Driving track matching method and device, equipment and medium

Abstract

The present application relates to the field of trajectory data processing, and discloses a driving trajectory matching method, device, equipment and medium, the method comprises: obtaining a driving trajectory, determining the logical road network topology corresponding to the driving trajectory; according to the characteristic index data of the driving trajectory, selecting the trajectory reference point in the driving trajectory; according to the trajectory reference point, determine the target road section corresponding to the trajectory section where the trajectory reference point is located in the logical road network topology. The present application realizes the scheme of positioning first and then matching by realizing the matching of the road section through the reference point, reduces the time consumption of matching, optimizes the matching performance, avoids the problem of overall deviation of the matching result, improves the accuracy of the road section matching in the matching process, realizes the further accurate alignment of the trajectory and the road network, improves the accuracy of the logical road section matching in the road network matching process, and optimizes the effect of the road network matching.

Description

Technical Field

[0001] This invention relates to the field of trajectory data processing, and in particular to a method, apparatus, device, and medium for matching vehicle trajectories. Background Technology

[0002] Most road network matching schemes applied to intelligent maps are based on GPS information and road feature information, employing methods such as Hidden Markov Models (HMMs) and geometric matching to solve the problem of aligning trajectories with road networks. HMMs learn to create road classification algorithms from massive amounts of road feature information; geometric matching schemes extract geometric feature information from trajectories to identify road networks with similar geometric features. However, these road network matching schemes rely heavily on large amounts of road and geometric feature information, resulting in time-consuming matching processes, low model performance, high bias rates, low accuracy, and poor overall road network matching performance.

[0003] Therefore, it is necessary to propose a solution to optimize road network matching. The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a driving trajectory matching method, device, equipment, and medium, which aims to optimize the matching effect of road network.

[0005] To achieve the above objectives, the present invention provides a driving trajectory matching method, the driving trajectory matching method comprising:

[0006] Obtain the driving trajectory and determine the logical road network topology corresponding to the driving trajectory;

[0007] Based on the characteristic index data of the driving trajectory, select the trajectory reference point in the driving trajectory;

[0008] Based on the trajectory reference point, determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0009] Optionally, before the step of selecting a trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory, the method further includes:

[0010] Based on the trajectory data of the driving trajectory, determine the corresponding feature index data;

[0011] After the step of determining the corresponding feature index data, the step of selecting the trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory includes:

[0012] Based on the feature index data of the trajectory data, a trajectory reference point on the driving trajectory is determined, and the feature index data of the trajectory reference point meets a preset feature index threshold.

[0013] Optionally, the step of determining the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology based on the trajectory reference point includes:

[0014] Based on the driving trajectory, obtain the time-series trajectory point sequence corresponding to the driving trajectory;

[0015] Based on the trajectory reference point, and according to the time-series trajectory point sequence, the driving trajectory segment where the trajectory reference point is located is matched with the logical road segment of the logical road network topology to determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0016] Optionally, the step of matching the trajectory segment containing the trajectory reference point with the logical road segments of the logical road network topology according to the time-series trajectory point sequence, and determining the target road segment corresponding to the trajectory segment in the logical road network topology, includes:

[0017] Based on the trajectory segment where the trajectory reference point is located, perform first direction matching on the time-series trajectory point sequence to determine the first segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology;

[0018] Based on the trajectory segment where the trajectory reference point is located, the time-series trajectory point sequence is matched in a second direction to determine the endpoint of the second road segment in the logical road network topology where the trajectory reference point is located, wherein the second direction is opposite to the first direction;

[0019] By connecting the endpoints of the first road segment and the second road segment, the target road segment in the logical road network topology is determined where the trajectory reference point is located.

[0020] Optionally, the step of performing a first direction match on the time-series trajectory point sequence based on the trajectory segment where the trajectory reference point is located, and determining the endpoint of the first road segment of the trajectory segment where the trajectory reference point is located in the logical road network topology, includes:

[0021] Based on the logical road network topology, determine the adjacent road segments in the first direction of the trajectory segment where the trajectory reference point is located;

[0022] Based on the time-series trajectory point sequence, the adjacent road segments in the first direction are traversed to determine whether there is a corresponding first trajectory endpoint in the adjacent road segments in the first direction.

[0023] If the first trajectory endpoint exists, the driving trajectory is divided according to the preset trajectory division rules to determine the first road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0024] Optionally, the step of performing second-direction matching on the time-series trajectory point sequence based on the trajectory segment where the trajectory reference point is located, to determine the second segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology, wherein the second direction is opposite to the first direction, includes:

[0025] Based on the logical road network topology, determine the adjacent road segments in the second direction of the trajectory segment where the trajectory reference point is located;

[0026] Based on the time-series trajectory point sequence, the adjacent road segments in the second direction are traversed to determine whether there is a corresponding second trajectory endpoint in the adjacent road segments in the second direction.

