A road matching method and device

Abstract

The present specification provides a road matching method and device, which obtain two roads to be compared on different maps, and obtain a number of shape points on each road to be compared; for each shape point, determine the position of the shape point, and use the angle between the entry line segment and the exit line segment corresponding to the shape point as the corner of the shape point; the entry line segment and the exit line segment corresponding to the shape point are respectively the connecting lines between the shape point and two adjacent shape points; determine a shape point pair consisting of two shape points that match the positions on different maps, and determine the degree of similarity of the corners between the two roads to be compared based on the corners of the two shape points included in each shape point pair; in response to the corner similarity being greater than a preset similarity threshold, determine that the two roads to be compared belong to the same road.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of computer application technologies, and in particular, to a road matching method and apparatus. Background Art

[0002] Map matching is the process of matching two maps obtained under different conditions so that the same locations on the two maps correspond to each other. For example, in the process of route planning for vehicle autonomous driving, a high-precision map is generally used as an aid. Since the high-precision map is not a complete map and may only include maps of some road segments, in order to plan a route, it is necessary to correspond the road segments in the high-precision map with the road segments in the standard-precision map so that a complete route can be planned based on the standard-precision map.

[0003] In the process of map matching, since the acquisition conditions of the two maps are not completely the same, the same road on the two maps cannot completely coincide. Therefore, there is a need to determine whether two roads with approximate geographical positions on the two maps are the same road. Summary of the Invention

[0004] In view of this, one or more embodiments of this specification provide a road matching method and apparatus.

[0005] According to a first aspect of one or more embodiments of this specification, a road matching method is proposed, including:

[0006] Obtain two roads to be compared on different maps, and obtain a number of shape points on each road to be compared;

[0007] For each shape point, determine the position of the shape point, and use the angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point; the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the connections between the shape point and two adjacent shape points;

[0008] Determine pairs of shape points composed of two shape points with matching positions on different maps, and determine the similarity degree of corners between the two roads to be compared according to the corners of the two shape points included in each pair of shape points;

[0009] In response to the corner similarity degree being greater than a preset similarity degree threshold, determine that the two roads to be compared belong to the same road.

[0010] According to a second aspect of one or more embodiments of this specification, a map matching method is proposed, including:

[0011] Obtain a map and vehicle trajectory positioning data;

[0012] Determine the roads to be compared on the map, and use the vehicle trajectory positioning data as another road to be compared;

[0013] Match the two roads to be compared by the aforementioned road matching method.

[0014] According to the third aspect of one or more embodiments of this specification, there is provided a map matching method, including:

[0015] Obtain the trajectory data and the standard-precision map on the high-precision map;

[0016] Determine the roads to be compared on the standard-precision map, and use the trajectory data on the high-precision map as another road to be compared;

[0017] Match the two roads to be compared by the aforementioned road matching method.

[0018] According to the fourth aspect of the embodiments of this specification, there is provided a road matching device, including:

[0019] A shape point acquisition module, configured to acquire two roads to be compared on different maps, and acquire a plurality of shape points on each road to be compared;

[0020] A corner determination module, configured to, for each shape point, determine the position of the shape point, and use the angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point; the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the connections between the shape point and two adjacent shape points;

[0021] A corner similarity degree determination module, configured to determine the pairs of shape points formed by two shape points with matching positions on different maps, and determine the corner similarity degree between the two roads to be compared according to the corners of the two shape points included in each pair of shape points;

[0022] A road matching module, configured to determine that the two roads to be compared belong to the same road in response to the corner similarity degree being greater than a preset similarity degree threshold.

[0023] According to the fifth aspect of the embodiments of this specification, there is provided a map matching device, including:

[0024] A trajectory positioning data acquisition module, configured to acquire a map and vehicle trajectory positioning data;

[0025] A road to be compared determination module, configured to determine the road to be compared on the map, and use the vehicle trajectory positioning data as another road to be compared;

[0026] A road matching module, configured to match the two roads to be compared by the aforementioned road matching method.

[0027] According to a sixth aspect of the embodiments of the present specification, there is provided a map matching device, including:

[0028] A map acquisition module, configured to acquire trajectory data and a standard-precision map on a high-precision map;

[0029] A road to be compared determination module, configured to determine a road to be compared on the standard-precision map, and use the trajectory data on the high-precision map as another road to be compared;

[0030] A road matching module, configured to match the two roads to be compared by the foregoing road matching method.

[0031] According to a seventh aspect of the embodiments of the present specification, there is provided a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the foregoing road matching method or map matching method is implemented.

[0032] According to an eighth aspect of the embodiments of the present specification, there is provided a computer device, where the computer device includes:

[0033] A processor;

[0034] A memory for storing instructions executable by the processor;

[0035] The processor runs the executable instructions to implement the foregoing road matching method or map matching method.

