Map data cluster clustering method and device, equipment and storage medium

通过聚类处理和合并地图数据簇,利用时间戳差值和重合面积,解决了众包地图数据精度低的问题,提高了地图数据的准确性和精度。

CN119066455APending Publication Date: 2024-12-03CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310628417.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

In the prior art, there are problems such as inaccurate collection of crowdsourcing map data and incorrectly identifying map objects, resulting in low accuracy of crowdsourcing maps.

Method used

By obtaining multiple target map data clusters and clustering according to the timestamp difference value, interference value and overlapping area, similar data clusters are merged to improve data accuracy and ensure the accuracy and accuracy of clustering results.

Benefits of technology

It effectively reduces the occurrence of duplicate objects in map data clusters, avoids interference in clustering results, and improves the accuracy and accuracy of crowdsourcing maps.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066455A_ABST
    Figure CN119066455A_ABST
Patent Text Reader

Abstract

The invention relates to a map data cluster clustering method and device, equipment and a storage medium, and relates to the technical field of intelligent transportation. The method comprises the following steps: acquiring a plurality of target map data clusters; each target map data cluster comprises a map data cluster obtained by clustering a map object set; the target map data cluster comprises a first map object and a second map object; determining a first map data cluster and a second map data cluster from the plurality of target map data clusters; an interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is smaller than a first interference threshold value; determining a first overlapping area; and if the first overlapping area is greater than a preset first area threshold, merging the first map data cluster and the second map data cluster to obtain a third map data cluster, and determining the third map data cluster as a map data cluster in a clustering result of the map object set.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a map data clustering method, device, equipment and storage medium. Background Art

[0002] Nowadays, in order to produce high-precision maps for autonomous driving, crowdsourcing mapping is used to obtain data on map objects such as arrows, zebra crossings and boundaries in the lanes captured by sensors on the vehicles while the vehicles are driving. The large amount of data obtained is then clustered to determine accurate crowdsourced map data from the large amount of data.

[0003] However, in the related art, due to the problems of inaccuracy in the collected data and errors in the recognition of map objects, the crowdsourcing map obtained by clustering the collected data in the related art has a technical problem of low precision. Summary of the invention

[0004] The present application provides a map data clustering method, device, equipment and storage medium to at least solve the technical problem of low accuracy of crowdsourced maps in related technologies. The technical solution of the present application is as follows:

[0005] According to a first aspect of the present application, a map data cluster clustering method is provided, comprising: obtaining a plurality of target map data clusters; each target map data cluster comprises a map data cluster obtained by clustering a map object set; the target map data cluster comprises a first map object and a second map object; a difference between timestamps of the first map object and the second map object is greater than a first time threshold; determining a first map data cluster and a second map data cluster from the plurality of target map data clusters; an interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold; determining a first overlapping area; the first overlapping area is an overlapping area between the first map data cluster and the second map data cluster; if the first overlapping area is greater than a preset first area threshold, merging the first map data cluster and the second map data cluster to obtain a third map data cluster, and determining the third map data cluster as a map data cluster in the clustering result of the map object set.

[0006] According to the above technical means, the present application can obtain multiple target map data clusters, and determine the first map data cluster and the second map data cluster from the multiple target map data clusters; and determine the first overlap area of ​​the first map data cluster and the second map data cluster. Further, if the first overlap area is greater than the preset first area threshold, the first map data cluster and the second map data cluster are merged to obtain a third map data cluster, and the third map data cluster is determined as the map data cluster in the clustering result of the map object set. In this way, since the map objects in the clustered map data clusters will be repeated when the vehicle turns back, the target map data cluster is determined from the map data clusters obtained by clustering the map object set according to the predetermined first time threshold, which can minimize the occurrence of repeated map objects in the target map data cluster and improve the accuracy of the target map data cluster. By pre-judging the map type in the two target map data clusters before merging, interference between different map objects in the map data clusters in the clustering result can be avoided, and inaccurate clustering results can be avoided. And, when the overlapping area of ​​the first map data cluster and the second map data cluster is greater than a preset first area threshold, the first map data cluster and the second map data cluster are merged. By merging some of the map data clusters obtained by clustering, the accuracy of the crowdsourced map can be improved.

[0007] In a possible implementation, the method further includes: each target map data cluster does not contain a map object of a target map object type; the target map object type includes an aerial sign, a traffic light, a text sign, and a speed reduction marking.

[0008] According to the above technical means, the present application can obtain multiple target map data clusters, and determine the first map data cluster and the second map data cluster from the multiple target map data clusters; and determine the first overlapping area of ​​the first map data cluster and the second map data cluster. Further, if the first overlapping area is greater than the preset first area threshold, the first map data cluster and the second map data cluster are merged to obtain a third map data cluster, and the third map data cluster is determined as a map data cluster in the clustering result of the map object set. In this way, since there is no map object of the target map object type in each target map data cluster, a method of pre-eliminating the target map object type from multiple target map data clusters is implemented, which can improve the accuracy of the crowdsourced map.

[0009] In a possible implementation, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, wherein the merging to obtain the target map data cluster includes: clustering the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; determining a fifth map data cluster and a sixth map data cluster from the plurality of fourth map data clusters; a first condition satisfied by the fifth map data cluster and the sixth map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, an angle between the two map data clusters is less than a preset first angle threshold, a distance between the two map data clusters is less than a preset first distance threshold, and among all time stamps composed of time stamps of map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold; and merging the fifth map data cluster and the sixth map data cluster to obtain the target map data cluster.

[0010] According to the above technical means, the present application can obtain multiple fourth map data clusters by clustering the first map object set; and determine the fifth map data cluster and the sixth map data cluster from the multiple fourth map data clusters. Further, the fifth map data cluster and the sixth map data cluster are merged to obtain the target map data cluster. In this way, if the average elevation difference between the two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is less than the preset first angle threshold and the distance between the two map data clusters is less than the preset first distance threshold, the two map data clusters are merged, which can realize the merging of multiple map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0011] In a possible implementation, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, wherein the merging to obtain the target map data cluster includes: clustering the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; determining a seventh map data cluster and an eighth map data cluster from the plurality of fourth map data clusters; the second condition satisfied by the seventh map data cluster and the eighth map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is greater than a preset first angle threshold or the distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, the second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, and among all timestamps composed of the timestamps of the map objects of the two map data clusters, there are two timestamps with a difference greater than the first time threshold; and merging the seventh map data cluster and the eighth map data cluster to obtain the target map data cluster.

[0012] According to the above technical means, the present application can obtain multiple fourth map data clusters by clustering the first map object set; determine the seventh map data cluster and the eighth map data cluster from the multiple fourth map data clusters; and merge the seventh map data cluster and the eighth map data cluster to obtain the target map data cluster. In this way, if the average elevation difference between two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is greater than the preset first angle threshold or the distance between the two map data clusters is greater than the preset first distance threshold, if the elevations of the two map data clusters intersect and the second overlapping area of ​​the two map data clusters is greater than the preset second area threshold, the two map data clusters are merged, and it is also possible to merge multiple map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0013] In a possible implementation, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, wherein the merging to obtain the target map data cluster includes: clustering the second map object set to obtain a plurality of ninth map data clusters; the map objects in the second map object set include zebra crossings; determining a tenth map data cluster and an eleventh map data cluster from the plurality of ninth map data clusters; the third condition satisfied by the tenth map data cluster and the eleventh map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the distance between the two map data clusters is less than a preset second distance threshold, the angle difference between the two map data clusters is less than a preset second angle threshold, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold; and merging the tenth map data cluster and the eleventh map data cluster to obtain the target map data cluster.

