Point cloud data matching method and device, electronic equipment and computer readable medium

Abstract

The application relates to a point cloud data matching method and device, electronic equipment and a computer readable medium. The method comprises the following steps: acquiring a vehicle position and a target position; acquiring road surface data corresponding to the vehicle according to the vehicle position; determining a query lane line corresponding to the target and a vehicle driving direction corresponding to the vehicle in the road surface data according to the distance relationship between the vehicle position and the target position; acquiring a query lane area range according to the vehicle position, the query lane line and the vehicle driving direction; calculating an intersection range of the query lane area range and a preset target area range of the target position; and outputting query point cloud data corresponding to the intersection range. The scheme provided by the application can quickly find point cloud data with higher correlation with a target object, realize data noise reduction, reduce data processing amount, and improve computing efficiency.

Description

Technical Field

[0001] This application relates to the field of high-precision mapping technology, and in particular to point cloud data matching methods, apparatus, electronic devices and computer-readable media. Background Technology

[0002] LiDAR point cloud data is a dataset of spatial points obtained by scanning with a 3D LiDAR device. Each point contains 3D coordinate information, commonly referred to as X, Y, and Z elements, and some also include color information, reflection intensity information, and echo count information. LiDAR point cloud data is obtained by an onboard laser scanning system emitting laser signals into its surroundings and then collecting the reflected laser signals. Through field data acquisition, integrated navigation, and point cloud computation, the accurate spatial information of these points can be calculated. The application of 3D point clouds in the field of autonomous driving can be divided into the following two aspects:

[0003] Real-time environmental perception and processing based on scene understanding and target detection;

[0004] Generation and construction of high-precision maps and city models based on reliable positioning and reference.

[0005] In the process of processing and producing visually acquired data, it is common to use matched point cloud data to correct the accuracy of related data in high-precision maps, so as to make the produced data more accurate.

[0006] In related technologies, point cloud data is generally matched by topological relationships. However, the above method of matching point cloud data is prone to matching point cloud data with low relevance to the current scene, resulting in a lot of invalid calculations, increasing the amount of computation in the subsequent data fusion process, and affecting the efficiency of the overall data processing flow. Summary of the Invention

[0007] To address or partially address the problems existing in related technologies, this application provides a point cloud data matching method, apparatus, electronic device, and computer-readable medium, which can quickly find point cloud data with higher relevance to the target object, achieve data noise reduction, reduce data processing volume, and improve computational efficiency.

[0008] The first aspect of this application provides a point cloud data matching method, including:

[0009] Obtain the vehicle location and target location;

[0010] Obtain the road surface data corresponding to the vehicle based on the vehicle's location;

[0011] Based on the distance relationship between the vehicle position and the target position, determine the query lane line corresponding to the target and the vehicle driving direction corresponding to the vehicle in the road surface data;

[0012] Based on the vehicle location, the lane lines, and the vehicle's direction of travel, the range of the query lane area is obtained;

[0013] Calculate the intersection range of the query lane area range and the preset target area range of the target location;

[0014] Output the query point cloud data corresponding to the intersection range.

[0015] In some embodiments, before obtaining the road surface data corresponding to the vehicle based on the vehicle location, the method further includes:

[0016] Query the lane line data within a preset area surrounding the target location;

[0017] The step of obtaining road surface data corresponding to the vehicle based on the vehicle's location includes:

[0018] Based on the vehicle's location, obtain the road surface data corresponding to the vehicle from the lane line data within the preset surrounding area.

[0019] In some embodiments, the preset surrounding range is obtained in the following manner:

[0020] Based on the distance relationship between the target location and the vehicle location, a preset surrounding range is obtained.

[0021] In some embodiments, obtaining a preset surrounding range based on the distance relationship between the target location and the vehicle location includes:

[0022] Based on the condition that the distance between the target location and the vehicle location is less than or equal to a preset distance threshold, the preset distance threshold is defined as a preset surrounding radius; or

[0023] The distance between the target location and the vehicle location is defined as the preset surrounding radius based on the fact that the distance between the target location and the vehicle location is greater than a preset distance threshold.

[0024] In some embodiments, the method further includes:

[0025] The acquired road surface data is subjected to data filtering processing;

[0026] The data objects undergoing the data filtering process include at least: lane line data for U-turn lanes, lane line data for reverse lanes, and lane line data for auxiliary lanes.