[0036] The present specification provides a road matching method and device, which acquire two roads to be compared on different maps, and acquire a plurality of shape points on each road to be compared; for each shape point, determine the position of the shape point, and use the included angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point; the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the connections between the shape point and two adjacent shape points; determine a pair of shape points composed of two shape points with matching positions on different maps, and determine the similarity degree of corners between the two roads to be compared according to the corners of the two shape points included in each pair of shape points; in response to the corner similarity degree being greater than a preset similarity degree threshold, determine that the two roads to be compared belong to the same road.

[0037] By calculating whether the corners at the corresponding positions on the two roads to be compared are similar, it is determined whether the two roads to be compared are similar, and the road matching result is determined more accurately and simply.

[0038] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings here are incorporated into and form a part of this specification, showing embodiments consistent with this specification, and are used together with the specification to explain the principles of this specification.

[0040] Figure 1 It is a flowchart of a road matching method shown in accordance with an exemplary embodiment of this specification.

[0041] Figure 2 It is a schematic diagram of a corner shown in accordance with an exemplary embodiment of this specification.

[0042] Figure 3 It is another schematic diagram of a corner shown in accordance with an exemplary embodiment of this specification.

[0043] Figure 4 It is a flowchart of a road matching method shown in accordance with a specific embodiment of this specification.

[0044] Figure 5 It is a flowchart of a map matching method shown in accordance with an exemplary embodiment of this specification.

[0045] Figure 6 It is a flowchart of another map matching method shown in accordance with an exemplary embodiment of this specification.

[0046] Figure 7 It is a block diagram of a road matching device shown in accordance with an exemplary embodiment of this specification.

[0047] Figure 8 It is a block diagram of a map matching device shown in accordance with an exemplary embodiment of this specification.

[0048] Figure 9 It is a block diagram of another map matching device shown in accordance with an exemplary embodiment of this specification.

[0049] Figure 10 It is a hardware structure diagram of an electronic device shown in accordance with an exemplary embodiment of this specification. Detailed Description of the Specific Embodiments

[0050] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. On the contrary, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0051] It should be noted that: In other embodiments, the steps of the corresponding method are not necessarily executed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may also be combined into a single step for description in other embodiments.

[0052] In practical applications, there is a need for map matching in a variety of scenarios.

[0053] For example, during the process of vehicle autonomous driving, it is necessary to obtain the actual driving trajectory of the vehicle (hereinafter referred to as the vehicle trajectory positioning data, and the actual driving trajectory is also a kind of map of the real world) through means such as the Global Positioning System (GPS). In order to determine which road the current vehicle is actually driving on, it is necessary to correspond the vehicle trajectory positioning data to the specific roads on the electronic map. At this time, it is necessary to match the driving trajectory composed of the vehicle trajectory positioning data with the roads on the electronic map to determine the position of the current vehicle.

[0054] In addition, for vehicle autonomous driving, generally, a high-precision map is used to assist in determining the route, that is, the driving trajectory of the vehicle on the high-precision map is first determined through the vehicle trajectory positioning data and the high-precision map. However, some data (such as road condition information) is only available on the standard-precision map; and the high-precision map is not a complete map. The high-precision map may lack the maps of some sections. It is impossible to complete the determination of the future trajectory only through the high-precision map. Then, it is necessary to correspond the driving trajectory on the high-precision map to the specific roads on the standard-precision map to obtain road condition information and determine the future trajectory of the vehicle according to the standard-precision map.

[0055] In addition, there is also a need to match the roads of different standard-precision maps and the roads of different high-precision maps.

[0056] During the process of map matching, due to different map acquisition methods, the specific drawing methods of different maps are different. Therefore, two roads with similar positions may not be exactly the same, and there is a need to match the two roads.

[0057] In the related art, generally, the Hidden Markov Model (HMM) is used to match two roads. This method is relatively complex, making it inconvenient to match two roads.

[0058] To solve the above problems, considering that a road is actually a line segment including multiple inflection points, and the corner at each inflection point indicates a change in the driving direction of the road. Then, it is possible to determine whether two roads are the same road by judging whether the corners at each inflection point are the same.

[0059] Based on this, this specification provides a road matching method and apparatus, which obtain two roads to be compared on different maps and determine at least two shape points on each road to be compared; for each shape point, determine the position of the shape point on the road to be compared to which the shape point belongs, and use the angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point; the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the connections between the shape point and two adjacent shape points; determine shape point pairs composed of two shape points with matching positions on different roads to be compared, and determine the similarity degree of corners between the two roads to be compared according to the corners of the two shape points included in each shape point pair; in response to the similarity degree of corners being greater than a preset similarity degree threshold, determine that the two roads to be compared belong to the same road.

[0060] By calculating whether the corners at corresponding positions in the two roads to be compared are similar, it is determined whether the two roads to be compared are similar, and the road matching result is determined more accurately and simply.

[0061] Next, a road matching method shown in this specification will be described.

[0062] As Figure 1 shown, Figure 1 is a road matching method shown in this specification according to an exemplary embodiment, including the following steps:

[0063] Step 101, obtain two roads to be compared on different maps and obtain a number of shape points on each road to be compared.