[0027] If the second trajectory point exists, the driving trajectory is divided according to the preset trajectory division rules to determine the second road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0028] Optionally, the step of dividing the driving trajectory according to a preset trajectory division rule includes:

[0029] Determine whether the driving trajectory involves an intersection area;

[0030] If the driving trajectory does not involve intersection areas, the driving trajectory is divided based on the first division rule;

[0031] If the driving trajectory involves an intersection area, then determine whether the driving trajectory passes through the intersection area;

[0032] If the driving trajectory passes through the intersection area, the driving trajectory is divided based on the second division rule;

[0033] If the driving trajectory does not pass through the intersection area, the driving trajectory is divided based on the third division rule.

[0034] To achieve the above objectives, the present invention also provides a vehicle trajectory matching device, the vehicle trajectory matching device comprising:

[0035] The matching module is used to acquire the driving trajectory and determine the logical road network topology corresponding to the driving trajectory;

[0036] The trajectory node selection module is used to select trajectory reference points in the driving trajectory based on the feature index data of the driving trajectory.

[0037] The logical road segment determination module is used to determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology, based on the trajectory reference point.

[0038] In this invention, each functional module of the vehicle trajectory matching device implements the steps of the vehicle trajectory matching method described above during operation.

[0039] To achieve the above objectives, the present invention also provides an apparatus comprising: a memory, a processor, and a driving trajectory matching program stored in the memory and executable on the processor, wherein the driving trajectory matching program, when executed by the processor, implements the steps of the driving trajectory matching method as described above.

[0040] To achieve the above objectives, the present invention also proposes a computer-readable storage medium storing a vehicle trajectory matching program, wherein the vehicle trajectory matching program, when executed by a processor, implements the steps of the vehicle trajectory matching method as described above.

[0041] This invention provides a driving trajectory matching method, apparatus, device, and medium. The method includes: acquiring a driving trajectory and determining the logical road network topology corresponding to the driving trajectory; selecting a trajectory reference point in the driving trajectory based on the characteristic index data of the driving trajectory; and determining the target road segment in the logical road network topology corresponding to the trajectory segment where the trajectory reference point is located based on the trajectory reference point.

[0042] This solution selects a trajectory reference point based on the driving trajectory and the logical road network topology. Based on this trajectory reference point, it determines the corresponding target road segment in the logical road network topology and achieves road segment matching through the reference point. This realizes a positioning-then-matching approach, reducing matching time and optimizing matching performance. It avoids the problem of overall offset in matching results, improves the accuracy of road segment matching during the matching process, achieves further precise alignment between the trajectory and the road network, improves the accuracy of logical road segment matching during the road network matching process, and optimizes the effect of road network matching. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the hardware operating environment involved in the embodiments of the present invention;

[0044] Figure 2 This is a flowchart illustrating the first embodiment of the vehicle trajectory matching method of the present invention;

[0045] Figure 3 This is an exemplary schematic diagram of the geometric road network in the first embodiment of the vehicle trajectory matching method of the present invention;

[0046] Figure 4This is an exemplary schematic diagram of the logical road network topology in the first embodiment of the vehicle trajectory matching method of the present invention;

[0047] Figure 5 This is a flowchart illustrating the second embodiment of the vehicle trajectory matching method of the present invention;

[0048] Figure 6 This is a flowchart illustrating the third embodiment of the vehicle trajectory matching method of the present invention;

[0049] Figure 7 This is a flowchart illustrating the fourth embodiment of the vehicle trajectory matching method of the present invention;

[0050] Figure 8 This is a flowchart illustrating the fifth embodiment of the vehicle trajectory matching method of the present invention;

[0051] Figure 9 This is an exemplary schematic diagram of the first division rule in the fifth embodiment of the vehicle trajectory matching method of the present invention;

[0052] Figure 10 This is an exemplary schematic diagram of the second division rule in the fifth embodiment of the vehicle trajectory matching method of the present invention;

[0053] Figure 11 This is an exemplary schematic diagram of the third division rule in the fifth embodiment of the vehicle trajectory matching method of the present invention;

[0054] Figure 12 This is a schematic diagram of the functional modules of the vehicle trajectory matching device involved in the vehicle trajectory matching method of the present invention.

[0055] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0056] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0057] Specifically, refer to Figure 1 , Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention. For example... Figure 1As shown, the device may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or stable non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0058] like Figure 1 As shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle trajectory matching program. The operating system is a program that manages and controls the hardware and software resources of the device, supporting the operation of the vehicle trajectory matching program and other software or programs. The network communication module manages and controls the network interface 1002. The user interface 1003 is mainly used for data communication with clients. The network interface 1004 is mainly used for establishing communication connections with servers. The processor 1001 can be used to call the vehicle trajectory matching program stored in the memory 1005.

[0059] When the driving trajectory matching program stored in the aforementioned memory 1005 is executed by the processor, it performs the following steps:

[0060] Obtain the driving trajectory and determine the logical road network topology corresponding to the driving trajectory;

[0061] Based on the characteristic index data of the driving trajectory, select the trajectory reference point in the driving trajectory;

[0062] Based on the trajectory reference point, determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0063] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0064] Based on the trajectory data of the driving trajectory, determine the corresponding feature index data;

[0065] Based on the feature index data of the trajectory data, a trajectory reference point on the driving trajectory is determined, and the feature index data of the trajectory reference point meets a preset feature index threshold.