[0014] According to the above technical means, the present application can obtain multiple ninth map data clusters by clustering the second map object set; determine the tenth map data cluster and the eleventh map data cluster from the multiple ninth map data clusters; and merge the tenth map data cluster and the eleventh map data cluster to obtain the target map data cluster. In this way, if the average elevation difference between the two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the average elevation difference between the two map data clusters is within the preset range, if the distance between the two map data clusters is less than the preset second distance threshold and the angle difference between the two map data clusters is less than the preset second angle threshold, the two map data clusters are merged, which can achieve the merging of some map data clusters in the multiple map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0015] In a possible implementation manner, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, wherein the merging to obtain the target map data cluster includes: clustering the third map object set to obtain a plurality of twelfth map data clusters; the map objects in the third map object set include boundaries; determining a thirteenth map data cluster and a fourteenth map data cluster from the plurality of twelfth map data clusters; the thirteenth map data cluster and the fourteenth map data cluster satisfying a fourth condition including: the two map data clusters are on the same side of the vehicle driving track, the elevations of the two map data clusters have an intersection, the third overlapping area of ​​the two map data clusters is greater than a preset third overlapping area, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than a first time threshold; and merging the thirteenth map data cluster and the fourteenth map data cluster to obtain the target map data cluster.

[0016] According to the above technical means, the present application can obtain multiple twelfth map data clusters by clustering the third map object set; determine the thirteenth map data cluster and the fourteenth map data cluster from the multiple twelfth map data clusters; and merge the thirteenth map data cluster and the fourteenth map data cluster to obtain the target map data cluster. In this way, since only two map data clusters are on different sides of the lane, the map objects in the two map data clusters are different lane lines. Therefore, when the two map data clusters are on the same side of the vehicle's driving trajectory, the elevations of the two map data clusters intersect, and the third overlap area of ​​the two map data clusters is greater than the preset third overlap area, the two map data clusters are merged, which can achieve the merging of multiple map data clusters obtained by the initial clustering of the acquired boundary map objects, thereby improving the accuracy of clustering.

[0017] According to a second aspect provided by the present application, a map data cluster clustering device is provided, comprising an acquisition unit, a determination unit and a processing unit; the acquisition unit is used to acquire a plurality of target map data clusters; each target map data cluster comprises a map data cluster obtained by clustering a map object set; the target map data cluster comprises a first map object and a second map object; the difference between the timestamps of the first map object and the second map object is greater than a first time threshold; the determination unit is used to determine the first map data cluster and the second map data cluster from the plurality of target map data clusters; the interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold; the determination unit is used to determine a first overlapping area; the first overlapping area is the overlapping area of ​​the first map data cluster and the second map data cluster; the processing unit is used to merge the first map data cluster and the second map data cluster to obtain a third map data cluster if the first overlapping area is greater than a preset first area threshold; the determination unit is also used to determine the third map data cluster as a map data cluster in the clustering result of the map object set.

[0018] In a possible implementation manner, there is no map object of the target map object type in each of the target map data clusters; the target map object types include aerial signs, traffic lights, text signs, and speed reduction markings.

[0019] In a possible implementation manner, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, and the merging to obtain the target map data cluster includes: a processing unit further configured to perform clustering on the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; a determining unit further configured to determine a fifth map data cluster and a sixth map data cluster from the plurality of fourth map data clusters; a first condition satisfied by the fifth map data cluster and the sixth map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, an angle between the two map data clusters is less than a preset first angle threshold, a distance between the two map data clusters is less than a preset first distance threshold, and among all time stamps composed of time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold; and the processing unit further configured to merge the fifth map data cluster and the sixth map data cluster to obtain the target map data cluster.

[0020] In a possible implementation manner, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: a processing unit further configured to perform clustering on the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; a determining unit further configured to determine a seventh map data cluster and an eighth map data cluster from the plurality of fourth map data clusters; the second condition satisfied by the seventh map data cluster and the eighth map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is greater than a preset first angle threshold or the distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, the second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold; and the processing unit further configured to merge the seventh map data cluster and the eighth map data cluster to obtain the target map data cluster.

[0021] In a possible implementation manner, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, and the merging to obtain the target map data cluster includes: a processing unit further configured to perform clustering on the second map object set to obtain a plurality of ninth map data clusters; the map objects in the second map object set include zebra crossings; a determining unit further configured to determine a tenth map data cluster and an eleventh map data cluster from the plurality of ninth map data clusters; a third condition satisfied by the tenth map data cluster and the eleventh map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, a distance between the two map data clusters is less than a preset second distance threshold, an angle difference between the two map data clusters is less than a preset second angle threshold, and among all time stamps composed of time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than a first time threshold; and the processing unit further configured to merge the tenth map data cluster and the eleventh map data cluster to obtain the target map data cluster.

[0022] In a possible implementation manner, the plurality of target map data clusters further include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: a processing unit further configured to perform clustering on the third map object set to obtain a plurality of twelfth map data clusters; the map objects in the third map object set include boundaries; a determining unit further configured to determine a thirteenth map data cluster and a fourteenth map data cluster from the plurality of twelfth map data clusters; a fourth condition satisfied by the thirteenth map data cluster and the fourteenth map data cluster includes: the two map data clusters are on the same side of the vehicle driving track, the elevations of the two map data clusters have an intersection, the third overlapping area of ​​the two map data clusters is greater than a preset third overlapping area, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than a first time threshold; and the processing unit further configured to merge the thirteenth map data cluster and the fourteenth map data cluster to obtain the target map data cluster.

[0023] According to the third aspect provided by the present application, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0024] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0025] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0026] It should be noted that the technical effects brought about by any implementation method in the second to fifth aspects can refer to the technical effects brought about by the corresponding implementation method in the first aspect, and will not be repeated here.

[0027] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application.

[0028] Therefore, the above technical features of the present application have the following beneficial effects:

[0029] (1) Acquire multiple target map data clusters, and determine a first map data cluster and a second map data cluster from the multiple target map data clusters; and determine a first overlap area between the first map data cluster and the second map data cluster. Further, if the first overlap area is greater than a preset first area threshold, merge the first map data cluster and the second map data cluster to obtain a third map data cluster, and determine the third map data cluster as a map data cluster in the clustering result of the map object set. In this way, since map objects in the clustered map data clusters may be repeated when the vehicle turns back, the target map data cluster is determined from the map data clusters obtained by clustering the map object set according to the predetermined first time threshold, so that repeated map objects in the target map data cluster can be minimized and the accuracy of the target map data cluster can be improved. By pre-judging the map types in the two target map data clusters before merging, interference between different map objects in the map data clusters in the clustering result can be avoided, and inaccurate clustering results can be avoided. And, if the overlap area between the first map data cluster and the second map data cluster is greater than the preset first area threshold, merge the first map data cluster and the second map data cluster. By merging some of the map data clusters obtained through clustering, the accuracy of crowdsourced maps can be improved.

[0030] (2) Acquire multiple target map data clusters, and determine a first map data cluster and a second map data cluster from the multiple target map data clusters; and determine a first overlapping area of ​​the first map data cluster and the second map data cluster. Further, if the first overlapping area is greater than a preset first area threshold, merge the first map data cluster and the second map data cluster to obtain a third map data cluster, and determine the third map data cluster as a map data cluster in the clustering result of the map object set. In this way, since there is no map object of the target map object type in each target map data cluster, a method for pre-eliminating the target map object type from multiple target map data clusters is implemented, which can improve the accuracy of the crowdsourced map.