[0064] To determine the angle of each inflection point, considering that the lines displayed on the map are formed by connecting several points (such points are called shape points), then some or all of the shape points on the road to be compared can be used as inflection points. Therefore, at least two shape points on each road to be compared need to be obtained.

[0065] After an overall introduction to step 101, the following will provide a detailed description of step 101.

[0066] Different maps, that is, two different electronic maps to be subjected to road matching in this specification (i.e., maps that can be represented by data understandable by a computer), can be real maps (i.e., vehicle trajectory positioning data, and the roads on the real map are the roads traveled by the vehicle) and high-precision maps, high-precision maps and standard-precision maps, high-precision maps obtained under two different conditions, or high-precision maps obtained under two different conditions, etc.

[0067] To improve the road matching efficiency, two roads to be compared can be screened out first through geographical location information. For example, if it is necessary to match the first road to be compared on the first map to the second map, at least one road to be compared can be found at the corresponding position on the second map according to the position information of the first road to be compared on the first map (such as longitude and latitude information, intersection information passed through, etc.), and then the first road to be compared is respectively matched with the at least one road to be compared found according to this method.

[0068] A shape point is a point, and the line segments on the map are all connected by stored shape points. A shape point is also multiple discrete points on the map.

[0069] All the shape points of the road to be compared can be used as the obtained shape points, or some shape points can be selected from the road to be compared as the obtained shape points. For example, at a certain interval, one shape point can be selected as the obtained shape point every certain distance / certain number of shape points. Of course, the method of obtaining shape points is not limited to the above.

[0070] Step 103: For each shape point, determine the position of the shape point, and use the angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point.

[0071] Among them, the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the line segments connecting the shape point to two adjacent shape points.

[0072] Specifically, in order to compare whether two roads are the same, it is necessary to compare whether the corners of the two roads are the same. Therefore, it is necessary to first determine the corner of each shape point. The way to determine the corner, that is, to calculate: the angle between the line segments connecting each determined shape point to the shape points on both sides of the shape point.

[0073] After giving an overall description of step 103, the following will give a detailed description of step 103.

[0074] The position of the shape point is determined because, in order to compare whether two corners are the same, it is necessary to compare whether the corners at the same position are the same. Therefore, it is necessary to determine the position of the shape point.

[0075] Among them, the position of the shape point can be represented by intersections on the map. For example, the position of the shape point can be between intersection A and intersection B. The position of the shape point can also be represented by other elements on the map, not limited to intersection positions.

[0076] In addition, the position of the shape point can be represented not only by position elements on the map, but also by the position of the shape point on the road to be compared. For example, each road to be compared has a starting point. Then, the position of the shape point on the road to be compared can be represented by the distance between the starting point and the shape point. This distance can be a straight-line distance or the distance required to pass through the road to be compared from the starting point to the shape point.

[0077] In the latter case, determining the position of the shape point in step 103 includes: calculating the distance of each shape point from the starting point of the road to be compared to which the shape point belongs, and taking the calculated distance as the driving distance of the shape point. That is, the position of the shape point is represented by the driving distance. It should be noted that in addition to representing the position of the shape point on the road to be compared by the distance between the shape point and the starting point, it can also be represented by the distance between the shape point and the end point, or by the distance between the shape point and a certain intersection.

[0078] Of course, the position of the shape point can also be determined by a combination of multiple methods, and this specification does not limit the representation method of the distance of the shape point.

[0079] After explaining how to determine the position of the shape point, the method for determining the corner will be described next.

[0080] See Figure 2 , Figure 2 The middle point among the three points in is the shape point of the corner to be calculated, and the other two points are the two shape points adjacent to this shape point on the road to be compared. Among them, the adjacent shape points can be determined by the distance between each shape point, and the two shape points closest to this shape point are used as the two shape points adjacent to this shape point. In addition, the shape points can also be numbered. According to a certain direction (for example, for vehicle trajectory positioning data, numbered in the order of the acquisition time of the positioning data from front to back), the shape points with numbers adjacent to this shape point are used as the adjacent shape points. For example, if the shape point of the corner to be calculated is No. 10, then the No. 11 shape point and the No. 9 shape point are the shape points adjacent to the shape point of the corner to be calculated.

[0081] The lines connecting the shape point of the corner to be calculated with the other two shape points are the incoming line segment and the outgoing line segment. Figure 2 The left line segment in is the incoming line segment, the right line segment is the outgoing line segment, and the dotted line is the extension line of the incoming line segment. The corner is Figure 2The angle drawn in [description] represents the angle that needs to be turned when driving from the incoming line segment to the outgoing line segment.

[0082] In addition, to distinguish between left turns and right turns, the corners have positive and negative values. For example, a left turn can be set as positive and a right turn as negative. For specific details, see Figure 3 , Figure 3 In [description], the left corner is a left turn with a positive value, and the right corner is a right turn with a negative value. Of course, it is also possible to set a right turn as positive and a left turn as negative. Here, only one way of distinguishing left and right turns is shown, and it does not represent a limitation to this specification.

