candidate standard line segment and the high-precision line segment is determined.

[0009] Based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment, the shape similarity between each candidate standard line segment and the high-precision line segment is determined.

[0010] Based on average distance similarity and shape similarity, a candidate high-precision line segment is selected from multiple candidate high-precision line segments as the high-precision line segment that matches the high-precision line segment.

[0011] In some embodiments, obtaining the high-precision line segment to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map includes:

[0012] Obtain at least one candidate high-precision road shape line, and the minimum distance between the candidate high-precision road shape line and the high-precision line segment is less than or equal to a preset minimum distance threshold.

[0013] A distance feature point is determined at preset lengths on the high-precision line segment, wherein the start and end points of the high-precision line segment are both distance feature points;

[0014] For each candidate road shape line, a distance feature point is determined at preset lengths along the candidate road shape line, and the start and end points of the candidate road shape line are both distance feature points.

[0015] If the number of distance feature points included in the candidate precision road shape line is greater than the number of distance feature points included in the high precision line segment, then multiple candidate precision line segments are determined based on the candidate precision road shape line. The number of distance feature points included in each candidate precision line segment is the same as the number of distance feature points included in the high precision line segment.

[0016] In some embodiments, determining the average distance similarity between each candidate standard line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment includes:

[0017] Determine the order of each distance feature point on the high-precision line segment, and the order of each distance feature point on each candidate high-precision line segment;

[0018] For any candidate precision line segment, determine the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment;

[0019] Based on a preset distance threshold and the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment is determined.

[0020] Based on the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the average distance similarity between the candidate precision line segment and the high precision line segment is determined.

[0021] In some embodiments, determining the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment includes:

[0022] For any candidate precision line segment, project each shape feature point on the candidate precision line segment onto the high precision line segment proportionally to obtain the first set of points on the high precision line segment; and project each shape feature point on the high precision line segment onto the candidate precision line segment proportionally to obtain the second set of points on the candidate precision line segment; wherein, proportional projection means that the length ratio of the shape feature point on its own line segment is the same as the length ratio of the projected point on the projected line segment;

[0023] Form a first vector from the adjacent points in the first set of points; and form a second vector from the adjacent points in the second set of points;

[0024] Determine the vector similarity between the first and second vectors in the first and second vector sets that are in the same order, and determine the shape similarity weight corresponding to the vector similarity based on the length ratio of the points that make up the vectors on the line segments they are on.

[0025] Based on vector similarity and the corresponding shape similarity weights, the shape similarity between the candidate precision line segment and the high precision line segment is determined.

[0026] In some embodiments, the shape similarity weight corresponding to the vector similarity is determined based on the length proportion of the points constituting the vector on the line segment they occupy, including:

[0027] Determine the relative length ratio of the two points that make up the first vector on the high-precision line segment, or determine the relative length ratio of the two points that make up the second vector on the candidate high-precision line segment; and determine the relative length ratio as the shape similarity weight corresponding to the vector similarity.

[0028] In some embodiments, based on average distance similarity and shape similarity, a candidate precision line segment is selected from multiple candidate precision line segments as the precision line segment that matches the high-precision line segment, including:

[0029] The overall similarity is determined based on average distance similarity and shape similarity;

[0030] The candidate line segment with the highest comprehensive similarity among multiple candidate line segments is selected as the line segment that matches the high-precision line segment.

[0031] Secondly, embodiments of this disclosure also provide a road longitudinal matching device, the device comprising:

[0032] The first acquisition unit is used to acquire the high-precision line segment to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map.

[0033] The second acquisition unit is used to acquire the distance feature points and shape feature points included in the high-precision line segment, and to acquire the distance feature points and shape feature points included in each candidate high-precision line segment;

[0034] The first determining unit is used to determine the average distance similarity between each candidate standard line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment.

[0035] The second determining unit is used to determine the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment.

[0036] The matching unit is used to select one candidate high-precision line segment from multiple candidate high-precision line segments as the high-precision line segment to match the high-precision line segment, based on average distance similarity and shape similarity.

[0037] Thirdly, embodiments of this disclosure also provide an electronic device, which includes a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the road longitudinal matching method as described in any embodiment of the first aspect.

[0038] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of the road longitudinal matching method as described in any embodiment of the first aspect.

[0039] Fifthly, embodiments of this disclosure also provide a computer program product comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the steps of the road longitudinal matching method as described in any embodiment of the first aspect.

[0040] As can be seen, in at least one embodiment of this disclosure, by acquiring the distance feature points and shape feature points included in the high-precision line segment and the candidate standard line segment respectively, the average distance similarity and shape similarity between the high-precision line segment and the candidate standard line segment can be determined. The average distance similarity comprehensively considers the average distance from the high-precision line segment to the candidate standard line segment, rather than only considering the projection of the first and last points of the high-precision line segment, which can reduce the lateral and longitudinal offset caused by the positional accuracy error of the first and last points of the standard line segment. The shape similarity realizes matching based on shape (including shape information such as position, direction, and angle), reducing the longitudinal offset caused by shape differences. Therefore, based on the average distance similarity and shape similarity, a candidate standard line segment can be selected from multiple candidate standard line segments as the standard line segment that matches the high-precision line segment, reducing the longitudinal offset and improving driving safety. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings.