[0031] (3) A plurality of fourth map data clusters are obtained by clustering the first map object set; and a fifth map data cluster and a sixth map data cluster are determined from the plurality of fourth map data clusters. Further, the fifth map data cluster and the sixth map data cluster are merged to obtain a target map data cluster. In this way, if the average elevation difference between two map data clusters is outside a preset range, it indicates that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is less than a preset first angle threshold and the distance between the two map data clusters is less than a preset first distance threshold, the two map data clusters are merged, so that the multiple map data clusters obtained by the initial clustering of the acquired arrow map objects can be merged, thereby improving the accuracy of clustering.

[0032] (4) A plurality of fourth map data clusters are obtained by clustering the first map object set; a seventh map data cluster and an eighth map data cluster are determined from the plurality of fourth map data clusters; and the seventh map data cluster and the eighth map data cluster are merged to obtain a target map data cluster. In this way, if the average elevation difference between two map data clusters is outside a preset range, it indicates that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is greater than a preset first angle threshold or the distance between the two map data clusters is greater than a preset first distance threshold, if the elevations of the two map data clusters intersect and the second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, the two map data clusters are merged, and it is also possible to merge the plurality of map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0033] (5) A plurality of ninth map data clusters are obtained by clustering the second map object set; a tenth map data cluster and an eleventh map data cluster are determined from the plurality of ninth map data clusters; and the tenth map data cluster and the eleventh map data cluster are merged to obtain a target map data cluster. In this way, if the average elevation difference between two map data clusters is outside a preset range, it indicates that the two map data clusters are map data clusters of two different lanes; when the average elevation difference between the two map data clusters is within the preset range, if the distance between the two map data clusters is less than a preset second distance threshold and the angle difference between the two map data clusters is less than a preset second angle threshold, the two map data clusters are merged, so that some of the map data clusters among the plurality of map data clusters obtained by the initial clustering of the acquired arrow map objects can be merged, thereby improving the accuracy of clustering.

[0034] (6) A plurality of twelfth map data clusters are obtained by clustering the third map object set; a thirteenth map data cluster and a fourteenth map data cluster are determined from the plurality of twelfth map data clusters; and the thirteenth map data cluster and the fourteenth map data cluster are merged to obtain a target map data cluster. In this way, since only when two map data clusters are on different sides of a lane, the map objects in the two map data clusters are different lane lines, when the two map data clusters are on the same side of the vehicle driving trajectory, the elevations of the two map data clusters intersect, and the third overlap area of ​​the two map data clusters is greater than a preset third overlap area, the two map data clusters are merged, so that the plurality of map data clusters obtained by the initial clustering of the acquired boundary map objects can be merged, thereby improving the accuracy of clustering. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application, and do not constitute an improper limitation on the present application.

[0036] Figure 1 is a flow chart of a map data clustering method according to an exemplary embodiment;

[0037] Figure 2 is a flow chart showing a method for merging to obtain a target map data cluster according to an exemplary embodiment;

[0038] Figure 3 is a flowchart showing another method for merging to obtain a target map data cluster according to an exemplary embodiment;

[0039] Figure 4 is a flowchart showing another method for merging to obtain a target map data cluster according to an exemplary embodiment;

[0040] Figure 5 is a flowchart showing another method for merging to obtain a target map data cluster according to an exemplary embodiment;

[0041] Figure 6 is a flow chart of an arrow data clustering method according to an exemplary embodiment;

[0042] Figure 7 is a flow chart of a zebra crossing clustering method according to an exemplary embodiment;

[0043] Figure 8 is a flow chart of a boundary clustering method according to an exemplary embodiment;

[0044] Fig. 9 is a block diagram of a map data clustering device according to an exemplary embodiment;

[0045] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0046] In order to enable ordinary persons in the art to better understand the technical solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0047] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0048] For ease of understanding, the map data clustering method provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0049] Figure 1 is a flow chart of a map data clustering method according to an exemplary embodiment. Figure 1 As shown, the map data clustering method includes the following steps:

[0050] S101: The electronic device obtains a plurality of target map data clusters.

[0051] Each target map data cluster includes a map data cluster obtained by clustering a map object set; the target map data cluster includes a first map object and a second map object; and a difference between timestamps of the first map object and the second map object is greater than a first time threshold.

[0052] As a possible implementation manner, the electronic device performs density-based spatial clustering of applications with noise (DBSCAN) processing on the map object set to obtain multiple map data clusters.

[0053] The electronic device calculates the difference between any two time stamps in each map data cluster to obtain a plurality of difference values.

[0054] If any one of the multiple differences is greater than the first time threshold, the electronic device determines the map data cluster as a target map data cluster.

[0055] Furthermore, the electronic device obtains multiple target map data clusters.

[0056] It should be noted that there is no map object type in the target map data cluster that is the target map object type; the target map object type includes air signs, traffic lights, text signs and speed reduction markings.

[0057] Exemplarily, the first time threshold is 0.5 hours. If the multiple differences calculated from any two timestamps in the map data cluster are 0.3 hours, 0.4 hours, 0.5 hours and 0.7 hours, and there is a difference greater than the first time threshold, the electronic device determines the map data cluster as a target map data cluster; if the multiple differences calculated from any two timestamps in the map data cluster are 0.3 hours, 0.4 hours, 0.2 hours and 0.1 hours, and there is no difference greater than the first time threshold, the electronic device determines the map data cluster as a non-target map data cluster.

[0058] As another possible implementation manner, the electronic device performs density-based clustering DBSCAN processing on the map object set to obtain multiple map data clusters.

[0059] The electronic device calculates the difference between any two time stamps in each map data cluster to obtain a plurality of difference values.

[0060] The electronic device determines a difference value having the largest value from among the plurality of difference values.

[0061] If the largest difference among the multiple differences is greater than the first time threshold, the electronic device determines the map data cluster as the target map data cluster.

[0062] Furthermore, the electronic device obtains multiple target map data clusters.

[0063] Exemplarily, the first time threshold is 0.5 hours. If the maximum difference among multiple differences calculated from any two timestamps in the map data cluster is 0.6 hours, the electronic device determines the map data cluster as a target map data cluster; if the maximum difference among multiple differences calculated from any two timestamps in the map data cluster is 0.4 hours, the electronic device determines the map data cluster as a non-target map data cluster.

[0064] S102: The electronic device determines a first map data cluster and a second map data cluster from a plurality of target map data clusters.

[0065] The interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold.

[0066] As a possible implementation manner, the electronic device queries the type of each map object in any two map data clusters among the multiple target map data clusters to obtain all types of all map objects in each map data cluster.

[0067] The electronic device determines whether an interference value between any map object type in one map data cluster and any map object type in another map data cluster is greater than a first interference threshold according to a plurality of preset map object correspondences between different map objects greater than a first interference threshold.

[0068] If any map object type in one of the map data clusters is in a plurality of map object correspondences with any map object type in another map data cluster, the electronic device determines that an interference value between any map object type in one of the map data clusters and any map object type in another map data cluster is greater than a first interference threshold, and does not determine the two map data clusters as the first map data cluster and the second map data cluster.

[0069] If any map object type in one of the map data clusters is not in a plurality of map object correspondences with any map object type in another map data cluster, the electronic device determines that an interference value between any map object type in one of the map data clusters and any map object type in another map data cluster is less than a first interference threshold, and determines the two map data clusters as a first map data cluster and a second map data cluster.