[0083] It should be noted that in addition to Figure 2 the angle in [description] as the corner, the supplementary angle of the angle marked in Figure 2 can also be used as the corner. This specification does not limit which specific included angle is used as the corner. However, it is necessary to ensure that the calculation criteria for the corners of all shape points are the same, so as to compare the corners at the same positions of different roads to be compared.

[0084] In addition, considering that due to limited map acquisition conditions, the trajectories of the roads on the map cannot be completely accurate, then some shape points with relatively small corners (under the corner calculation method shown in Figure 2 ) may actually be noise points. To prevent noise points from affecting subsequent judgments, noise points can also be filtered out before performing step 105.

[0085] In other words, before step 105, it also includes: for each shape point, in response to the absolute value of the corner of the shape point being not less than a preset threshold, determining that the shape point pair is a valid shape point.

[0086] Step 105: Determine the shape point pairs composed of two shape points that match in position on different maps, and determine the similarity degree of the corners between the two roads to be compared according to the corners of the two shape points included in each shape point pair.

[0087] Specifically, to compare whether the corners of the two roads to be compared are similar, it is necessary to first match the same corners of the two roads, and then compare whether each group of matched corners is similar.

[0088] After a general description of step 105, the following will provide a detailed description of step 105.

[0089] A shape point pair refers to two shape points that match in two maps. Matching in position means that when the two shape points are placed in the same map, the positions of the two shape points are adjacent or close.

[0090] When the position of a shape point is characterized by the elements on the map described above, the matching of the positions of two shape points can be determined according to the positions of the elements. For example, when the position of a shape point is characterized by passing through an intersection, shape point 1 is between intersection A and intersection B, and shape point 2 is also between intersection A and intersection B, then it can be considered that the positions of shape point 1 and shape point 2 match.

[0091] When the position of a shape point is characterized by the position on the road to be compared described above, two shape points with the difference in the distance from a certain fixed point within a certain range can be used as the shape points with matching positions.

[0092] In other words, taking the distance from the starting point to characterize the position of a shape point on the road to be compared as an example, in step 105, determining the shape point pairs composed of two shape points with matching positions on different maps includes: determining the shape point pairs according to the driving distances of each shape point; the absolute value of the difference in the driving distances of the two shape points included in the shape point pair is less than a preset difference threshold, and the two shape points included in the shape point pair belong to different roads to be compared.

[0093] After explaining the method for determining shape point pairs, the countermeasures for the situation where some shape points cannot form shape point pairs will be described next.

[0094] In addition, considering that in some cases, the number of original shape points on two roads to be compared is inconsistent, or the number of shape points obtained in step 101 when obtaining shape points is inconsistent, or due to other reasons, the number of shape points on two roads to be compared is inconsistent. In the case where a shape point cannot find a shape point with a matching position, the shape point can be discarded.

[0095] In the above situation, in addition to discarding the shape point, for the shape points that cannot form shape point pairs, a supplementary shape point can be added at the corresponding position (i.e., the position where the shape point is located) on the other road to be compared (except for the road to which the shape point belongs) to form a shape point pair with the shape point, and the corner of the supplementary shape point is determined according to the changing trend of the road.

[0096] In other words, step 105 includes: for each shape point on any road to be compared that has not formed a shape point pair: in response to the existence of a shape point on the other road to be compared whose position on the road to be compared matches the position of this shape point, determining that this shape point and the matching shape point form a shape point pair. In response to the non-existence of a shape point on the other road to be compared whose position on the road to be compared matches the position of this shape point, generating a supplementary shape point on the other road to be compared, and determining that this shape point and the supplementary shape point form a shape point pair; the position of the supplementary shape point on the other road to be compared matches the position of this shape point on the road to be compared.

[0097] After explaining the shape point pairs, the method for determining the similarity degree of corners will be described next.

[0098] The similarity degree of corners between two roads is a parameter for judging whether the corresponding corners at the same positions between the two roads are similar.

[0099] The method for determining the similarity degree of corners between two roads can be to first determine the similarity degree of corners for each shape point pair, and then comprehensively determine the similarity degree of corners between the two roads to be compared by integrating the similarity degrees of corners of all shape point pairs. It can also be to simply compare each shape point pair without generating the similarity degree of corners, and then process the comparison results of all shape point pairs to obtain the similarity degree of corners between the two roads.

[0100] For the latter case mentioned above, it can be to first simply compare each shape point pair to determine the corner difference between the two shape points included in each shape point pair, and then integrate and process the corner differences of all shape point pairs to obtain the similarity degree of corners used to describe whether the corners of all shape points are similar.

