Crossroad adjustment method, device, equipment and storage medium

Abstract

The present application relates to an intersection road adjustment method, device, equipment and storage medium. The method comprises: obtaining two road lines to be processed, wherein the two road lines to be processed correspond to public road sections in the intersection opposite roads; there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed, determining the center point between the two sampling points contained in the sampling point pair, identifying abnormal sampling points and normal sampling points in each sampling point according to the distribution of each sampling point and the center point in the two road lines to be processed, and adjusting the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point, wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point in each sampling point of the two road lines to be processed. The use of this method can improve the accuracy of road line construction.

Description

Technical Field

[0001] The present application relates to the field of map technology, and in particular to a method, device, equipment and storage medium for adjusting cross roads. Background Art

[0002] With the rapid development of electronic map technology, in order to improve the accuracy of electronic maps, it is necessary to accurately construct road lines in electronic maps. Existing road line construction methods generally perform fitting processing on vehicle driving trajectories, and then use the fitted curve as the road line in the electronic map.

[0003] For the opposite roads in real roads, such roads can be regarded as two adjacent roads that are almost parallel but in opposite directions. However, due to the deviation of vehicle trajectories and the technical limitations of fitting, when constructing the road lines of the opposite roads, the two road lines obtained may intersect, which is inconsistent with the actual situation. Summary of the invention

[0004] Based on this, it is necessary to provide an intersection road adjustment method, device, equipment and storage medium that can improve the accuracy of road line construction results in response to the above technical problems.

[0005] In a first aspect, the present application provides a cross-road adjustment method, comprising:

[0006] Obtain two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0007] Determine the center point between two sampling points included in the sampling point pair;

[0008] According to the distribution of each sampling point and the central point in the two road lines to be processed, the abnormal sampling points and the normal sampling points in each sampling point are identified;

[0009] The abnormal sampling point is adjusted in position according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0010] In one of the embodiments, adjusting the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point includes: generating an adjustment vector of the abnormal sampling point according to the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point; and adjusting the position of the abnormal sampling point according to the center point corresponding to the abnormal sampling point and the corresponding adjustment vector.

[0011] In one of the embodiments, generating an adjustment vector of an abnormal sampling point according to a sampling vector constructed by a reference sampling point and a center point corresponding to the reference sampling point includes: determining a rotation angle according to the center point corresponding to the reference sampling point and center points corresponding to other normal sampling points adjacent to the reference sampling point; and rotating the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point according to the rotation angle to obtain the adjustment vector of the abnormal sampling point.

[0012] In one of the embodiments, determining the rotation angle according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point includes: constructing a first center vector according to the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point; constructing a second center vector according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point; and determining the rotation angle according to the first center vector and the second center vector.

[0013] In one of the embodiments, according to the distribution of each sampling point and the center point in two road lines to be processed, abnormal sampling points and normal sampling points in each sampling point are identified, including: for each sampling point, according to the sampling point and the corresponding center point, a sampling vector corresponding to the sampling point is constructed; according to the center point corresponding to the sampling point and the center point corresponding to the adjacent sampling points of the sampling point in a preset extension direction, a center vector corresponding to the sampling point is constructed; according to the sampling vector corresponding to the sampling point and / or the corresponding center vector, the category to which the sampling point belongs is determined; wherein the category to which the sampling point belongs is an abnormal sampling point or a normal sampling point.

[0014] In one of the embodiments, determining the category of the sampling point according to the sampling vector and / or the corresponding center vector corresponding to the sampling point includes at least one of the following: determining whether the sampling point is an abnormal sampling point according to the vector value of the sampling vector corresponding to the sampling point; determining whether the sampling point is an abnormal sampling point according to the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector; determining whether the sampling point is an abnormal sampling point according to the travel direction of the road line to be processed to which the sampling point belongs predicted by the sampling vector corresponding to the sampling point and the corresponding center vector.

[0015] In one of the embodiments, determining whether a sampling point is an abnormal sampling point according to a vector value of a sampling vector corresponding to the sampling point includes: if the vector value of the sampling vector corresponding to the sampling point is less than an abnormal spacing threshold, determining the sampling point to be an abnormal sampling point; wherein the abnormal spacing threshold is determined in the following manner: determining the sampling point spacing corresponding to the sampling point pair according to the spacing between the sampling points included in the sampling point pair; determining the abnormal spacing threshold according to the sorting of the sampling point spacings corresponding to each sampling point pair.

[0016] In one of the embodiments, obtaining two road lines to be processed includes: obtaining original road lines corresponding to two opposite roads; determining the public road lines corresponding to the public road sections on the two original road lines when the two original road lines intersect; determining whether there is an abnormal intersection between the two original road lines based on the length of the public road line, the angle between the two public road lines, and the height difference between the public road sections corresponding to the two public road lines; and using the two original road lines with the abnormal intersection as two road lines to be processed.

[0017] In a second aspect, the present application further provides a cross-road adjustment device, comprising:

[0018] An acquisition module is used to acquire two road lines to be processed; wherein the two road lines to be processed correspond to public road sections in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0019] A determination module, used to determine a center point between two sampling points included in a sampling point pair;

[0020] An identification module, used for identifying abnormal sampling points and normal sampling points among the sampling points according to the distribution of the sampling points and the center point in the two road lines to be processed;

[0021] The adjustment module is used to adjust the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0022] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0023] Obtain two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0024] Determine the center point between two sampling points included in the sampling point pair;

[0025] According to the distribution of each sampling point and the central point in the two road lines to be processed, the abnormal sampling points and the normal sampling points in each sampling point are identified;

[0026] The abnormal sampling point is adjusted in position according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Obtain two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0029] Determine the center point between two sampling points included in the sampling point pair;

[0030] According to the distribution of each sampling point and the central point in the two road lines to be processed, the abnormal sampling points and the normal sampling points in each sampling point are identified;

[0031] The abnormal sampling point is adjusted in position according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0032] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0033] Obtain two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0034] Determine the center point between two sampling points included in the sampling point pair;

[0035] According to the distribution of each sampling point and the central point in the two road lines to be processed, the abnormal sampling points and the normal sampling points in each sampling point are identified;