[0070] It should be noted that the interference value between two map objects in the multiple map object correspondences is greater than the first interference threshold, and the two map objects are mutually exclusive.

[0071] Exemplarily, the correspondence between multiple map objects includes: the map object type of warning area corresponds to the map object type of thin dashed line segment, thick dashed line segment, single dashed line, single solid line, double dashed line, double solid line, left solid right dashed line, right solid left dashed line; the map object type of speed bump corresponds to the map object type of thin dashed line segment, thick dashed line segment, single dashed line, single solid line, double dashed line, double solid line, left solid right dashed line, right solid left dashed line; the map object type of guide line corresponds to the map object type of thin dashed line segment, thick dashed line segment, single dashed line, single solid line, double dashed line, double solid line, left solid right dashed line, right solid left dashed line, stop line, stop and yield line, and slow down and yield line; the map object type of zebra crossing corresponds to the map object type of stop line, stop and yield line, slow down and yield line, guide line, arrow, thin dashed line segment, thick dashed line segment, single dashed line, single solid line, double dashed line, double solid line, left solid right dashed line, right solid left dashed line, and zebra crossing.

[0072] S103: The electronic device determines a first overlapping area.

[0073] The first overlapping area is the overlapping area between the first map data cluster and the second map data cluster.

[0074] As a possible implementation manner, the electronic device obtains the geometric polygon object of the first map data cluster and the polygon object of the second map data cluster to calculate the overlapping area of ​​the first map data cluster and the second map data cluster.

[0075] S104: The electronic device determines whether the first overlapping area is greater than a first area threshold.

[0076] Exemplarily, the first area threshold is 0.5. If the first overlapping area is 0.6, the electronic device determines that the first overlapping area is greater than the first area threshold; if the first overlapping area is 0.4, the electronic device determines that the first overlapping area is less than the first area threshold.

[0077] S105: If the first overlapping area is greater than a preset first area threshold, the electronic device merges the first map data cluster and the second map data cluster to obtain a third map data cluster.

[0078] The third map data cluster includes a plurality of map data clusters obtained by merging map objects in the first map data cluster and map objects in the second map data cluster.

[0079] S106: The electronic device determines the third map data cluster as a map data cluster in the clustering result of the map object set.

[0080] It can be understood that the technical solution provided by the embodiment of the present application obtains multiple target map data clusters, and determines the first map data cluster and the second map data cluster from the multiple target map data clusters; and determines the first overlap area of ​​the first map data cluster and the second map data cluster. Further, if the first overlap area is greater than the preset first area threshold, the first map data cluster and the second map data cluster are merged to obtain a third map data cluster, and the third map data cluster is determined as the map data cluster in the clustering result of the map object set. In this way, since the map objects in the clustered map data clusters will be repeated when the vehicle turns back, the target map data cluster is determined from the map data clusters obtained by clustering the map object set according to the predetermined first time threshold, which can minimize the occurrence of repeated map objects in the target map data cluster and improve the accuracy of the target map data cluster. By pre-judging the map types in the two target map data clusters before merging, interference between different map objects in the map data clusters in the clustering result can be avoided, and inaccurate clustering results can be avoided. And, when the overlapping area of ​​the first map data cluster and the second map data cluster is greater than a preset first area threshold, the first map data cluster and the second map data cluster are merged. By merging some of the map data clusters obtained by clustering, the accuracy of the crowdsourced map can be improved.

[0081] In some embodiments, in order to obtain a target map data cluster, such as Figure 2 As shown, the multiple target map data clusters also include a map data cluster obtained by merging the map data clusters obtained by clustering processing, and merging to obtain the target map data cluster includes the following steps:

[0082] S201: The electronic device performs clustering processing on a first map object set to obtain a plurality of fourth map data clusters.

[0083] The map objects in the first map object set include arrows.

[0084] As a possible implementation manner, the electronic device performs DBSCAN clustering processing on the first map object set to obtain a plurality of fourth map data clusters.

[0085] S202: The electronic device determines a fifth map data cluster and a sixth map data cluster from a plurality of fourth map data clusters.

[0086] Among them, the first condition satisfied by the fifth map data cluster and the sixth map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is less than a preset first angle threshold, the distance between the two map data clusters is less than a preset first distance threshold, and among all timestamps composed of the timestamps of the map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold.

[0087] As a possible implementation manner, the electronic device obtains the polygon of each fourth map data cluster; obtains the elevation of each map object in each fourth map data cluster, and obtains the elevations of all map objects in each fourth map data cluster.

[0088] The electronic device determines the maximum elevation and the minimum elevation from the elevations of all map objects in each fourth map data cluster according to the elevations of all map objects in each fourth map data cluster, and calculates the average elevation of each fourth map data cluster. Further, the electronic device calculates a plurality of average elevations corresponding to each fourth map data cluster.

[0089] The electronic device calculates the average elevation difference between two fourth map data clusters according to the average elevations of two map data clusters among the plurality of fourth map data clusters.

[0090] The electronic device determines whether the average elevation difference between the two map data clusters is within a preset range.

[0091] If the average elevation difference between the two map data clusters is within a preset range, the electronic device calculates the angle between the two map data clusters, and determines the coordinate information of the map objects closest to each other in the two map data clusters, and calculates the minimum distance between the two fourth map data clusters based on the coordinate information of the two map objects and the Euclidean distance calculation formula.

[0092] The electronic device determines whether the angle between the two map data clusters is less than a preset first angle threshold.

[0093] The electronic device determines whether the minimum distance between two map data clusters is less than a preset first distance threshold.

[0094] If the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is less than a preset first angle threshold, and the minimum distance between the two map data clusters is less than a preset first distance threshold, the electronic device determines the above two map data clusters as the fifth map data cluster and the sixth map data cluster, respectively.

[0095] It should be noted that if the two map data clusters do not satisfy at least one of the following conditions: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is less than a preset first angle threshold, and the minimum distance between the two map data clusters is less than a preset first distance threshold, then the electronic device will not determine the above two map data clusters as the fifth map data cluster and the sixth map data cluster, respectively.

[0096] The following specifically describes how the electronic device calculates the angle between two map data clusters:

[0097] The electronic device obtains the coordinates of all map objects in the two map data clusters and the centroid coordinates of the two map data clusters.

[0098] The electronic device calculates a first distance between a first map object and a second map object in a map data cluster, and calculates a second distance between the second map object and a third map object.

[0099] When the first distance is greater than the second distance, the electronic device determines that the line between the first map object and the second map object is the longest side in the map data cluster, and determines the first distance as the length of the longest side in the map data cluster.

[0100] When the first distance is less than or equal to the second distance, the electronic device determines the line between the second map object and the third map object as the longest side in the map data cluster, and determines the second distance as the length of the longest side in the map data cluster.

[0101] Further, the electronic device determines the longest side and the length of the longest side of the two map data clusters.

[0102] The electronic device determines the longest side with a longer length from the two longest sides.

[0103] The electronic device calculates and obtains the angle between the longest side of the two map data clusters and the line connecting the two centroid coordinates.

[0104] It should be noted that if the number of map objects in the map data cluster is less than 4, the electronic device determines that the longest side and the shortest side do not exist in the map data cluster, and determines that the length of the longest side and the length of the shortest side are both 1e-12.

