Road matching method and device

By detecting the non-ambiguous paths of candidate matching roads, the problem of low road matching accuracy in complex road network scenarios is solved, the accuracy of trajectory point matching roads is improved, and the reliability of service is ensured.

CN119063744APending Publication Date: 2024-12-03DITU (BEIJING) TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411356835.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-26
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The prior art is difficult to ensure the accuracy of road matching in complex road network scenarios, especially in complex road network environments such as main and auxiliary roads and upper and lower viaducts, resulting in the accuracy of trajectory points matching roads that cannot be guaranteed.

Method used

By detecting whether the candidate matching road has a target parallel road and determining non-ambiguous paths, it assists in verifying the accuracy of the candidate matching road, thereby improving the accuracy of road matching in complex road network scenarios.

Benefits of technology

It effectively avoids the impact of complex road network scenarios on road matching results, improves the accuracy of matching roads determined by trajectory points, and ensures the reliability and accuracy of services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063744A_ABST
    Figure CN119063744A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a road matching method and device. According to the embodiment of the invention, when it is detected that the candidate matching road of the current track point has the corresponding target parallel road, at least one non-ambiguous path of the candidate matching road is determined, and when it is detected that any non-ambiguous path is matched with the track to be matched, the candidate matching road is determined as the target matching road of the current track point. Wherein the current track point is a track point in the to-be-matched track, and the non-ambiguous path is a path which is only communicated with the candidate matching road, is not communicated with the target parallel road and is not parallel to the target parallel road. Therefore, the non-ambiguous path of the candidate matching road is determined, and the accuracy of the candidate matching road is subjected to auxiliary verification according to the non-ambiguous path, so that the influence of a complex road network scene on a road matching result can be avoided, and the accuracy of the matching road determined for the track point is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of map data processing, and in particular to a road matching method and device. Background Art

[0002] With the development of the Internet and the popularity of online ride-hailing, more and more people are choosing to travel by online ride-hailing. In order to provide passengers and drivers with better services (for example, navigation services, positioning services, route planning services, or trip tracking services, etc.), online ride-hailing platforms need to match the driving trajectory of online ride-hailing vehicles with city maps to find matching roads for each track point in the driving trajectory. However, the current road matching method only performs well in simple road network scenarios. Once faced with complex road network scenarios with multiple parallel roads at the same time, such as main and auxiliary roads, upper and lower viaducts, the accuracy of the matching roads determined for the track points cannot be guaranteed. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a road matching method and device to avoid the influence of complex road network scenes on road matching results, thereby improving the accuracy of matching roads determined for trajectory points.

[0004] In a first aspect, an embodiment of the present invention provides a road matching method, the method comprising:

[0005] Determine a candidate matching road for a current trajectory point, wherein the current trajectory point is a trajectory point in a trajectory to be matched;

[0006] In response to detecting that the candidate matching road has a corresponding target parallel road, determining at least one non-ambiguous path of the candidate matching road, the non-ambiguous path being a path that is only connected to the candidate matching road but not connected to the target parallel road and is not parallel to the target parallel road;

[0007] In response to the existence of any of the non-ambiguous paths matching the to-be-matched trajectory, the candidate matching road is determined as a target matching road for the current trajectory point.

[0008] In a second aspect, an embodiment of the present invention provides a road matching device, the device comprising:

[0009] A road matching unit, used to determine a candidate matching road for a current trajectory point, wherein the current trajectory point is a trajectory point in a trajectory to be matched;

[0010] a non-ambiguous path determination unit, configured to determine, in response to detecting that the candidate matching road has a corresponding target parallel road, at least one non-ambiguous path of the candidate matching road, wherein the non-ambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road and is not parallel to the target parallel road;

[0011] The matching road determining unit is configured to determine the candidate matching road as a target matching road of the current trajectory point in response to the existence of any of the non-ambiguous paths matching the trajectory to be matched.

[0012] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0013] In a fourth aspect, an embodiment of the present invention provides an electronic device, the device comprising:

[0014] a memory for storing one or more computer program instructions;

[0015] A processor, wherein the one or more computer program instructions are executed by the processor to implement the method as described in the first aspect.

[0016] In a fifth aspect, an embodiment of the present invention provides a computer program product, which, when executed on a computer, enables the computer to execute the method as described in the first aspect.