[0036] The abnormal sampling point is adjusted in position according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0037] The above-mentioned intersection road adjustment method, device, equipment and storage medium introduce the center point between the two sampling points contained in each sampling point pair in the two road lines to be processed, and identify the abnormal sampling points and normal sampling points in each sampling point according to the distribution of each sampling point and the center point, and the two road lines to be processed are public road sections in the corresponding intersecting opposite roads. Therefore, the distribution of each sampling point and the center point can reflect the intersection of the road lines to be processed to a certain extent. Correspondingly, after determining the normal sampling point adjacent to the abnormal sampling point as the reference sampling point from each sampling point of the two road lines to be processed, and adjusting the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point, it can ensure the fit between the position adjustment result and the actual situation, thereby improving the accuracy of the constructed road line. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A schematic diagram of a flow chart of a cross-road adjustment method in one embodiment;

[0040] Figure 2 A schematic diagram of a road line to be processed in an embodiment;

[0041] Figure 3 A schematic diagram of a flow chart of position adjustment in one embodiment;

[0042] Figure 4 A schematic diagram of adjusting vectors in one embodiment;

[0043] Figure 5 A schematic diagram of position adjustment in an embodiment;

[0044] Figure 6 A schematic diagram of a flow chart of determining an adjustment vector in one embodiment;

[0045] Figure 7 A schematic diagram of position adjustment in an embodiment;

[0046] Figure 8 A schematic diagram of a flow chart of determining a sampling point type in one embodiment;

[0047] Fig. 9 A schematic diagram of a process for determining a road line to be processed in one embodiment;

[0048] Fig.10 A schematic flow chart of a cross-road adjustment method in another embodiment;

[0049] Fig.11 is a structural block diagram of a cross-road adjustment device in one embodiment;

[0050] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0052] In one embodiment, Figure 1 As shown, a cross-road adjustment method is provided. This embodiment takes the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0053] S110: Obtain two road lines to be processed.

[0054] The two road lines to be processed correspond to public road segments in the intersecting roads. For example, the public road segments may be road segments in the intersecting roads that include intersections of various roads. For example, when the intersections in the intersecting roads are determined to be m and n, the roads in the intersecting roads that at least include the road segment between points m and n may be taken as public road segments.

[0055] In an optional implementation, two road lines to be processed may be obtained from an original road line, wherein the original road line is constructed based on a driving track, for example, by collecting a driving track of a vehicle to construct the original road line.

[0056] For any opposite road, it is possible to determine whether there is an intersection in the opposite road based on the change in the interval distance between two road lines in the opposite road; then, when it is determined that there is an intersection between the two road lines in the opposite road, the public road section in the opposite road can be determined based on the location of the intersection.

[0057] It can be understood that in order to facilitate the subsequent adjustment of the two road lines in the public road section, the two road lines in the public road section can be sampled and processed separately to obtain two road lines to be processed, so that there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed.

[0058] In an optional implementation, any endpoint of a road line in a public road segment can be used as the first sampling point; based on the first sampling point that has been determined, the next sampling point is determined according to a preset sampling point interval, until the distance between the latest sampling point and the other endpoint of the road line is less than a preset threshold, at which point a road line to be processed containing sampling points is obtained. The sampling point interval can be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this.

[0059] Correspondingly, for another road line in the public road segment, the other road line can be evenly divided according to the number of sampling points in the determined road line to be processed, so as to determine the same number of sampling points on the other road line, thereby obtaining another road line to be processed containing sampling points.

[0060] Alternatively, you can refer to Figure 2 The schematic diagram of the road line to be processed shown directly uses a preset number of road divisions to evenly divide the two road lines in the public road section. Subsequently, the position points corresponding to the road division positions and the two end points of the road line can be used as sampling points in the road line to obtain the road line to be processed containing the sampling points.

[0061] The number of road divisions may be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this. For example, the number of road divisions may be 100, and in this case, there are 101 sampling points in each road line to be processed.

[0062] Furthermore, since the driving directions of the two road lines to be processed are opposite, the driving direction of any one of the road lines to be processed can be adjusted to the opposite direction first, so that the driving directions of the two road lines to be processed are the same; according to the order of the sampling points in the driving directions of the road lines to be processed, the sampling points in the two road lines to be processed are matched one by one to form a sampling point pair between the two road lines to be processed.

[0063] S120: Determine a center point between two sampling points included in a sampling point pair.

[0064] The center point is the center between the two sampling points in the sampling point pair.

[0065] In an optional implementation, for each sampling point pair, the center point of the sampling point pair may be determined based on the position information of the two sampling points included in the sampling point pair. For example, the two sampling points in the sampling point pair may be connected, and the point in the middle of the connecting line is used as the center point of the sampling point pair.

[0066] Alternatively, for each sampling point pair, the center point position of the sampling point pair can be determined according to the longitude and latitude values ​​corresponding to the two sampling points in the sampling point pair. For example, the longitude mean of the two sampling points can be used as the longitude value of the center point, and the latitude mean of the two sampling points can be used as the latitude value of the center point.

[0067] For example, suppose the sampling point sequences on the two road lines to be processed are S A and S B ; Then, the center point sequence S can be calculated using the following formula (1): C The i-th center point c i The longitude value of the center point sequence S is calculated using the following formula (2): C The i-th center point c i The latitude value of .

[0068] (1)

[0069] (2)

[0070] Among them, S A ={a i |0≤i≤N}, (a i .x,a i .y) represents the latitude and longitude coordinates of the i-th sampling point in the road line A to be processed, and N is the number of sampling points; S B ={b i |0≤i≤N}, (b i .x,b i .y) represents the latitude and longitude coordinates of the i-th sampling point in the road line B to be processed; (c i .x,c i .y) represents the longitude and latitude coordinates of the i-th center point.

[0071] S130, identifying abnormal sampling points and normal sampling points among the sampling points according to the distribution of the sampling points and the central point in the two road lines to be processed.

[0072] The distribution of each sampling point and the center point may include but is not limited to the distance distribution between each sampling point and the center point, and the direction distribution between each sampling point and the center point; the abnormal sampling point is the sampling point that can characterize the intersection of the road line to be processed and other sampling points adjacent to the intersection among the sampling points. Furthermore, the adjacent intersection is the interval close to the intersection and located outside the intersection in the road line to be processed. In the embodiment of the present application, the abnormal sampling point is the reason for the intersection of the road line to be processed; the normal sampling point is the sampling point that can characterize the road line to be processed except the abnormal sampling point. Exemplarily, the abnormal sampling point can be the sampling point within the extended range of the intersection area formed by the intersection points in the road line to be processed; correspondingly, the normal sampling point can be the sampling point outside the above extended range formed by the intersection points in the road line to be processed. The size of the above extended range can be determined based on manual experience or through a large number of experiments, and the present application does not make any limitation on this.