[0105] The first distance between the first map object and the second map object is represented by distance1, the second distance between the second map object and the third map object is represented by distance2, the longest side is represented by long_side, the length of the longest side is represented by max_distance, the shortest side is represented by short_side, and the length of the shortest side is represented by min_distance. The electronic device determines that the longest side, the shortest side, the length of the longest side, and the length of the shortest side in a map data cluster satisfy the following formula 1:

[0106]

[0107] When the number of map objects in the map data cluster is greater than 4, the electronic device determines the longest side, the shortest side, the length of the longest side, and the length of the shortest side of the map data cluster, satisfying the following formula 2:

[0108]

[0109]

[0110] S203: The electronic device combines the fifth map data cluster and the sixth map data cluster to obtain a target map data cluster.

[0111] The target map data cluster includes a plurality of map data clusters consisting of map objects in the fifth map data cluster and map objects in the sixth map data cluster.

[0112] It can be understood that the technical solution provided in the embodiment of the present application obtains multiple fourth map data clusters by clustering the first map object set; and determines the fifth map data cluster and the sixth map data cluster from the multiple fourth map data clusters. Further, the fifth map data cluster and the sixth map data cluster are merged to obtain the target map data cluster. In this way, if the average elevation difference between the two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is less than the preset first angle threshold and the distance between the two map data clusters is less than the preset first distance threshold, the two map data clusters are merged, which can realize the merging of multiple map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0113] In some embodiments, in order to obtain a target map data cluster, such as Figure 3 As shown, the multiple target map data clusters also include a map data cluster obtained by merging the map data clusters obtained by clustering processing, and merging to obtain the target map data cluster includes the following steps:

[0114] S301: The electronic device performs clustering processing on a first map object set to obtain a plurality of fourth map data clusters.

[0115] The map objects in the first map object set include arrows.

[0116] As a possible implementation manner, the electronic device performs DBSCAN clustering processing on the first map object set to obtain a plurality of fourth map data clusters.

[0117] S302: The electronic device determines a seventh map data cluster and an eighth map data cluster from a plurality of fourth map data clusters.

[0118] Among them, the second condition satisfied by the seventh map data cluster and the eighth map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is greater than a preset first angle threshold or the distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, the second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, and among all timestamps composed of the timestamps of the map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold; the distance between the two map data clusters is the minimum distance between the two map data clusters.

[0119] As a possible implementation manner, the electronic device calculates and obtains an average elevation difference between two map data clusters in the plurality of fourth map data clusters.

[0120] The electronic device determines whether the average elevation difference between the two map data clusters is within a preset range.

[0121] If the average elevation difference between the two map data clusters is within a preset range, the electronic device calculates the angle between the two map data clusters and the minimum distance between the two map data clusters.

[0122] The electronic device determines whether an angle between two map data clusters is greater than a preset first angle threshold.

[0123] The electronic device determines whether the minimum distance between two map data clusters is greater than a preset first distance threshold.

[0124] If the included angle between the two map data clusters is greater than a preset first angle threshold or the minimum distance between the two map data clusters is greater than a preset first distance threshold, the electronic device determines whether the elevations of the two map data clusters intersect.

[0125] If the elevations of the two map data clusters intersect, the electronic device calculates the overlapping area of ​​the two map data clusters.

[0126] The electronic device determines whether the overlapping area of ​​the two map data clusters is greater than a preset second area threshold.

[0127] If the average elevation difference between the two map data clusters is within a preset range, the included angle between the two map data clusters is greater than a preset first angle threshold, or the minimum distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, and the overlapping area of ​​the two map data clusters is greater than a preset second area threshold, the electronic device determines the above two map data clusters as the seventh map data cluster and the eighth map data cluster, respectively.

[0128] If the two map data clusters do not satisfy at least one of the following conditions: the average elevation difference between the two map data clusters is within a preset range, the included angle between the two map data clusters is greater than a preset first angle threshold, the minimum distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, and the overlapping area of ​​the two map data clusters is greater than a preset second area threshold, the electronic device does not determine the above two map data clusters as the seventh map data cluster and the eighth map data cluster, respectively.

[0129] It should be noted that the electronic device may calculate the average elevation difference between two map data clusters by referring to the implementation method of S202 above, and calculate the minimum distance between two map data clusters and the overlapping area of ​​two map data clusters by referring to the implementation method of S103 above, which will not be repeated here.

[0130] The following specifically describes how the electronic device determines whether the elevations of two map data clusters intersect:

[0131] The electronic device obtains the maximum elevation and the minimum elevation of the two map data clusters respectively, obtains the maximum elevation and the minimum elevation of one of the map data clusters, and obtains the maximum elevation and the minimum elevation of the other map data cluster.

[0132] If the minimum elevation of one of the map data clusters is greater than or equal to the minimum elevation of the other map data cluster, and less than or equal to the maximum elevation of the other map data cluster, the electronic device determines that the elevations of the two map data clusters intersect.

[0133] If the minimum elevation of one of the map data clusters is smaller than the minimum elevation of the other map data cluster, or is larger than the maximum elevation of the other map data cluster, the electronic device determines that there is no intersection between the elevations of the two map data clusters.

[0134] It should be noted that the electronic device determines that the elevations of two map data clusters have an intersection that satisfies the following formula 3:

[0135]

[0136] S303: The electronic device combines the seventh map data cluster and the eighth map data cluster to obtain a target map data cluster.

[0137] The target map data cluster includes a plurality of map data clusters consisting of map objects in the seventh map data cluster and map objects in the eighth map data cluster.

[0138] It can be understood that the technical solution provided in the embodiment of the present application obtains multiple fourth map data clusters by clustering the first map object set; determines the seventh map data cluster and the eighth map data cluster from the multiple fourth map data clusters; and merges the seventh map data cluster and the eighth map data cluster to obtain the target map data cluster. In this way, if the average elevation difference between two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the angle between the two map data clusters is greater than the preset first angle threshold or the distance between the two map data clusters is greater than the preset first distance threshold, if the elevations of the two map data clusters intersect and the second overlapping area of ​​the two map data clusters is greater than the preset second area threshold, the two map data clusters are merged, and it is also possible to merge multiple map data clusters obtained by the initial clustering of the acquired arrow map objects, thereby improving the accuracy of clustering.

[0139] In some embodiments, in order to obtain a target map data cluster, such as Figure 4 As shown, the multiple target map data clusters also include a map data cluster obtained by merging the map data clusters obtained by clustering processing, and merging to obtain the target map data cluster includes the following steps:

[0140] S401: The electronic device performs clustering processing on the second map object set to obtain a plurality of ninth map data clusters.

[0141] The map objects in the second map object set include zebra crossings.

[0142] As a possible implementation manner, the electronic device performs DBSCAN clustering processing on the second map object set to obtain a plurality of ninth map data clusters.

[0143] S402: The electronic device determines a tenth map data cluster and an eleventh map data cluster from a plurality of ninth map data clusters.

[0144] Among them, the third condition satisfied by the tenth map data cluster and the eleventh map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the distance between the two map data clusters is less than a preset second distance threshold, the angle difference between the two map data clusters is less than a preset second angle threshold, and among all timestamps composed of the timestamps of the map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold; the distance between the two map data clusters is the minimum distance between the two map data clusters.

[0145] As a possible implementation manner, the electronic device calculates and obtains an average elevation difference between two map data clusters in the plurality of ninth map data clusters.

[0146] The electronic device determines whether the average elevation difference between the two map data clusters is within a preset range.

[0147] If the average elevation difference between the two map data clusters is within a preset range, the electronic device calculates the minimum distance between the two map data clusters.

