A method for generating road divergence and confluence points based on original trajectories

Abstract

The present invention provides a method for generating a road divergence and confluence point based on an original trajectory, comprising: obtaining original trajectory data, normalizing the obtained original trajectory data, calculating weighted values ​​for each trajectory point on the same road, offsetting the position of each trajectory point in a direction perpendicular to the driving direction according to the calculated weighted values, aggregating the scattered trajectories together through iteration to form a road skeleton line with similar distribution widths of each trajectory, obtaining the road divergence and confluence point based on the connectivity of the road skeleton line and the trajectory, evaluating the obtained road divergence and confluence point results, calculating the confidence value of each result, and retaining the results with high reliability according to the confidence value corresponding to each result. The universality of parameters and the generalization of algorithms can be improved; the generated road skeleton line retains the corresponding relationship with the original trajectory, so that the connectivity of the trajectory can be known; the results can be evaluated as a whole and are reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of crowdsourcing high-precision map production, and in particular to a method for generating road divergence and confluence points based on original trajectories. Background Art

[0002] As an important element in high-precision maps, road-level topology is an important foundation for subsequent modules such as intersections, lane-level topology, and lane line structuring. By finding the divergence and confluence points at the road level, the correct road-level topology can be obtained. Based on this demand, the most widely used method is the raster image refinement method, but this method is not very suitable for elevation processing and sparse trajectory coverage. Moreover, after converting the data into image processing, the final result will have some disadvantages such as destroying the continuity of the trajectory and losing the connectivity of the original trajectory. Summary of the invention

[0003] The present invention provides a method for generating a road divergence and merging point based on an original trajectory, which overcomes the above problems or at least partially solves the above problems.

[0004] According to a first aspect of the present invention, a method for generating a road divergence and confluence point based on an original trajectory is provided, comprising: obtaining original trajectory data, normalizing the obtained original trajectory data, calculating a weighted value for each trajectory point on the same road, offsetting the position of each trajectory point in a direction perpendicular to the driving direction according to the calculated weighted value, aggregating scattered trajectories together through iteration to form a road skeleton line with similar distribution widths of each trajectory, obtaining a road divergence and confluence point based on the connectivity of the road skeleton line and the trajectory, evaluating the obtained results of the road divergence and confluence point, calculating a confidence value for each result, and retaining a result with high reliability according to the confidence value corresponding to each result.

[0005] Based on the above technical solution, the present invention can also make the following improvements.

[0006] Optionally, the road skeleton line retains the correspondence with the original trajectory during processing, and the connectivity of the trajectory is obtained through the correspondence between the road skeleton line and the original trajectory, so that the connectivity of the road skeleton line is consistent with the original trajectory, so as to facilitate tracing the connected domain of the original trajectory.

[0007] Optionally, the trajectory on the same road is composed of a plurality of trajectory points, and a weighted value is calculated for each trajectory point according to the density distribution of trajectory points distributed around it, and the weighted value is used as an adjustment basis for the trajectory point corresponding to the weighted value.

[0008] Optionally, the road divergence and merging points obtained based on the connectivity of the road skeleton line and the trajectory are compared with the road divergence and merging points in the original trajectory, and the comparison results are fed back. The comparison results include areas where there are inconsistencies in the divergence and merging points marked in the two compared objects, and are recorded and displayed in the original trajectory or road skeleton line.

[0009] Optionally, when calculating the weighted values ​​of the trajectory points, the normalization processing involved includes coordinate transformation of the original trajectory, unification of the density of the trajectory points, and elimination of abnormal values ​​existing in the trajectory points in the original trajectory.

[0010] Optionally, the road trajectory aggregation includes the following steps:

[0011] S1: According to each trajectory point Pi(x i ,y i ), obtain the set of similar trajectory points Qi near it, and the distance from the point Pi is less than the parameter threshold d, and the angle deviation between the driving direction angle and Pi does not exceed the parameter threshold angle_d, where i is a positive integer;

[0012] S2: Based on the similar trajectory point set Qi, calculate the offset distance Δdi of the trajectory point Pi to be offset and the coordinates after offset. The calculation method is as follows:

[0013] With Pi as the origin, the driving direction as the positive direction of the y-axis, and the direction 90° clockwise from the driving direction as the positive direction of the x-axis, a plane rectangular coordinate system Oxy is established. Since only the vertical direction of the driving direction needs to be offset, only the similar trajectory points (x a ,y a ) in the Oxy coordinate system is:

[0014] x′ a =cosθ*(x a -x i )-sinθ*(y a -y i );

[0015] Suppose the set of trajectory points whose x-axis coordinates are less than 0 in the set Qi is Qa, and the set of trajectory points whose x-axis coordinates are greater than 0 is Qb, where a and b are positive integers, then the offset distance Δdi of the offset trajectory point Pi is:

[0016]

[0017] Where m is the number of points in set Qa, x′ k is the x coordinate of the points in the set Qa in the Oxy coordinate system above, d ki is the distance from the point in set Qa to point Pi; n is the number of points in set Qb, x′j is the x coordinate of the points in the set Qb in the Oxy coordinate system above, d ji is the distance from the point in the set Qb to the point Pi;

[0018] Then the offset coordinates of point Pi are:

[0019]

[0020] S3: traverse all trajectory points to calculate the offset coordinates;

[0021] S4: Calculate the average offset distance Δd of all trajectory points. When Δd is less than the parameter threshold δ, the trajectory aggregation is terminated.

[0022] Optionally, when calculating the confidence value, the change in the trajectory line distance near the divergence and confluence point is used as the confidence value.

[0023] The present invention provides a method for generating road divergence and confluence points based on original trajectories. After obtaining the original trajectory data, the distribution width of the trajectories for each road is basically the same. On this basis, the road skeleton line is regenerated, and then the road divergence and confluence points can be obtained based on the connectivity of the skeleton line and the trajectory. Finally, the confidence value is introduced to evaluate the divergence and confluence points, thereby obtaining reliable results. The distribution width of the trajectories on each road is basically the same, which can improve the universality of the parameters and the generalization of the algorithm; the generated road skeleton line retains the corresponding relationship with the original trajectory, so that the connectivity of the trajectory can be known; overall, the results can be evaluated and have reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a method for generating a road divergence and merging point based on an original trajectory provided by an embodiment of the present invention;

[0025] Figure 2 A schematic diagram of an original trajectory of a method for generating a road divergence and merging point based on an original trajectory provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of road trajectory aggregation of a method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of a road divergence and merging point of a method for generating a road divergence and merging point based on an original trajectory provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0028] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0029] Figure 1 A flowchart of a method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes: obtaining original trajectory data, normalizing the obtained original trajectory data, calculating weighted values ​​for each trajectory point on the same road, offsetting the position of each trajectory point in a direction perpendicular to the driving direction according to the calculated weighted value, aggregating scattered trajectories together through iteration to form a road skeleton line with similar distribution widths of each trajectory, obtaining the divergence and confluence points of the road based on the connectivity of the road skeleton line and the trajectory, evaluating the results of the divergence and confluence points of the road, calculating the confidence value of each result, and retaining the results with high reliability according to the confidence value corresponding to each result.

[0030] It can be understood that the method for generating a road divergence and confluence point based on the original trajectory can be summarized as follows: reading the original trajectory data, then normalizing the read original trajectory data, then performing road trajectory aggregation, and then generating a road skeleton line, generating a road divergence and confluence point based on the generated road skeleton line, and then calculating a confidence value to obtain a reliable result.

[0031] Specifically, after obtaining the original trajectory data, normalization processing is first performed, including coordinate conversion, trajectory point density unification, outlier removal, etc., to obtain a standardized data set. Due to the different widths of different roads and the different densities of trajectories, it is difficult to use unified parameters or positions to define the divergence and confluence points. In this step, unified processing will be performed to provide a unified data interface for the subsequent processing steps; therefore, this paper first aggregates the trajectories, calculates the weighted values ​​of the trajectories on the same road according to the density of the surrounding trajectory points, and offsets them in the vertical direction of their driving direction, such as Figure 2 As shown, Figure 2 A schematic diagram of an original trajectory of a method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention; the trajectory points are gathered together as much as possible, so that for each road, the distribution width of the trajectory is basically the same, and the road skeleton line is regenerated on this basis, such as Figure 3 As shown, Figure 3 A schematic diagram of a road trajectory after aggregation of a method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention; then the road divergence and confluence point can be obtained based on the connectivity of the skeleton line and the trajectory, and finally the confidence value is introduced to evaluate the divergence and confluence point, so as to obtain a reliable result, such as Figure 4 As shown, Figure 4A schematic diagram of a road divergence and confluence point of a method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention. The trajectory distribution widths on each road are made basically consistent, which can improve the universality of parameters and the generalization of the algorithm; the generated road skeleton line retains the corresponding relationship with the original trajectory, so that the connectivity of the trajectory can be known; overall, the result can be evaluated and has reliability.

[0032] In a possible implementation manner, the road skeleton line retains the correspondence with the original trajectory during processing, and the connectivity of the trajectory is obtained through the correspondence between the road skeleton line and the original trajectory, so that the connectivity of the road skeleton line is consistent with the original trajectory, so as to facilitate tracing the connected domain of the original trajectory.