[0073] In one of the embodiments, the intersection area between the two road lines to be processed can be determined according to the distribution of each sampling point and the center point in the two road lines to be processed; then, the sampling points located within the extended range of the intersection area can be regarded as abnormal sampling points, and the sampling points located outside the extended range of the intersection area can be regarded as normal sampling points.

[0074] Alternatively, the sampling distribution features between each sampling point pair and the center point can be extracted according to the distribution of each sampling point and the center point in the two road lines to be processed; and the abnormal sampling points and the normal sampling points can be determined from each sampling point according to the preset standard distribution features and the sampling distribution features between each sampling point pair and the center point. The standard distribution features can be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this.

[0075] Exemplarily, for each sampling distribution feature, the deviation value between the sampling distribution feature and the standard distribution feature can be calculated; the deviation values ​​of each sampling distribution feature are sorted in descending order, and the sampling points corresponding to the preset number of sampling distribution features in the first order are taken as abnormal sampling points, and the remaining sampling points are taken as normal sampling points. The preset number can be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this.

[0076] It should be noted that, in this embodiment, since there is a one-to-one correspondence between the sampling points, the normal sampling points and the abnormal sampling points also appear in pairs.

[0077] S140: Adjust the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point.

[0078] The reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed. That is to say, at least one of the normal sampling point adjacent to the first abnormal sampling point (e.g., the previous normal sampling point) and the normal sampling point adjacent to the last abnormal sampling point (e.g., the next normal sampling point) in the corresponding driving direction of the road line to be processed can be used as the reference sampling point.

[0079] In an optional implementation, when there is only one set of reference sampling points, the anomaly adjustment strategy can be determined directly based on the distribution characteristics between the reference sampling points and the corresponding center points; then, the anomaly adjustment strategy is used to adjust the positions of the abnormal sampling points to obtain the sampling points to be verified corresponding to the abnormal sampling points.

[0080] In another optional implementation, when there are two groups of reference sampling points, it is necessary to first determine the reference sampling points corresponding to each abnormal sampling point based on the distances between each abnormal sampling point and the two groups of reference sampling points; then, based on the distribution characteristics between each group of reference sampling points and the corresponding center point, two abnormal adjustment strategies are determined, and the two abnormal adjustment strategies are used to adjust the positions of the abnormal sampling points corresponding to each group of reference sampling points, respectively, to obtain the sampling points to be verified corresponding to the abnormal sampling points.

[0081] Exemplarily, a dividing auxiliary line for dividing two reference areas can be determined at the middle position between the two groups of reference sampling points, wherein the abnormal sampling points located in the left reference area correspond to the reference sampling points located on the left, and the abnormal sampling points located in the right reference area correspond to the reference sampling points located on the right. If a sampling point pair at the middle position is divided into different reference areas, the distances between the two sampling points in the sampling point pair and the dividing auxiliary line can be calculated respectively, and the sampling points closer to the dividing auxiliary line can be adjusted to the other reference area.

[0082] Furthermore, the process in the above step S110 can be referred to to determine whether there is an intersection between the road lines to be verified formed by the sampling points to be verified. If the judgment result is that the road lines to be verified do not intersect, it proves that the opposite intersecting roads have been adjusted to opposite parallel lanes. At this time, the adjustment operation is completed, and the road line to be verified can be directly used as the adjusted road line.

[0083] It is understandable that since the position of the adjusted road line has changed to a certain extent compared to the road line to be processed, there may be a misalignment between the adjusted road line and the unadjusted road line in the opposite road. Based on this, the adjusted public road section can be translated to the connected position of the unadjusted road line according to the adjustment distance of the abnormal sampling point, or the unadjusted road line can be translated to the connected position of the adjusted public road section.

[0084] If the judgment result is that the road line to be verified still intersects, the road line to be verified is used as a new road line to be processed, and the process returns to steps S110 - S140 until the judgment result is that the road line to be verified does not intersect.

[0085] In the above-mentioned intersection road adjustment method, by introducing the center point between the two sampling points contained in each sampling point pair in the two road lines to be processed, and according to the distribution of each sampling point and the center point, the abnormal sampling point and the normal sampling point in each sampling point are identified, and the two road lines to be processed are public road sections in the corresponding intersecting opposite roads. Therefore, the distribution of each sampling point and the center point can reflect the intersection of the road lines to be processed to a certain extent. Correspondingly, after determining the normal sampling point adjacent to the abnormal sampling point as the reference sampling point from each sampling point of the two road lines to be processed, and adjusting the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point, it can ensure the fit between the position adjustment result and the actual situation, thereby improving the accuracy of the constructed road line.

[0086] Based on the technical solution of the above embodiment, the present application also provides an optional embodiment. In this embodiment, the process of adjusting the position of the abnormal sampling point in step S140 is described in detail.

[0087] See Figure 3 The position adjustment steps shown include:

[0088] S310, generating an adjustment vector of the abnormal sampling point according to a sampling vector constructed by a reference sampling point and a center point corresponding to the reference sampling point.

[0089] The sampling vector is used to represent the vector constructed based on the sampling point and the center point. Exemplarily, the sampling vector can be constructed based on the positional relationship between the sampling point and the center point. For example, for any center point, the center point can be used as the starting point of the vector, and the two sampling points corresponding to the center point can be used as the end points of the vector to construct a pair of sampling vectors with the same length but opposite directions.

[0090] Further, the adjustment vector is a vector used to adjust the position of the abnormal sampling point. It should be noted that in this embodiment, since the sampling vectors appear in pairs, the adjustment vectors generated according to the sampling vectors also appear in pairs, and are respectively used to adjust the abnormal sampling points located on both sides of the center point.

[0091] In an optional implementation, the above steps may be referred to to determine a sampling vector corresponding to each reference sampling point; and based on the number of reference sampling point pairs and the sampling vector corresponding to each reference sampling point, an adjustment vector may be determined.

[0092] For example, if there is only one set of reference sampling point pairs in the road line to be processed, the center point corresponding to the reference sampling point pair can be used as the starting point of the vector and the two reference sampling points contained in the reference sampling point pair can be used as the end points of the vector respectively to construct the sampling vector corresponding to each reference sampling point in the reference sampling point pair; and the adjustment vector can be constructed according to the direction and length of the sampling vector. For example, the size of the sampling vector can be directly used as the size of the adjustment vector, and the direction of the sampling vector can be used as the direction of the adjustment vector. That is, the sampling vector constructed between the reference sampling point and the center point corresponding to the reference sampling point is used as the adjustment vector of the abnormal sampling point.