[0148] The electronic device determines whether the minimum distance between two map data clusters is greater than a preset second distance threshold.

[0149] If the minimum distance between the two map data clusters is greater than a preset first distance threshold, the electronic device obtains the angle matrices of the two map data clusters respectively to obtain two angle matrices corresponding to the two map data clusters.

[0150] The electronic device calculates the angle difference between the two map data clusters according to the two angle matrices.

[0151] The electronic device determines whether the angle difference between the two map data clusters is less than a preset second angle threshold.

[0152] If the average elevation difference between the two map data clusters is within a preset range, the distance between the two map data clusters is less than a preset second distance threshold, and the angle difference between the two map data clusters is less than a preset second angle threshold, the electronic device determines the above two map data clusters as the tenth map data cluster and the eleventh map data cluster, respectively.

[0153] If the two map data clusters do not satisfy at least one of the following conditions: the average elevation difference between the two map data clusters is within a preset range, the distance between the two map data clusters is less than a preset second distance threshold, and the angle difference between the two map data clusters is less than a preset second angle threshold, the electronic device does not determine the above two map data clusters as the tenth map data cluster and the eleventh map data cluster, respectively.

[0154] It should be noted that the electronic device may calculate the average elevation difference between two map data clusters by referring to the implementation of S202 above, and calculate the minimum distance between two map data clusters by referring to the implementation of S103 above, which will not be described in detail here.

[0155] S403: The electronic device merges the tenth map data cluster and the eleventh map data cluster to obtain a target map data cluster.

[0156] The target map data cluster includes a plurality of map data clusters consisting of map objects in the tenth map data cluster and map objects in the eleventh map data cluster.

[0157] It can be understood that the technical solution provided in the embodiment of the present application obtains a plurality of ninth map data clusters by clustering the second map object set; determines the tenth map data cluster and the eleventh map data cluster from the plurality of ninth map data clusters; and merges the tenth map data cluster and the eleventh map data cluster to obtain a target map data cluster. In this way, if the average elevation difference between the two map data clusters is outside the preset range, it means that the two map data clusters are map data clusters of two different lanes; when the average elevation difference between the two map data clusters is within the preset range, if the distance between the two map data clusters is less than the preset second distance threshold and the angle difference between the two map data clusters is less than the preset second angle threshold, the two map data clusters are merged, so that some of the map data clusters in the plurality of map data clusters obtained by the initial clustering of the acquired arrow map objects can be merged to improve the accuracy of clustering.

[0158] In some embodiments, in order to obtain a target map data cluster, such as Figure 5 As shown, the multiple target map data clusters also include a map data cluster obtained by merging the map data clusters obtained by clustering processing, and merging to obtain the target map data cluster includes the following steps:

[0159] S501: The electronic device performs clustering processing on the third map object set to obtain a plurality of twelfth map data clusters.

[0160] The map objects in the third map object set include boundaries.

[0161] As a possible implementation manner, the electronic device performs DBSCAN clustering processing on the third map object set to obtain a plurality of twelfth map data clusters.

[0162] S502: The electronic device determines a thirteenth map data cluster and a fourteenth map data cluster from a plurality of twelfth map data clusters.

[0163] Among them, the fourth condition satisfied by the thirteenth map data cluster and the fourteenth map data cluster includes: the two map data clusters are on the same side of the vehicle's driving trajectory, the elevations of the two map data clusters intersect, the third overlapping area of ​​the two map data clusters is greater than the preset third overlapping area, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold.

[0164] As a possible implementation manner, the electronic device obtains a direction identification of each twelfth map data cluster in the vehicle driving track.

[0165] The electronic device determines whether two map data clusters among the plurality of twelfth map data clusters are on the same side of the vehicle's driving track according to the direction identifiers of the two map data clusters on the vehicle's driving track.

[0166] If the two map data clusters are on the same side of the vehicle's driving track, the electronic device determines whether the elevations of the two map data clusters intersect.

[0167] If the elevations of the two map data clusters intersect, the electronic device calculates the overlapping area of ​​the two map data clusters.

[0168] The electronic device determines whether an overlapping area of ​​two map data clusters is greater than a preset third overlapping area.

[0169] If the two map data clusters are on the same side of the lane, the elevations of the two map data clusters intersect, and the third overlapping area of ​​the two map data clusters is greater than the preset third overlapping area, the electronic device determines the two map data clusters as the thirteenth map data cluster and the fourteenth map data cluster, respectively.

[0170] It should be noted that the electronic device may determine whether the elevations of two map data clusters intersect with each other by referring to the implementation of S302 above, and calculate the overlapping area of ​​the two map data clusters by referring to the implementation of S103 above, which will not be described in detail here.

[0171] The following specifically describes how the electronic device determines whether two map data clusters are on the same side of the vehicle's driving trajectory:

[0172] The electronic device obtains two direction identifiers corresponding one to one with the direction identifiers of the two map data clusters on the vehicle driving track.

[0173] The electronic device determines that the two direction identifiers are not empty and are equal.

[0174] If the two direction identifiers are not empty and are equal, the electronic device determines that the two map data clusters are on the same side of the vehicle's driving trajectory.

[0175] If one of the two direction identifiers is empty, the electronic device determines that the two map data clusters are not on the same side of the vehicle's driving track.

[0176] It can be understood that if the two map data clusters are not on the same side of the vehicle's driving trajectory, the two map data clusters are obtained by clustering map objects of different lanes.

[0177] In actual application, the direction identifier is represented by is_left. If the direction identifier is empty, is_left=0; if the direction identifier is not empty, is_left=1.

[0178] S503: The electronic device merges the thirteenth map data cluster and the fourteenth map data cluster to obtain a target map data cluster.

[0179] The target map data cluster includes a plurality of map data clusters consisting of map objects in the thirteenth map data cluster and map objects in the fourteenth map data cluster.

[0180] It can be understood that the technical solution provided in the embodiment of the present application obtains a plurality of twelfth map data clusters by clustering the third map object set; determines a thirteenth map data cluster and a fourteenth map data cluster from the plurality of twelfth map data clusters; and merges the thirteenth map data cluster and the fourteenth map data cluster to obtain a target map data cluster. In this way, since only two map data clusters are on different sides of the lane, the map objects in the two map data clusters are different lane lines, so when the two map data clusters are on the same side of the vehicle's driving trajectory, the elevations of the two map data clusters intersect, and the third overlap area of ​​the two map data clusters is greater than the preset third overlap area, the two map data clusters are merged, so that the multiple map data clusters obtained by the initial clustering of the acquired boundary map objects can be merged, thereby improving the accuracy of clustering.

[0181] Figure 6 FIG. 1 is a flow chart of a method for clustering arrow data in an actual application process according to an exemplary embodiment. Figure 6As shown, the method comprises the following steps:

[0182] S601. The electronic device obtains an arrow data set and performs clustering processing to obtain multiple arrow data clusters.

[0183] S602. The electronic device obtains a geometric ploygon object, a maximum elevation, a minimum elevation, and an average elevation of each arrow data cluster in a plurality of arrow data clusters.

[0184] S603. The electronic device calculates the average elevation difference, angle and distance between any two arrow data clusters.

[0185] S604: The electronic device determines whether the average elevation difference between the two arrow data clusters is less than 5 meters.

[0186] S605: The electronic device determines whether the angle between the two arrow data clusters is less than 30 degrees and the distance between them is less than 2 meters.