[0101] For the former case mentioned above, the way to integrate the similarity degrees of corners can be to calculate the average value of the similarity degrees of corners of each shape point pair. Of course, it can also be to sum up the similarity degrees of corners of each shape point pair. Of course, it can also be calculated by other methods, such as adding the reciprocals of the similarity degrees of corners and then taking the reciprocal of the resulting sum, etc. This specification does not limit the method for integrating the similarity degrees of corners.

[0102] It should be noted that if the similarity degree of corners between two roads to be compared is calculated by summing up the similarity degrees of corners of each shape point pair, considering that in some cases, the roads to be compared in different comparisons are of different lengths, sometimes the roads to be compared are short and sometimes they are long, then it may result in a smaller similarity degree of corners when the roads to be compared are long.

[0103] To solve the above problem, the length of the road to be compared can be introduced when calculating the similarity degree of roads between two roads, so as to obtain the similarity degree of corners per unit length between the two roads.

[0104] In other words, the method for determining the similarity degree of the corners between the two roads to be compared in step 105 is as follows: for each pair of shape points, according to the corners of the two shape points included in the pair of shape points, determine the similarity degree of the corners of the two shape points included in the pair of shape points; according to the similarity degrees of the corners of the two shape points included in each pair of shape points, determine the total corner similarity degree between the two roads to be compared; according to the lengths of the two roads to be compared and the total corner similarity degree, determine the corner similarity degree per unit length of the two roads to be compared, and use the corner similarity degree per unit length as the corner similarity degree between the two roads to be compared.

[0105] The method for determining the length of the road to be compared can be to use the length of any one of the roads to be compared as the length of the road to be compared. However, considering that there may be differences in the lengths between different roads to be compared. For example, because the acquisition methods of the two roads to be compared are different and the precisions are different, the road to be compared with higher precision may have more arcs (which are not shown in the road to be compared with lower precision), which may result in the road to be compared with higher precision being longer. To solve this problem, the average value of the lengths of the two roads to be compared can be used as the length of the road to be compared.

[0106] In other words, the above-mentioned determination of the corner similarity degree per unit length of the two roads to be compared according to the lengths of the two roads to be compared and the total corner similarity degree includes: determining the average road length according to the lengths of the two roads to be compared on the map; determining the total corner similarity degree per unit length of the two roads to be compared according to the average length and the total corner similarity degree.

[0107] After explaining the method for determining the length of the road to be compared, next, the method for determining the corner similarity degree corresponding to each pair of shape points will be explained.

[0108] The similarity degree of the corners corresponding to each pair of shape points can be the reciprocal of the absolute value of the difference between the corners of the two shape points included in the pair of shape points, or the reciprocal of the variance of the corners of the two shape points included in the pair of shape points. Of course, the method for determining the similarity degree of the corners of the pair of shape points can also be other methods, and the above examples do not represent a limitation to this specification.

[0109] When determining the similarity degree of corners using variance, the similarity degree of the corners of the two shape points included in the shape point pair is determined according to the corners of the two shape points included in the shape point pair. Specifically, it includes: calculating the variance of the corners of the two shape points included in the shape point pair according to the corners of the two shape points included in the shape point pair; the variance corresponding to the shape point pair is inversely proportional to the similarity degree of the corners of the two shape points included in the shape point pair. According to the similarity degree of the corners of the two shape points included in each shape point pair, the total corner similarity degree between the two roads to be compared is determined, including: summing the variances corresponding to each shape point pair to obtain the variance sum, and the variance sum is inversely proportional to the total corner similarity degree between the two roads to be compared.

[0110] Of course, in addition to representing the total corner similarity degree by the variance sum, the average value of the variances can also be used to represent the similarity degree of two corners.

[0111] In addition, in the case of filtering out valid shape points, step 105 is also based on the valid shape points for operation. That is, step 105 includes: determining, from the valid shape points, a shape point pair composed of two shape points with matching positions on different roads to be compared.

[0112] Step 107, in response to the corner similarity degree being greater than a preset similarity degree threshold, determining that the two roads to be compared belong to the same road.

[0113] In other words, the more similar the corners between two roads are, the more it indicates that the two roads to be compared are the same road.

[0114] Next, a specific embodiment will be used to illustrate a road matching method shown in this specification.

[0115] As Figure 4 shown, the road matching method includes the following steps:

[0116] Step 401, determining the driving distance of the shape point.

[0117] In other words, it is necessary to first determine several shape points of the two roads to be compared from the map, calculate the distance from the starting point to each shape point, and use this distance as the driving distance of each shape point.

[0118] Step 403, calculating the corner of each shape point.

[0119] For the specific calculation method, refer to Figure 2 and the corresponding description, which will not be elaborated here.

[0120] Step 405, filtering out corner noise points.

[0121] Filter out the noise points with angle values between -10° and 10°.

[0122] Step 407: Convert the driving distance and the corner to the distance-corner coordinate system.

[0123] Take the corner as the x-axis of the Cartesian coordinate and the driving distance as the y-axis of the Cartesian coordinate. Convert the distance and corner of each shape point to the distance-corner coordinate system, so as to correspond each corner through the driving distance on the y-axis to obtain several pairs of shape points.