[0093] If there are two groups of reference sampling point pairs in the road line to be processed, the sampling vectors corresponding to the reference sampling points can be constructed respectively with reference to the above steps; then, the adjustment vector can be constructed according to the sampling vectors corresponding to the reference sampling points contained in the two groups of reference sampling point pairs. For example, the average value between the sampling vectors corresponding to the two groups of reference sampling point pairs can be used as the adjustment vector, that is, for the two sampling vectors pointing to the same side in the two groups of reference sampling point pairs, the direction of the adjustment vector can be determined according to the average value of the angles corresponding to the two directions, and the average value of the two sizes can be used as the size of the adjustment direction.

[0094] S320: Adjust the position of the abnormal sampling point according to the center point corresponding to the abnormal sampling point and the corresponding adjustment vector.

[0095] It should be noted that the adjustment vectors appear in pairs. Therefore, before using the adjustment vectors to adjust the positions of the abnormal sampling points, it is necessary to determine the adjustment vector corresponding to each abnormal sampling point in advance from the adjustment vector pairs.

[0096] In an optional implementation, for each abnormal sampling point, the adjustment vector pointing to the road line to be processed where the abnormal sampling point is located in the adjustment vector can be used as the adjustment vector corresponding to the abnormal sampling point. Figure 4The adjustment vector diagram shown in FIG. 1 , wherein the adjustment vector pair includes adjustment vectors F1 and F2. At this time, the abnormal sampling point A' located in the road line A to be processed corresponds to the adjustment vector F1, and the abnormal sampling point B' located in the road line B to be processed corresponds to the adjustment vector F2.

[0097] Further, for each abnormal sampling point, the position of the abnormal sampling point can be adjusted at the center point position corresponding to the abnormal sampling point, with the adjustment vector corresponding to the abnormal sampling point as an indication. Exemplarily, a new sampling point can be generated according to the adjustment vector of the abnormal sampling point with the center point corresponding to the abnormal sampling point as the origin, and the new sampling point is used as the abnormal sampling point after the position adjustment.

[0098] For example, refer to Figure 5 As shown in the position adjustment diagram, for the abnormal sampling point Q1, the corresponding adjustment vector F3 can be placed at the center point Q of the abnormal sampling point Q1. C-1 Subsequently, the abnormal sampling point Q1 is adjusted in the direction indicated by the adjustment vector F3, and the adjustment distance is the vector size corresponding to the adjustment vector F3.

[0099] In the above embodiment, by generating an adjustment vector of the abnormal sampling point based on the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point, it is possible to ensure that the adjustment method of the abnormal sampling point is more in line with the characteristics of the road line to be processed. Furthermore, when the center point and the adjustment vector corresponding to the abnormal sampling point are used to adjust the position of the abnormal sampling point, the accuracy of the adjustment of the abnormal sampling point can be ensured.

[0100] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining the adjustment vector of the abnormal sampling point in step S310 is described in detail.

[0101] See Figure 6 The adjustment vector determination steps shown include:

[0102] S610: Determine a rotation angle according to a center point corresponding to the reference sampling point and center points corresponding to other normal sampling points adjacent to the reference sampling point.

[0103] The rotation angle is used to adjust the direction of the sampling vector. It should be noted that the rotation angle may include both the rotation direction (eg, clockwise and counterclockwise) and the angle value, and may only include the angle value when the default rotation direction is set, and this application does not impose any limitation on this.

[0104] In an optional implementation, the center point corresponding to other normal sampling points adjacent to the reference sampling point may be used as the target center point; then, the rotation angle may be determined according to the positional relationship between the target center point and the center point corresponding to the reference sampling point.

[0105] In another optional implementation, a first center vector may be constructed based on the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point; a second center vector may be constructed based on the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point; and a rotation angle may be determined based on the first center vector and the second center vector.

[0106] Among them, the center vector is used to represent the vector constructed by the center point; further, the first center vector is a vector constructed by the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point, and the second center vector is a vector constructed by the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point.

[0107] Exemplarily, a first central vector can be constructed with the center point corresponding to the abnormal sampling point as the starting point of the vector and the center point corresponding to the reference sampling point as the end point of the vector; a second central vector can be constructed with the center point corresponding to the reference sampling point as the starting point of the vector and the center points corresponding to other normal sampling points adjacent to the reference sampling point as the end point of the vector.

[0108] Subsequently, the rotation angle can be determined according to the direction difference between the first center vector and the second center vector. Exemplarily, the rotation angle can be determined according to the rotation method of rotating the first vector to the second center vector. For example, referring to Figure 7 As shown in the position adjustment schematic diagram, for the abnormal sampling point Q2, a first center vector I1 and a second center vector I2 can be constructed; then, the rotation angle d is determined according to the angle between I1 and I2.

[0109] S620: Rotate the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point according to the rotation angle to obtain an adjustment vector of the abnormal sampling point.

[0110] In an optional implementation, after constructing a sampling vector using reference sampling points and center points corresponding to the reference sampling points, the sampling vector located at the center point corresponding to the abnormal sampling point can be directly rotated using a rotation angle to obtain an adjustment vector of the abnormal sampling point.

[0111] For example, refer to Figure 7 As shown in the position adjustment diagram, for the abnormal sampling point Q2, the corresponding adjustment vector F4 can be placed at the center point Q of the abnormal sampling point Q2. C-2subsequently, the rotation angle d is used to adjust the direction of the adjustment vector F4, thereby obtaining the adjustment vector F4' of the abnormal sampling point Q2.

[0112] In the above embodiment, by determining the rotation angle according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point, and then rotating the sampling vector according to the sampling rotation angle, the adjustment vector of the abnormal sampling point is obtained, which can make the adjustment direction of the abnormal sampling point more accurate, thereby ensuring the accuracy of subsequent adjustment of the abnormal sampling point.

[0113] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining abnormal sampling points and normal sampling points in step S130 is described in detail.

[0114] See Figure 8 The steps for determining the sampling point type shown include:

[0115] S810: For each sampling point, construct a sampling vector corresponding to the sampling point according to the sampling point and the corresponding center point.

