Map data fusion method and device, electronic equipment, storage medium and vehicle

Abstract

The invention relates to a map data fusion method and apparatus, an electronic device, a storage medium and a vehicle. The method comprises the steps of obtaining target crowdsourcing map data; detecting whether the target crowdsourcing map data meets a map data fusion condition or not; and if yes, fusing the target crowdsourcing map data and the high-precision map data to obtain target map data. According to the method, the target map data is obtained by fusing the target crowdsourcing map data serving as the supplementary map data and the high-precision map data, and the target map data obtained after fusion has the advantages of high precision of the high-precision map data and high timeliness of the crowdsourcing map data at the same time, so that the map data production efficiency is improved, and the user experience is improved. The technical problem of low map data production efficiency is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving, and particularly to a method, device, electronic device, storage medium and vehicle for map data fusion. Background Art

[0002] With the development of society and the progress of technology, autonomous driving technology has become an important research direction for major automobile manufacturers. No matter which autonomous driving technology solution, in principle, it is to enable the vehicle to realize the intelligent "perception - decision - execution" process. In this process, the commercial value of the map is thus highlighted.

[0003] Currently, most automobile manufacturers' autonomous driving technologies use high-precision maps. As a digital map that precisely records road information such as roads, traffic signs, and lane lines, it can provide a large amount of key information for autonomous driving technology and is an essential basic component of the autonomous driving system.

[0004] However, the production process of high-precision maps is complex. After centralized data collection, there are still many links such as data fusion, data processing, publishing, and delivery. Therefore, there is a problem of low map data production efficiency. Summary of the Invention

[0005] To overcome the problems in the related art, the present invention provides a method, device, electronic device, storage medium and vehicle for map data fusion.

[0006] According to the first aspect of the embodiments of the present invention, a method for map data fusion is provided. The method includes:

[0007] Obtain target crowdsourced map data;

[0008] Detect whether the target crowdsourced map data meets the map data fusion conditions;

[0009] If it meets the conditions, fuse the target crowdsourced map data and high-precision map data to obtain target map data.

[0010] Optionally, the detecting whether the target crowdsourced map data meets the map data fusion conditions includes:

[0011] Detect whether the target crowdsourced map data meets data integrity, and detect whether the target crowdsourced map data meets geometric topological integrity.

[0012] Optionally, the obtaining target crowdsourced map data includes:

[0013] Detect whether there is abnormal data in the high-precision map data;

[0014] If it exists, obtain the range of abnormal data, and determine whether there is crowdsourced map data within the range of the abnormal data;

[0015] If it exists, obtain the corresponding crowdsourced map data according to the range of the abnormal data;

[0016] Perform geometric processing on the crowdsourced map data to generate target crowdsourced map data.

[0017] Optionally, before the step of detecting whether there is abnormal data in the high-precision map data, the method includes:

[0018] Obtain initial high-precision map data and initial crowdsourced map data;

[0019] Convert the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system to obtain high-precision map data and crowdsourced map data.

[0020] Optionally, detecting whether there is abnormal data in the high-precision map data includes:

[0021] Detect whether there are map geometry anomalies in the high-precision map data, and detect whether there are map attribute anomalies in the high-precision map data.

[0022] Optionally, the method includes:

[0023] Detect whether there is data anomaly in the target map data;

[0024] If it exists, record the information related to the abnormal data in the current target map data through the abnormal record module.

[0025] According to the second aspect of the embodiments of the present invention, there is provided a map data fusion device, the device includes:

[0026] A target crowdsourced map data acquisition module, configured to acquire target crowdsourced map data;

[0027] A map data fusion condition judgment module, configured to detect whether the target crowdsourced map data meets the map data fusion conditions;

[0028] A map data fusion module, configured to, if it is satisfied, fuse the target crowdsourced map data and the high-precision map data to obtain target map data.

[0029] Optionally, the map data fusion condition judgment module includes:

[0030] A target crowdsourced map data detection sub-module, configured to detect whether the target crowdsourced map data meets data integrity, and detect whether the target crowdsourced map data meets geometric topological integrity.

