A data processing method, device and electronic equipment
By using automated data processing methods to filter and bind map vector fragment matching rules, the problem of erroneous matching information in high-precision map construction was solved, improving the accuracy of map matching results and vehicle positioning accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG GEELY HLDG GRP CO LTD
- Filing Date
- 2022-08-31
- Publication Date
- 2026-06-09
AI Technical Summary
Existing technologies, when constructing high-precision maps, contain erroneous matching information in the map vector fragment matching results, leading to a decrease in vehicle positioning accuracy and high manual processing costs.
By using automated data processing methods, the matching results of multiple map vector fragments are filtered using preset servers and algorithms to determine the matching groups that meet the preset similarity requirements, and matching rules are bound to eliminate erroneous matching results, thereby improving the accuracy of the matching results.
Without human intervention, incorrect matching results can be quickly filtered out, improving the accuracy of map vector fragment matching results and thus enhancing vehicle positioning accuracy.
Smart Images
Figure CN115422312B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image processing, and in particular to a data processing method, apparatus, and electronic device. Background Technology
[0002] High-precision maps are electronic maps with higher accuracy and more data dimensions. Higher accuracy is reflected in their centimeter-level precision, while more data dimensions are reflected in their inclusion of traffic-related static information beyond road details. As a key component in achieving autonomous driving, high-precision maps can effectively supplement existing sensors, providing vehicles with more reliable perception capabilities. Therefore, accurately constructing high-precision maps is essential.
[0003] Current methods for constructing high-precision maps generally involve collecting environmental information about the vehicle's surroundings, such as road and building information, from which the necessary map information for building the high-precision map is extracted. This map information extraction process requires matching multiple map vector fragments collected by the vehicle.
[0004] During map vector fragment matching, issues such as sensor misidentification can lead to erroneous matching information between two matched map vector fragments, such as incorrect vehicle pose matching or lane line matching. These erroneous matching results affect the accuracy of the map vector fragment matching, thus impacting vehicle positioning precision. Therefore, further processing of each matching result corresponding to a map vector fragment is necessary to improve the accuracy of the map matching outcome. Currently, processing map vector fragment matching results is generally done manually, which incurs high labor and time costs. Summary of the Invention
[0005] This application discloses a data processing method, apparatus, and electronic device. Based on the above data processing method, a filtering model corresponding to the matching results can be obtained without human intervention. This can quickly filter out erroneous matching results in each matching result, thereby improving the accuracy of map vector fragment matching results and helping to improve vehicle positioning accuracy.
[0006] In a first aspect, this application provides a data processing method, the method comprising:
[0007] Obtain the matching results of each target object among multiple map vector fragments, wherein the target object is the element information required to build a high-precision map;
[0008] Pair the matching rules corresponding to each matching result into pairs to obtain each pairing group;
[0009] Each target pairing group is identified from all the pairing groups, and the matching rules corresponding to each target pairing group are bound together, wherein the similarity value between each matching rule corresponding to the target pairing group meets the preset requirements;
[0010] Among all the matching rules, identify the target matching rules that are bound to each other in pairs, and determine the matching results corresponding to each target matching rule as the correct matching results.
[0011] By using the above method, the matching rules corresponding to each matching result are matched again to determine the correct matching result among each matching result, thereby optimizing and filtering each matching result and improving the accuracy of the matching result.
[0012] In one possible design, obtaining the matching results of each target object among multiple map vector fragments includes:
[0013] Acquire environmental information about the vehicle's surroundings, wherein the environmental information includes at least road information;
[0014] Calculate the first map vector fragment corresponding to the environmental information, and upload the first map vector fragment to a preset server;
[0015] The preset server obtains second map vector fragments corresponding to N vehicles on the same road segment, where N is an integer greater than or equal to 2;
[0016] Match the target objects among the N second map vector segments to obtain the matching results for each target object.
[0017] Using the above method, preliminary matching results can be obtained for multiple map vector segments.
[0018] In one possible design, determining each target pairing group among all pairing groups includes:
[0019] Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group;
[0020] Based on the first matching rule, calculate the reference rule corresponding to the second matching rule;
[0021] When the similarity value between the reference rule and the second matching rule is greater than a preset threshold, it is determined that the similarity value between the first matching rule and the second matching rule meets the preset requirement;
[0022] When the similarity value between the first matching rule and the second matching rule meets the preset requirement, the first pairing group is determined to be the target pairing group.
[0023] Using the above method, target pairings whose similarity values between matching rules meet preset requirements can be selected from each pairing group.