[0116] In an optional implementation, for each sampling point on the road line to be processed, a sampling vector corresponding to the sampling point can be constructed according to the positional relationship between the sampling point and the corresponding center point. Exemplarily, for the sampling points on the road lines A and B to be processed, the center point corresponding to each sampling point can be used as the starting point of the sampling vector, and then each sampling point can be used as the end point of the sampling vector to obtain the sampling vector corresponding to the sampling point, that is, the sampling vector set on the road line A to be processed is CA={(a i .xc i .x,a i .xc i .x)|0≤i≤N,a i ∈S A ,c i ∈S C}, where (a i .x,a i .y) represents the latitude and longitude coordinates of the i-th sampling point in the road line A to be processed, (c i .x,c i .y) represents the longitude and latitude coordinates of the i-th center point, S A is the sampling point sequence on the road line A to be processed, S C is the center point sequence, N is the number of sampling points; the sampling vector set on the road line B to be processed is CB={(b i .xc i .x,b i .xc i.x)|0≤i≤N,b i ∈S B ,c i ∈S C}, where (b i .x,b i .y) represents the latitude and longitude coordinates of the i-th sampling point in the road line B to be processed, S B is the sampling point sequence on the road line B to be processed.

[0117] S820: construct a center vector corresponding to the sampling point according to the center point corresponding to the sampling point and the center points corresponding to the neighboring sampling points of the sampling point in a preset extension direction.

[0118] The preset extension direction is the extension direction of the center line formed by the center points. In this embodiment, the preset extension direction can be consistent with the sequence direction of the sampling point pairs in the road line to be processed, that is, the direction in which the sequence numbers of the sampling point pairs on the road line to be processed gradually increase from small to large is the preset extension direction.

[0119] In an optional implementation, for each sampling point, a center vector corresponding to the sampling point may be constructed according to a positional relationship between a center point corresponding to the sampling point and center points corresponding to neighboring sampling points of the sampling point in a preset extension direction.

[0120] For example, for each sampling point, the center point corresponding to the sampling point can be used as the starting point of the center vector, and then the adjacent sampling points of the sampling point in the preset extension direction can be used as the end point of the center vector to obtain the center vector corresponding to the sampling point. That is, the center vector set is CC={(c i+1 .xc i .x,c i+1 .xc i .x)| 0≤i≤N-1,c i ∈S C}, where (c i .x,c i .y) represents the longitude and latitude coordinates of the ith center point, (c i+1 .x,c i+1 .y) represents the longitude and latitude coordinates of the i+1th center point, N is the number of sampling points, S C is the center point sequence.

[0121] S830: Determine the category to which the sampling point belongs according to the sampling vector and / or the corresponding center vector corresponding to the sampling point.

[0122] Among them, the category of the sampling point is abnormal sampling point or normal sampling point.

[0123] In an optional implementation, since the sampling vectors corresponding to the sampling points in the road lines to be processed can reflect the proximity between the road lines to be processed to a certain extent, and the closer the road lines to be processed are, the more likely the intersection is to occur, therefore, for any sampling point, the category to which the sampling point belongs can be determined only based on the sampling vector corresponding to the sampling point. Exemplarily, whether the sampling point is an abnormal sampling point can be determined based on the vector features of the sampling vector corresponding to the sampling point.

[0124] In another optional implementation, due to the angle feature and direction difference between the sampling vector and the corresponding center vector, the abnormal intersection corresponding to the sampling point can be detected. Therefore, for any sampling point, the category to which the sampling point belongs can be determined based on the sampling vector and the corresponding center vector corresponding to the sampling point. Exemplarily, the vector deviation between the sampling vector and the center vector can be determined based on the sampling vector and the corresponding center vector corresponding to the sampling point; then, whether the sampling point is an abnormal sampling point can be determined based on the vector deviation.

[0125] In the above embodiment, by constructing a sampling vector and a center vector that can characterize the intersection of the road line to be processed, and determining whether the sampling point is an abnormal sampling point according to the sampling vector and / or the corresponding center vector corresponding to the sampling point, it can be ensured that the determined abnormal sampling point is more in line with reality, thereby improving the accuracy of determining the abnormal sampling point.

[0126] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining abnormal sampling points in step S830 is described in detail. Specifically, it includes the following contents:

[0127] In an optional implementation, whether the sampling point is an abnormal sampling point can be determined based on the vector value of the sampling vector corresponding to the sampling point. For example, the vector value of the sampling vector corresponding to the sampling point can be compared with a preset standard vector range. If the vector value corresponding to the sampling point is within the standard vector range, the category to which the sampling point belongs is determined to be a normal sampling point; if the vector value corresponding to the sampling point is outside the standard vector range, the category to which the sampling point belongs is determined to be an abnormal sampling point. The standard vector range can be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this.

[0128] In another optional implementation, the vector value of the sampling vector corresponding to the sampling point can be compared with a preset abnormal spacing threshold, and if the vector value of the sampling vector corresponding to the sampling point is less than the abnormal spacing threshold, the sampling point is determined to be an abnormal sampling point. The abnormal spacing threshold is used to characterize the spacing value that can measure the abnormality of the vector; further, the abnormal spacing threshold can be determined based on manual experience, or it can be determined in the following way:

[0129] The first step is to determine the sampling point spacing corresponding to the sampling point pair according to the spacing between the sampling points included in the sampling point pair. For example, the following formula (3) can be used to convert the sampling point sequence S A and S B Half of the straight-line distance between the corresponding sampling points in is taken as the sampling point spacing D corresponding to the sampling point pair:

[0130] (3)

[0131] Among them, S D is the sampling point spacing set of each fixed sampling point pair; a i .distance(b i ) is the sampling point a i and point b i The straight-line distance.

[0132] The second step is to determine the abnormal spacing threshold according to the order of the spacings between the corresponding sampling points of each sampling point pair. For example, S D The spacing of each sampling point in is sorted to obtain the spacing sorting result, and referring to the following formula (4) and formula (5), the 25% item and the 75% item are extracted from the spacing sorting result respectively as reference data:

[0133] (4)

[0134] (5)

[0135] Among them, S D .percentile(p) is the data set S D After ascending sorting, the p%th data item, where p is the empirical value or test value; then, the following formula (6) can be referred to to calculate the two reference data to obtain the abnormal spacing threshold D T :

[0136] D T =max(0.5,(2.5*q1-1.5*q3)) (6)

[0137] Among them, q1 and q3 are the above reference data; 2.5 and 1.5 are empirical values ​​or test values; max() is the maximum value function.