[0031] Optionally, the target crowdsourced map data acquisition module includes:

[0032] A high-precision map data detection sub-module for detecting whether there is abnormal data in the high-precision map data;

[0033] An abnormal data range acquisition sub-module for, if any, acquiring the range of the abnormal data and determining whether there is crowdsourced map data within the range of the abnormal data;

[0034] A crowdsourced map data acquisition sub-module for, if any, acquiring the corresponding crowdsourced map data according to the range of the abnormal data;

[0035] A target crowdsourced map data generation sub-module for performing geometric processing on the crowdsourced map data to generate target crowdsourced map data.

[0036] Optionally, the device further includes:

[0037] An initial map data acquisition sub-module for acquiring initial high-precision map data and initial crowdsourced map data;

[0038] An initial map data conversion sub-module for converting the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system to obtain high-precision map data and crowdsourced map data.

[0039] Optionally, the high-precision map data detection sub-module includes:

[0040] A high-precision map data detection unit for detecting whether there is map geometry abnormality in the high-precision map data, and detecting whether there is map attribute abnormality in the high-precision map data.

[0041] Optionally, the device further includes:

[0042] A target map data detection module for detecting whether there is data abnormality in the target map data;

[0043] An abnormal data recording module for, if any, recording information related to the abnormal data existing in the current target map data through the abnormal recording module.

[0044] According to the third aspect of the embodiments of the present invention, there is provided an electronic device, including:

[0045] A processor;

[0046] A memory for storing executable instructions of the processor;

[0047] Wherein, the processor is configured to execute the instructions to implement the map data fusion method as described in the first aspect.

[0048] According to a fourth aspect of the embodiments of the present invention, there is provided a computer storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, the mobile terminal is enabled to execute the map data fusion method as described in the first aspect of the present invention.

[0049] According to a fifth aspect of the embodiments of the present invention, there is provided a vehicle, including the map data fusion device as described in the second aspect of the present invention.

[0050] According to a sixth aspect of the embodiments of the present invention, there is provided a computer program product, when the computer program product runs on a terminal device, the terminal device is enabled to execute the map data fusion method as described in any one of the above first aspects.

[0051] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0052] In the present invention, by obtaining target crowdsourced map data, it is detected whether the target crowdsourced map data meets the map data fusion conditions. If it meets, the target crowdsourced map data and high-precision map data are fused to obtain target map data. High-precision map data often requires the mapping vehicle to collect data back and forth multiple times when mapping a road to ensure the accuracy of the map data. And the high-precision map production process is complicated. After centralized data collection, there are still many links such as data fusion, data processing, publishing, and delivery. This results in low production efficiency of high-precision map data and is not conducive to subsequent continuous maintenance of high-precision maps for roads with changing conditions. Crowdsourced map data is generated by a large number of non-professional collection vehicles driving on the road, using on-vehicle sensors to collect road data, and has the ability to quickly obtain and update a large amount of geographical information data. Therefore, in this application, by using the target crowdsourced map data as supplementary map data to fuse with high-precision map data to obtain target map data, the obtained target map data after fusion has both the high accuracy of high-precision map data and the high timeliness of crowdsourced map data, improving the production efficiency of map data and solving the technical problem of low production efficiency of map data; and high-precision map data can only be collected by professional mapping vehicles equipped with expensive devices such as lidar, and the data collection cost is relatively high. While crowdsourced map data can be collected through the sensors of autonomous driving vehicles or other low-cost sensor hardware, and the required cost is relatively low. Therefore, in this application, by using the target crowdsourced map data as supplementary map data to fuse with high-precision map data, the target crowdsourced map data largely makes up for the shortcomings of high-precision map data, that is, there is no need to maintain expensive collection vehicles, thereby reducing the production cost of map data and solving the technical problem of relatively high production cost of map data.