[0187] S606: If the average elevation difference between the two arrow data clusters is less than 5 meters, and the angle between the two arrow data clusters is less than 30 degrees and the distance between the two arrow data clusters is less than 2 meters, the electronic device merges the two arrow data clusters.

[0188] S607: If the angle between the two arrow data clusters is greater than 30 degrees or the distance between the two arrow data clusters is greater than 2 meters, the electronic device determines whether the elevations of the two arrow data clusters intersect.

[0189] S608: If the elevations of the two arrow data clusters intersect, the electronic device calculates the overlapping area of ​​the two arrow data clusters.

[0190] S609: The electronic device determines whether the overlapping area of ​​the two arrow data clusters is greater than a preset second area threshold.

[0191] S610. If the average elevation difference between the two arrow data clusters is less than 5 meters, the angle between the two arrow data clusters is greater than 30 degrees or the distance is greater than 2 meters, the elevations of the two arrow data clusters intersect, and the overlapping area of ​​the two arrow data clusters is greater than a preset second area threshold, the electronic device merges the above two arrow data clusters.

[0192] S611. If the average elevation difference between the two arrow data clusters is greater than or equal to 5 meters, or there is no intersection in the elevation, or the overlapping area is less than the preset second area threshold, the electronic device obtains any other two arrow data clusters and repeats the above steps S603-S610.

[0193] Figure 7 FIG. 1 is a flow chart of a zebra crossing clustering method in an actual application process according to an exemplary embodiment. Figure 7 As shown, the method comprises the following steps:

[0194] S701. The electronic device obtains a zebra crossing data set and performs clustering processing to obtain a plurality of zebra crossing data clusters.

[0195] S702: The electronic device obtains a geometric ploygon object, a maximum elevation, a minimum elevation, and an average elevation of each zebra crossing data cluster in a plurality of zebra crossing data clusters.

[0196] S703: The electronic device calculates the average elevation difference, distance and angle difference between any two zebra crossing data clusters.

[0197] S704: The electronic device determines whether the average elevation difference between the two zebra crossing data clusters is less than 5 meters.

[0198] S705: The electronic device determines whether the distance between two zebra crossing data clusters is less than 3 meters.

[0199] S706: The electronic device determines whether the angle difference between the two zebra crossing data clusters is less than a preset angle threshold.

[0200] S707: If the average elevation difference between the two zebra crossing data clusters is less than 5 meters, the distance is less than 3 meters, and the angle difference is less than a preset angle threshold, the electronic device merges the two zebra crossing data clusters.

[0201] S708. If the average elevation difference between the two zebra crossing data clusters is greater than 5 meters or the distance is greater than 3 meters or the angle difference is greater than a preset angle threshold, the electronic device obtains any other two zebra crossing data clusters and repeats the above steps S703-S707.

[0202] Figure 8 FIG. 1 is a flow chart showing a boundary clustering method in an actual application process according to an exemplary embodiment. Figure 8 As shown, the method comprises the following steps:

[0203] S801: The electronic device obtains a boundary data set and performs clustering processing to obtain a plurality of boundary data clusters.

[0204] S802: The electronic device obtains the geometric ploygon object, the maximum elevation, the minimum elevation, the average elevation and the left identification information of each boundary data cluster in the plurality of boundary data clusters.

[0205] S803: The electronic device determines whether the left identification information of any two boundary data clusters is not empty and equal.

[0206] S804: If the left identification information of the two boundary data clusters is not empty and is equal, the electronic device determines whether the elevations of the two boundary data clusters intersect.

[0207] S805: If the elevations of the two boundary data clusters intersect, the electronic device calculates the overlapping area of ​​the two boundary data clusters.

[0208] S806: The electronic device determines whether the overlapping area of ​​the two boundary data clusters is greater than a third overlapping area.

[0209] S807: If the left identification information of the two boundary data clusters is not empty and is equal, the elevations have an intersection, and the overlapping area is greater than the third overlapping area, the electronic device merges the two boundary data clusters.

[0210] S808. If the left identification information of the two boundary data clusters is empty or the elevations do not have an intersection or the overlapping area is smaller than the third overlapping area, the electronic device obtains any other two boundary data clusters and repeats the above steps S803-S807.

[0211] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to realize the above functions, the map data clustering device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed in this document, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0212] The embodiments of the present application can exemplarily divide the functional modules of the map data clustering device or the electronic device according to the above method. For example, the map data clustering device or the electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0213] Fig. 9 is a block diagram of a map data clustering device according to an exemplary embodiment. Fig. 9 The map data clustering device 900 includes: an acquisition unit 901 , a determination unit 902 and a processing unit 903 .

[0214] The acquisition unit 901 is used to acquire multiple target map data clusters; each target map data cluster includes a map data cluster obtained by clustering a map object set; the target map data cluster includes a first map object and a second map object; the difference between the timestamps of the first map object and the second map object is greater than a first time threshold.

[0215] The determining unit 902 is used to determine a first map data cluster and a second map data cluster from a plurality of target map data clusters; an interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold.

[0216] The determining unit 902 is used to determine a first overlapping area; the first overlapping area is an overlapping area between the first map data cluster and the second map data cluster.

[0217] The processing unit 903 is configured to merge the first map data cluster and the second map data cluster to obtain a third map data cluster if the first overlapping area is greater than a preset first area threshold.

[0218] The determining unit 902 is further configured to determine the third map data cluster as a map data cluster in the clustering result of the map object set.

[0219] Optional, such as Fig. 9 As shown, there is no map object of the target map object type in each target map data cluster; the target map object type includes air signs, traffic lights, text signs and speed reduction markings.

[0220] Optional, such as Fig. 9 As shown, the multiple target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering processing, and the target map data cluster obtained by merging includes: a processing unit 903, which is also used to perform clustering processing on the first map object set to obtain multiple fourth map data clusters; the map objects in the first map object set include arrows.

[0221] The determination unit 902 is further used to determine a fifth map data cluster and a sixth map data cluster from the plurality of fourth map data clusters; the first condition satisfied by the fifth map data cluster and the sixth map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, an angle between the two map data clusters is less than a preset first angle threshold, a distance between the two map data clusters is less than a preset first distance threshold, and among all timestamps consisting of timestamps of map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold.

[0222] The processing unit 903 is further configured to merge the fifth map data cluster and the sixth map data cluster to obtain a target map data cluster.

[0223] Optional, such as Fig. 9 As shown, the multiple target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering processing, and the target map data cluster obtained by merging includes: a processing unit 903, which is also used to perform clustering processing on the first map object set to obtain multiple fourth map data clusters; the map objects in the first map object set include arrows.

[0224] The determining unit 902 is further used to determine a seventh map data cluster and an eighth map data cluster from the plurality of fourth map data clusters; the second condition satisfied by the seventh map data cluster and the eighth map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, an angle between the two map data clusters is greater than a preset first angle threshold or a distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, a second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, and among all timestamps consisting of timestamps of map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold.

[0225] The processing unit 903 is further configured to merge the seventh map data cluster and the eighth map data cluster to obtain a target map data cluster.

[0226] Optional, such as Fig. 9 As shown, the multiple target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering processing, and the merging target map data cluster includes: a processing unit 903, which is also used to cluster the second map object set to obtain multiple ninth map data clusters; the map objects in the second map object set include zebra crossings.

[0227] The determining unit 902 is further used to determine a tenth map data cluster and an eleventh map data cluster from the plurality of ninth map data clusters; the third condition satisfied by the tenth map data cluster and the eleventh map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, a distance between the two map data clusters is less than a preset second distance threshold, an angle difference between the two map data clusters is less than a preset second angle threshold, and among all timestamps consisting of timestamps of map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold.