[0066] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0067] Based on the driving trajectory, obtain the time-series trajectory point sequence corresponding to the driving trajectory;

[0068] Based on the trajectory reference point, and according to the time-series trajectory point sequence, the driving trajectory segment where the trajectory reference point is located is matched with the logical road segment of the logical road network topology to determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0069] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0070] Based on the trajectory segment where the trajectory reference point is located, perform first direction matching on the time-series trajectory point sequence to determine the first segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology;

[0071] Based on the trajectory segment where the trajectory reference point is located, the time-series trajectory point sequence is matched in a second direction to determine the endpoint of the second road segment in the logical road network topology where the trajectory reference point is located, wherein the second direction is opposite to the first direction;

[0072] By connecting the endpoints of the first road segment and the second road segment, the target road segment in the logical road network topology is determined where the trajectory reference point is located.

[0073] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0074] Based on the logical road network topology, determine the adjacent road segments in the first direction of the trajectory segment where the trajectory reference point is located;

[0075] Based on the time-series trajectory point sequence, the adjacent road segments in the first direction are traversed to determine whether there is a corresponding first trajectory endpoint in the adjacent road segments in the first direction.

[0076] If the first trajectory endpoint exists, the driving trajectory is divided according to the preset trajectory division rules to determine the first road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0077] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0078] Based on the logical road network topology, determine the adjacent road segments in the second direction of the trajectory segment where the trajectory reference point is located;

[0079] Based on the time-series trajectory point sequence, the adjacent road segments in the second direction are traversed to determine whether there is a corresponding second trajectory endpoint in the adjacent road segments in the second direction.

[0080] If the second trajectory point exists, the driving trajectory is divided according to the preset trajectory division rules to determine the second road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0081] Furthermore, when the driving trajectory matching program stored in memory 1005 is executed by the processor, it also performs the following steps:

[0082] Determine whether the driving trajectory involves an intersection area;

[0083] If the driving trajectory does not involve intersection areas, the driving trajectory is divided based on the first division rule;

[0084] If the driving trajectory involves an intersection area, then determine whether the driving trajectory passes through the intersection area;

[0085] If the driving trajectory passes through the intersection area, the driving trajectory is divided based on the second division rule;

[0086] If the driving trajectory does not pass through the intersection area, the driving trajectory is divided based on the third division rule.

[0087] To better understand the above technical solutions, exemplary embodiments of this disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of this disclosure to those skilled in the art.

[0088] Specifically, refer to Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the vehicle trajectory matching method of the present invention. The vehicle trajectory matching method includes:

[0089] Step S10: Obtain the driving trajectory and determine the logical road network topology corresponding to the driving trajectory;

[0090] It should be noted that, in this embodiment, the logical road network topology is obtained by performing GPS positioning on the trajectory data corresponding to the user's driving trajectory, achieving physical coarse alignment of the trajectory data, performing road network matching based on the trajectory data, determining the geometric road network corresponding to the trajectory data, obtaining the geometric road network information where the trajectory data is located, and extracting the corresponding logical road network topology based on the geometric road network information.

[0091] Optionally, by performing GPS positioning on the user's driving trajectory data, physical coarse alignment of the trajectory data can be achieved. The geometric road network in which the trajectory line of the trajectory data is located can be determined by using schemes such as Hidden Markov Model (HMM) and geometric matching to achieve geometric matching of logical data. In this embodiment, the method of performing preliminary geometric matching is not specifically limited.

[0092] Specifically, the logical road network topology can be extracted by adding intersection regions, logical nodes, road sections, and logical nodes to the geometric road network that includes road links, intersection joints, and road vertices joints, thereby obtaining the logical road network topology.

[0093] Reference Figure 3 , Figure 3 This is an exemplary schematic diagram of a geometric road network; see reference. Figure 4 , Figure 4 This is an exemplary schematic diagram of a logical road network topology. Specifically, the logical road network topology differs from the geometric road network in that it contains more logical nodes, which enhances the connection between logical points in the road network matching process and improves the integrity of the road network data.

[0094] Step S20: Select a trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory;

[0095] It should be noted that, in this embodiment, based on the trajectory data of the driving trajectory, the characteristic index data of each trajectory point in the driving trajectory is determined, and based on whether the characteristic index data meets the preset characteristic index threshold, the trajectory reference point in the driving trajectory is determined.

[0096] Optionally, the trajectory reference point can be selected by matching the feature index data corresponding to the trajectory data of the driving trajectory with the feature index threshold, determining the trajectory points in the trajectory data that meet the preset standard threshold, selecting the trajectory reference point among the trajectory points that meet the preset standard threshold, and mapping the trajectory reference point to the logical road network topology to establish the association between the driving trajectory and the logical road network topology.

[0097] Specifically, for example, the feature index data of the above trajectory data includes at least: logical link relationships, height dimension information, road surface markings and common sense principles, etc. Based on comparing each feature index data with the corresponding feature index threshold, the initial trajectory points in the above trajectory data that meet the above feature index thresholds are determined.