[0053] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings herein are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0055] Figure 1 is one of the flowchart diagrams of steps of a map data fusion method shown according to an exemplary embodiment;

[0056] Figure 2 is the second of the flowchart diagrams of steps of a map data fusion method shown according to an exemplary embodiment;

[0057] Figure 3 is the third of the flowchart diagrams of steps of a map data fusion method shown according to an exemplary embodiment;

[0058] Figure 4 is the fourth of the flowchart diagrams of steps of a map data fusion method shown according to an exemplary embodiment;

[0059] Figure 5 is the block diagram of a map data fusion device shown according to an exemplary embodiment;

[0060] Figure 6 is the block diagram of an electronic device shown according to an exemplary embodiment;

[0061] Figure 7 is the schematic diagram of an application scenario of a map data fusion method shown according to an exemplary embodiment;

[0062] Figure 8 is the schematic diagram of a map data fusion shown according to an exemplary embodiment;

[0063] Figure 9 is the schematic diagram of recording map data abnormal information shown according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0065] It should be noted that in the embodiments of the present invention, the technical solution of the present invention is applied to the HDM middleware, and the HDM middleware may further include a fusion module and an exception recording module, as Figure 7 shown, the HDM middleware is integrated into the intelligent vehicle domain controller system on the vehicle.

[0066] The first embodiment of the present invention relates to a map data fusion method, Figure 1 which is a step flowchart of a map data fusion method shown according to an exemplary embodiment, as Figure 1 shown, and includes the following steps:

[0067] Step 101, obtain target crowdsourced map data.

[0068] It should be noted that in the embodiments of the present invention, the specific process of obtaining the target crowdsourced map data can refer to the detailed description of steps 201-204, which will not be elaborated here.

[0069] Furthermore, as Figure 2 shown, in the embodiments of the present invention, step 101 may further include the following steps:

[0070] Step 201, detect whether there is abnormal data in the high-precision map data.

[0071] Step 202, if it exists, obtain the range of the abnormal data, and determine whether there is crowdsourced map data within the range of the abnormal data.

[0072] It should be noted that in the embodiments of the present invention, traverse the high-precision map data to detect whether there is abnormal data in all the high-precision map data, including but not limited to traversing all the road section data in the high-precision map data to detect whether all the road section data is abnormal.

[0073] If there is abnormal data in the high-precision map data, obtain the regional range of the abnormal data in the high-precision map, that is, the range of the abnormal data. And map the range of the abnormal data to the crowdsourced map data, and determine whether there is crowdsourced map data within the range of the abnormal data.

[0074] If there is no abnormal data in the high-precision map data, continue to obtain the next frame of high-precision map data, and determine whether there is abnormal data in the obtained high-precision map data.

[0075] Step 203, if it exists, obtain the corresponding crowdsourced map data according to the range of the abnormal data.

[0076] Step 204, perform geometric processing on the crowdsourced map data to generate target crowdsourced map data.

[0077] It should be noted that in the embodiments of the present invention, if it is detected that there is crowdsourced map data within the range of the acquired abnormal data, the crowdsourced map data corresponding to the range of the abnormal data is acquired.

[0078] After acquiring the crowdsourced map data corresponding to the range of the abnormal data, geometric processing is performed on the crowdsourced map data, and then target crowdsourced map data can be obtained. For example: in the process of performing geometric processing on the crowdsourced map data, for the same lane, the lane line corresponding to the lane should be continuous. In the high-precision map data, the lane line is a complete straight line, while in the crowdsourced map data, the lane line may not be a continuous straight line and is composed of multiple line segments. At this time, it is necessary to merge the multiple line segments representing the lane line in the crowdsourced map data to form a complete straight line to represent the lane line. Since there are requirements for the order of lanes in the high-precision map data, after completing the merging of the multiple line segments representing the lane line in the crowdsourced map data, it is also necessary to arrange the order of the lanes according to the order of lanes in the high-precision map data. By performing geometric processing on the crowdsourced map data, geometric errors in the crowdsourced map data can be eliminated or corrected, and a new crowdsourced map data that conforms to the actual map coordinate system can be generated, that is, the target crowdsourced map data.

[0079] As Figure 9 shown, if it is detected that there is no crowdsourced map data within the range of the acquired abnormal data, it is only necessary to record the relevant information (i.e., abnormal information) of the abnormal data existing in the current high-precision map data through the abnormal record module in the HDM middleware. Among them, the relevant information of the abnormal data includes but is not limited to the original error information of the abnormal data, the location information of the abnormal data, the type information of the abnormal data, etc.

[0080] Furthermore, as Figure 3 shown, in the embodiments of the present invention, the following steps may further be included before step 201:

[0081] Step 301, acquire initial high-precision map data and initial crowdsourced map data.

[0082] It should be noted that in the embodiments of the present invention, the current real-time position of the vehicle needs to be acquired in advance.