[0017] The embodiment of the present invention will determine at least one non-ambiguous path of the candidate matching road when it is detected that the candidate matching road of the current trajectory point has a corresponding target parallel road, and then determine the candidate matching road as the target matching road of the current trajectory point when it is detected that there is any non-ambiguous path matching the trajectory to be matched. Among them, the current trajectory point is a trajectory point in the trajectory to be matched, and the non-ambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road, and is not parallel to the target parallel road. Therefore, by determining the non-ambiguous path of the candidate matching road and performing auxiliary verification on the accuracy of the candidate matching road based on the non-ambiguous path, the embodiment of the present invention can avoid the influence of complex road network scenes on the road matching results, thereby improving the accuracy of the matching road determined for the trajectory point. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0019] Figure 1 is a flow chart of a road matching method according to an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a verification process of candidate matching roads according to an embodiment of the present invention;

[0021] Figure 3 A flowchart of a method for determining a target parallel road according to an embodiment of the present invention;

[0022] Figure 4 A flowchart of a method for determining candidate parallel roads according to an embodiment of the present invention;

[0023] Figure 5 A schematic diagram of segmentation of candidate matching roads according to an embodiment of the present invention;

[0024] Figure 6 A flowchart of a method for determining candidate parallel roads according to an embodiment of the present invention;

[0025] Figure 7 Schematic diagram of a process for determining candidate parallel roads according to an embodiment of the present invention;

[0026] Figure 8 A flowchart of a method for determining a target parallel road according to an embodiment of the present invention;

[0027] Fig. 9 is a flow chart of a method for determining a non-ambiguous path according to an embodiment of the present invention;

[0028] Fig.10 Schematic diagram of a process for determining a non-ambiguous road according to an embodiment of the present invention;

[0029] Fig.11 A flowchart of a non-ambiguous path matching method according to an embodiment of the present invention;

[0030] Fig.12 is a schematic diagram of a road matching device according to an embodiment of the present invention;

[0031] Fig.13 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0033] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0034] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0035] In the description of this application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0036] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0037] In the following description, the vehicle driving trajectory in the online car-hailing scenario will be used as the road matching object for explanation, but it should be understood that the solution of the embodiment of the present invention can also be applied to other scenarios with road matching requirements (such as travel navigation scenarios or logistics distribution scenarios, etc.). Relatively speaking, when applied to different scenarios, the solution of the embodiment of the present invention can be used to perform road matching on the driving trajectory of different related equipment (such as shared bicycles, delivery vehicles, delivery unmanned vehicles, buses or taxis, etc.) or the moving trajectory of people, etc., and this application does not limit this.

[0038] Figure 1 is a flow chart of the road matching method of the embodiment of the present invention. It should be understood that the executor of the road matching method of the embodiment of the present invention may be a corresponding road matching device. According to the way in which the user (in this embodiment, the user is a driver or a passenger) obtains the service and the type of service obtained, the road matching device may be a server, or a terminal device held by the user (such as a smart phone, tablet computer, smart wearable device or laptop computer, etc.), or a data processing terminal mounted on a vehicle, etc., and this application does not impose any restrictions on this. Figure 1 As shown, the road matching method may specifically include the following steps:

[0039] Step S100: Determine candidate matching roads for the current trajectory point.

[0040] Specifically, the trajectory to be matched (in this embodiment, the trajectory to be matched refers to the vehicle driving trajectory of the online car-hailing vehicle) may include a series of trajectory points. The device may select any unselected trajectory point in the trajectory to be matched as the current trajectory point, and determine the candidate matching road for the current trajectory point. It should be understood that in this embodiment, the candidate matching road may refer to a matching road that has not been verified for accuracy. The candidate matching road will not be used as a basis for providing relevant services to users.

[0041] Optionally, in this embodiment, as an implementation method, the device may first determine the candidate matching roads for each trajectory point in the trajectory to be matched, and then perform auxiliary verification on the accuracy of the candidate matching roads for each trajectory point. Alternatively, as another implementation method, the device may also perform auxiliary verification on the accuracy of the candidate matching roads for each trajectory point in the process of determining the candidate matching roads for each trajectory point in the trajectory to be matched (that is, each time a candidate matching road for a trajectory point is determined, the currently determined candidate matching road is verified), and the present application does not limit this. In step S100, if the above-mentioned first implementation method is adopted, since the candidate matching roads for each trajectory point have been determined in advance, the device can determine the candidate matching roads for the current trajectory point based on the historical road matching records. If the above-mentioned second implementation method is adopted, the device can directly determine the candidate matching roads for the current trajectory point.

[0042] Furthermore, regardless of which of the above implementation methods is adopted, the candidate matching roads can be determined by the device by matching the current trajectory point in the city map. Specifically, the city map may include road information of each city road in the city, such as road length, road width, road shape, whether the road is open to traffic, and the direction of travel allowed by the road. Each trajectory point may have corresponding trajectory point information, such as collection time, collection location, forward direction and speed. The device can match each city road with the current trajectory point according to the road information of each city road in the city map and the trajectory point information corresponding to the current trajectory point to determine the candidate matching roads of the current trajectory point.