[0042] Figure 1 This is a schematic diagram of road longitudinal matching that combines intersection anchor points and direct projection;

[0043] Figure 2 A schematic flowchart illustrating a road longitudinal matching method provided in an embodiment of this disclosure;

[0044] Figure 3 This is a schematic diagram of the road shape line of a road L provided in an embodiment of the present disclosure;

[0045] Figure 4 A schematic diagram of a process for obtaining high-precision line segments and candidate standard precision line segments provided in this embodiment of the disclosure;

[0046] Figure 5 A schematic diagram of a process for determining average distance similarity provided in an embodiment of this disclosure;

[0047] Figure 6 A schematic diagram of a process for determining shape similarity provided in an embodiment of this disclosure;

[0048] Figure 7 A schematic flowchart illustrating the selection of candidate precision line segments provided in this embodiment of the disclosure;

[0049] Figure 8 A schematic diagram of a road longitudinal matching device provided in an embodiment of this disclosure;

[0050] Figure 9 This is an exemplary block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0051] To better understand the above-described objectives, features, and advantages of this disclosure, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It is to be understood that the described embodiments are only some, not all, of the embodiments of this disclosure. The specific embodiments described herein are merely for explaining this disclosure and are not intended to limit it. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure are within the scope of protection of this disclosure.

[0052] It should be noted that in this article, relational terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0053] Currently, the longitudinal matching method for roads combines intersection anchor points with direct projection. Roads near intersections are aligned using intersection anchor points, while non-nearby roads between intersections are directly projected. For example... Figure 1 As shown, A is the road shape line on the high-precision map, and A1 and A2 are the two intersection anchor points of A; B is the road shape line on the standard-precision map, and B1 and B2 are the two intersection anchor points of B; the road segment formed by A1 to A3 (the projection point of A3 on B is B1) corresponds to the intersection anchor point B1 on B, realizing the alignment of intersection anchor points; the road segment formed by A3 to A2 (the projection point of A2 on B is B3) adopts the direct projection method, projecting it onto the road segment B1 to B3 on B, realizing the direct projection of non-nearby roads between intersections.

[0054] It can be seen that, due to the fact that the roads in the high-precision map are in the longitudinal direction (i.e. Figure 1 The arrow direction in B has a precision error. After matching using the above matching method, there is a vertical offset (i.e., Figure 1 Furthermore, if the road curvature is large, the length of the matched standard road will differ significantly from the length of the high-precision road, resulting in a greater longitudinal offset and potential driving safety hazards.

[0055] To address the problem that current road longitudinal matching methods suffer from longitudinal (which can be understood as the direction of vehicle travel) accuracy errors in the high-precision map, resulting in longitudinal offset of the matched high-precision road and causing driving safety hazards, this disclosure provides a road longitudinal matching method, apparatus, device, medium, or computer program product. By acquiring the distance and shape feature points of both the high-precision line segment and the candidate high-precision line segment, the average distance similarity and shape similarity between the high-precision line segment and the candidate high-precision line segment are determined. The average distance similarity comprehensively considers the average distance from the high-precision line segment to the candidate high-precision line segment, rather than just considering the projection of the first and last points of the high-precision line segment, thus reducing lateral and longitudinal offsets caused by positional accuracy errors at the first and last points of the high-precision line segment. The shape similarity achieves matching based on shape (including position, direction, angle, and other shape information), reducing longitudinal offsets caused by shape differences. Therefore, based on the average distance and shape similarity, a candidate high-precision line segment can be selected from multiple candidate high-precision line segments as the matching high-precision line segment, reducing longitudinal offset and improving driving safety.

[0056] Figure 2This is a flowchart illustrating a road longitudinal matching method provided in an embodiment of the present disclosure. The execution subject of the road longitudinal matching method is an electronic device, including but not limited to vehicle-mounted devices, smartphones, PDAs, tablets, wearable devices with displays, desktop computers, laptops, all-in-one computers, smart home devices, servers, etc. The server can be an independent server or a cluster of multiple servers, and can include servers built locally and servers set up in the cloud.

[0057] like Figure 2 As shown, the road longitudinal matching method may include, but is not limited to, steps 201 to 205:

[0058] In step 201, the high-precision line segments to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map are obtained.

[0059] Since roads are represented by lines in the high-resolution map, road shape lines can be used to represent the corresponding roads when performing longitudinal road matching. Figure 3 The road shape line of road L is shown. Figure 3 As shown, road L has a certain width, and the centerline of road L is used ( Figure 3 The dashed line in the diagram represents the road shape line of road L.

[0060] Based on the start and end points of the high-precision line segment to be matched, the length of the high-precision line segment can be determined. In some embodiments, the length of the candidate high-precision line segment is the same as the length of the high-precision line segment. It can be seen that by obtaining multiple candidate high-precision line segments with the same length as the high-precision line segment, the high-precision line segment and the matching candidate high-precision line segment are made to have the same length. In scenarios with large shape curvature, large lateral accuracy error, or large longitudinal accuracy error, the longitudinal offset caused by the length difference is reduced.

[0061] In some embodiments, at least one candidate road shape line can be obtained from the high-precision map. For any candidate road shape line, since the roads in the high-precision map have accuracy errors in the longitudinal direction (which can be understood as the vehicle's driving direction), if the length of the candidate road shape line is less than or equal to the length of the high-precision line segment, then the candidate road shape line is directly regarded as a candidate high-precision line segment; if the length of the candidate road shape line is greater than the length of the high-precision line segment, then multiple candidate high-precision line segments can be determined based on the candidate road shape line, and each candidate high-precision line segment has the same length as the high-precision line segment.