[0083] As Figure 8 shown, since the initial high-precision map data is stored locally on the vehicle side, it is necessary to acquire the initial high-precision map data from the vehicle side locally by the HDM middleware according to the current real-time position of the vehicle in advance; while the initial crowdsourced map data is stored in the cloud server, it is necessary to request the cloud server to acquire the initial crowdsourced map data by the HDM middleware according to the current real-time position of the vehicle in advance.

[0084] Among them, the initial high-precision map data is a high-precision map for autonomous driving, with a map accuracy that can reach the centimeter level. It includes road data, such as lane information like the position, type, width, slope, and curvature of lanes, and also includes fixed object information around the lanes, such as traffic signs, traffic lights, etc., lane height limits, sewer inlets, obstacles, and other road details. It also includes infrastructure information such as elevated objects, guardrails, numbers, road edge types, and roadside landmarks.

[0085] Among them, the initial crowdsourced map data is that a large number of users collect video data through the camera sensors of their own autonomous vehicles or by installing special cameras separately, perform some basic road element extraction on their own vehicles, and upload the extraction results. These data will ultimately help map providers / solution integrators create high-precision maps. It can also be that a large number of users obtain point cloud data through the lidar of their own autonomous vehicles, and use AI to identify road features from the point cloud data obtained by the lidar, identify the features of road edges, lane lines, and some billboards, and establish map updates or directly construct a perception layer.

[0086] Step 302: Convert the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system to obtain high-precision map data and crowdsourced map data.

[0087] It should be noted that in the embodiment of the present invention, the initial high-precision map data encrypts the coordinates once again on the coordinate system in use, while the initial crowdsourced map data is not encrypted. This will cause a deviation between the initial high-precision map data and the initial crowdsourced map data. Therefore, in order to eliminate the deviation between the two, it is necessary to convert the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system, that is, to unify the geographic coordinate system, and represent the position information in the initial high-precision map data and the initial crowdsourced map data under the same geographic coordinate system. After completing the unification of the geographic coordinate system for the initial high-precision map data and the initial crowdsourced map data, high-precision map data and crowdsourced map data can be obtained.

[0088] Furthermore, in the embodiment of the present invention, step 201 may further include the following steps: detecting whether there are map geometry anomalies in the high-precision map data, and detecting whether there are map attribute anomalies in the high-precision map data.

[0089] It should be noted that in the embodiments of the present invention, geometric anomalies mainly refer to lines with phenomena such as broken lines, loop lines, duplicate lines, or self-intersections. The existence of some of these phenomena (broken lines, self-intersections) causes contradictions or inconsistencies between the topographic map graphics and the actual situation, and some (such as loop lines, duplicate lines) increase the amount of topographic map data. Therefore, detecting whether there are map geometric anomalies in the high-precision map data means detecting whether there are lines with phenomena such as broken lines, loop lines, duplicate lines, or self-intersections in the high-precision map data.

[0090] Detecting whether there are map attribute anomalies in the high-precision map data. Specifically, taking the lanes in the high-precision map data as an example, lanes have attribute information such as driving direction, width, speed limit, and curvature of the official road area. If there is a situation where the attribute information corresponding to the lanes in the high-precision map data is missing, or if the attribute information corresponding to the lanes in the high-precision map data does not match the attribute information corresponding to the lanes in the real scene, it indicates that there are map attribute anomalies in the high-precision map data; if there is no missing attribute information corresponding to the lanes in the high-precision map data, or if the attribute information corresponding to the lanes in the high-precision map data matches the attribute information corresponding to the lanes in the real scene, it indicates that there are no map attribute anomalies in the high-precision map data.

[0091] Step 102, detecting whether the target crowdsourced map data meets the map data fusion conditions.

[0092] Furthermore, in the embodiments of the present invention, step 102 may further include the following steps: detecting whether the target crowdsourced map data meets data integrity, and detecting whether the target crowdsourced map data meets geometric topological integrity.

[0093] It should be noted that in the embodiments of the present invention, after geometric processing of the crowdsourced map data to generate the target crowdsourced map data, it is necessary to further detect whether the target crowdsourced map data meets the map data fusion conditions. Specifically, it is to detect whether the target crowdsourced map data meets data integrity and detect whether the target crowdsourced map data meets geometric topological integrity.