[0043] Further, in this embodiment, the road matching method adopted by the device may include a matching method based on geometric information, a matching method based on topological information, or a matching method based on comprehensive information, etc. Among them, the matching method based on geometric information may refer to using the nearest neighbor algorithm to determine the urban road closest to the current trajectory point as the candidate matching road for the current trajectory point. The matching method based on topological information may refer to aligning the current trajectory point and the adjacent trajectory point with the corresponding road nodes in the city map, respectively, and calculating the shortest path between the road nodes according to the shortest path algorithm, and then determining the shortest path between the road nodes as the candidate matching road for the current trajectory point. The matching method based on comprehensive information may refer to using machine learning or data mining methods, such as Hidden Markov Model (HMM), to determine the candidate matching road for the current trajectory point by setting corresponding topological constraints for it. It should be understood that in addition to the above-mentioned road matching methods, the device may also use other road matching methods to determine the candidate matching roads for the current trajectory point, and this application does not limit this.

[0044] Optionally, in this embodiment, the trajectory points in the trajectory to be matched can be collected and determined at preset time intervals by corresponding sensors (such as position sensors, direction sensors, and speed sensors, etc.) mounted on the vehicle or on the user terminal device during the vehicle's driving process.

[0045] Step S200: In response to detecting that the candidate matching road has a corresponding target parallel road, determining at least one non-ambiguous path of the candidate matching road.

[0046] Specifically, after determining the candidate matching roads of the current trajectory point, the device can detect whether the candidate matching roads have corresponding target parallel roads. If it is detected that the candidate matching roads have corresponding target parallel roads, the device can determine at least one non-ambiguous path of the candidate matching roads. Among them, the non-ambiguous path can be a path that is only connected to the candidate matching roads but not to the target parallel roads, and is not parallel to the target parallel roads (it can be completely non-parallel, or some of the roads can be non-parallel). It should be understood that in this embodiment, since the non-ambiguous path can clearly distinguish the candidate matching roads from the target parallel roads, the non-ambiguous path can be used as a verification basis for auxiliary verification of the accuracy of the candidate matching roads.

[0047] Figure 2 FIG. 1 is a schematic diagram of the verification process of candidate matching roads in an embodiment of the present invention. It should be understood that in this embodiment, the thick solid line with arrows and the hollow dots can be used to represent roads and track points, respectively. The directions pointed by the arrows of the two can be used to represent the allowed driving direction of the road and the forward direction of the track point, respectively. Figure 2As shown, for the current trajectory point 21, after detecting that the candidate matching road 22 of the current trajectory point 21 has a corresponding target parallel road 23, the device can determine the non-ambiguous path of the candidate matching road 22 (that is, the path composed of roads 24 and 22). The non-ambiguous path can be used as a verification basis for auxiliary verification of the accuracy of the candidate matching road 22. Specifically, since the non-ambiguous path is only connected to the candidate matching road 22 but not to the target parallel road 23, and is not parallel to the target parallel road 23, the device only needs to determine whether the trajectory to be matched matches the non-ambiguous path to verify the accuracy of the candidate matching road 22.

[0048] Figure 3 Flow chart of the target parallel road determination method according to an embodiment of the present invention. It should be understood that by executing Figure 3 The target parallel road determination method shown in the figure can find these target parallel roads when the candidate matching roads have corresponding target parallel roads. Figure 3 As shown, the target parallel road determination method may specifically include the following steps:

[0049] Step S210: Determine candidate parallel roads of the candidate matching road.

[0050] Specifically, the device may first determine candidate parallel roads of the candidate matching road, wherein the candidate parallel roads may be roads parallel to the candidate matching road found by the device after preliminary screening of roads located near the candidate matching road.

[0051] Optionally, in this embodiment, in order to ensure comprehensiveness of screening of candidate parallel roads, the device may divide the candidate matching road into multiple sub-roads, and search for candidate parallel roads of the candidate matching road based on each sub-road respectively.

[0052] Figure 4 FIG. 1 is a flow chart of a candidate parallel road determination method according to an embodiment of the present invention. It should be understood that by executing Figure 4 In the candidate parallel road determination method shown in the figure, the device can comprehensively screen the candidate parallel roads of the candidate matching road, that is, implement the above step S210. Figure 4 As shown, the candidate parallel road determination method may specifically include the following steps:

[0053] Step S211: segment the candidate matching road according to the turning angle and the curvature of the candidate matching road to obtain a plurality of sub-roads.

[0054] Specifically, in this embodiment, if the curvature of the candidate matching road is too large or the steering angle changes suddenly, the subsequent screening of the candidate parallel roads will be incomplete. Therefore, the device can divide the candidate matching road according to the steering angle and curvature of the candidate matching road to obtain multiple sub-roads. The curvature of each sub-road should be ensured to be within the preset curvature range, and there is no point in the road where the steering angle changes suddenly.

[0055] Optionally, as an implementation method, in step S211, the device may first find the points where the turning angle suddenly changes in the candidate matching road, and perform a preliminary segmentation of the candidate matching road based on the found points, and then perform a second segmentation on each part of the candidate matching road obtained after the preliminary segmentation based on the arc, thereby obtaining multiple sub-roads.