[0228] The processing unit 903 is further configured to merge the tenth map data cluster and the eleventh map data cluster to obtain a target map data cluster.

[0229] Optional, such as Fig. 9As shown, the multiple target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering processing, and the target map data cluster obtained by merging includes: a processing unit 903, which is also used to cluster the third map object set to obtain multiple twelfth map data clusters; the map objects in the third map object set include boundaries.

[0230] The determining unit 902 is further used to determine a thirteenth map data cluster and a fourteenth map data cluster from the plurality of twelfth map data clusters; the fourth condition satisfied by the thirteenth map data cluster and the fourteenth map data cluster includes: the two map data clusters are on the same side of the vehicle driving trajectory, the elevations of the two map data clusters intersect, a third overlapping area of ​​the two map data clusters is greater than a preset third overlapping area, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold.

[0231] The processing unit 903 is further configured to merge the thirteenth map data cluster and the fourteenth map data cluster to obtain a target map data cluster.

[0232] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0233] Fig.10 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Fig.10 As shown, the electronic device 1000 includes but is not limited to: a processor 1001 and a memory 1002 .

[0234] The memory 1002 is used to store executable instructions of the processor 1001. It can be understood that the processor 1001 is configured to execute instructions to implement the map data clustering method in the above embodiment.

[0235] It should be noted that those skilled in the art can understand that Fig.10 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Fig.10 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0236] The processor 1001 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 1002, and calling data stored in the memory 1002, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 1001 may include one or more processing units. Optionally, the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1001.

[0237] The memory 1002 may be used to store software programs and various data. The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0238] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1002 including instructions. The instructions can be executed by the processor 1001 of the electronic device 800 to implement the map data clustering method in the above embodiment.

[0239] In actual implementation, Fig. 9 The functions of the acquisition unit 901, the determination unit 902 and the processing unit 903 in Fig.10 The processor 1001 in the embodiment calls the computer program stored in the memory 1002. The specific execution process can refer to the description of the map data clustering method in the above embodiment, which will not be repeated here.

[0240] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0241] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 1001 of the electronic device to complete the map data clustering method in the above embodiment.

[0242] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned map data clustering method embodiment are implemented, and the same technical effect as the above-mentioned map data clustering method can be achieved. In order to avoid repetition, they will not be repeated here.

[0243] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0244] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0245] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0246] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0247] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0248] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A map data clustering method, It is characterized in that include: Obtain multiple target map data clusters; Each target map data cluster includes a map data cluster obtained by clustering a map object set; The target map data cluster includes a first map object and a second map object; A difference between the timestamps of the first map object and the second map object is greater than a first time threshold; determining a first map data cluster and a second map data cluster from the plurality of target map data clusters; an interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold; Determine a first overlapping area; the first overlapping area is an overlapping area of ​​the first map data cluster and the second map data cluster; If the first overlapping area is greater than a preset first area threshold, the first map data cluster and the second map data cluster are merged to obtain a third map data cluster, and the third map data cluster is determined as a map data cluster in the clustering result of the map object set.

2. The method according to claim 1, It is characterized in that The method further comprises: There is no map object of the target map object type in each target map data cluster; the target map object type includes air signs, traffic lights, text signs and speed reduction markings.

3. The method according to claim 1, It is characterized in that The plurality of target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: Performing clustering processing on the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; A fifth map data cluster and a sixth map data cluster are determined from the plurality of fourth map data clusters; the first condition satisfied by the fifth map data cluster and the sixth map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, an angle between the two map data clusters is less than a preset first angle threshold, a distance between the two map data clusters is less than a preset first distance threshold, and among all timestamps consisting of timestamps of map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold; The fifth map data cluster and the sixth map data cluster are merged to obtain the target map data cluster.

4. The method according to claim 1, It is characterized in that The plurality of target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: Performing clustering processing on the first map object set to obtain a plurality of fourth map data clusters; the map objects in the first map object set include arrows; A seventh map data cluster and an eighth map data cluster are determined from the plurality of fourth map data clusters; the second condition satisfied by the seventh map data cluster and the eighth map data cluster includes: the average elevation difference between the two map data clusters is within a preset range, the angle between the two map data clusters is greater than a preset first angle threshold or the distance between the two map data clusters is greater than a preset first distance threshold, the elevations of the two map data clusters intersect, the second overlapping area of ​​the two map data clusters is greater than a preset second area threshold, and among all timestamps consisting of the timestamps of the map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold; The seventh map data cluster and the eighth map data cluster are merged to obtain the target map data cluster.

5. The method according to claim 1, It is characterized in that The plurality of target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: performing clustering processing on the second map object set to obtain a plurality of ninth map data clusters; the map objects in the second map object set include zebra crossings; determining a tenth map data cluster and an eleventh map data cluster from the plurality of ninth map data clusters; the third condition satisfied by the tenth map data cluster and the eleventh map data cluster includes: an average elevation difference between the two map data clusters is within a preset range, a distance between the two map data clusters is less than a preset second distance threshold, an angle difference between the two map data clusters is less than a preset second angle threshold, and among all timestamps consisting of timestamps of map objects of the two map data clusters, there are two timestamps whose difference is greater than the first time threshold; The tenth map data cluster and the eleventh map data cluster are merged to obtain the target map data cluster.

6. The method according to claim 1, It is characterized in that The plurality of target map data clusters also include a map data cluster obtained by merging map data clusters obtained by clustering, and the target map data cluster obtained by merging includes: Performing clustering processing on the third map object set to obtain a plurality of twelfth map data clusters; the map objects in the third map object set include boundaries; Determining a thirteenth map data cluster and a fourteenth map data cluster from the plurality of twelfth map data clusters; the fourth condition satisfied by the thirteenth map data cluster and the fourteenth map data cluster includes: the two map data clusters are on the same side of the vehicle driving track, the elevations of the two map data clusters have an intersection, the third overlapping area of ​​the two map data clusters is greater than a preset third overlapping area, and among all time stamps composed of the time stamps of the map objects of the two map data clusters, there are two time stamps whose difference is greater than the first time threshold; The thirteenth map data cluster and the fourteenth map data cluster are merged to obtain the target map data cluster.

7. A map data clustering device, It is characterized in that include: an acquisition unit, a determination unit, and a processing unit; The acquisition unit is used to acquire multiple target map data clusters; Each target map data cluster includes a map data cluster obtained by clustering a map object set; The target map data cluster includes a first map object and a second map object; A difference between the timestamps of the first map object and the second map object is greater than a first time threshold; The determining unit is used to determine a first map data cluster and a second map data cluster from the plurality of target map data clusters; an interference value between any map object type in the first map data cluster and any map object type in the second map data cluster is less than a first interference threshold; The determining unit is used to determine a first overlapping area; the first overlapping area is an overlapping area of ​​the first map data cluster and the second map data cluster; The processing unit is configured to merge the first map data cluster and the second map data cluster to obtain a third map data cluster if the first overlapping area is greater than a preset first area threshold; The determining unit is further configured to determine the third map data cluster as a map data cluster in the clustering result of the map object set.

8. The device according to claim 7, It is characterized in that There is no map object of the target map object type in each target map data cluster; the target map object type includes air signs, traffic lights, text signs and speed reduction markings.

9. An electronic device, It is characterized in that include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, It is characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method as claimed in any one of claims 1 to 6.