[0094] Among them, detecting whether the target crowdsourced map data meets data integrity means detecting whether there is a missing situation in the target crowdsourced map data. Data missing may be the missing of the entire data or the missing of a certain field information in the data. The integrity of data quality is relatively easy to evaluate, and generally can be evaluated through the record values and unique values in data statistics. During the data collection process, multiple methods should be combined to judge data omission, eliminate invalid data and duplicate data to ensure data integrity.

[0095] Detecting whether the target crowdsourced map data meets geometric topological integrity refers to detecting the correctness of the mutual relationships between features in the target crowdsourced map data. In the target crowdsourced map data, the topological relationships between features include inclusion, contact, adjacency, intersection, etc. Incorrectness of any one relationship may lead to incorrect analysis of the data and inaccurate calculation results. Therefore, geometric topological integrity detection is the basis for ensuring the quality of the target crowdsourced map data and the correctness of geographical analysis results. For example: For the same lane in the target crowdsourced map data, the lane lines corresponding to the lane should be continuous, that is, the lane line is a complete straight line in the target crowdsourced map data. However, due to problems in data collection, the collected data is incomplete. Then, in the target crowdsourced map data, the lane line is composed of several separate lines, which indicates that the lane line is geometrically topologically incomplete and does not meet geometric topological integrity. If the lane line is a complete straight line in the target crowdsourced map data, it means that the lane line is geometrically topologically complete and meets geometric topological integrity.

[0096] Step 103, if satisfied, fuse the target crowdsourced map data and the high-precision map data to obtain the target map data.

[0097] It should be noted that in the embodiments of the present invention, as Figure 8 shown, if the target crowdsourced map data simultaneously meets data integrity and geometric topological integrity, the target crowdsourced map data and the high-precision map data can be fused through the fusion module in the HDM middleware, that is, the target crowdsourced map data is used as supplementary map data to perform map data fusion with the high-precision map data, and then the fused map data, that is, the target map data, is obtained.

[0098] If the target crowdsourced map data does not meet data integrity, or the target crowdsourced map data does not meet geometric topological integrity, no map data fusion is performed on the target crowdsourced map data and the high-precision map data.

[0099] Furthermore, as Figure 4 shown, in the embodiments of the present invention, the method may further include the following steps:

[0100] Step 401, detect whether there is data anomaly in the target map data.

[0101] Step 402, if there is, record the relevant information of the abnormal data in the current target map data through the abnormal record module.

[0102] It should be noted that in the embodiments of the present invention, after obtaining the target map data, it is necessary to further detect the target map data to determine whether there is data abnormality in the target map data, including detecting whether the target map data meets data integrity and detecting whether the target map data meets geometric topological integrity. The specific processes of detecting whether the target map data meets data integrity and detecting whether the target map data meets geometric topological integrity are as described in detail in the step "detecting whether the target crowdsourced map data meets data integrity and detecting whether the target crowdsourced map data meets geometric topological integrity", which will not be elaborated here.

[0103] As Figure 9 shown, if the target map data does not meet data integrity or the target map data does not meet geometric topological integrity, the relevant information (i.e., the abnormal information) of the abnormal data existing in the current high-precision map data can be recorded through the abnormal record module in the HDM middleware. The relevant information of the abnormal data includes but is not limited to the original error information of the abnormal data, the fused abnormal information, the location information of the abnormal data, the type information of the abnormal data, etc.