[0056] Figure 5 FIG. 1 is a schematic diagram of segmenting candidate matching roads according to an embodiment of the present invention. It should be understood that Figure 5 The road intercepted between any two solid points in is the sub-road in this embodiment. Figure 5 As shown, the device can first find the point 511 where the turning angle suddenly changes in the candidate matching road 51, and perform a preliminary segmentation on the candidate matching road 51 according to the point 511 to divide the candidate matching road 51 into two parts, and then perform a second segmentation on each part of the candidate matching road obtained after the preliminary segmentation according to the arc ( Figure 5 The other points except point 511 are the segmentation points selected in the second segmentation process), thereby obtaining multiple sub-roads.

[0057] It should be understood that the segmentation method given above is only for illustration. In actual application, the device can also use other methods to segment the candidate matching roads on the premise of ensuring that each sub-road obtained by segmentation meets the conditions. This application does not limit this.

[0058] Step S212: determining the candidate parallel roads according to the sub-roads.

[0059] Specifically, after obtaining multiple sub-roads, the device may search for candidate parallel roads of the candidate matching road based on each sub-road.

[0060] Optionally, in step S212, the device may first find a road located near the sub-road, and then determine a candidate parallel road among the found roads according to an angular relationship between the found road and the candidate matching road.

[0061] Figure 6 FIG. 1 is a flow chart of a candidate parallel road determination method according to an embodiment of the present invention. It should be understood that by executing Figure 6The candidate parallel road determination method shown in the figure can find candidate parallel roads of the candidate matching road based on each sub-road, that is, implement the above step S212. Figure 6 As shown, the candidate parallel road determination method may specifically include the following steps:

[0062] Step S2121: For each of the sub-roads, a first rectangular buffer zone is constructed according to a line connecting a road start point and a road end point of the sub-road.

[0063] Specifically, the device may construct corresponding first rectangular buffer zones according to the connection lines between the road start points and the road end points of each sub-road.

[0064] Optionally, when constructing the first rectangular buffer, the device may select a 0.05 quantile and a 0.95 quantile on the line between the road start point and the road end point of the sub-road, respectively, and construct the first rectangular buffer with the line between the two quantiles as the center. The width of the first rectangular buffer may be set to a first preset width, such as 30 meters, which may be adjusted by relevant personnel according to actual conditions.

[0065] Figure 7 FIG. 2 is a schematic diagram of a process for determining candidate parallel roads according to an embodiment of the present invention. Figure 7 As shown, for sub-road 71, the device can select point 712 (i.e., 0.05 quantile) and point 713 (i.e., 0.95 quantile) on the line 711 between the road starting point and the road end point of sub-road 71, and construct a first rectangular buffer zone 72 with the line between the point 712 and the point 713 quantiles as the center.

[0066] Step S2122: For each map road covered by the first rectangular buffer zone, determine the angle deviation between the map road and the candidate matching road.

[0067] Specifically, for the map roads covered by the first rectangular buffer, the device can confirm that they are located near the sub-roads. Furthermore, for these map roads, the device can determine the angle deviation between them and the candidate matching roads.

[0068] like Figure 7 As shown, for the map roads 73 and 74 covered by the first rectangular buffer 72, the device can confirm that both are located near the sub-road. Then, the device can determine the angle deviation between the map roads 73 and 74 and the candidate matching roads respectively. It should be understood that Figure 7 The map roads 73 and 74 shown in the figure are only a part of the actual map roads. In the present embodiment, as long as a part of a map road is covered by the first rectangular buffer zone, the map road will be identified as a map road covered by the first rectangular buffer zone.

[0069] It should be understood that in this embodiment, since the curvature of each sub-road is within the preset curvature range and there is no point in the road where the turning angle changes suddenly, the first rectangular buffer zone constructed by the device based on the sub-roads can cover as many map roads as possible that may be parallel to the candidate matching roads.

[0070] Optionally, a road is usually composed of multiple road nodes. When determining the angular deviation between the map road and the candidate matching road, the device can first determine the turning angle of the map road at each road node, and determine the turning angle of the candidate matching road at each road node, and then determine the angular deviation between the map road and the candidate matching road based on the turning angle of the map road at each road node and the turning angle of the candidate matching road at each road node. Among them, the angular deviation between the map road and the candidate matching road can be determined based on data such as the maximum steering angle and / or average steering angle of the map road and the candidate matching road at each road node. It should be understood that the present application does not limit the specific method for determining the angular deviation between the map road and the candidate matching road, which can be set and adjusted by relevant personnel according to actual needs.

[0071] Step S2123: Determine the map roads whose angle deviation is less than or equal to the preset angle threshold as the candidate parallel roads.

[0072] Specifically, after determining the angle deviation between each map road and the candidate matching road, the device may determine the map roads whose angle deviation is less than or equal to a preset angle threshold as candidate parallel roads.