[0033] It can be understood that in this embodiment, when the road skeleton line is generated, the correspondence between the generated road skeleton line and the original trajectory is retained, so as to facilitate the subsequent tracing of the connectivity of the trajectory and the original trajectory, as well as the ability to make reference and comparison.

[0034] In a possible implementation manner, the trajectory on the same road is composed of a plurality of trajectory points, and a weighted value is calculated for each trajectory point according to the density distribution of trajectory points distributed around it, and the weighted value serves as an adjustment basis for the trajectory point corresponding to the weighted value.

[0035] It can be understood that in this embodiment, the trajectory on the same road is divided into several closely connected trajectory points. For each trajectory point, the weight is calculated according to the density distribution of the surrounding trajectory points, and the trajectory point is offset in the direction perpendicular to its driving direction. Through iteration, the scattered trajectories can be slowly aggregated together, so that the algorithm is minimized by the influence of different road widths and different trajectory distribution densities.

[0036] In one possible implementation manner, the road divergence and merging points obtained based on the connectivity of the road skeleton line and the trajectory are compared with the road divergence and merging points in the original trajectory, and the comparison results are fed back. The comparison results include areas where there are inconsistencies in the divergence and merging points marked in the two compared objects, and are recorded and displayed in the original trajectory or the road skeleton line.

[0037] It can be understood that since the correspondence of the original trajectory is retained in the road skeleton line, the two can be correlated and traced back to each other. Therefore, by comparing the trajectory points or trajectories in the road skeleton line with the trajectory points or trajectories in the original trajectory, the inconsistent areas between the two can be determined and marked or displayed for designers or users to view the changed areas or areas with large changes for later review and comparison.

[0038] In a possible implementation manner, when calculating the weighted value of the trajectory point, the normalization process involved includes coordinate transformation of the original trajectory, normalization of the trajectory point density, and elimination of abnormal values ​​existing in the trajectory points in the original trajectory.

[0039] It can be understood that in this embodiment, the normalization process is to aggregate the data of the original trajectory, which requires coordinate conversion, uniform density of trajectory points, and elimination of abnormal data values ​​to ensure the accuracy and reliability of the normalization processing results.

[0040] In a possible implementation manner, road trajectory aggregation includes the following steps:

[0041] S1: According to each trajectory point Pi(x i ,y i ), obtain the set of similar trajectory points Qi near it, and the distance from the point Pi is less than the parameter threshold d, and the angle deviation between the driving direction angle and Pi does not exceed the parameter threshold angle_d, where i is a positive integer;

[0042] S2: Based on the similar trajectory point set Qi, calculate the offset distance Δdi of the trajectory point Pi to be offset and the coordinates after offset. The calculation method is as follows:

[0043] With Pi as the origin, the driving direction as the positive direction of the y-axis, and the direction 90° clockwise from the driving direction as the positive direction of the x-axis, a plane rectangular coordinate system Oxy is established. Since only the vertical direction of the driving direction needs to be offset, only the similar trajectory points (x a ,y a ) in the Oxy coordinate system is:

[0044] x′ a =cosθ*(x a -x i )-sinθ*(y a -y i );

[0045] Suppose the set of trajectory points whose x-axis coordinates are less than 0 in the set Qi is Qa, and the set of trajectory points whose x-axis coordinates are greater than 0 is Qb, where a and b are positive integers, then the offset distance Δdi of the offset trajectory point Pi is:

[0046]

[0047] Where m is the number of points in set Qa, x′ k is the x coordinate of the points in the set Qa in the Oxy coordinate system above, d ki is the distance from the point in set Qa to point Pi; n is the number of points in set Qb, x′j is the x coordinate of the points in the set Qb in the Oxy coordinate system above, d ji is the distance from the point in the set Qb to the point Pi;

[0048] Then the offset coordinates of point Pi are:

[0049]

[0050] S3: traverse all trajectory points to calculate the offset coordinates;

[0051] S4: Calculate the average offset distance Δd of all trajectory points. When Δd is less than the parameter threshold δ, the trajectory aggregation is terminated.

[0052] In a possible implementation manner, when calculating the confidence value, the change value of the trajectory line distance near the divergence and confluence point is used as the confidence value.

[0053] It can be understood that since there will be bifurcation or merging of trajectory lines at the divergence and confluence, the distance between trajectory lines will increase or decrease. The change value of the trajectory line distance near the divergence and confluence point is calculated and used as the confidence value. Since the trajectory lines on the same road surface have been aggregated to new trajectory lines with a very small distance after the above road aggregation, the confidence value parameter can use the same parameter here and is not affected by the different widths of the roads.