[0062] It is evident that multiple candidate benchmark line segments may originate from the same candidate benchmark road shape line or from different candidate benchmark road shape lines.

[0063] In step 202, the distance feature points and shape feature points included in the high-precision line segment are obtained, and the distance feature points and shape feature points included in each candidate standard precision line segment are obtained.

[0064] Distance feature points can be understood as points used to divide line segments. In some embodiments, the length between adjacent distance feature points on the same line segment is the same. Since the length of each candidate precision line segment is the same as that of the high-precision line segment, the number of distance feature points included in each high-precision line segment and each candidate precision line segment is the same. It should be noted that since the shapes of the high-precision line segment and the candidate precision line segment are not completely identical, the positions (i.e., two-dimensional coordinates) of distance feature points on the high-precision line segment are different from those on the candidate precision line segment.

[0065] Shape feature points can be understood as abrupt changes in shape on a line segment. If the line segment is a straight line segment, then distance feature points can be used as shape feature points. A high-precision line segment includes multiple shape feature points, and each candidate high-precision line segment also includes multiple shape feature points. However, the number of shape feature points included in the candidate high-precision line segment may be the same as or different from the number of shape feature points included in the high-precision line segment.

[0066] In step 203, the average distance similarity between each candidate standard line segment and the high-precision line segment is determined based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment.

[0067] Since the high-precision line segment and each candidate standard line segment contain the same number of distance feature points, for any given line segment, each distance feature point on the segment is sequentially numbered. Specifically, the starting point of the line segment (which is also considered a distance feature point) is numbered 1, the distance feature points adjacent to the starting point are numbered 2, and so on. Furthermore, the distance between each distance feature point on any candidate standard line segment and the corresponding distance feature points of the same order on the high-precision line segment can be determined. These distances are then averaged to obtain the corresponding average distance similarity.

[0068] As can be seen, the average distance similarity takes into account the average distance between the high-precision line segment and the candidate standard line segment. The higher the average distance similarity, the better the candidate standard line segment matches the high-precision line segment.

[0069] Existing technologies only consider the projection of the first and last points of high-precision line segments for matching, without considering the average distance similarity. Therefore, the high-precision line segments matched by existing technologies are not optimal. In contrast, the embodiments of this disclosure consider the average distance similarity, and the selected high-precision line segments are superior to those of existing technologies. Since positional accuracy errors at the first and last points of the high-precision line segments can cause lateral and longitudinal offsets, and the high-precision line segments selected in the embodiments of this disclosure are superior, the high-precision line segments selected in the embodiments of this disclosure can reduce the lateral and longitudinal offsets caused by positional accuracy errors at the first and last points of the high-precision line segments.

[0070] In step 204, the shape similarity between each candidate standard line segment and the high-precision line segment is determined based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment.

[0071] Since the number of shape feature points in the candidate precision line segment may be the same as or different from the number of shape feature points in the high-precision line segment, each shape feature point on the candidate precision line segment can be projected proportionally onto the high-precision line segment, and vice versa. This proportional projection means that the length ratio of the shape feature point on its current line segment is the same as the length ratio of the projected point on the projected line segment. Therefore, the total number of shape feature points and projected points on the candidate precision line segment is the same as the total number of shape feature points and projected points on the high-precision line segment. Furthermore, a vector can be formed from any two adjacent points on the line segment, and this vector can express the local shape information of the line segment, including its position, direction, and angle.

[0072] Therefore, by comparing the vectors included in the candidate precision line segment with the vectors included in the high precision line segment, the vector similarity between the vectors on the candidate precision line segment and the vectors on the high precision line segment can be determined. Then, the shape similarity between the candidate precision line segment and the high precision line segment can be expressed based on the vector similarity.

[0073] As can be seen, shape similarity enables matching based on shape (including shape information such as position, orientation, and angle), reducing the vertical offset caused by shape differences.

[0074] In step 205, based on average distance similarity and shape similarity, a candidate precision line segment is selected from multiple candidate precision line segments as the precision line segment that matches the high precision line segment.

[0075] Since average distance similarity and shape similarity evaluate the similarity between candidate precision line segments and high precision line segments from two dimensions, by comprehensively considering average distance similarity and shape similarity, the optimal candidate precision line segment can be selected from multiple candidate precision line segments as the precision line segment that matches the high precision line segment, which can reduce longitudinal offset and improve driving safety.

[0076] Based on the above embodiments, step 201, "obtaining the high-precision line segments to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map", may include, but is not limited to, the following: Figure 4 The following steps 401 to 404 are shown:

[0077] In step 401, at least one candidate marked road shape line is obtained, and the minimum distance between the candidate marked road shape line and the high-precision line segment is less than or equal to a preset minimum distance threshold.

[0078] Each candidate precision road shape line represents a different precision road. By setting a minimum distance threshold, the lateral distance range of the high-precision line segment can be determined, thereby controlling the lateral deviation.

[0079] The distance between the starting point of the candidate precision road shape line and the starting point of the high precision line segment is less than or equal to a preset first distance threshold. If there are multiple points on the candidate precision road shape line whose distances to the starting point of the high precision line segment are all less than or equal to the first distance threshold, then the first target point is selected as the starting point of the candidate precision road shape line. The first target point satisfies the following condition: the first point that the vehicle passes through when traveling longitudinally along the candidate precision road shape line.