[0073] Step S220: splicing the candidate parallel roads into at least one candidate parallel path according to the connectivity relationship between the candidate parallel roads.

[0074] Specifically, after determining the candidate parallel roads of the candidate matching road, the device may splice the candidate parallel roads into at least one candidate parallel path according to the connectivity relationship between the candidate parallel roads, wherein the candidate parallel paths may include candidate parallel roads that are sequentially connected.

[0075] Step S230: determining a target parallel road of the candidate matching roads according to each of the candidate parallel paths.

[0076] Specifically, after at least one candidate parallel path is obtained by splicing, the device may perform a secondary screening on each candidate parallel path, and determine the candidate parallel roads in the screened candidate parallel paths as target parallel roads of the candidate matching roads.

[0077] Figure 8FIG. 1 is a flow chart of a method for determining a target parallel road according to an embodiment of the present invention. It should be understood that by executing Figure 8 In the target parallel road determination method shown in FIG. 1 , the device can perform a second screening on each candidate parallel path, and determine the candidate parallel roads included in the screened candidate parallel paths as target parallel roads of the candidate matching roads, that is, to implement the above step S230. Figure 8 As shown, the target parallel road determination method may specifically include the following steps:

[0078] Step S231: construct a second rectangular buffer according to the connection line between the path start point and the path end point of the candidate parallel path.

[0079] Specifically, the device may construct a second rectangular buffer according to a connection line between a path start point and a path end point of the candidate parallel path.

[0080] Optionally, similar to the process of constructing the first rectangular buffer, the device can select a 0.05 quantile and a 0.95 quantile on the line between the path start point and the path end point of the candidate parallel path, respectively, and construct a second rectangular buffer with the line between the two quantiles as the center. The width of the second rectangular buffer can be set to a second preset width, such as 30 meters, which can be adjusted by relevant personnel according to actual conditions.

[0081] Step S232: For each of the candidate parallel paths, in response to the coverage of the candidate matching road by the second rectangular buffer zone constructed based on the candidate parallel paths satisfying a preset coverage threshold, each candidate parallel road in the candidate parallel paths is determined as a target parallel road of the candidate matching road.

[0082] Specifically, after constructing the second rectangular buffer based on each candidate parallel path, the device can determine whether the coverage rate of the constructed second rectangular buffer on the candidate matching road meets the preset coverage rate threshold. If it is detected that the coverage rate of the second rectangular buffer constructed based on the candidate parallel path on the candidate matching road meets the preset coverage rate threshold, the device can determine each candidate parallel road included in the candidate parallel path as the target parallel road of the candidate matching road.

[0083] Optionally, if no candidate parallel road of the candidate matching road is detected in step S210, or if it is detected in step S232 that the coverage of the candidate matching road by the second rectangular buffer constructed based on each candidate matching path does not meet the preset coverage threshold, the device may confirm that the candidate matching road does not have a corresponding target parallel road. Further, after confirming that the candidate matching road does not have a corresponding target parallel road, the device may directly determine the candidate matching road as the target matching road of the current trajectory point.

[0084] Optionally, in order to ensure the accuracy of verification, this embodiment needs to find all non-ambiguous paths of the candidate matching road. In order to meet this requirement, when determining at least one non-ambiguous path of the candidate matching road, the device can traverse the preceding and succeeding roads of the candidate matching road, and find non-ambiguous roads that meet the requirements during the traversal process, and then determine the non-ambiguous path of the candidate matching road based on the non-ambiguous roads.

[0085] Fig. 9 FIG. 1 is a flow chart of a method for determining a non-ambiguous path according to an embodiment of the present invention. It should be understood that by executing Fig. 9 According to the non-ambiguous path determination method shown in FIG. 1 , the device can determine at least one non-ambiguous path of the candidate matching road. Fig. 9 As shown, the non-ambiguous path determination method may specifically include the following steps:

[0086] Step S240: Traverse the preceding roads and the succeeding roads of the candidate matching road, and determine the preceding roads and the succeeding roads whose road distances to the candidate matching road are less than a preset distance threshold and which are not parallel to and connected to the target parallel road as non-ambiguous roads.

[0087] Specifically, the device can traverse the preceding roads and succeeding roads that are directly connected or intermittently connected to the candidate matching roads, and during the traversal process, determine the preceding roads and succeeding roads whose road distances to the candidate matching roads are less than a preset distance threshold and which are not parallel to and connected to the target parallel road as non-ambiguous roads.

[0088] It should be understood that if there is no distance restriction, any two roads in the city map will eventually be connected. In this embodiment, the non-ambiguous road is not connected to the target parallel road specifically means that the non-ambiguous road is not connected to the target parallel road in the current area of ​​interest. Among them, the current area of ​​interest can be specifically limited by a preset distance threshold, and the specific value of the preset distance threshold can be set and adjusted by relevant personnel according to actual needs. For example, the preset distance threshold can be set to 500 meters.