[0024] In one possible design, after determining the matching results corresponding to each target matching rule as the correct matching result, the following is also included:
[0025] Filter out all matching results except for the correct match;
[0026] Treat any matching result other than the correct match as an incorrect match.
[0027] The incorrect matches are removed from all the matching results to obtain the final matching result.
[0028] By using the above method, incorrect matches can be removed from all matching results, thus improving the accuracy of the matching results.
[0029] Secondly, this application provides a data processing apparatus, the apparatus comprising:
[0030] The acquisition module is used to acquire the matching results of each target object among multiple map vector fragments, wherein the target object is the element information required to build a high-precision map;
[0031] The matching module is used to pair the matching rules corresponding to each matching result to obtain each pairing group;
[0032] The binding module is used to identify each target pairing group in all pairing groups and bind the matching rules corresponding to each target pairing group to each other, wherein the similarity value between each matching rule corresponding to the target pairing group meets the preset requirements.
[0033] The determination module is used to identify each pair of target matching rules among all matching rules, and to determine the matching results corresponding to each target matching rule as the correct matching results.
[0034] In one possible design, the acquisition module is specifically used for:
[0035] Acquire environmental information about the vehicle's surroundings, wherein the environmental information includes at least road information;
[0036] Calculate the first map vector fragment corresponding to the environmental information, and upload the first map vector fragment to a preset server;
[0037] The preset server obtains second map vector fragments corresponding to N vehicles on the same road segment, where N is an integer greater than or equal to 2;
[0038] Match the target objects among the N second map vector segments to obtain the matching results for each target object.
[0039] In one possible design, the binding module is specifically used for:
[0040] Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group;
[0041] Based on the first matching rule, calculate the reference rule corresponding to the second matching rule;
[0042] When the similarity value between the reference rule and the second matching rule is greater than a preset threshold, it is determined that the similarity value between the first matching rule and the second matching rule meets the preset requirement;
[0043] When the similarity value between the first matching rule and the second matching rule meets the preset requirement, the first pairing group is determined to be the target pairing group.
[0044] In one possible design, the device further includes:
[0045] The filtering module is used to filter out all matching results except for the correct matching results; and to treat the matching results other than the correct matching results as incorrect matching results.
[0046] The elimination module is used to remove the erroneous matching results from all matching results to obtain the final matching result.
[0047] Thirdly, this application provides an electronic device, comprising:
[0048] Memory, used to store computer programs;
[0049] When a processor executes a computer program stored in the memory, it implements the above-described data processing method steps.
[0050] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described data processing method steps.
[0051] Based on the above data processing method, without human intervention, the filtering model corresponding to the matching results can be obtained, which can quickly filter out the erroneous matching results in each matching result, thereby improving the accuracy of map vector fragment matching results and helping to improve vehicle positioning accuracy.
[0052] The technical effects of each of the second to fourth aspects mentioned above, as well as the technical effects that each aspect may achieve, are described above with reference to the technical effects that can be achieved for the first aspect or the various possible solutions in the first aspect, and will not be repeated here. Attached Figure Description
[0053] Figure 1 A flowchart of a data processing method provided in this application;
[0054] Figure 2 A schematic diagram illustrating a map vector fragment matching process provided in this application;
[0055] Figure 3 This application provides a schematic diagram of a map vector segment matching result;
[0056] Figure 4 A schematic diagram of a marker point provided in this application;
[0057] Figure 5 This application provides a schematic diagram of a marker binding result;
[0058] Figure 6 A schematic diagram of an optimized map vector fragment matching result provided in this application;
[0059] Figure 7 A schematic diagram of the structure of a data processing device provided in this application;
[0060] Figure 8 This is a schematic diagram of an electronic device structure provided in this application. Detailed Implementation
[0061] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The specific operational methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that in the description of this application, "multiple" is understood as "at least two". "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. A connected to B can represent: A and B directly connected, and A and B connected through C. Furthermore, in the description of this application, terms such as "first" and "second" are used only for distinguishing the purpose of description and should not be construed as indicating or implying relative importance or order.
[0062] The embodiments of this application will now be described in detail with reference to the accompanying drawings.
[0063] Current methods for constructing high-precision maps generally involve collecting environmental information about the vehicle's surroundings, such as road and building information, from which the necessary map information for building the high-precision map is extracted. This map information extraction process requires matching multiple map vector fragments collected by the vehicle.