[0054] A method for generating a road divergence and confluence point based on an original trajectory provided by an embodiment of the present invention has the following beneficial effects:

[0055] The trajectory points are gathered together as much as possible, so that for each road, the distribution width of the trajectory is basically the same. On this basis, the road skeleton line is generated, and then the divergence and confluence points of the road can be obtained based on the connectivity of the skeleton line and the trajectory. Finally, the confidence value is introduced to evaluate the divergence and confluence points to obtain reliable results. Making the distribution width of the trajectories on each road basically consistent can improve the universality of the parameters and the generalization of the algorithm; the generated road skeleton line retains the corresponding relationship with the original trajectory, so that the connectivity of the trajectory can be known; overall, the results are evaluable and reliable.

[0056] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0057] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0061] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0062] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for generating a road divergence and confluence point based on an original trajectory, characterized in that: include: The original trajectory data is obtained and normalized, a weighted value is calculated for each trajectory point on the same road, and then the position of each trajectory point is offset in a direction perpendicular to the driving direction according to the calculated weighted value, and the scattered trajectories are aggregated together through iteration to form a road skeleton line with similar distribution widths of each trajectory. The road skeleton line retains the corresponding relationship with the original trajectory during processing, and the divergence and confluence points of the road are obtained based on the connectivity of the road skeleton line and the trajectory. The results of the divergence and confluence points of the road are evaluated, and the confidence value of each result is calculated, and the results with high reliability are retained according to the confidence value corresponding to each result.

2. The method for generating a road divergence and confluence point based on an original trajectory according to claim 1, characterized in that: The connectivity of the trajectory is obtained through the correspondence between the road skeleton line and the original trajectory, so that the connectivity of the road skeleton line is consistent with the original trajectory, so as to facilitate tracing the connected domain of the original trajectory.

3. The method for generating a road divergence and confluence point based on an original trajectory according to claim 1, characterized in that: The trajectory on the same road is composed of several trajectory points. A weighted value is calculated for each trajectory point according to the density distribution of trajectory points distributed around it, and the weighted value serves as the adjustment basis for the trajectory point corresponding to the weighted value.

4. The method for generating a road divergence and confluence point based on an original trajectory according to claim 2, characterized in that: The road divergence and merging points obtained based on the connectivity of the road skeleton line and the trajectory are compared with the road divergence and merging points in the original trajectory, and the comparison results are fed back. The comparison results include areas where there are inconsistencies in the divergence and merging points marked in the two compared objects, and are recorded and displayed in the original trajectory or the road skeleton line.

5. The method for generating a road divergence and confluence point based on an original trajectory according to claim 3, characterized in that: When calculating the weighted values ​​of the trajectory points, the normalization processing involved includes coordinate transformation of the original trajectory, unification of the density of the trajectory points, and elimination of abnormal values ​​existing in the trajectory points in the original trajectory.

6. The method for generating a road divergence and confluence point based on an original trajectory according to claim 1, characterized in that: Road trajectory aggregation includes the following steps: S1: According to each trajectory point Pi (x i ,y i ), obtain the set of similar trajectory points Qi near it, and the distance from the point Pi is less than the parameter threshold d, and the angle deviation between the driving direction angle and Pi does not exceed the parameter threshold angle_d, where i is a positive integer; S2: Based on the similar trajectory point set Qi, calculate the offset distance Δdi of the trajectory point Pi to be offset and the coordinates after offset. The calculation method is as follows: Take Pi as the origin, the driving direction as the positive direction of the y-axis, and the direction 90° clockwise from the driving direction as the positive direction of the x-axis to establish a plane rectangular coordinate system Oxy. Since only the vertical direction of the driving direction needs to be offset, only the similar trajectory points (x a ,y a ) The x coordinate in the Oxy coordinate system is: ； Suppose the set of trajectory points whose x-axis coordinates are less than 0 in the set Qi is Qa, and the set of trajectory points whose x-axis coordinates are greater than 0 is Qb, where a and b are positive integers, then the offset distance Δdi of the offset trajectory point Pi is: ； Where m is the number of points in set Qa, is the x-coordinate of the points in the set Qa in the above Oxy coordinate system, is the distance from the point in set Qa to point Pi; n is the number of points in set Qb, is the x-coordinate of the points in the set Qb in the above Oxy coordinate system, is the distance from the point in the set Qb to the point Pi; Then the offset coordinates of point Pi are: ； S3: traverse all trajectory points to calculate the offset coordinates; S4: Calculate the average offset distance Δd of all trajectory points. When Δd is less than the parameter threshold δ, the trajectory aggregation is terminated.

7. The method for generating a road divergence and confluence point based on an original trajectory according to claim 6, characterized in that: When calculating the confidence value, the change in the trajectory distance near the divergence and confluence point is used as its confidence value.

Images