[0089] Fig.10 FIG. 1 is a schematic diagram of the process of determining a non-ambiguous road according to an embodiment of the present invention. It should be understood that the process of traversing the preceding roads of the candidate matching roads is similar to the process of traversing the following roads. Therefore, for the convenience of illustration, Fig.10 Only the process of traversing the preceding roads of the candidate matching roads is shown. Fig.10 As shown, road AB is a candidate matching road for the current trajectory point, and road EF is a target parallel road for the candidate matching road.

[0090] First, the device will take road AB as the starting point, and extend forward to find predecessor roads BC, BG, and BE. Among them, the road distance between the predecessor road BC and the candidate matching road AB is less than the preset distance threshold, and it is not parallel to and connected with the target parallel road EF, so it will be determined by the device as a non-ambiguous road. The predecessor road BE is connected to the target parallel road EF, so it will be skipped by the device. The predecessor road BG is parallel to the target parallel road EF, so it will be skipped by the device. It should be understood that in order to improve the traversal efficiency, for the predecessor road connected to the target parallel road, even if the distance between the predecessor road and the candidate matching road has not exceeded the preset distance threshold, the device may no longer use the predecessor road as the starting point to find the next predecessor road.

[0091] Furthermore, after traversing the previous roads BC, BG, and BE, the device can determine whether the distance between the previous roads BC and BG and the candidate matching road AB exceeds a preset distance threshold. If so, the traversal process will be stopped. If not, the device will continue to use the previous roads BC and BG as the starting point to continue searching for the next previous road.

[0092] Step S250: For each of the non-ambiguous roads, determine the non-ambiguous road and the connecting road between the non-ambiguous road and the candidate matching road as the non-ambiguous path.

[0093] Specifically, the more complete the non-ambiguous path finally obtained is, the higher the matching accuracy rate will be when it is subsequently matched with the trajectory to be matched. Therefore, after determining each non-ambiguous road, for each non-ambiguous road, the device can determine the non-ambiguous road, the connecting road between the non-ambiguous road and the candidate matching road, and the candidate matching road as a non-ambiguous path.

[0094] Step S300: In response to detecting that any of the non-ambiguous paths matches the trajectory to be matched, determining the candidate matching road as the target matching road of the current trajectory point.

[0095] Specifically, after determining at least one non-ambiguous path of the candidate matching road, the device may match each non-ambiguous path with the trajectory to be matched. If it is detected that there is any non-ambiguous path matching the trajectory to be matched, the device may determine the candidate matching road as the target matching road of the current trajectory point. It should be understood that in this embodiment, the candidate matching road may refer to a matching road that has been verified for accuracy and passed the verification. The target matching road can be used as a service provision basis for providing relevant services to users.

[0096] like Figure 2 As shown, if it is detected that a non-ambiguous path (ie, a path composed of roads 24 and 22 ) is matched with the trajectory to be matched, the device may determine the candidate matching road 22 as the target matching road of the current trajectory point 21 .

[0097] It should be understood that after determining the target matching road of the current track point, the device can detect whether there are any track points that have not been selected in the track to be matched. If there are any track points that have not been selected in the track to be matched, the device can return to step S100 to reselect a new current track point from the track points that have not been selected, and determine the target matching road for the reselected current track point. It should be understood that in this embodiment, the target matching roads of adjacent track points can be the same or different, and this application does not limit this.

[0098] Optionally, in step S300 , for any non-ambiguous path, the device may determine whether the non-ambiguous path matches the trajectory to be matched by comparing the similarity between the non-ambiguous path and the trajectory to be matched.

[0099] Fig.11 FIG. 1 is a flow chart of a non-ambiguous path matching method according to an embodiment of the present invention. It should be understood that if there is a non-ambiguous path matching the trajectory to be matched, by executing Fig.11 The non-ambiguous path matching method shown in FIG. 1 can find a non-ambiguous path that matches the trajectory to be matched based on the similarity between each non-ambiguous path and the trajectory to be matched. Fig.11 As shown, the non-ambiguous path matching method may specifically include the following steps:

[0100] Step S310: For each of the non-ambiguous paths, determine the similarity between the non-ambiguous path and the trajectory formed by the corresponding matching trajectory points.

[0101] Specifically, the trajectory to be matched usually records the trajectory of the vehicle during the entire driving process. Therefore, when performing similarity matching, for each non-ambiguous path, the device can first find the trajectory points that match the non-ambiguous path in the trajectory to be matched, and determine the trajectory points that match the non-ambiguous path as the matching trajectory points of the non-ambiguous path, and then perform similarity matching between the trajectory composed of the matching trajectory points and the non-ambiguous path.