[0064] During map vector fragment matching, issues such as sensor misidentification can lead to erroneous matching information between two matched map vector fragments, such as incorrect vehicle pose matching or lane line matching. These erroneous matching results affect the accuracy of the map vector fragment matching, thus impacting vehicle positioning precision. Therefore, further processing of each matching result corresponding to a map vector fragment is necessary to improve the accuracy of the map matching outcome. Currently, processing map vector fragment matching results is generally done manually, which incurs high labor and time costs.
[0065] To address the aforementioned problems, this application provides a data processing method. This method re-matches the matching rules corresponding to each matching result, thereby identifying the correct matching result from among the various matching results. This optimizes and filters the matching results, improving their accuracy. The methods and apparatus described in this application are based on the same technical concept. Since the principles by which the methods and apparatus solve the problems are similar, embodiments of the apparatus and methods can be referred to interchangeably, and repeated details will not be elaborated further.
[0066] like Figure 1 The diagram shown is a flowchart of a data processing method provided in this application, which specifically includes the following steps:
[0067] S11, obtain the matching results of each target object among multiple map vector segments;
[0068] In this embodiment, the target object is the element information required to build a high-precision map. The matching results between target objects include at least the matching results between trajectories and the matching results between vehicle poses. The method for obtaining each matching result may be:
[0069] First, vehicle-mounted sensors such as Global Positioning System (GPS), Light Detection and Ranging (LiDAR), Camera, and Inertial Measurement Unit (IMU) are used to acquire information about the vehicle's surrounding environment. This environmental information includes at least road information, such as lane lines, boundary lines, and traffic intersections, and may also include building information and traffic sign information.
[0070] Then, a preset algorithm is used to extract target objects needed to construct a high-precision map from the environmental information, such as trajectories and vehicle poses, thereby obtaining the first map vector fragment corresponding to the environmental information. The preset algorithm can be a Simultaneous Localization and Mapping (SLAM) algorithm. Furthermore, the first map vector fragment is uploaded to a preset server, such as a cloud server with highly distributed and virtualized characteristics, where the map vector fragments corresponding to each vehicle are stored.
[0071] Furthermore, N second map vector segments corresponding to the same road segment for N vehicles are obtained from a preset server, where N is an integer greater than or equal to 2. Then, using the Iterative Closest Point (ICP) algorithm and the absolute pose corresponding to the odometry coordinates (odom), the target objects among the N second map vector segments are matched to obtain the matching results for each target object.
[0072] For example, such as Figure 2 The image shown is a schematic diagram of a map vector fragment matching process provided in this application. Figure 2Vector fragment 1 and vector fragment 2 are map vector fragments corresponding to different vehicles on the same road segment, obtained from the cloud server. Each vector fragment contains vehicle trajectory information and lane line information. During the matching process, the trajectory in vector fragment 1 is matched with the trajectory in vector fragment 2, and the lane line in vector fragment 1 is matched with the lane line in vector fragment 2. At this time, the trajectory and lane line are the target objects for matching, and thus the matching results corresponding to each target object are obtained.
[0073] S12, pair the matching rules corresponding to each matching result in pairs to obtain each pairing group;
[0074] After obtaining each matching result, the matching rules corresponding to each matching result are further paired up. For example, such as Figure 3 As shown, Figure 3 It contains map vector fragment a and map vector fragment b, each containing trajectory information. Figure 3 Each object connected by a double arrow represents a matching result in the trajectory information matching process. Figure 3 It contains 7 matching results: Matching result 1: object a1 matches object b1; Matching result 2: object b1 matches object a3; Matching result 3: object a2 matches object b2; Matching result 4: object a4 matches object b3; Matching result 5: object b3 matches object a5; Matching result 6: object b4 matches a5; Matching result 7: object a4 matches object b5.
[0075] Each of the above matching results corresponds to a matching rule. Now, the seven matching results are paired up to obtain the following pairing groups: (matching result 1, matching result 2), (matching result 1, matching result 3), ..., (matching result 1, matching result 7); (matching result 2, matching result 3), (matching result 2, matching result 4), ..., (matching result 2, matching result 7); (matching result 3, matching result 4), (matching result 3, matching result 5), ..., (matching result 3, matching result 7); (matching result 4, matching result 5), (matching result 4, matching result 6), (matching result 4, matching result 7); (matching result 5, matching result 6), (matching result 5, matching result 7); (matching result 6, matching result 7).