[0098] Step S30: Based on the trajectory reference point, determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0099] It should be noted that, in this embodiment, based on the time-series trajectory point sequence of the driving trajectory, the trajectory segment where the trajectory reference point is located is bidirectionally matched with the logical road segment in the logical road network topology to determine the target road segment corresponding to the reference point in the logical road network topology.

[0100] Optionally, bidirectional inference is performed on the trajectory reference point to determine the logical road segment in the logical road network topology where the trajectory segment where the trajectory reference point is located is mapped. Based on the logical road segment, the adjacent road segments corresponding to the trajectory segment where the trajectory reference point is located in two directions are determined. Based on the time-series trajectory point sequence, it is determined whether there are far endpoints corresponding to the trajectory reference point in the two adjacent road segments in the two directions. If there are, the corresponding target road segment is determined based on the far endpoints in the two directions.

[0101] This embodiment achieves trajectory point matching based on logical road network topology. By matching trajectory points, the target road segment where the trajectory data is located is determined. Trajectory point matching is performed on the basis of logical road network topology, and the trajectory is further aligned with the road network by matching the target road segment. This reduces the deviation rate of road network matching, improves the accuracy of road network matching, and optimizes the effect of road network matching.

[0102] Furthermore, based on the first embodiment of the vehicle trajectory matching method of the present invention described above, a second embodiment of the vehicle trajectory matching method of the present invention is proposed. This embodiment is an extension and refinement of step S20, which involves selecting trajectory reference points in the vehicle trajectory based on the feature index data of the vehicle trajectory, referring to... Figure 4 Specifically, it includes:

[0103] Step S21: Determine the corresponding feature index data based on the trajectory data of the driving trajectory;

[0104] Step S22: Based on the feature index data of the trajectory data, determine the trajectory reference point on the driving trajectory, wherein the feature index data of the trajectory reference point meets the preset feature index threshold.

[0105] It should be noted that, in this embodiment, the trajectory data is the trajectory data containing various vehicle motion data corresponding to the vehicle's driving trajectory during the user's driving process. By extracting the feature index data of preset items from the trajectory data and matching it with preset feature index thresholds, the initial trajectory points in the trajectory data that meet the preset standards are determined, and the initial trajectory points are mapped to the corresponding trajectory reference points in the logical road network topology.

[0106] Specifically, the feature index data of the above trajectory data includes at least: logical link relationships, height dimension information, road markings and basic principles, etc. By extracting the feature index data of preset items in the trajectory data and matching them with preset feature index thresholds, the initial trajectory points in the trajectory data that meet the preset standards are determined.

[0107] Optionally, based on a set of preset multiple indicator features, a trajectory point on the trajectory data is selected to achieve precise matching between the trajectory point and the road segment. Specifically, the aforementioned multiple indicator features may be:

[0108] 1. Does a logical road network exist near the trajectory point?

[0109] 2. Are the floor and height information consistent?

[0110] 3. Whether there are features such as lane lines or arrows near the trajectory point, and the credibility of arrow features near the trajectory point;

[0111] 4. Whether the trajectory point is located within the road boundary range determined based on the perceived lane line.

[0112] By extracting the above-mentioned multiple indicator features from the trajectory data of the driving trajectory, and matching the multiple indicator features of the trajectory points in the trajectory data with the preset feature indicator thresholds, all initial trajectory points in the driving trajectory that meet the indicator features are determined, and the initial trajectory points are mapped to the logical road network topology to determine the trajectory reference point.

[0113] Specifically, for example, the trajectory data contains trajectory points A and B, and multiple feature indicators of trajectory points A and B satisfy their corresponding preset indicator feature thresholds. For example, trajectory points A and B are located on the same logical road segment corresponding to the trajectory data, and their corresponding logical road network is determined after matching. The layer height information of trajectory points A and B can also correspond to the height dimension information in the logical topology network. There are road surface features such as perceived lane lines and arrows near trajectory point A, but trajectory point B does not satisfy the above multiple indicator feature 4: "Whether the trajectory point is located within the road boundary range determined according to the perceived lane lines". Therefore, given the presence of road surface features such as perceived lane lines and arrows, trajectory point A has high alignment accuracy and reliable alignment quality for the road segment. However, trajectory point B does not have road surface features such as perceived lane lines and arrows around it, making it impossible to determine whether trajectory point B is located within the specific road boundary range determined by perceived lane lines. Furthermore, the uncertainty of trajectory data, alignment algorithm, and perceived data results in low data reliability for trajectory point B. Therefore, trajectory point A is mapped to the logical road network topology as a trajectory reference point. By using road surface features such as perceived lane lines and arrows near the trajectory reference point, the data features are enhanced, thereby improving data reliability.

[0114] This invention selects trajectory reference points that meet multiple characteristic indicators, increases the data support points for the selection of trajectory reference points, enhances the data characteristics of trajectory reference points, and improves the credibility of road network matching data and the accuracy of road network matching results when performing logical road segment matching based on these trajectory reference points.