[0080] If the distance between the endpoint of the candidate precision road shape line and the endpoint of the high precision line segment is less than or equal to a preset second distance threshold, and if there are multiple points on the candidate precision road shape line whose distances to the endpoint of the high precision line segment are all less than or equal to the second distance threshold, then the second target point is selected as the endpoint of the candidate precision road shape line. The second target point satisfies the following condition: the last point the vehicle passes through when traveling longitudinally along the candidate precision road shape line.

[0081] The second distance threshold can be the same as or different from the first distance threshold.

[0082] In step 402, a distance feature point is determined at preset lengths on the high-precision line segment, wherein the start and end points of the high-precision line segment are both distance feature points.

[0083] For example, if a high-precision line segment is a straight line segment of 4 meters, then starting from the starting point of the high-precision line segment, a distance feature point is determined every preset length (e.g., 1 meter) on the high-precision line segment, so the high-precision line segment includes 5 distance feature points.

[0084] If the length between the endpoint of the high-precision line segment and an adjacent distance feature point is less than a preset length but greater than or equal to half of the preset length, then the adjacent distance feature point is retained; if the length between the endpoint of the high-precision line segment and an adjacent distance feature point is less than half of the preset length, then the adjacent distance feature point is deleted.

[0085] For example, if a high-precision line segment is a straight line segment of 4.6 meters, then a distance feature point is determined every 1 meter on the high-precision line segment. Since the length between the end point of the high-precision line segment and the adjacent distance feature point is 0.6 meters, which is less than 1 meter and greater than 0.5 meters, the adjacent distance feature point is retained. Therefore, the high-precision line segment includes 6 distance feature points.

[0086] For example, if a high-precision line segment is a straight line segment of 4.3 meters, then a distance feature point is determined every 1 meter on the high-precision line segment. Since the length between the end point of the high-precision line segment and the adjacent distance feature point is 0.3 meters, which is less than 0.5 meters, the adjacent distance feature point is deleted. Therefore, the high-precision line segment includes 5 distance feature points.

[0087] In step 403, for each candidate road shape line, a distance feature point is determined at a preset length on the candidate road shape line, and the starting point and ending point of the candidate road shape line are both distance feature points.

[0088] For example, if the candidate road shape line is a straight segment of 6 meters, then starting from the starting point of the candidate road shape line, a distance feature point is determined every preset length (e.g., 1 meter) on the candidate road shape line, so the candidate road shape line includes 7 distance feature points.

[0089] If the length between the endpoint of the candidate road shape line and an adjacent distance feature point is less than a preset length but greater than or equal to half of the preset length, then the adjacent distance feature point is retained; if the length between the endpoint of the candidate road shape line and an adjacent distance feature point is less than half of the preset length, then the adjacent distance feature point is deleted.

[0090] For example, if the candidate road shape line is a straight segment of 6.6 meters, then a distance feature point is determined every 1 meter on the candidate road shape line. Since the length between the end point of the candidate road shape line and the adjacent distance feature point is 0.6 meters, which is less than 1 meter and greater than 0.5 meters, the adjacent distance feature point is retained. Therefore, the candidate road shape line includes 8 distance feature points.

[0091] For example, if the candidate road shape line is a straight segment of 6.3 meters, then a distance feature point is determined every 1 meter on the candidate road shape line. Since the length between the end point of the candidate road shape line and the adjacent distance feature point is 0.3 meters, which is less than 0.5 meters, the adjacent distance feature point is deleted. Therefore, the candidate road shape line includes 7 distance feature points.

[0092] In step 404, if the number of distance feature points included in the candidate precision road shape line is greater than the number of distance feature points included in the high precision line segment, then multiple candidate precision line segments are determined based on the candidate precision road shape line, and the number of distance feature points included in each candidate precision line segment is the same as the number of distance feature points included in the high precision line segment.

[0093] For example, if the candidate precision road shape line is a straight segment of 6 meters, then the candidate precision road shape line includes 7 distance feature points; if the high precision line segment is a straight segment of 4 meters, then the high precision line segment includes 5 distance feature points.

[0094] Since the number of distance feature points (7) included in the candidate precision road shape line is greater than the number of distance feature points (5) included in the high precision line segment, three candidate precision line segments can be determined based on the candidate precision road shape line. Each candidate precision line segment includes five distance feature points. Specifically, the seven distance feature points included in the candidate precision road shape line are numbered sequentially, that is, the starting point of the line segment is numbered 1, the distance feature points adjacent to the starting point are numbered 2, ..., and so on. Then, the three candidate precision line segments respectively include distance feature points numbered 1 to 5, distance feature points numbered 2 to 6, and distance feature points numbered 3 to 7.

[0095] In some embodiments, the number of distance feature points included in the candidate precision line segment is the same as the number of distance feature points included in the high precision line segment, and the lengths between adjacent distance feature points on the same line segment are all the same. Therefore, the candidate precision line segment and the high precision line segment have the same length, reducing the longitudinal offset caused by the length difference. It should be noted that the distance between the endpoint of the candidate precision line segment and its adjacent distance feature points may be different from the distance between the endpoint of the high precision line segment and its adjacent distance feature points. The impact on subsequent calculations can be ignored and does not affect the final matching result.

[0096] Based on the above embodiments, step 203, which involves determining the average distance similarity between each candidate standard line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment, may include, but is not limited to, the following: Figure 5 The following steps 501 to 504 are shown:

[0097] In step 501, the order of each distance feature point on the high-precision line segment and the order of each distance feature point on each candidate precision line segment are determined.