[0124] Step 409: Calculate the variance corresponding to the corner.

[0125] According to each corner corresponding to Step 404, calculate the variance of the two corners included in each pair of shape points, and find the sum C of the calculated variances.

[0126] Step 411: Determine the similarity degree between two roads to be compared.

[0127] Determine the average road length K of the two roads to be compared. Obtain the correlation value F of the two roads according to the following formula (1), and this correlation value is inversely proportional to the similarity degree between the two roads.

[0128] F = a·(C / K) (1)

[0129] Where a is any positive integer.

[0130] Next, two examples will be used to illustrate the application scenarios of the above road matching method.

[0131] As mentioned above, the above road matching method can be used to judge whether the vehicle driving trajectory matches certain roads in the high-precision map, so as to determine the driving trajectory of the autonomous vehicle in the high-precision map, and thus can navigate the autonomous vehicle more conveniently and quickly.

[0132] As Figure 5 shown, Figure 5 is a map matching method shown in this specification according to an exemplary embodiment, including:

[0133] Step 501: Obtain the map and vehicle trajectory positioning data.

[0134] Step 503: Determine the roads to be compared on the map, and use the vehicle trajectory positioning data as another road to be compared.

[0135] Step 505: Match the two roads to be compared by the foregoing road matching method.

[0136] Through the above method, the vehicle trajectory positioning data is corresponded to the high-precision map, so as to determine the position of the autonomous vehicle on the high-precision map, so that the autonomous vehicle can be navigated in real time through the high-precision map.

[0137] In addition, as described above, some road condition information is only available in the refined map, and there are imperfections in the high-precision map. It is necessary to determine the position of the vehicle in the refined map, so as to provide road condition information for the autonomous driving vehicle through the refined map and plan the trajectory of the autonomous driving vehicle through the refined map.

[0138] As Figure 6 shown, Figure 5 is a map matching method shown in this specification according to an exemplary embodiment, including:

[0139] Step 601, obtain the trajectory data on the high-precision map and the refined map.

[0140] Step 603, determine the road to be compared on the refined map, and use the trajectory data on the high-precision map as another road to be compared.

[0141] Step 605, match the two roads to be compared through the aforementioned road matching method.

[0142] In this way, the position of the vehicle on the refined map can be determined, road condition information can be provided for the user through the refined map, and the future trajectory of the vehicle can be planned through the refined map.

[0143] Of course, it should be noted that the solution provided in this specification can be applied not only to the above application scenarios, but also to matching different roads on two maps, or matching two trajectories, etc. The above examples do not represent a limitation to this specification.

[0144] Corresponding to the embodiment of the foregoing method, this specification also provides an embodiment of a device and a terminal to which the device is applied.

[0145] As Figure 7 shown, Figure 7 is a block diagram of a road matching device shown in this specification according to an exemplary embodiment. The device includes:

[0146] A shape point acquisition module 710, configured to acquire two roads to be compared on different maps and acquire a plurality of shape points on each road to be compared;

[0147] A corner determination module 720, configured to, for each shape point, determine the position of the shape point and use the included angle between the incoming line segment and the outgoing line segment corresponding to the shape point as the corner of the shape point; the incoming line segment and the outgoing line segment corresponding to the shape point are respectively the connections between the shape point and two adjacent shape points;

[0148] The corner similarity determination module 730 is configured to determine a pair of shape points formed by two shape points with matching positions on different maps, and determine the corner similarity between two roads to be compared according to the corners of the two shape points included in each pair of shape points;

[0149] The road matching module 740 is configured to determine that the two roads to be compared belong to the same road in response to the corner similarity being greater than a preset similarity threshold.

[0150] Among them, the corner determination module 720 includes a position determination sub-module 721 (not shown in the figure) and a corner determination sub-module 722 (not shown in the figure), and the corner similarity determination module 730 includes a shape point pair determination sub-module 731 and a corner similarity determination sub-module 732 (not shown in the figure).

[0151] In an optional embodiment, the position determination sub-module 721 is configured to: calculate the distance of each shape point from the starting point of the road to be compared to which the shape point belongs, and use the calculated distance as the driving distance of the shape point. The shape point pair determination sub-module 731 is configured to: determine a pair of shape points according to the driving distances of the respective shape points; the absolute value of the difference in the driving distances of the two shape points included in the pair of shape points is less than a preset difference threshold, and the two shape points included in the pair of shape points belong to different roads to be compared.

[0152] In an optional embodiment, the shape point pair determination sub-module 731 is configured to: for each shape point on any road to be compared that has not formed a pair of shape points: in response to the existence of a shape point on another road to be compared whose position matches the position of the shape point on the road to be compared, determine that the shape point and the matching shape point form a pair of shape points; in response to the non-existence of a shape point on another road to be compared whose position matches the position of the shape point on the road to be compared, generate a supplementary shape point on the other road to be compared, and determine that the shape point and the supplementary shape point form a pair of shape points; the position of the supplementary shape point on the other road to be compared matches the position of the shape point on the road to be compared.