[0076] S13, identify each target pairing group from all pairing groups, and bind the matching rules corresponding to each target pairing group to each other;
[0077] In this embodiment of the application, after obtaining the matching groups corresponding to each matching rule, the matching groups that satisfy each target matching group are further determined, wherein the similarity values between the matching rules corresponding to the target matching groups meet preset requirements. Specifically:
[0078] Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group. Then, combine the trajectory information between the pairing results in each first pairing group and the first matching rule to calculate the reference rule corresponding to the second matching rule. The reference rule is not a matching rule that actually exists between the matching results, but a kind of inference result.
[0079] For example, you can refer to Figure 3 , Figure 3 It contains map vector fragment a and map vector fragment b, each containing trajectory information. Figure 3 Each double-arrow connecting an object represents a matching result in the trajectory information matching process. If the first pairing is (matching result 1, matching result 3), the matching rule 1 corresponding to matching result 1 is A = B. At the same time, through the trajectory information corresponding to trajectory a, we know that the matching rule 2 between object a1 and object a2 is B = C. Through the trajectory information corresponding to trajectory b, we know that the matching rule 3 between object b1 and object b2 is D = A. Then, from matching rule 1, matching rule 2, and matching rule 3, we can calculate that the reference rule corresponding to matching result 2 is C = D.
[0080] Furthermore, the similarity value between the reference rule and the second matching rule is calculated. When the similarity value between the reference rule and the second matching rule is greater than a preset threshold, it is determined that the similarity value between the first matching rule and the second matching rule meets the preset requirements, and the first pairing group is determined as the target pairing group.
[0081] For example, refer to Figure 3 If the first pairing group is (matching result 1, matching result 3), the matching rule 1 corresponding to matching result 1 is A = B. Simultaneously, based on the trajectory information corresponding to trajectory a, the matching rule 2 between object a1 and object a2 is B = C. Based on the trajectory information corresponding to trajectory b, the matching rule 3 between object b1 and object b2 is D = A. Then, from matching rule 1, matching rule 2, and matching rule 3, the reference rule corresponding to matching result 2 can be calculated as C = D. If the second matching rule corresponding to matching result 2 is C = D, then it can be determined that the similarity value between the reference rule and the second matching rule meets the preset requirements. At this point, the first pairing group is determined as the target pairing group.
[0082] Similarly, if the first pairing group is (matching result 2, matching result 3), the matching rule 1 corresponding to matching result 2 is A = C. Simultaneously, based on the trajectory information corresponding to trajectory a, the matching rule 2 between object a2 and object a3 is B = C. Based on the trajectory information corresponding to trajectory b, the matching rule 3 between object b1 and object b2 is D = A. Therefore, from matching rule 1, matching rule 2, and matching rule 3, the reference rule corresponding to matching result 2 can be calculated as B = D. If the second matching rule corresponding to matching result 2 is E = D, then it can be determined that the similarity value between the reference rule and the second matching rule does not meet the preset requirements. In this case, the first pairing group is determined to be a non-target pairing group.
[0083] Using the above method, each target pairing group can be identified in each pairing group. After obtaining each target pairing group, the matching rules corresponding to each target pairing group are bound together.
[0084] For example, if (match result 1, match result 2) and (match result 1, match result 3) are target pairs, then the matching rule corresponding to match result 1 will be bound to the matching rule corresponding to match result 2, and the matching rule corresponding to match result 1 will also be bound to the matching rule corresponding to match result 2.
[0085] S14: Determine the target matching rules that are bound to each other in all the matching rules, and determine the matching results corresponding to each target matching rule as the correct matching results.
[0086] In this embodiment, after binding the matching rules corresponding to each target pairing group to each other, the target matching rules that are bound to each other in pairs are determined from all the matching rules, and the matching results corresponding to each target matching rule are determined as correct matching results. At the same time, the matching results other than the correct matching results are filtered out from all the matching results and are regarded as incorrect matching results; then, all incorrect matching results are removed from all the matching results to obtain the final matching result. The specific application scenarios of the results are described below.
[0087] Specifically, Figure 3 Each matching result is converted into a marker point, where the marker point represents the matching rule corresponding to the matching result, and can be represented by characters or numbers. Figure 4 To be Figure 3 The matching results are converted into a schematic diagram after marking points. Figure 4 In the middle, marker 1 is Figure 3 The marker point corresponding to matching result 1 is shown in the figure. Similarly, marker points 2 to 7 are the marker points corresponding to matching results 2 to 7, respectively.