[0098] For example, if both the candidate precision line segment and the high precision line segment include N distance feature points (including the start and end points), then the order of the start point of the high precision line segment is 1, the order of the distance feature points adjacent to the start point is 2, ..., the order of the distance feature points adjacent to the end point is N-1, and the order of the end point is N; similarly, the order of the start point of any candidate precision line segment is 1, the order of the distance feature points adjacent to the start point is 2, ..., the order of the distance feature points adjacent to the end point is N-1, and the order of the end point is N.

[0099] In step 502, for any candidate precision line segment, the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment is determined.

[0100] For example, if both the candidate precision line segment and the high precision line segment include N distance feature points, then the distance between the i-th distance feature point on the candidate precision line segment and the i-th distance feature point on the high precision line segment is denoted as d(i), where i = 1, 2, 3, ..., N. Here, d(i) is the distance calculated based on the coordinates of the i-th distance feature point on the candidate precision line segment and the i-th distance feature point on the high precision line segment.

[0101] In step 503, based on a preset distance threshold and the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment is determined.

[0102] For example, the distance similarity between the i-th distance feature point on the candidate precision line segment and the i-th distance feature point on the high precision line segment is denoted as s(i):

[0103] s(i)=1-d(i) / D

[0104] Where D is a preset distance threshold, which can be the maximum lateral accuracy deviation in the statistical results of high-precision roads and standard-precision roads. If s(i) < 0, it means that d(i) is greater than the distance threshold and cannot be matched. Therefore, s(i) = 0 is set.

[0105] In step 504, the average distance similarity between the candidate precision line segment and the high precision line segment is determined based on the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment.

[0106] For example, both the candidate precision line segment and the high precision line segment include N distance feature points. The distance between the i-th distance feature point on the candidate precision line segment and the i-th distance feature point on the high precision line segment is d(i), i = 1, 2, 3, ..., N. The distance similarity corresponding to d(i) is denoted as s(i). Then, the average distance similarity between the candidate precision line segment and the high precision line segment is S. 距离 :

[0107]

[0108] As can be seen, the average distance similarity takes into account the average distance between the high-precision line segment and the candidate standard line segment. The higher the average distance similarity, the better the candidate standard line segment matches the high-precision line segment.

[0109] Existing technologies only consider the projection of the first and last points of high-precision line segments for matching, without considering the average distance similarity. Therefore, the high-precision line segments matched by existing technologies are not optimal. In contrast, the embodiments of this disclosure consider the average distance similarity, and the selected high-precision line segments are superior to those of existing technologies. Since positional accuracy errors at the first and last points of the high-precision line segments can cause lateral and longitudinal offsets, and the high-precision line segments selected in the embodiments of this disclosure are superior, the high-precision line segments selected in the embodiments of this disclosure can reduce the lateral and longitudinal offsets caused by positional accuracy errors at the first and last points of the high-precision line segments.

[0110] Based on the above embodiments, step 204, which involves determining the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment, may include, but is not limited to, the following: Figure 6 The following steps 601 to 604 are shown:

[0111] In step 601, for any candidate precision line segment, each shape feature point on the candidate precision line segment is projected proportionally onto the high precision line segment to obtain a first set of points on the high precision line segment; and each shape feature point on the high precision line segment is projected proportionally onto the candidate precision line segment to obtain a second set of points on the candidate precision line segment; wherein, proportional projection means that the length ratio of the shape feature point on its line segment is the same as the length ratio of the projected point on the projected line segment.

[0112] The first set of points includes all shape feature points on the high-precision line segment and the proportionally projected points of all shape feature points on the candidate standard line segment onto the high-precision line segment; the second set of points includes all shape feature points on the candidate standard line segment and the proportionally projected points of all shape feature points on the high-precision line segment onto the candidate standard line segment. Therefore, the first set of points and the second set of points contain the same number of points.

[0113] For example, if a high-precision line segment includes 3 shape feature points and a candidate standard line segment includes 4 shape feature points, then the projection positions of the start and end points of the candidate standard line segment onto the high-precision line segment coincide with the start and end points of the high-precision line segment. The other 2 shape feature points of the candidate standard line segment are projected onto the high-precision line segment, resulting in 2 projection points. Therefore, the first set of points on the high-precision line segment includes 3 shape feature points and 2 projection points, for a total of 5 points. Similarly, the second set of points on the candidate standard line segment includes 4 shape feature points and 1 projection point, for a total of 5 points.

[0114] The proportion of the length of a shape feature point on the line segment can be understood as the ratio of the length between the shape feature point and the starting point of the line segment to the total length of the line segment.

[0115] Taking the projection of a high-precision line segment onto a candidate precision line segment as an example, the first shape feature point (i.e., the starting point) on the high-precision line segment is projected onto the starting point of the candidate precision line segment, meaning that the projected point coincides with the starting point of the candidate precision line segment. The length of the second shape feature point on the high-precision line segment accounts for 1 / 3 of the length of the line segment it occupies. Therefore, the length between the projection point of this shape feature point on the candidate precision line segment and the starting point of the candidate precision line segment is also 1 / 3 of the total length of the candidate precision line segment. In other words, the length of the projection point on the candidate precision line segment accounts for 1 / 3 of the length of the candidate precision line segment.

[0116] In step 602, adjacent points in the first set of points are combined to form a first vector, resulting in a first vector set; and adjacent points in the second set of points are combined to form a second vector, resulting in a second vector set.