[0138] In practical applications, the vector angle between the sampling vector and the corresponding center vector should normally be about 90°. Based on this, in another optional implementation, whether the sampling point is an abnormal sampling point can be determined based on the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector. The angle range of the vector angle is [0°, 180°].

[0139] For example, the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector can be compared with the preset standard angle range. If the vector angle is within the standard angle range, the sampling point is determined to be a normal sampling point; if the vector angle is outside the standard angle range, the sampling point is determined to be an abnormal sampling point. The standard angle range can be determined based on manual experience or through a large number of experiments, and this application does not impose any restrictions on this. In this embodiment, the standard angle range can be [45°, 135°].

[0140] In practical applications, if the opposite roads do not intersect, the travel direction of the road lines on either side of the center line of the opposite roads will remain unchanged. Based on this, in another optional implementation, it is possible to determine whether a sampling point is an abnormal sampling point based on the travel direction of the road line to be processed to which the sampling point belongs predicted by the sampling vector corresponding to the sampling point and the corresponding center vector.

[0141] Exemplarily, since the positive or negative sign of the cross product between two vectors can reflect the positional relationship between the two vectors, the cross product value between the sampling vector corresponding to the sampling point and the corresponding center vector can be calculated. If the cross product value is greater than 0, it proves that the sampling vector is in the counterclockwise direction of the center vector, that is, the sampling point is to the left of the center point; if the cross product value is less than 0, it proves that the sampling vector is in the clockwise direction of the center vector, that is, the sampling point is to the right of the center point.

[0142] Furthermore, the travel direction of the road line to be processed to which the sampling point belongs can be predicted based on the positional relationship between the sampling point and the center point and the preset positional relationship between the road line and the center line under normal circumstances. For example, the preset positional relationship between the road line and the center line under normal circumstances is that the travel direction of the road line located on the left side of the center line is from south to north, and the travel direction of the road line located on the right side of the center line is from north to south. If any sampling point is on the right side of the center point, it is predicted that the travel direction of the road line to be processed to which the sampling point belongs is from north to south.

[0143] At this time, if the predicted travel direction of the road line to be processed to which the sampling point belongs is consistent with the actual travel direction, the sampling point is determined to be a normal sampling point; if the predicted travel direction of the road line to be processed to which the sampling point belongs is inconsistent with the actual travel direction, the sampling point is determined to be an abnormal sampling point.

[0144] It should be noted that since the central vector that can be constructed by the central point must be one less than the number of sampling points, the corresponding central vector cannot be constructed for the last sampling point. At this time, it can be determined whether the last sampling point is an abnormal sampling point based on the abnormal situation of the previous sampling point (i.e., the second to last sampling point).

[0145] In the above embodiment, whether a sampling point is an abnormal sampling point is determined by three different methods: the vector value of the sampling vector, the vector angle between the sampling vector and the corresponding center vector, and the predicted travel direction of the road line to be processed to which the sampling point belongs. This ensures the flexibility of determining the abnormal sampling point and the accuracy of determining the abnormal sampling point.

[0146] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this embodiment, the process of determining the road line to be processed in step S110 is described in detail.

[0147] See Fig. 9 The steps of determining the road line to be processed include:

[0148] S910: Obtain original road lines corresponding to two opposite roads.

[0149] The original road line is a road line that is directly constructed, for example, a road line that is constructed according to a driving trajectory.

[0150] In an optional implementation, original road lines corresponding to the two opposite roads can be constructed based on the driving tracks of each vehicle on the opposite road. For example, a preset number of driving tracks on the two opposite roads can be extracted in advance; then, the preset number of driving tracks are fitted to obtain the original road lines corresponding to the two opposite roads.

[0151] S920: When two original road lines intersect, determine the public road lines corresponding to the public road segments on the two original road lines.

[0152] Among them, the public road line is the road lines on both sides of the public road section between the two original road lines.

[0153] In an optional implementation, the content in the above step S110 can be referred to to determine whether the two original road lines intersect, and if the two original road lines intersect, the public road line of the corresponding public road segment on the two original road lines can be determined based on the intersection of the two original road lines.

[0154] For example, when two original road lines intersect, the starting point and end point of any original road line can be used to project onto the other original road line, and the starting point and end point of the other original road line can be used to project onto the original road line, thereby obtaining two common road lines.

[0155] For example, the original road line L A From the starting point to the original road line L B Projection, L B The end point is L A Projection, used to determine L A The starting point of the upper public part, and L B The end point of the upper common part; similarly L A The end point is L B Projection, L B Starting point to L A Projection, used to determine L A The end point of the upper common part, and L B The starting point of the upper public part.

[0156] S930: Determine whether there is an abnormal intersection between two original road lines according to the length of the public road line, the angle between the two public road lines, and the height difference between the public road sections corresponding to the two public road lines.

[0157] In actual applications, special intersection scenes such as road intersections and overpasses may be judged as opposite roads, which may lead to unnecessary road line adjustment operations. Based on this, in an optional implementation, it is possible to determine whether two original road lines have abnormal intersections under opposite roads based on the length of the common road line.

[0158] Exemplarily, the length of the public road line can be compared with a preset length threshold. If the lengths of the two public road lines are both greater than the length threshold, it is determined that the two original road lines have an abnormal intersection. If the length of any of the two public road lines is less than the length threshold, it is proved that the actual scene corresponding to the public road line may be a road intersection. Therefore, it is determined that the two original road lines do not have an abnormal intersection. The length threshold can be determined based on manual experience or through a large number of experiments, and this application does not impose any restrictions on this. In this embodiment, the length threshold can be 5 meters.

[0159] In another optional implementation manner, it can be determined whether two original road lines have an abnormal intersection under opposite roads based on the angle between the two public road lines.

[0160] Exemplarily, the angle between the direction from the starting point to the end point on any public road line and the direction from the starting point to the end point on another public road line can be used as the common part angle; then, the common part angle can be compared with a preset angle threshold. If the common part angle is greater than the angle threshold, it is determined that the two original road lines have an abnormal intersection under the opposite road; if the common part angle is less than or equal to the angle threshold, it proves that the actual scene corresponding to the public road line may be a road intersection, and therefore, it is determined that the two original road lines do not have an abnormal intersection. Among them, the angle threshold can be determined based on manual experience or through a large number of experiments, and this application does not impose any limitation on this. In this embodiment, the angle threshold can be 145°.