[0104] The present invention obtains target crowdsourced map data, detects whether the target crowdsourced map data meets the map data fusion condition, and if so, fuses the target crowdsourced map data with high-precision map data to obtain target map data. In order to ensure the accuracy of map data, high-precision map data often requires the mapping vehicle to collect data multiple times back and forth when mapping a road. Moreover, the production process of high-precision maps is complex. After centralized data collection, many links such as data fusion, data processing, publishing, and delivery are still required. This results in low production efficiency of high-precision map data and is not conducive to subsequent continuous maintenance of high-precision maps for roads with changing conditions. Crowdsourced map data is generated by a large number of non-professional collection vehicles driving on the road, using in-vehicle sensors to collect road data, and has the ability to quickly obtain and update a large amount of geographical information data. Therefore, in this application, the target crowdsourced map data is used as supplementary map data and fused with high-precision map data to obtain target map data. The target map data obtained after fusion combines the advantages of high precision of high-precision map data and high timeliness of crowdsourced map data, improves the production efficiency of map data, and solves the technical problem of low production efficiency of map data. Moreover, high-precision map data can only be collected by professional mapping vehicles equipped with expensive devices such as lidar, and the data collection cost is relatively high. However, crowdsourced map data can be collected through the sensors of autonomous driving vehicles or other low-cost sensor hardware, and the required cost is relatively low. Therefore, in this application, the target crowdsourced map data is used as supplementary map data and fused with high-precision map data, enabling the target crowdsourced map data to largely make up for the shortcomings of high-precision map data, that is, without maintaining expensive collection vehicles, thereby reducing the production cost of map data and solving the technical problem of relatively high production cost of map data.

[0105] The second embodiment of the present invention relates to a map data fusion device Figure 5 which is a device block diagram of a map data fusion device shown according to an exemplary embodiment, as Figure 5 shown. The device includes:

[0106] A target crowdsourced map data acquisition module 501, configured to acquire target crowdsourced map data;

[0107] A map data fusion condition judgment module 502, configured to detect whether the target crowdsourced map data meets the map data fusion condition;

[0108] A map data fusion module 503, configured to, if it meets the condition, fuse the target crowdsourced map data with high-precision map data to obtain target map data.

[0109] Optionally, the map data fusion condition judgment module 502 includes:

[0110] The target crowdsourced map data detection sub-module is used to detect whether the target crowdsourced map data meets data integrity and whether the target crowdsourced map data meets geometric topological integrity.

[0111] Optionally, the target crowdsourced map data acquisition module includes:

[0112] The high-precision map data detection sub-module is used to detect whether there is abnormal data in the high-precision map data;

[0113] The abnormal data range acquisition sub-module is used to, if any, acquire the range of the abnormal data and determine whether there is crowdsourced map data within the range of the abnormal data;

[0114] The crowdsourced map data acquisition sub-module is used to, if any, acquire the corresponding crowdsourced map data according to the range of the abnormal data;

[0115] The target crowdsourced map data generation sub-module is used to perform geometric processing on the crowdsourced map data to generate the target crowdsourced map data.

[0116] Optionally, the device further includes:

[0117] The initial map data acquisition sub-module is used to acquire the initial high-precision map data and the initial crowdsourced map data;

[0118] The initial map data conversion sub-module is used to convert the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system to obtain the high-precision map data and the crowdsourced map data.

[0119] Optionally, the high-precision map data detection sub-module includes:

[0120] The high-precision map data detection unit is used to detect whether there are map geometric anomalies in the high-precision map data and whether there are map attribute anomalies in the high-precision map data.

[0121] Optionally, the device further includes:

[0122] The target map data detection module is used to detect whether there is data anomaly in the target map data;

[0123] The abnormal data recording module is used to, if any, record the relevant information of the abnormal data existing in the current target map data through the abnormal recording module.

[0124] The present invention obtains target crowdsourced map data, detects whether the target crowdsourced map data meets the map data fusion condition, and if it meets, fuses the target crowdsourced map data and high-precision map data to obtain target map data. In order to ensure the accuracy of map data, high-precision map data often requires the mapping vehicle to collect data multiple times back and forth when mapping a road. Moreover, the production process of high-precision maps is complicated. After centralized data collection, there are still many links such as data fusion, data processing, publishing, and delivery. This results in low production efficiency of high-precision map data and is not conducive to subsequent continuous maintenance of high-precision maps for roads with changing conditions. Crowdsourced map data is generated by a large number of non-professional collection vehicles driving on the road, using on-vehicle sensors to collect road data, and has the ability to quickly obtain and update a large amount of geographical information data. Therefore, in this application, by using the target crowdsourced map data as supplementary map data and fusing it with high-precision map data to obtain target map data, the target map data obtained after fusion combines the advantages of high precision of high-precision map data and high timeliness of crowdsourced map data, improves the production efficiency of map data, and solves the technical problem of low production efficiency of map data; moreover, high-precision map data can only be collected by professional mapping vehicles equipped with expensive devices such as lidar, and the data collection cost is relatively high. However, crowdsourced map data can be collected through the sensors of autonomous driving vehicles or other low-cost sensor hardware, and the required cost is relatively low. Therefore, in this application, by using the target crowdsourced map data as supplementary map data and fusing it with high-precision map data, the target crowdsourced map data largely makes up for the shortcomings of high-precision map data, that is, there is no need to maintain expensive collection vehicles, thereby reducing the production cost of map data and solving the technical problem of relatively high production cost of map data.