[0115] Furthermore, based on the first and second embodiments of the driving trajectory matching method of the present invention described above, a third embodiment of the driving trajectory matching method of the present invention is proposed. This embodiment is a refinement of step S30: "Based on the trajectory reference point, determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology," referring to... Figure 5 Specifically, it includes:

[0116] Step S31: Based on the driving trajectory, obtain the time-series trajectory point sequence corresponding to the driving trajectory;

[0117] It should be noted that in this embodiment, by acquiring the trajectory data of the driving trajectory, the time-series trajectory point sequence corresponding to the driving trajectory is determined. Specifically, the time-series trajectory sequence refers to the existence of corresponding trajectory points in the vehicle's driving trajectory. The driving trajectory consists of several trajectory points, and the time-series trajectory point sequence corresponding to the driving trajectory is determined based on the timeline of the occurrence of the trajectory points.

[0118] Step S32: Based on the trajectory reference point, and according to the time-series trajectory point sequence, match the driving trajectory segment where the trajectory reference point is located with the logical road segment of the logical road network topology to determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology.

[0119] It should be noted that in this embodiment, by performing bidirectional inference matching for the two directions of the trajectory reference point according to the time-series trajectory point sequence, the trajectory endpoints of the trajectory segment where the trajectory reference point is located in the two directions are determined, and the trajectory endpoints in the two directions are mapped to the corresponding logical road segments in the logical road network topology. The two road segment endpoints in the logical road network corresponding to the trajectory node are determined, and then the target road segment corresponding to the driving trajectory in the logical road network topology is determined based on the above two road segment endpoints.

[0120] This embodiment performs bidirectional inference matching based on trajectory reference points. By accurately matching road segments with trajectory reference points, it further realizes the accurate matching of trajectory data and logical road network. The target road segment is inferred from the time-series trajectory sequence of trajectory reference points, which improves the accuracy of trajectory and road segment matching, reduces the deviation rate in subsequent matching, and optimizes the effect of road network matching.

[0121] Furthermore, based on the third embodiment of the driving trajectory matching method of the present invention described above, a fourth embodiment of the logical road network generation method of the present invention is proposed. This embodiment refines step 32, which involves matching the driving trajectory segment where the trajectory reference point is located with the logical road segments of the logical road network topology according to the time-series trajectory point sequence, based on the trajectory reference point, to determine the refinement of the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology, referring to... Figure 6 Specifically, it includes:

[0122] Step S321: Based on the trajectory segment where the trajectory reference point is located, perform first direction matching on the time-series trajectory point sequence to determine the first segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology;

[0123] Optionally, the step of performing first-direction matching on the time-series trajectory point sequence based on the trajectory segment where the trajectory reference point is located, and determining the first road segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology, includes: determining the adjacent road segments in the first direction of the trajectory segment where the trajectory reference point is located based on the logical road network topology; traversing the adjacent road segments in the first direction based on the time-series trajectory point sequence, and determining whether there is a corresponding first trajectory endpoint among the adjacent road segments in the first direction; if there is a first trajectory endpoint, then dividing the driving trajectory according to a preset trajectory division rule, and determining the first road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0124] It should be noted that in this embodiment, the trajectory reference point is a trajectory point in the driving trajectory. The trajectory reference point is associated with the logical road network topology during the selection process. That is, there is a corresponding association between the trajectory reference point and the logical road network topology. By matching the trajectory segment where the trajectory reference point is located with the time-series trajectory point sequence point by point, starting from the trajectory reference point, the time-series trajectory point sequence is matched point by point with the trajectory segment where the trajectory reference point is located in the first direction to determine the first trajectory endpoint of the trajectory reference point in the first direction, and further determine the first road segment endpoint mapped to the logical road network topology based on the first trajectory endpoint.

[0125] Specifically, based on the trajectory reference point mapped to the logical road network topology, adjacent road segments connected to the logical road segment where the trajectory reference point is located are determined. Based on the trajectory points in the time-series trajectory sequence, the adjacent road segments are traversed to determine the first trajectory endpoint corresponding to the trajectory reference point in the first direction. Then, based on this first trajectory endpoint, the first road segment endpoint mapped to the logical road network topology is determined. For example, based on the time-series trajectory point sequence of the driving trajectory, starting from the trajectory reference point in the forward direction, the logical road segment (Roadsection) where the trajectory reference point is located in the logical road network topology is determined. Then, all adjacent road segments (InterRoadsections) connected to this logical road segment (Roadsection) are queried in the logical road network topology, and all adjacent road segments (InterRoadsections) are traversed to determine the far endpoint (LogicNode) within each adjacent road segment (InterRoadsection). Finally, by dividing the trajectory of intersecting road segments, the corresponding road segment endpoint in the logical road network topology is determined.