[0088] like Figure 3 The target pairings are: (matching result 1, matching result 2), (matching result 1, matching result 3), (matching result 1, matching result 1), (matching result 1, matching result 6), (matching result 3, matching result 4), (matching result 3, matching result 6), (matching result 4, matching result 6), (matching result 5, matching result 6), (matching result 5, matching result 7). After binding the markers corresponding to each matching result, the binding example diagram is as follows. Figure 5 As shown.
[0089] Depend on Figure 5 It can be seen that markers 1, 3, 4, and 6 are interconnected pairwise. That is, the matching rules corresponding to markers 1, 3, 4, and 6 are mutually bound. Therefore, it can be determined that matching results 1, 3, 4, and 6 are correct matches, while matching results 2, 5, and 7 are incorrect matches. Furthermore, [the text continues...] Figure 3 After deleting incorrect matches, the resulting matching results can be referenced. Figure 6 .
[0090] Based on the above data processing method, without human intervention, the filtering model corresponding to the matching results can be obtained, which can quickly filter out the erroneous matching results in each matching result, thereby improving the accuracy of map vector fragment matching results and helping to improve vehicle positioning accuracy.
[0091] Based on the same inventive concept, this application also provides a data processing device, such as... Figure 7 The diagram shown is a structural schematic of a data processing apparatus according to this application. The apparatus includes:
[0092] The acquisition module 71 is used to acquire the matching results of each target object among multiple map vector segments, wherein the target object is the element information required to build a high-precision map;
[0093] Matching module 72 is used to pair the matching rules corresponding to each matching result to obtain each pairing group;
[0094] The binding module 73 is used to determine each target pairing group in all pairing groups and bind the matching rules corresponding to each target pairing group to each other, wherein the similarity value between each matching rule corresponding to the target pairing group meets the preset requirements.
[0095] The determination module 74 is used to determine each target matching rule that is bound to each other in all matching rules, and to determine the matching result corresponding to each target matching rule as the correct matching result.
[0096] In one possible design, the acquisition module 71 is specifically used for:
[0097] Acquire environmental information about the vehicle's surroundings, wherein the environmental information includes at least road information;
[0098] Calculate the first map vector fragment corresponding to the environmental information, and upload the first map vector fragment to a preset server;
[0099] The preset server obtains second map vector fragments corresponding to N vehicles on the same road segment, where N is an integer greater than or equal to 2;
[0100] Match the target objects among the N second map vector segments to obtain the matching results for each target object.
[0101] In one possible design, the binding module 73 is specifically used for:
[0102] Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group;
[0103] Based on the first matching rule, calculate the reference rule corresponding to the second matching rule;
[0104] When the similarity value between the reference rule and the second matching rule is greater than a preset threshold, it is determined that the similarity value between the first matching rule and the second matching rule meets the preset requirement;
[0105] When the similarity value between the first matching rule and the second matching rule meets the preset requirement, the first pairing group is determined to be the target pairing group.
[0106] In one possible design, the device further includes:
[0107] The filtering module is used to filter out all matching results except for the correct matching results; and to treat the matching results other than the correct matching results as incorrect matching results.
[0108] The elimination module is used to remove the erroneous matching results from all matching results to obtain the final matching result.
[0109] Based on the aforementioned data processing device, without human intervention, the filtering model corresponding to the matching results can be obtained, which can quickly filter out erroneous matching results in each matching result, thereby improving the accuracy of map vector fragment matching results and helping to improve vehicle positioning accuracy.
[0110] Based on the same inventive concept, this application also provides an electronic device that can realize the functions of the aforementioned data processing method apparatus. (Refer to...) Figure 8 The electronic device includes:
[0111] At least one processor 81 and a memory 82 connected to the at least one processor 81. In this embodiment, the specific connection medium between the processor 81 and the memory 82 is not limited. Figure 8 The example shown is the connection between processor 81 and memory 82 via bus 80. Bus 80 is... Figure 8 The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. Bus 80 can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 8 The term is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, the processor 81 can also be called a controller; there is no restriction on the name.
[0112] In this embodiment, memory 82 stores instructions executable by at least one processor 81. By executing the instructions stored in memory 82, at least one processor 81 can perform the data processing method described above. Processor 81 can implement... Figure 7 The functions of each module in the device shown.
[0113] The processor 81 is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 82 and calling data stored in memory 82, the processor can perform various functions and process data, thereby monitoring the device as a whole.
[0114] In one possible design, processor 81 may include one or more processing units. Processor 81 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 81. In some embodiments, processor 81 and memory 82 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.