[0125] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0126] The third embodiment of the present invention provides a communication device, as Figure 6 shown, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604. Among them, the processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604.

[0127] The memory 603 is used to store a computer program.

[0128] The processor 601, when executing the program stored in the memory 603, can implement the following steps:

[0129] Obtain target crowdsourced map data;

[0130] Detect whether the target crowdsourced map data meets the map data fusion conditions;

[0131] If it meets the conditions, fuse the target crowdsourced map data and the high-precision map data to obtain the target map data.

[0132] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0133] The communication interface is used for communication between the above terminal and other devices.

[0134] The memory can include a Random Access Memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory can also be at least one storage device located far from the aforementioned processor.

[0135] The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0136] The fourth embodiment of the present invention provides a computer storage medium. Instructions are stored in this computer-readable storage medium. When it runs on a computer, it causes the computer to execute the map data fusion method described in any one of the above embodiments.

[0137] The fifth embodiment of the present invention provides a vehicle, including the map data fusion device described in the second embodiment of the present invention.

[0138] A sixth embodiment of the present invention provides a computer program product including instructions that, when run on a computer, cause the computer to execute the map data fusion method described in any one of the above embodiments.

[0139] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or third database to another website, computer, server, or third database by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or third database that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0140] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0141] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0142] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. A method for map data fusion, characterized in that, The method includes: Obtaining target crowdsourced map data; Detecting whether the target crowdsourced map data meets the map data fusion condition; If it meets the condition, fusing the target crowdsourced map data and the high-precision map data to obtain target map data.

2. The map data fusion method according to claim 1, wherein The detecting whether the target crowdsourced map data meets the map data fusion condition includes: Detecting whether the target crowdsourced map data meets data integrity, and detecting whether the target crowdsourced map data meets geometric topology integrity.

3. The map data fusion method according to claim 1, characterized in that The obtaining target crowdsourced map data includes: Detecting whether there is abnormal data in the high-precision map data; If there is, obtaining the range of the abnormal data and determining whether there is crowdsourced map data within the range of the abnormal data; If there is, obtaining the corresponding crowdsourced map data according to the range of the abnormal data; Performing geometric processing on the crowdsourced map data to generate target crowdsourced map data.

4. The map data fusion method according to claim 3, wherein Before the step of detecting whether there is abnormal data in the high-precision map data, the method includes: Obtaining initial high-precision map data and initial crowdsourced map data; Converting the initial high-precision map data and the initial crowdsourced map data to the same geographic coordinate system to obtain high-precision map data and crowdsourced map data.

5. The map data fusion method according to claim 3, wherein The detecting whether there is abnormal data in the high-precision map data includes: Detecting whether there is map geometry abnormality in the high-precision map data, and detecting whether there is map attribute abnormality in the high-precision map data.

6. The map data fusion method according to claim 1, wherein The method includes: Detecting whether there is data abnormality in the target map data; If there is, recording relevant information of the abnormal data existing in the current target map data through an abnormal record module.

7. A map data fusion device, characterized in that, The map data fusion device includes: A target crowdsourced map data acquisition module for obtaining target crowdsourced map data; A map data fusion condition judgment module for detecting whether the target crowdsourced map data meets the map data fusion condition; A map data fusion module for, if it meets the condition, fusing the target crowdsourced map data and the high-precision map data to obtain target map data.

8. An electronic device, characterized in that, Includes: A processor; A memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the map data fusion method according to any one of claims 1 to 6.

9. A computer storage medium, when the instructions in the storage medium are executed by a processor of a mobile terminal, enabling the mobile terminal to execute the map data fusion method according to any one of claims 1 to 6.

10. A vehicle, characterized in that, Includes the map data fusion method device according to claim 7.

Images