[0126] Step S322: Based on the trajectory segment where the trajectory reference point is located, perform second direction matching on the time-series trajectory point sequence to determine the second segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology, wherein the second direction is opposite to the first direction;

[0127] Optionally, based on the trajectory segment where the trajectory reference point is located, a second direction matching is performed on the time-series trajectory point sequence to determine the second road segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology. The step of the second direction being opposite to the first direction includes: determining the adjacent road segments in the second direction of the trajectory segment where the trajectory reference point is located according to the logical road network topology; traversing the adjacent road segments in the second direction according to the time-series trajectory point sequence to determine whether a corresponding second trajectory endpoint exists among the adjacent road segments in the second direction; if a second trajectory point exists, dividing the driving trajectory according to a preset trajectory division rule to determine the second road segment endpoint corresponding to the driving trajectory in the logical road network topology.

[0128] It should be noted that, in this embodiment, the trajectory reference point is a trajectory point in the driving trajectory. Starting from the trajectory reference point, the time-series trajectory point sequence is matched point by point to the trajectory segment where the trajectory reference point is located in the second direction to determine the second trajectory endpoint of the trajectory reference point in the second direction, and further, the second road segment endpoint mapped to the logical road network topology is determined based on the second trajectory endpoint.

[0129] In this embodiment, the method of inferring and matching the second trajectory point in the second direction based on the trajectory reference point is the same as the method of inferring and matching in the first direction. By inferring whether there is a remote endpoint in the second direction based on the time-series trajectory sequence points, and mapping the remote endpoint to the logical road network topology, the corresponding second road segment endpoint is determined.

[0130] Step S323: Connect the first road segment endpoint and the second road segment endpoint to determine the target road segment in the logical road network topology where the trajectory reference point is located.

[0131] It should be noted that, in this embodiment, the target road segment corresponding to the trajectory segment where the trajectory reference point is located is determined in the logical road network topology based on the first road segment endpoint and the second road segment endpoint determined in the logical road network topology according to the trajectory reference point. In this embodiment, the method of inferring and matching the second trajectory point in the second direction based on the trajectory reference point is the same as the method of inferring and matching in the first direction, but the first direction and the second direction are opposite to each other. This allows the first trajectory point in the first direction and the second trajectory point in the second direction to be inferred from the time-series trajectory sequence points during the matching process through the trajectory reference point. The trajectory segment connected by the first trajectory point and the second trajectory point is then mapped to the logical road network topology to determine the corresponding target road segment in the logical road network topology. The bidirectional inference matching method improves the data integrity from points to lines during the inference process.

[0132] Specifically, for example, if a trajectory data point shows a vehicle traveling from the parking lot entrance to the parking lot interior, then the route from the parking lot entrance to the vehicle's parking spot constitutes a driving trajectory for the vehicle. This trajectory is used for location tracking and matching within a digital map to determine the logical road network topology in which the trajectory resides. In this exemplary embodiment, the driving trajectory from the parking lot entrance to the vehicle's parking spot needs to be placed into a specific logical road segment within its corresponding logical road network topology. The specific implementation method is as follows:

[0133] An initial trajectory point (trajectory reference point) is selected from the driving trajectory from the parking lot entrance to the vehicle parking spot. Using this trajectory reference point, bidirectional inference is performed to accurately determine the target road segment corresponding to the driving trajectory from the parking lot entrance to the vehicle parking spot in the logical road network topology. On one hand, based on the initial trajectory point in the driving trajectory, inference is made towards the interior of the parking lot to determine the trajectory point A of the vehicle existing in the internal roads of the parking lot. On the other hand, based on the initial trajectory point in the driving trajectory, inference is made towards the exterior of the parking lot entrance to determine whether there is a trajectory point B of the vehicle in the road connected to the parking lot entrance. The trajectory points A and B matched by the bidirectional inference are then connected to determine the corresponding target road segment in the logical road network topology.

[0134] This embodiment performs bidirectional inference based on trajectory reference points. By accurately matching the road segments of the trajectory points, it further realizes the accurate matching of trajectory data and logical road network. It infers the far endpoints of adjacent road segments from the time-series trajectory sequence of the trajectory reference points, confirms the target road segment in the logical road network topology, reduces the deviation rate of road network matching, improves the accuracy of road network matching, and optimizes the effect of road network matching.

[0135] Furthermore, based on the first and fourth embodiments of the driving trajectory matching method of the present invention described above, a fifth embodiment of the logical road network generation method of the present invention is proposed. This embodiment is a refinement of the division of the driving trajectory according to a preset trajectory division rule, referring to... Figure 7 The method further includes:

[0136] Step S301: Determine whether the driving trajectory involves an intersection area;

[0137] It should be noted that in this embodiment, when the driving trajectory is mapped to a road segment switching point in the logical road network topology, the driving trajectory needs to be precisely divided to determine the corresponding logical road segment in the logical road network topology. Specifically, based on the classification of the user's driving trajectory into different regions and different driving types, the corresponding partition node information is determined according to the different types of trajectory data.

[0138] Furthermore, determining whether the driving trajectory involves an intersection area is based on whether the trajectory line corresponding to the driving trajectory passes through a preset intersection area (an intersection area refers to the intersection area where n logical road segments intersect, n>2). Therefore, the driving trajectory data is used to determine whether the driving trajectory involves an intersection area where two or more road segments intersect.