[0117] If both the first and second point sets have M points, then the i-th first vector A in the first vector set... i It is composed of the i-th point and the (i+1)-th point in the first point set. For example, A1 is composed of the 1st point (i.e., the starting point of the high-precision line segment) and the 2nd point in the first point set, and the direction of A1 is from the 1st point to the 2nd point. Similarly, the i-th second vector B in the second vector set... i It is composed of the i-th point and the (i+1)-th point in the second set of points. Therefore, both the first and second vector sets have M-1 vectors.

[0118] By vectorizing the first set of points into a first set of vectors and the second set of points into a second set of vectors, we can use vectors to express the local shape information of a line segment, including its position, direction, and angle.

[0119] In step 603, the vector similarity between the first vector and the second vector in the first vector set and the second vector set that are in the same order is determined, and the shape similarity weight corresponding to the vector similarity is determined based on the length ratio of the points that make up the vector on the line segment they are on.

[0120] For example, the first vector A in the first vector set i With the second vector B in the second vector set i For the same order i, then A i With B i The vector similarity between them is denoted as α(A i B i ):

[0121] α(A i B i )=(min(||A i ||,||B i ||) / max(||A i ||,||Bi ||))×([A i ·B i ] / (||A i ||×||B i ||))

[0122] Among them, [A] i ·B i ]=||A i ||×||B i ||×cosθ;||A i || represents the first vector A i The length of ||B i || is the second vector B i The length of [A] i ·B i ] is the first vector A i With the second vector B i The dot product, θ is the first vector A i With the second vector B i The included angle, θ∈[0°,180°].

[0123] In this embodiment of the disclosure, the shape similarity weight corresponding to the vector similarity can be determined based on the length ratio of the points constituting the vector on the line segment where they are located. Specifically: determine the relative length ratio of the two points constituting the first vector on the high-precision line segment (or, determine the relative length ratio of the two points constituting the second vector on the candidate high-precision line segment, the values ​​of these two relative length ratios are the same); and determine the relative length ratio as the shape similarity weight corresponding to the vector similarity.

[0124] For example, the first vector A i It consists of the i-th point and the (i+1)-th point in the first set of points, and the length of the i-th point on the high-precision line segment is k. i The length ratio of the (i+1)th point on the high-precision line segment is k. i+1 The relative length ratio of the i-th point and the (i+1)-th point on the high-precision line segment is k. i+1 -k i Then (k) i+1 -k i ) is determined to be A i With B i Vector similarity α(A) between i B i The corresponding shape similarity weight.

[0125] In step 604, the shape similarity between the candidate precision line segment and the high precision line segment is determined based on the vector similarity and the shape similarity weight corresponding to the vector similarity.

[0126] Among them, the shape similarity between the candidate precision line segment and the high precision line segment is the weighted average of the vector similarity.

[0127] For example, the shape similarity between a candidate precision line segment and a high precision line segment is denoted as S. 形状 :

[0128]

[0129] Where M-1 is the number of vectors, α(A i B i ) is A i With B i Vector similarity between (k) i+1 -k i ) is α(A i B i The corresponding shape similarity weight.

[0130] In some embodiments, if distance feature points are used as shape feature points, and the high-precision line segment and the candidate standard line segment have the same length, and the high-precision line segment and the candidate standard line segment include the same number of distance feature points, N, then the shape similarity is denoted as S. 形状 The calculation formula simplifies to:

[0131]

[0132] In the above calculation formula, the value may be negative. In order to ensure that S 形状 The range of its value is [0,1], which is further adjusted to:

[0133]

[0134] Based on the above embodiments, step 205, which involves selecting a candidate precision line segment from multiple candidate precision line segments based on average distance similarity and shape similarity as the precision line segment that matches the high-precision line segment, may include, but is not limited to, the following: Figure 7 The following steps 701 and 702 are shown:

[0135] 701. Determine the comprehensive similarity based on average distance similarity and shape similarity.

[0136] The overall similarity is denoted as S:

[0137] S=β×S 距离 +γ×S 形状

[0138] Wherein, β is the weight of average distance similarity, γ is the weight of shape similarity, and β and γ are predetermined constants, for example, β = 0.3 and γ = 0.7. Those skilled in the art can determine the values ​​of β and γ in advance according to the actual application scenario. This embodiment does not limit the values ​​of β and γ.

[0139] 702. Select the candidate precision line segment with the highest comprehensive similarity from multiple candidate precision line segments as the precision line segment that matches the high precision line segment.

[0140] As can be seen, by acquiring the distance feature points and shape feature points included in both the high-precision line segment and the candidate standard line segment, the average distance similarity and shape similarity between the high-precision line segment and the candidate standard line segment can be determined. The average distance similarity comprehensively considers the average distance from the high-precision line segment to the candidate standard line segment, reducing the longitudinal offset caused by the positional accuracy error of the first and last points of the standard line segment. The shape similarity realizes shape-based matching, reducing the longitudinal offset caused by shape differences. Therefore, based on the average distance similarity and shape similarity, the standard line segment that matches the high-precision line segment can be determined, reducing the longitudinal offset and improving driving safety.

[0141] Figure 8 This is a schematic diagram of a road longitudinal matching device provided in an embodiment of this disclosure. This device can be applied to electronic devices, including but not limited to in-vehicle devices, smartphones, PDAs, tablets, wearable devices with displays, desktop computers, laptops, all-in-one computers, smart home devices, and servers. The server can be a standalone server or a cluster of multiple servers, and can include locally located servers and cloud-based servers. The road longitudinal matching device provided in this embodiment can execute the processing flow provided in the road longitudinal matching method embodiment, such as... Figure 8 As shown, the road longitudinal matching device includes: a first acquisition unit 81, a second acquisition unit 82, a first determination unit 83, a second determination unit 84, and a matching unit 85.