[0161] In yet another optional implementation, it may be determined whether two original road lines have an abnormal intersection under opposite roads based on the height difference between the public road sections corresponding to the two public road lines.

[0162] Exemplarily, the minimum height difference between the two public road lines can be determined first, and the minimum height difference can be compared with a preset height difference threshold. If the minimum height difference is less than the height difference threshold, it is determined that the two original road lines have an abnormal intersection under the opposite road; if the minimum height difference is greater than or equal to the height difference threshold, it is proved that the actual scene corresponding to the public road line may be an overpass, therefore, it is determined that the two original road lines do not have an abnormal intersection. Among them, the height difference threshold can be determined based on manual experience or through a large number of experiments, and this application does not make any limitation to this. In this embodiment, the height difference threshold can be 4 meters.

[0163] S940: The two original road lines with abnormal intersection are used as two road lines to be processed.

[0164] In an optional implementation, if it is determined that there is no abnormal intersection between the two original road lines, there is no need to process the original road lines; if it is determined that there is an abnormal intersection between the two original road lines under the opposite roads, it is necessary to perform intersection adjustment processing on the original road lines. At this time, the two original road lines can be used as two road lines to be processed, and the intersection adjustment processing can be performed with reference to the steps in the above embodiment.

[0165] In the above embodiment, by determining whether there is an abnormal intersection between two original road lines based on the length of the public road line, the angle between the two public road lines, and the height difference between the public road sections corresponding to the two public road lines, it is possible to exclude the situation where the intersecting road line is a road line corresponding to a normal intersecting road in the actual scene, thereby ensuring the adaptability of the intersection adjustment process to the actual scene.

[0166] In order to facilitate those skilled in the art to understand the present solution, the road network matching provided in this application should be introduced in detail.

[0167] See also Fig.10 The cross-road adjustment method shown includes:

[0168] S1001, obtaining original road lines corresponding to two opposite roads, and determining a public road line corresponding to a public road segment on the two original road lines when the two original road lines intersect.

[0169] S1002: If the length of the public road line is greater than G1, or the angle between the two public road lines is less than G2, or the height difference between the corresponding public road sections of the two public road lines is less than G3, it is determined that there is an abnormal intersection between the two original road lines.

[0170] Among them, G1 can be 5 meters; G2 can be 145°; G3 can be 4 meters.

[0171] S1003: Two original road lines with abnormal intersection are used as two road lines to be processed.

[0172] S1004: Determine the center point between two sampling points included in the sampling point pairs on two road lines to be processed.

[0173] S1005: construct a sampling vector corresponding to each sampling point according to each sampling point and the corresponding center point.

[0174] S1006: construct a center vector corresponding to each sampling point according to the center point corresponding to each sampling point and the center points corresponding to the adjacent sampling points of each sampling point in a preset extension direction.

[0175] S1007: If the vector value of the sampling vector corresponding to any sampling point is less than G4, or the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector is outside [G5, G6], or the travel direction of the road line to be processed to which the sampling point belongs predicted by the sampling vector corresponding to the sampling point and the corresponding center vector is opposite to the actual travel direction, then the sampling point is determined to be an abnormal sampling point.

[0176] Among them, G4 can be determined in the following manner: according to the spacing between the sampling points included in the sampling point pair, the sampling point spacing corresponding to the sampling point pair is determined; according to the sorting between the sampling point spacings corresponding to each sampling point pair, the abnormal spacing threshold is determined. Among them, [G5, G6] can be [45°, 135°].

[0177] S1008: Among the sampling points of the two road lines to be processed, the normal sampling points adjacent to the abnormal sampling points are used as reference sampling points.

[0178] S1009: Determine a rotation angle according to a center point corresponding to the reference sampling point and center points corresponding to other normal sampling points adjacent to the reference sampling point.

[0179] S1010: Construct a first center vector according to the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point.

[0180] S1011: construct a second center vector according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point.

[0181] S1012, determining a rotation angle according to the first center vector and the second center vector, and rotating a sampling vector constructed by a reference sampling point and a center point corresponding to the reference sampling point according to the rotation angle to obtain an adjustment vector of the abnormal sampling point.

[0182] S1013: Adjust the position of the abnormal sampling point according to the center point corresponding to the abnormal sampling point and the corresponding adjustment vector.

[0183] The specific process of the above S1001-S1013 can be found in the description of the above method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0184] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0185] Based on the same inventive concept, the embodiment of the present application also provides an intersecting road adjustment device for implementing the intersecting road adjustment method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more intersecting road adjustment device embodiments provided below can refer to the limitations of the intersecting road adjustment method above, and will not be repeated here.

[0186] In an exemplary embodiment, Fig.11 As shown, a cross-road adjustment device is provided, including: an acquisition module 1110, a determination module 1120, an identification module 11130 and an adjustment module 1140, wherein:

[0187] The acquisition module 1110 is used to acquire two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in the intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed;

[0188] A determination module 1120, configured to determine a center point between two sampling points included in a sampling point pair;

[0189] An identification module 1130 is used to identify abnormal sampling points and normal sampling points among the sampling points according to the distribution of the sampling points and the center point in the two road lines to be processed;

[0190] The adjustment module 1140 is used to adjust the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

[0191] In an exemplary embodiment, the adjustment module 1140 includes: a vector generation unit, which is used to generate an adjustment vector of the abnormal sampling point according to a sampling vector constructed by a reference sampling point and a center point corresponding to the reference sampling point; and a position adjustment unit, which is used to adjust the position of the abnormal sampling point according to the center point corresponding to the abnormal sampling point and the corresponding adjustment vector.

[0192] In an exemplary embodiment, the vector generating unit is used to determine a rotation angle according to a center point corresponding to a reference sampling point and center points corresponding to other normal sampling points adjacent to the reference sampling point; and according to the rotation angle, rotate a sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point to obtain an adjustment vector of the abnormal sampling point.

[0193] In an exemplary embodiment, the vector generation unit is further used to construct a first center vector according to the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point; construct a second center vector according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point; and determine the rotation angle according to the first center vector and the second center vector.

[0194] In an exemplary embodiment, the identification module 1130 includes: a first unit, for constructing, for each sampling point, a sampling vector corresponding to the sampling point according to the sampling point and the corresponding center point; a second unit, for constructing a center vector corresponding to the sampling point according to the center point corresponding to the sampling point and the center points corresponding to the adjacent sampling points of the sampling point in a preset extension direction; a third unit, for determining the category to which the sampling point belongs according to the sampling vector corresponding to the sampling point and / or the corresponding center vector; wherein the category to which the sampling point belongs is an abnormal sampling point or a normal sampling point.