[0139] Step S302: If the driving trajectory does not involve an intersection area, the driving trajectory is divided based on the first division rule;

[0140] Optionally, when the driving trajectory does not involve intersection areas, i.e., the driving trajectory is a road segment or a turning point of a road segment connecting two road segments, it is known that there is no need to divide the driving trajectory when the driving trajectory is a road segment. When the driving trajectory involves a turning point of a road segment connecting two road segments, the driving trajectory corresponding to the two road segments is divided according to the first division rule. Specifically, the first division rule is the "angle bisector" division rule. By bisecting the angle generated by the two road segments and the three nodes NodeA, NodeB and NodeC, the corresponding angle bisector is determined. The angle bisector is extended to cut the driving trajectory, completing the division of the trajectory line that does not involve intersection areas and confirming the target road segment in the logical road network topology.

[0141] Reference Figure 8 , Figure 8 This is an exemplary schematic diagram of the first division rule. Specifically, the trajectory lines Traj / Lme1 and Traj / Lme2 in the diagram do not pass through the intersection area corresponding to NodeB. Therefore, the trajectory lines Traj / Lme1 and Traj / Lme2 are divided based on the "angle bisector" rule, determining that the trajectory lines Traj / Lme1 and Traj / Lme2 belong to the logical road segments of NodeA-NodeB and NodeB-NodeC respectively on the left and right sides of the angle bisector.

[0142] Step S303: If the driving trajectory involves an intersection area, determine whether the driving trajectory passes through the intersection area;

[0143] Step S304: If the driving trajectory passes through the intersection area, the driving trajectory is divided based on the second division rule;

[0144] It should be noted that in this embodiment, for a driving trajectory involving an intersection area (an intersection area refers to the intersection area where n logical road segments intersect, n>2), the corresponding division method is determined based on whether the driving trajectory intersects with the intersection area during the driving process, and the corresponding road segment node in the logical road network topology is determined.

[0145] Specifically, if the trajectory line entering the intersection area is of the first driving type, that is, the driving trajectory directly passes through the intersection area, then the second division rule is used to divide the trajectory line of the intersection area and determine the corresponding partition node information in the intersection area. Specifically, the second division rule is to divide the driving trajectory entering the intersection area according to the intersection boundary of the intersection area, and to cut the trajectory line segment of the intersection area to the InterSection of the intersection area, and to cut the trajectory line segment of the non-intersection area to the corresponding RoadSection.

[0146] Reference Figure 9 , Figure 9 This is an exemplary schematic diagram of the second division rule. Specifically, the boundary of the InterSection area is used as the dividing line to divide the trajectory line, thus dividing the driving trajectory into the InterSection area and the corresponding target road segment.

[0147] Step S305: If the driving trajectory does not pass through the intersection area, the driving trajectory is divided based on the third division rule.

[0148] It should be explained that, in this embodiment, if the driving trajectory entering the intersection area is of the second driving type, that is, although the driving trajectory is next to the intersection area, the driving trajectory does not pass through the intersection area, and the trajectory line corresponding to the driving trajectory travels directly from outside the InterSection, then the trajectory line is divided into trajectory data according to the third division rule to determine the partition node information corresponding to the third logical partition. Specifically, the third division rule uses the "angle bisector" of the two adjacent RoadSections of the InterSection to divide the trajectory data and determine the corresponding node information in the trajectory data.

[0149] Reference Figure 10 , Figure 10 This is an exemplary schematic diagram of the third partitioning rule. Specifically, the diagonal of the adjacent RoadSection is used as the dividing line to divide the trajectory line, and the driving trajectory is partitioned into the target road segment corresponding to the logical road network topology according to the diagonal dividing line.

[0150] This embodiment divides the trajectory lines corresponding to the trajectory data, determines the trajectory division rules corresponding to different types of trajectory data, and determines the corresponding partition node information, thereby increasing the data types, increasing the completeness of the road network data, and improving the accuracy of matching.

[0151] Furthermore, embodiments of the present invention also propose a vehicle trajectory matching device, referring to... Figure 11 , Figure 11 The diagram below illustrates the functional modules of the vehicle trajectory matching device of the present invention. The vehicle trajectory matching device includes:

[0152] Matching module 10 is used to acquire driving trajectory and determine the logical road network topology corresponding to the driving trajectory;

[0153] The selection module 20 is used to select a trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory.

[0154] The determination module 30 is used to determine the target road segment in the logical road network topology corresponding to the trajectory segment where the trajectory reference point is located, based on the trajectory reference point.

[0155] Furthermore, this embodiment of the invention also proposes a device, the device including a memory, a processor, and a driving trajectory matching program stored in the memory and executable on the processor, wherein when the driving trajectory matching program is executed by the processor, it implements the steps of the driving trajectory matching method as described above.

[0156] The various embodiments of the vehicle trajectory matching device and computer-readable storage medium of the present invention can be referred to the various embodiments of the vehicle trajectory matching method of the present invention, and will not be repeated here.

[0157] The specific embodiments of the computer program product of the present invention are basically the same as the embodiments of the above-described vehicle trajectory matching method, and will not be described in detail here.