[0142] The first acquisition unit 81 is used for high-precision line segments to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map.

[0143] The second acquisition unit 82 is used to acquire the distance feature points and shape feature points included in the high-precision line segment, and to acquire the distance feature points and shape feature points included in each candidate high-precision line segment;

[0144] The first determining unit 83 is used to determine the average distance similarity between each candidate standard line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment.

[0145] The second determining unit 84 is used to determine the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment.

[0146] Matching unit 85 is used to select one candidate precision line segment from multiple candidate precision line segments as the precision line segment that matches the high precision line segment, based on average distance similarity and shape similarity.

[0147] In some embodiments, the first acquisition unit 81 is configured to:

[0148] Obtain at least one candidate high-precision road shape line, and the minimum distance between the candidate high-precision road shape line and the high-precision line segment is less than or equal to a preset minimum distance threshold.

[0149] A distance feature point is determined at preset lengths on the high-precision line segment, wherein the start and end points of the high-precision line segment are both distance feature points;

[0150] For each candidate road shape line, a distance feature point is determined at preset lengths along the candidate road shape line, and the start and end points of the candidate road shape line are both distance feature points.

[0151] If the number of distance feature points included in the candidate precision road shape line is greater than the number of distance feature points included in the high precision line segment, then multiple candidate precision line segments are determined based on the candidate precision road shape line. The number of distance feature points included in each candidate precision line segment is the same as the number of distance feature points included in the high precision line segment.

[0152] In some embodiments, the first determining unit 83 is configured to:

[0153] Determine the order of each distance feature point on the high-precision line segment, and the order of each distance feature point on each candidate high-precision line segment;

[0154] For any candidate precision line segment, determine the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment;

[0155] Based on a preset distance threshold and the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment is determined.

[0156] Based on the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the average distance similarity between the candidate precision line segment and the high precision line segment is determined.

[0157] In some embodiments, the second determining unit 84 is configured to:

[0158] For any candidate precision line segment, project each shape feature point on the candidate precision line segment onto the high precision line segment proportionally to obtain the first set of points on the high precision line segment; and project each shape feature point on the high precision line segment onto the candidate precision line segment proportionally to obtain the second set of points on the candidate precision line segment; wherein, proportional projection means that the length ratio of the shape feature point on its own line segment is the same as the length ratio of the projected point on the projected line segment;

[0159] Form a first vector from the adjacent points in the first set of points; and form a second vector from the adjacent points in the second set of points;

[0160] Determine the vector similarity between the first and second vectors in the first and second vector sets that are in the same order, and determine the shape similarity weight corresponding to the vector similarity based on the length ratio of the points that make up the vectors on the line segments they are on.

[0161] Based on vector similarity and the corresponding shape similarity weights, the shape similarity between the candidate precision line segment and the high precision line segment is determined.

[0162] In some embodiments, the second determining unit 84 determines the shape similarity weight corresponding to the vector similarity based on the length ratio of the points constituting the vector on the line segment where they are located, including: determining the relative length ratio of the two points constituting the first vector on the high-precision line segment, or determining the relative length ratio of the two points constituting the second vector on the candidate high-precision line segment; and determining the relative length ratio as the shape similarity weight corresponding to the vector similarity.

[0163] In some embodiments, the matching unit 85 is used for:

[0164] The overall similarity is determined based on average distance similarity and shape similarity;

[0165] The candidate line segment with the highest comprehensive similarity among multiple candidate line segments is selected as the line segment that matches the high-precision line segment.

[0166] For details of the various embodiments of the road longitudinal matching device disclosed above, please refer to the details of the various embodiments of the road longitudinal matching method described above. To avoid repetition, they will not be repeated.

[0167] Figure 9 This is an exemplary block diagram of an electronic device provided in an embodiment of this disclosure. Figure 9As shown, the electronic device includes a memory 91, a processor 92, and a computer program stored on the memory 91. It is understood that the memory 91 in this embodiment may be a volatile memory or a non-volatile memory, or may include both.

[0168] In some implementations, memory 91 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating systems and applications.

[0169] The operating system includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic tasks and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application tasks. The program implementing the road longitudinal matching method provided in this disclosure can be included in the application programs.

[0170] In this embodiment of the disclosure, at least one processor 92 executes the steps of the various embodiments of the road longitudinal matching method provided in this disclosure by calling a program or instruction stored in at least one memory 91, specifically, a program or instruction stored in an application.

[0171] The road longitudinal matching method provided in this disclosure can be applied to, or implemented by, a processor 92. The processor 92 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware of the processor 92 or by instructions in software form. The processor 92 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor.

[0172] The steps of the road longitudinal matching method provided in this disclosure can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 91, and processor 92 reads the information in memory 91 and combines it with hardware to complete the steps of the method.

[0173] This disclosure also proposes a computer-readable storage medium storing a program or instructions that cause a computer to perform steps as described in the embodiments of the road longitudinal matching method; these steps will not be repeated here to avoid repetition. The computer-readable storage medium can be a non-transitory computer-readable storage medium.