[0195] In an exemplary embodiment, the third unit is used to determine whether the sampling point is an abnormal sampling point according to the vector value of the sampling vector corresponding to the sampling point; determine whether the sampling point is an abnormal sampling point according to the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector; determine whether the sampling point is an abnormal sampling point according to the travel direction of the road line to be processed to which the sampling point belongs predicted by the sampling vector corresponding to the sampling point and the corresponding center vector.

[0196] In an exemplary embodiment, the third unit is further used to determine that the sampling point is an abnormal sampling point if the vector value of the sampling vector corresponding to the sampling point is less than the abnormal spacing threshold; wherein the abnormal spacing threshold is determined in the following manner: determining the sampling point spacing corresponding to the sampling point pair according to the spacing between the sampling points included in the sampling point pair; determining the abnormal spacing threshold according to the sorting of the sampling point spacings corresponding to each sampling point pair.

[0197] In an exemplary embodiment, the acquisition module 1110 is used to acquire original road lines corresponding to two opposite roads; when the two original road lines intersect, determine the public road lines corresponding to the public road segments on the two original road lines; determine whether there is an abnormal intersection between the two original road lines based on the length of the public road line, the angle between the two public road lines, and the height difference between the public road segments corresponding to the two public road lines; and use the two original road lines with abnormal intersection as two road lines to be processed.

[0198] Each module in the above-mentioned intersection road adjustment device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0199] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a cross-road adjustment method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0200] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0201] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0202] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0203] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0204] It should be noted that the data involved in this application (including but not limited to road line data, etc.) are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0205] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0206] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0207] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for adjusting cross roads, characterized in that: include: Acquire two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed; Determine a center point between two sampling points included in the sampling point pair; According to the distribution of each sampling point and the central point in the two road lines to be processed, identifying abnormal sampling points and normal sampling points in each sampling point; The abnormal sampling point is adjusted in position according to a reference sampling point and a center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

2. The method according to claim 1, characterized in that: The step of adjusting the position of the abnormal sampling point according to the reference sampling point and the center point corresponding to the reference sampling point comprises: Generate an adjustment vector of the abnormal sampling point according to a sampling vector constructed by the reference sampling point and a center point corresponding to the reference sampling point; The position of the abnormal sampling point is adjusted according to the central point corresponding to the abnormal sampling point and the corresponding adjustment vector.

3. The method according to claim 2, characterized in that The step of generating the adjustment vector of the abnormal sampling point according to the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point includes: Determine a rotation angle according to a center point corresponding to the reference sampling point and center points corresponding to other normal sampling points adjacent to the reference sampling point; According to the rotation angle, the sampling vector constructed by the reference sampling point and the center point corresponding to the reference sampling point is rotated to obtain the adjustment vector of the abnormal sampling point.

4. The method according to claim 3, characterized in that The determining of the rotation angle according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point includes: Constructing a first center vector according to the center point corresponding to the abnormal sampling point and the center point corresponding to the reference sampling point; Constructing a second center vector according to the center point corresponding to the reference sampling point and the center points corresponding to other normal sampling points adjacent to the reference sampling point; The rotation angle is determined according to the first center vector and the second center vector.

5. The method according to any one of claims 1 to 4, characterized in that: The step of identifying abnormal sampling points and normal sampling points among the sampling points according to the distribution of the sampling points and the central point in the two road lines to be processed includes: For each sampling point, construct a sampling vector corresponding to the sampling point according to the sampling point and the corresponding center point; Constructing a center vector corresponding to the sampling point according to the center point corresponding to the sampling point and the center points corresponding to the adjacent sampling points of the sampling point in a preset extension direction; The category to which the sampling point belongs is determined according to the sampling vector and / or the corresponding center vector corresponding to the sampling point; wherein the category to which the sampling point belongs is an abnormal sampling point or a normal sampling point.

6. The method according to claim 5, characterized in that The determining, according to the sampling vector and / or the corresponding center vector corresponding to the sampling point, the category to which the sampling point belongs includes at least one of the following: Determining whether the sampling point is an abnormal sampling point according to a vector value of a sampling vector corresponding to the sampling point; Determine whether the sampling point is an abnormal sampling point according to the vector angle between the sampling vector corresponding to the sampling point and the corresponding center vector; Whether the sampling point is an abnormal sampling point is determined according to the travel direction of the road line to be processed to which the sampling point belongs predicted by the sampling vector corresponding to the sampling point and the corresponding central vector.

7. The method according to claim 6, characterized in that The determining, according to the vector value of the sampling vector corresponding to the sampling point, whether the sampling point is an abnormal sampling point includes: If the vector value of the sampling vector corresponding to the sampling point is less than the abnormal spacing threshold, the sampling point is determined to be an abnormal sampling point; The abnormal distance threshold is determined in the following manner: Determine the sampling point spacing corresponding to the sampling point pair according to the spacing between the sampling points included in the sampling point pair; The abnormal spacing threshold is determined according to the order of the spacings between the sampling points corresponding to the sampling point pairs.

8. The method according to any one of claims 1 to 4, characterized in that: The obtaining of two road lines to be processed includes: Obtain the original road lines corresponding to two opposite roads; When two original road lines intersect, determining the public road lines corresponding to the public road segments on the two original road lines; Determining whether there is an abnormal intersection between the two original road lines according to the length of the public road line, the angle between the two public road lines, and the height difference between the public road sections corresponding to the two public road lines; The two original road lines with abnormal intersection are used as the two road lines to be processed.

9. A cross-road adjustment device, characterized in that: include: An acquisition module is used to acquire two road lines to be processed; wherein the two road lines to be processed correspond to public road segments in intersecting opposite roads; and there are sampling point pairs formed by one-to-one corresponding sampling points on the two road lines to be processed; A determination module, used to determine a center point between two sampling points included in the sampling point pair; An identification module, used for identifying abnormal sampling points and normal sampling points among the sampling points according to the distribution of the sampling points and the central point in the two road lines to be processed; An adjustment module is used to adjust the position of the abnormal sampling point according to a reference sampling point and a center point corresponding to the reference sampling point; wherein the reference sampling point is a normal sampling point adjacent to the abnormal sampling point among the sampling points of the two road lines to be processed.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images