[0158] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0159] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0160] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0161] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for matching vehicle trajectories, characterized in that, The driving trajectory matching method includes: Obtain the driving trajectory and determine the logical road network topology corresponding to the driving trajectory; Based on the characteristic index data of the driving trajectory, select the trajectory reference point in the driving trajectory; Based on the trajectory reference point, determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology; The step of determining the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology based on the trajectory reference point includes: Based on the driving trajectory, obtain the time-series trajectory point sequence corresponding to the driving trajectory; Based on the trajectory segment where the trajectory reference point is located, perform first direction matching on the time-series trajectory point sequence to determine the first segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology; Based on the trajectory segment where the trajectory reference point is located, the time-series trajectory point sequence is matched in a second direction to determine the endpoint of the second road segment in the logical road network topology where the trajectory reference point is located, wherein the second direction is opposite to the first direction; By connecting the endpoints of the first road segment and the second road segment, the target road segment in the logical road network topology is determined where the trajectory reference point is located.

2. The driving trajectory matching method as described in claim 1, characterized in that, Before the step of selecting a trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory, the method further includes: Based on the trajectory data of the driving trajectory, determine the corresponding feature index data; After the step of determining the corresponding feature index data, the step of selecting the trajectory reference point in the driving trajectory based on the feature index data of the driving trajectory includes: Based on the feature index data of the trajectory data, a trajectory reference point on the driving trajectory is determined, and the feature index data of the trajectory reference point meets a preset feature index threshold.

3. The driving trajectory matching method as described in claim 1, characterized in that, The step of performing a first direction matching on the time-series trajectory point sequence based on the trajectory segment where the trajectory reference point is located, and determining the endpoint of the first road segment of the trajectory segment where the trajectory reference point is located in the logical road network topology, includes: Based on the logical road network topology, determine the adjacent road segments in the first direction of the trajectory segment where the trajectory reference point is located; Based on the time-series trajectory point sequence, the adjacent road segments in the first direction are traversed to determine whether there is a corresponding first trajectory endpoint in the adjacent road segments in the first direction. If the first trajectory endpoint exists, the driving trajectory is divided according to the preset trajectory division rules to determine the first road segment endpoint corresponding to the driving trajectory in the logical road network topology.

4. The driving trajectory matching method as described in claim 1, characterized in that, The step of performing second-direction matching on the time-series trajectory point sequence based on the trajectory segment where the trajectory reference point is located, to determine the second segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology, wherein the second direction is opposite to the first direction, includes: Based on the logical road network topology, determine the adjacent road segments in the second direction of the trajectory segment where the trajectory reference point is located; Based on the time-series trajectory point sequence, the adjacent road segments in the second direction are traversed to determine whether there is a corresponding second trajectory endpoint in the adjacent road segments in the second direction. If the second trajectory endpoint exists, the driving trajectory is divided according to the preset trajectory division rules to determine the second road segment endpoint corresponding to the driving trajectory in the logical road network topology.

5. The driving trajectory matching method as described in any one of claims 3-4, characterized in that, The step of dividing the driving trajectory according to the preset trajectory division rules includes: Determine whether the driving trajectory involves an intersection area; If the driving trajectory does not involve intersection areas, the driving trajectory is divided based on the first division rule; If the driving trajectory involves an intersection area, then determine whether the driving trajectory passes through the intersection area; If the driving trajectory passes through the intersection area, the driving trajectory is divided based on the second division rule; If the driving trajectory does not pass through the intersection area, the driving trajectory is divided based on the third division rule.

6. A vehicle trajectory matching device, characterized in that, The driving trajectory matching device includes: The matching module is used to acquire the driving trajectory and determine the logical road network topology corresponding to the driving trajectory; The trajectory node selection module is used to select trajectory reference points in the driving trajectory based on the feature index data of the driving trajectory. The logical road segment determination module is used to determine the target road segment corresponding to the trajectory segment where the trajectory reference point is located in the logical road network topology, based on the trajectory reference point. The logical road segment determination module is also used for: Based on the driving trajectory, obtain the time-series trajectory point sequence corresponding to the driving trajectory; Based on the trajectory segment where the trajectory reference point is located, perform first direction matching on the time-series trajectory point sequence to determine the first segment endpoint of the trajectory segment where the trajectory reference point is located in the logical road network topology; Based on the trajectory segment where the trajectory reference point is located, the time-series trajectory point sequence is matched in a second direction to determine the endpoint of the second road segment in the logical road network topology where the trajectory reference point is located, wherein the second direction is opposite to the first direction; By connecting the endpoints of the first road segment and the second road segment, the target road segment in the logical road network topology is determined where the trajectory reference point is located.

7. A device, characterized in that, The device includes a memory, a processor, and a driving trajectory matching program stored in the memory and executable on the processor, wherein the driving trajectory matching program, when executed by the processor, implements the steps of the driving trajectory matching method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle trajectory matching program, which, when executed by a processor, implements the steps of the vehicle trajectory matching method as described in any one of claims 1 to 5.

Images