[0115] Processor 81 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the data processing method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.
[0116] Memory 82, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 82 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 82 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 82 may also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.
[0117] By designing and programming the processor 81, the code corresponding to the data processing methods described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute these methods during operation. Figure 1 The steps of the data processing method in the illustrated embodiment are as follows. How to design and program the processor 81 is a technique well-known to those skilled in the art and will not be described further here.
[0118] Based on the same inventive concept, embodiments of this application also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the data processing method described above.
[0119] In some possible implementations, various aspects of the data processing method provided in this application may also be implemented as a program product comprising program code that, when the program product is run on a device, causes the control device to perform the steps of the data processing method according to the various exemplary embodiments of this application described above.
[0120] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0121] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0122] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0123] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0124] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A data processing method, characterized in that, The method includes: Obtain the matching results of each target object among multiple map vector fragments, wherein the target object is the element information required to build a high-precision map; Pair the matching rules corresponding to each matching result into pairs to obtain each pairing group; Each target pairing group is identified from all pairing groups, and the matching rules corresponding to each target pairing group are bound together. The similarity value between the matching rules corresponding to each target pairing group meets a preset requirement. This preset requirement is met when the similarity value between the second matching rule corresponding to the target pairing group and the reference rule corresponding to the second matching rule is greater than a preset threshold. The reference rule is calculated based on the first matching rule corresponding to the target pairing group. Among all the matching rules, identify the target matching rules that are bound to each other in pairs, and determine the matching results corresponding to each target matching rule as the correct matching results.
2. The method as described in claim 1, characterized in that, The step of obtaining the matching results of each target object among multiple map vector fragments includes: Acquire environmental information about the vehicle's surroundings, wherein the environmental information includes at least road information; Calculate the first map vector fragment corresponding to the environmental information, and upload the first map vector fragment to a preset server; The preset server obtains second map vector fragments corresponding to N vehicles on the same road segment, where N is an integer greater than or equal to 2; Match the target objects among the N second map vector segments to obtain the matching results for each target object.
3. The method as described in claim 1, characterized in that, The process of identifying each target pairing group among all pairing groups includes: Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group; The target pairing group is determined based on the first matching rule corresponding to the first pairing group and the second matching rule corresponding to the first pairing group.
4. The method as described in claim 1, characterized in that, After determining the matching results corresponding to each target matching rule as the correct matching results, the process further includes: Filter out all matching results except for the correct match; Treat any matching result other than the correct match as an incorrect match. The incorrect matches are removed from all the matching results to obtain the final matching result.
5. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire the matching results of each target object among multiple map vector fragments, wherein the target object is the element information required to build a high-precision map; The matching module is used to pair the matching rules corresponding to each matching result to obtain each pairing group; A binding module is used to identify each target pairing group from all pairing groups and bind the matching rules corresponding to each target pairing group to each other. The similarity value between the matching rules corresponding to each target pairing group meets a preset requirement. The preset requirement is that the similarity value between the second matching rule corresponding to the target pairing group and the reference rule corresponding to the second matching rule is greater than a preset threshold. The reference rule is calculated based on the first matching rule corresponding to the target pairing group. The determination module is used to identify each pair of target matching rules among all matching rules, and to determine the matching results corresponding to each target matching rule as the correct matching results.
6. The apparatus as claimed in claim 5, characterized in that, The acquisition module is specifically used for: Acquire environmental information about the vehicle's surroundings, wherein the environmental information includes at least road information; Calculate the first map vector fragment corresponding to the environmental information, and upload the first map vector fragment to a preset server; The preset server obtains second map vector fragments corresponding to N vehicles on the same road segment, where N is an integer greater than or equal to 2; Match the target objects among the N second map vector segments to obtain the matching results for each target object.
7. The apparatus as claimed in claim 5, characterized in that, The binding module is specifically used for: Select the first pairing group from all the pairing groups, and determine the first matching rule and the second matching rule corresponding to the first pairing group; The target pairing group is determined based on the first matching rule corresponding to the first pairing group and the second matching rule corresponding to the first pairing group.
8. The apparatus as claimed in claim 5, characterized in that, The device further includes: The filtering module is used to filter out all matching results except for the correct matching results; and to treat the matching results other than the correct matching results as incorrect matching results. The elimination module is used to remove the erroneous matching results from all matching results to obtain the final matching result.
9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a computer program stored in the memory, implements the method steps of any one of claims 1-4.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method steps of any one of claims 1-4.