[0153] In an optional embodiment, before the corner similarity determination module 730, there is further included: an effective shape point pair determination module 729 (not shown in the figure), which is configured to, for each shape point, determine that the shape point pair is an effective shape point in response to the absolute value of the corner of the shape point being not less than a preset threshold. The shape point pair determination sub-module 731 is configured to: determine a pair of shape points formed by two shape points with matching positions on different roads to be compared from the effective shape points.

[0154] In an optional embodiment, the corner similarity determination sub-module 732 includes:

[0155] A similarity determination unit, configured to determine, for each pair of shape points, the similarity degree of the corners of the two shape points included in the pair of shape points according to the corners of the two shape points included in the pair of shape points.

[0156] A total corner similarity determination unit, configured to determine the total corner similarity degree between two roads to be compared according to the similarity degrees of the corners of the two shape points included in each pair of shape points;

[0157] A total corner similarity determination unit per unit length, configured to determine the total corner similarity degree per unit length of the two roads to be compared according to the lengths of the two roads to be compared and the total corner similarity degree, and use the total corner similarity degree per unit length as the corner similarity degree between the two roads to be compared.

[0158] In an optional embodiment, the similarity determination unit is configured to calculate the variance of the corners of the two shape points included in the pair of shape points according to the corners of the two shape points included in the pair of shape points; the variance corresponding to the pair of shape points is inversely proportional to the similarity degree of the corners of the two shape points included in the pair of shape points. The total corner similarity determination unit is configured to sum the variances corresponding to each pair of shape points to obtain a variance sum, and the variance sum is inversely proportional to the total corner similarity degree between the two roads to be compared.

[0159] In an optional embodiment, the total corner similarity determination unit per unit length is configured to determine the average road length according to the lengths of the two roads to be compared on the map; determine the corner similarity degree per unit length of the two roads to be compared according to the average length and the total corner similarity degree.

[0160] In addition, as Figure 8 shown, this specification also shows a map matching device, including:

[0161] A trajectory positioning data acquisition module 810, configured to acquire a map and vehicle trajectory positioning data.

[0162] A road to be compared determination module 820, configured to determine the road to be compared on the map and use the vehicle trajectory positioning data as another road to be compared.

[0163] A road matching module 830, configured to match the two roads to be compared by the foregoing road matching method.

[0164] As Figure 9 shown, this specification also shows a map matching device, including:

[0165] A map acquisition module 910, configured to acquire trajectory data and a calibrated map on a high-precision map.

[0166] A road to be compared determination module 920, configured to determine a road to be compared on the accurate map and use the trajectory data on the high-precision map as another road to be compared.

[0167] A road matching module 930, configured to match the two roads to be compared by the foregoing road matching method.

[0168] For the implementation processes of the functions and effects of each module in the foregoing apparatus, refer to the implementation processes of the corresponding steps in the foregoing method for details, which will not be elaborated herein.

[0169] For the apparatus embodiment, since it basically corresponds to the method embodiment, refer to the partial description of the method embodiment for the relevant parts. The apparatus embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this specification. A person of ordinary skill in the art can understand and implement it without creative efforts.

[0170] As Figure 10 shown, Figure 10 shows a hardware structure diagram of the electronic device where the foregoing apparatus is located. The device may include: a processor 1010, a memory 1020 for storing executable instructions of the processor, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0171] The processor 1010 may be implemented in a general CPU (Central Processing Unit), a microprocessor, an application specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is configured to implement the technical solutions provided in the embodiments of this specification by running the executable instructions.

[0172] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0173] The input / output interface 1030 is used to connect to the input / output module to achieve information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0174] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to achieve communication and interaction between this device and other devices. Among them, the communication module can achieve communication through a wired method (such as USB, network cable, etc.) or can also achieve communication through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.).

[0175] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0176] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, this device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solutions of the embodiments of this specification and does not necessarily include all the components shown in the figure.

[0177] The embodiments of this specification also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the road matching method or the map matching method as described above.

[0178] Computer readable media include permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0179] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises one..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0180] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A road matching method, comprising: Obtain two roads to be compared on different maps, and obtain a number of shape points on each road to be compared; For each shape point, determine the position of the shape point, and take the angle between the entry line segment and the exit line segment corresponding to the shape point as the turning corner of the shape point; the entry line segment and the exit line segment corresponding to the shape point are the connecting lines between the shape point and two adjacent shape points respectively; Determine shape point pairs consisting of two shape points that match each other at positions on different maps, and determine the degree of similarity of corners between the two roads to be compared based on the corners of the two shape points included in each shape point pair; In response to the corner similarity being greater than a preset similarity threshold, it is determined that the two roads to be compared belong to the same road.