[0102] Optionally, if the device has predetermined candidate matching trajectories for each trajectory point, then in step S310, the device may determine the trajectory points that match the non-ambiguous path based on the historical road matching records. Further optionally, in order to reduce the uncertainty of the matching result, before the trajectory formed by the matching trajectory points is matched with the non-ambiguous path for similarity matching, the device may also expand the matching trajectory points and pre-process the expanded matching trajectory points. Among them, the expansion of the current matching trajectory points may be implemented by the device based on the time information and / or location information of the current matching trajectory points. Pre-processing the expanded matching trajectory points may specifically refer to removing low-quality and obviously erroneous matching trajectory points based on information such as the speed, direction, time and location of each matching trajectory point.

[0103] Step S320: In response to detecting that the similarity between any of the non-ambiguous paths and the trajectory formed by the corresponding matching trajectory points satisfies a preset similarity threshold, determining that the non-ambiguous path matches the trajectory to be matched.

[0104] Specifically, after determining the similarity between each non-ambiguous path and the corresponding matching trajectory point, if it is detected that the similarity between any non-ambiguous path and the corresponding matching trajectory point meets a preset similarity threshold, the device can determine that the non-ambiguous path matches the trajectory to be matched. Optionally, similarity matching can be implemented by the device based on traditional distance metrics or based on deep representation metrics, which is not limited in this application.

[0105] The embodiment of the present invention will determine at least one non-ambiguous path of the candidate matching road when it is detected that the candidate matching road of the current trajectory point has a corresponding target parallel road, and then determine the candidate matching road as the target matching road of the current trajectory point when it is detected that there is any non-ambiguous path matching the trajectory to be matched. Among them, the current trajectory point is a trajectory point in the trajectory to be matched, and the non-ambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road, and is not parallel to the target parallel road. Therefore, by determining the non-ambiguous path of the candidate matching road and performing auxiliary verification on the accuracy of the candidate matching road based on the non-ambiguous path, the embodiment of the present invention can avoid the influence of complex road network scenes on the road matching results, thereby improving the accuracy of the matching road determined for the trajectory point.

[0106] Fig.12 FIG. 1 is a schematic diagram of a road matching device according to an embodiment of the present invention. Fig.12 As shown, the road matching device of the embodiment of the present invention includes a road matching unit 121 , a non-ambiguous path determining unit 122 and a matching road determining unit 123 .

[0107] Specifically, the road matching unit 121 is used to determine a candidate matching road for a current trajectory point, where the current trajectory point is a trajectory point in a trajectory to be matched;

[0108] The unambiguous path determination unit 122 is used to determine at least one unambiguous path of the candidate matching road in response to detecting that the candidate matching road has a corresponding target parallel road, wherein the unambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road and is not parallel to the target parallel road;

[0109] The matching road determining unit 123 is configured to determine the candidate matching road as the target matching road of the current trajectory point in response to the existence of any of the non-ambiguous paths matching the to-be-matched trajectory.

[0110] The embodiment of the present invention will determine at least one non-ambiguous path of the candidate matching road when it is detected that the candidate matching road of the current trajectory point has a corresponding target parallel road, and then determine the candidate matching road as the target matching road of the current trajectory point when it is detected that there is any non-ambiguous path matching the trajectory to be matched. Among them, the current trajectory point is a trajectory point in the trajectory to be matched, and the non-ambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road, and is not parallel to the target parallel road. Therefore, by determining the non-ambiguous path of the candidate matching road and performing auxiliary verification on the accuracy of the candidate matching road based on the non-ambiguous path, the embodiment of the present invention can avoid the influence of complex road network scenes on the road matching results, thereby improving the accuracy of the matching road determined for the trajectory point.

[0111] Fig.13 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig.13 As shown, Fig.13The electronic device shown can be specifically the road matching device in the above embodiment, which can include a general computer hardware structure, which at least includes a processor 131 and a memory 132. The processor 131 and the memory 132 are connected via a bus 133. The memory 132 is suitable for storing instructions or programs executable by the processor 131. The processor 131 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 131 executes the instructions stored in the memory 132, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 133 connects the above multiple components together, and at the same time connects the above components to the display controller 134 and the display device and the input / output (I / O) device 135. The input / output (I / O) device 135 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 135 is connected to the system through an input / output (I / O) controller 136.

[0112] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] The present application is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0114] These computer program instructions may 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 including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0115] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0116] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0117] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A road matching method, It is characterized in that The method comprises: Determine a candidate matching road for a current trajectory point, wherein the current trajectory point is a trajectory point in a trajectory to be matched; In response to detecting that the candidate matching road has a corresponding target parallel road, determining at least one non-ambiguous path of the candidate matching road, the non-ambiguous path being a path that is only connected to the candidate matching road but not connected to the target parallel road and is not parallel to the target parallel road; In response to detecting that any of the non-ambiguous paths matches the to-be-matched trajectory, the candidate matching road is determined as a target matching road for the current trajectory point.