[0174] This disclosure also proposes a computer program product including computer instructions stored in a non-transitory computer-readable storage medium. When executed by a processor, the computer instructions implement the steps of the various embodiments of the road longitudinal matching method. To avoid repetition, these steps will not be repeated here.

[0175] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0176] Those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this disclosure and form different embodiments.

[0177] Those skilled in the art will understand that the descriptions of the various embodiments have different focuses, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0178] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A road longitudinal matching method, the method comprising: Obtain the high-precision line segments to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map; Obtain the distance feature points and shape feature points included in the high-precision line segment, and obtain the distance feature points and shape feature points included in each candidate high-precision line segment; wherein, the distance feature points are points used to divide the line segment, and the shape feature points are shape abrupt change points on the line segment; Based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment, the average distance similarity between each candidate standard line segment and the high-precision line segment is determined. Based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment, the shape similarity between each candidate standard line segment and the high-precision line segment is determined; Based on the average distance similarity and the shape similarity, a candidate precision line segment is selected from the plurality of candidate precision line segments as the precision line segment that matches the high precision line segment.

2. The method according to claim 1, wherein, The process of obtaining the high-precision line segment to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map includes: Obtain at least one candidate precision road shape line, wherein the minimum distance between the candidate precision road shape line and the high precision line segment is less than or equal to a preset minimum distance threshold; A distance feature point is determined at preset lengths on the high-precision line segment, wherein the start and end points of the high-precision line segment are both distance feature points; For each candidate road shape line, a distance feature point is determined every preset length on the candidate road shape line, and the start and end points of the candidate road shape line are both distance feature points; If the number of distance feature points included in the candidate precision road shape line is greater than the number of distance feature points included in the high precision line segment, then multiple candidate precision line segments are determined based on the candidate precision road shape line, and the number of distance feature points included in each candidate precision line segment is the same as the number of distance feature points included in the high precision line segment.

3. The method according to claim 1, wherein, The step of determining the average distance similarity between each candidate precision line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate precision line segment includes: Determine the order of each distance feature point on the high-precision line segment, and the order of each distance feature point on each candidate high-precision line segment; For any of the candidate precision line segments, determine the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment; Based on a preset distance threshold and the distance between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment is determined. Based on the distance similarity between each distance feature point on the candidate precision line segment and the corresponding distance feature points in the same order on the high precision line segment, the average distance similarity between the candidate precision line segment and the high precision line segment is determined.

4. The method according to claim 1, wherein, The step of determining the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment includes: For any of the candidate precision line segments, each shape feature point on the candidate precision line segment is projected proportionally onto the high precision line segment to obtain a first set of points on the high precision line segment; and each shape feature point on the high precision line segment is projected proportionally onto the candidate precision line segment to obtain a second set of points on the candidate precision line segment; wherein, the proportional projection means that the length ratio of the shape feature point on its current line segment is the same as the length ratio of the projected point on the projected line segment; The adjacent points in the first set of points are combined to form a first vector, resulting in a first vector set; and the adjacent points in the second set of points are combined to form a second vector, resulting in a second vector set. Determine the vector similarity between the first vector in the first vector set and the second vector in the second vector set, which are in the same order, and determine the shape similarity weight corresponding to the vector similarity based on the length ratio of the points that make up the vectors on the line segment they are on. Based on the vector similarity and the shape similarity weights corresponding to the vector similarity, the shape similarity between the candidate precision line segment and the high precision line segment is determined.

5. The method according to claim 4, wherein, The determination of shape similarity weights corresponding to vector similarity based on the length proportion of points on their respective line segments includes: Determine the relative length ratio of the two points that make up the first vector on the high-precision line segment, or determine the relative length ratio of the two points that make up the second vector on the candidate high-precision line segment; and determine the relative length ratio as the shape similarity weight corresponding to the vector similarity.

6. The method according to claim 1, wherein, The step of selecting a candidate precision line segment from the plurality of candidate precision line segments as the precision line segment matching the high-precision line segment based on the average distance similarity and the shape similarity includes: A comprehensive similarity is determined based on the average distance similarity and the shape similarity. The candidate line segment with the highest comprehensive similarity among the multiple candidate line segments is selected as the line segment that matches the high-precision line segment.

7. A road longitudinal matching device, the device comprising: The first acquisition unit is used to acquire the high-precision line segment to be matched on the high-precision map and multiple candidate standard-precision line segments on the standard-precision map. The second acquisition unit is used to acquire the distance feature points and shape feature points included in the high-precision line segment, and to acquire the distance feature points and shape feature points included in each candidate high-precision line segment; wherein, the distance feature points are points used to divide the line segment, and the shape feature points are shape abrupt change points on the line segment; The first determining unit is used to determine the average distance similarity between each candidate standard line segment and the high-precision line segment based on the distance feature points included in the high-precision line segment and the distance feature points included in each candidate standard line segment; The second determining unit is used to determine the shape similarity between each candidate standard line segment and the high-precision line segment based on the shape feature points included in the high-precision line segment and the shape feature points included in each candidate standard line segment; A matching unit is used to select one candidate precision line segment from the plurality of candidate precision line segments as the precision line segment that matches the high precision line segment, based on the average distance similarity and the shape similarity.

8. An electronic device, wherein, It includes a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the road longitudinal matching method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, wherein, The computer-readable storage medium stores a program or instructions that cause a computer to perform the steps of the road longitudinal matching method as described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, wherein, When executed by a processor, the computer instructions implement the steps of the road longitudinal matching method as described in any one of claims 1 to 6.

Images