2. The method according to claim 1, wherein determining the position of the shape point comprises: Calculate the distance between each shape point and the starting point of the road to be compared to which the shape point belongs, and use the calculated distance as the travel distance of the shape point; Determine a shape point pair consisting of two shape points that match positions on different maps, including: A shape point pair is determined according to the driving distance of each shape point; if the absolute value of the driving distance difference between two shape points included in the shape point pair is less than a preset difference threshold, the two shape points included in the shape point pair belong to different roads to be compared.

3. The method according to claim 1, wherein determining a shape point pair consisting of two shape points matching each other at positions on different maps comprises: For each shape point that does not form a shape point pair on any road to be compared: In response to the presence of a shape point on another road to be compared that has a position matching the position of the shape point on the road to be compared, determining that the shape point and the matching shape point form a shape point pair; In response to the absence of a shape point on another road to be compared whose position matches the position of the shape point on the road to be compared, a supplementary shape point is generated on the other road to be compared, and it is determined that the shape point and the supplementary shape point form a shape point pair; the position of the supplementary shape point on the other road to be compared matches the position of the shape point on the road to be compared.

4. The method according to claim 1, before determining a shape point pair consisting of two shape points matching positions on different maps, further comprising: For each shape point, in response to the absolute value of the corner of the shape point being not less than a preset threshold, determining the shape point pair as a valid shape point; The step of determining a shape point pair consisting of two shape points matching positions on different roads to be compared comprises: From the valid shape points, a shape point pair consisting of two shape points matching each other at positions on different roads to be compared is determined.

5. The method according to claim 1, wherein determining the degree of similarity of corners between two roads to be compared based on the corners of two shape points included in each shape point pair comprises: For each shape point pair, according to the corners of the two shape points included in the shape point pair, determine the similarity of the corners of the two shape points included in the shape point pair; Determine the total corner similarity between the two roads to be compared according to the similarity of the corners of the two shape points included in each shape point pair; According to the lengths of the two roads to be compared and the total corner similarity, the total corner similarity per unit length of the two roads to be compared is determined, and the total corner similarity per unit length is used as the corner similarity between the two roads to be compared.

6. The method according to claim 5, wherein determining the similarity of the corners of the two shape points included in the shape point pair according to the corners of the two shape points included in the shape point pair comprises: According to the corners of the two shape points included in the shape point pair, the variance of the corners of the two shape points included in the shape point pair is calculated; the variance corresponding to the shape point pair is inversely proportional to the similarity of the corners of the two shape points included in the shape point pair; Determining the total corner similarity between the two roads to be compared according to the similarity of the corners of the two shape points included in each shape point pair includes: The variances corresponding to each shape point pair are summed to obtain a variance sum, which is inversely proportional to the degree of similarity of the total corners between the two roads to be compared.

7. The method according to claim 5, wherein determining the total corner similarity per unit length of the two roads to be compared based on the lengths of the two roads to be compared and the total corner similarity comprises: According to the lengths of the two roads to be compared on the map, determine the average road length; The total corner similarity per unit length of the two roads to be compared is determined according to the length average value and the total corner similarity.

8. A map matching method, comprising: Obtain maps and vehicle trajectory positioning data; Determine a road to be compared on the map, and use the vehicle trajectory positioning data as another road to be compared; By using the method described in any one of claims 1 to 7, two roads to be compared are matched.

9. A map matching method, comprising: Obtain trajectory data and standard precision maps on high-precision maps; Determine a road to be compared on the standard precision map, and use the trajectory data on the high precision map as another road to be compared; By using the method described in any one of claims 1 to 7, two roads to be compared are matched.

10. A road matching device, comprising: A shape point acquisition module is used to acquire two roads to be compared on different maps, and acquire a number of shape points on each road to be compared; A corner determination module is used to determine the position of each shape point, and take the angle between the entry line segment and the exit line segment corresponding to the shape point as the corner of the shape point; the entry line segment and the exit line segment corresponding to the shape point are respectively the connecting lines between the shape point and two adjacent shape points; A corner similarity determination module is used to determine shape point pairs consisting of two shape points that match each other at different locations on different maps, and determine the corner similarity between two roads to be compared based on the corners of the two shape points included in each shape point pair; The road matching module is used to determine that the two roads to be compared belong to the same road in response to the corner similarity being greater than a preset similarity threshold.

11. A map matching device, comprising: A trajectory positioning data acquisition module is used to obtain maps and vehicle trajectory positioning data; A road to be compared determination module, used to determine a road to be compared on a map, and use the vehicle trajectory positioning data as another road to be compared; A road matching module, used to match two roads to be compared by using the method described in any one of claims 1 to 7.

12. A map matching device, comprising: Map acquisition module, used to obtain trajectory data and standard precision maps on high-precision maps; A road to be compared determination module is used to determine a road to be compared on the standard precision map, and use the trajectory data on the high-precision map as another road to be compared; A road matching module, used to match two roads to be compared by using the method described in any one of claims 1 to 7.

13. An electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 9 by running the executable instructions.

14. A computer-readable storage medium having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the method according to any one of claims 1 to 9.

Images