2. The method according to claim 1, It is characterized in that The method further comprises: Determining candidate parallel roads of the candidate matching road; splicing the candidate parallel roads into at least one candidate parallel path according to the connectivity relationship between the candidate parallel roads, wherein the candidate parallel path includes candidate parallel roads that are sequentially connected; A target parallel road of the candidate matching road is determined according to each of the candidate parallel paths.

3. The method according to claim 2, It is characterized in that The determining of the candidate parallel roads of the candidate matching roads comprises: Segmenting the candidate matching road according to the turning angle and the curvature of the candidate matching road to obtain a plurality of sub-roads; The candidate parallel roads are determined according to the sub-roads.

4. The method according to claim 3, It is characterized in that Determining the candidate parallel roads according to each of the sub-roads comprises: For each of the sub-roads, constructing a first rectangular buffer zone according to a connection line between a road start point and a road end point of the sub-road; For each map road covered by the first rectangular buffer zone, determining an angle deviation between the map road and the candidate matching road; The map roads whose angle deviation is less than or equal to a preset angle threshold are determined as the candidate parallel roads.

5. The method according to claim 4, It is characterized in that Determining the angle deviation between the map road and the candidate matching road includes: Determining the turning angle of the map road at each road node; Determining the turning angle of the candidate matching road at each road node; An angular deviation between the map road and the candidate matching road is determined according to a steering angle of the map road at each road node and a steering angle of the candidate matching road at each road node.

6. The method according to claim 2, It is characterized in that The step of determining the target parallel road of the candidate matching road according to each of the candidate parallel paths comprises: Constructing a second rectangular buffer according to the connection line between the path starting point and the path ending point of the candidate parallel path; For each of the candidate parallel paths, in response to the coverage of the candidate matching road by the second rectangular buffer zone constructed based on the candidate parallel paths satisfying a preset coverage threshold, each candidate parallel road in the candidate parallel paths is determined as a target parallel road of the candidate matching road.

7. The method according to claim 6, It is characterized in that The method further comprises: In response to not detecting a candidate parallel road of the candidate matching road, determining that the candidate matching road does not have a corresponding target parallel road; and / or In response to detecting that the coverage of the candidate matching road by the second rectangular buffer zone constructed based on each of the candidate matching paths does not meet the preset coverage threshold, it is determined that the candidate matching road does not have a corresponding target parallel road.

8. The method according to claim 7, It is characterized in that The method further comprises: In response to detecting that the candidate matching road does not have a corresponding target parallel road, the candidate matching road is determined as the target matching road of the current trajectory point.

9. The method according to claim 1, It is characterized in that The matching of each of the non-ambiguous paths with the to-be-matched trajectory comprises: For each of the non-ambiguous paths, determining the similarity between the non-ambiguous path and a trajectory formed by corresponding matching trajectory points, wherein the matching trajectory points are trajectory points in the trajectory to be matched that match the non-ambiguous path; In response to detecting that the similarity between any of the non-ambiguous paths and a trajectory formed by corresponding matching trajectory points satisfies a preset similarity threshold, it is determined that the non-ambiguous path matches the trajectory to be matched.

10. The method according to claim 1, It is characterized in that The determining of at least one non-ambiguous path of the candidate matching road comprises: Traversing the preceding and succeeding roads of the candidate matching road, determining the preceding and succeeding roads whose road distances to the candidate matching road are less than a preset distance threshold and which are not parallel to and connected with the target parallel road as non-ambiguous roads, wherein the preceding and succeeding roads are directly connected to or intermittently connected with the candidate matching road; For each of the non-ambiguous roads, the non-ambiguous road and a connecting road between the non-ambiguous road and the candidate matching road are determined as the non-ambiguous path.

11. The method according to claim 1, It is characterized in that Determining the candidate matching roads for the current trajectory point includes: The current trajectory point is matched in a city map to determine a candidate matching road for the current trajectory point.

12. A road matching device, It is characterized in that The device comprises: A road matching unit, used to determine a candidate matching road for a current trajectory point, wherein the current trajectory point is a trajectory point in a trajectory to be matched; a non-ambiguous path determination unit, configured to determine, in response to detecting that the candidate matching road has a corresponding target parallel road, at least one non-ambiguous path of the candidate matching road, wherein the non-ambiguous path is a path that is only connected to the candidate matching road but not connected to the target parallel road and is not parallel to the target parallel road; The matching road determining unit is configured to determine the candidate matching road as a target matching road of the current trajectory point in response to detecting that any of the non-ambiguous paths matches the trajectory to be matched.

13. A computer readable storage medium having computer program instructions stored thereon, It is characterized in that The computer program instructions implement the method according to any one of claims 1 to 11 when executed by a processor.

14. An electronic device, It is characterized in that The device comprises: a memory for storing one or more computer program instructions; A processor, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 11.

15. A computer program product, It is characterized in that When the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 11.

Citation Information

Cited By

  • Vehicle route matching method and device, processor and vehicle

    CN119984318A