[0027] In some embodiments, determining the query lane line corresponding to the target and the vehicle's driving direction in the road surface data based on the distance relationship between the vehicle's position and the target position includes:

[0028] Based on the vehicle's location, determine the driving lane data corresponding to the vehicle in the road surface data;

[0029] Based on the driving lane data, obtain the lane line closest to the target position in the lane where the vehicle is located and the corresponding driving direction of the vehicle, and define the lane line closest to the target position in the lane where the vehicle is located as the query lane line.

[0030] In some embodiments, the preset target area range is set according to the identifiable distance of the target.

[0031] A second aspect of this application provides a point cloud data matching device, comprising:

[0032] The positioning module is used to obtain the vehicle's location and the target's location;

[0033] The data acquisition module is used to acquire road surface data corresponding to the vehicle based on the vehicle's location;

[0034] The data determination module is used to determine the query lane line corresponding to the target and the vehicle driving direction corresponding to the vehicle in the road surface data, based on the vehicle position and the target position.

[0035] The query area range module is used to obtain the query lane area range based on the vehicle location, the query lane line, and the vehicle's driving direction.

[0036] The calculation module is used to calculate the intersection range of the query lane area range and the preset target area range of the target location;

[0037] The output module is used to output the query point cloud data corresponding to the intersection range.

[0038] A third aspect of this application provides an electronic device, comprising:

[0039] Processor; and

[0040] A memory that stores executable code, which, when executed by the processor, causes the processor to perform the method described above.

[0041] A fourth aspect of this application provides a computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method described above.

[0042] The technical solution provided in this application may include the following beneficial effects:

[0043] The technical solution of this application determines the query lane line and vehicle driving direction from the road surface data corresponding to the vehicle by the distance relationship between the vehicle position and the target position. The query lane area range is calculated by the vehicle position, query lane line and vehicle driving direction. The query point cloud data is obtained by using the intersection of the query lane area range and the preset target area range. This enables the rapid search of point cloud data with higher relevance to the target object, reduces noise data, reduces data processing volume and improves computing efficiency.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0045] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.

[0046] Figure 1 This is a flowchart illustrating the point cloud data matching method in an embodiment of this application;

[0047] Figure 2 This is another schematic flowchart illustrating the point cloud data matching method in an embodiment of this application;

[0048] Figure 3 This is a schematic diagram of the structure of the point cloud data matching device shown in the embodiments of this application;

[0049] Figure 4 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation

[0050] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make this application more thorough and complete, and to fully convey the scope of this application to those skilled in the art.

[0051] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0052] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0053] In related technologies, point cloud data is typically matched using topological relationships. However, this matching process can easily result in point cloud data with low relevance to the current scene, leading to a lot of invalid computation and increasing the complexity of subsequent data fusion.

[0054] To address the aforementioned issues, this application provides a point cloud data matching method that can quickly find point cloud data with higher relevance to the target object, thereby achieving data noise reduction, reducing data processing volume, and improving computational efficiency.

[0055] The point cloud data matching method of this application is mainly used in the process of high-precision map production, during the fusion and matching of visually acquired data and point clouds, to accurately locate the point cloud data of the road where the relevant visual image is located. The requesting end of the point cloud data matching process can be initiated by the local end or the server. After querying the corresponding target point cloud data using the point cloud data matching method of this application, the corresponding target point cloud data is returned or output to the requesting end.

[0056] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0057] Figure 1 This is a flowchart illustrating the point cloud data matching method in an embodiment of this application.

[0058] See Figure 1 The point cloud data matching method of this application includes:

[0059] S110, obtain the vehicle location and target location.

[0060] Vehicle location can be obtained using an onboard positioning device, such as a GPS (Global Positioning System) module. Specifically, the vehicle location can be obtained through the onboard positioning device to determine the vehicle's current GPS position. The target location can be the position of a landmark during image processing. Specifically, landmarks can include, but are not limited to, road signs, traffic lights, and road markings. It should be understood that the target location can be any location on the road in the map. For example, if the landmark corresponding to the target is a road sign, the target location is outside the lane; conversely, if the landmark corresponding to the target is a traffic light, the target location is inside the lane. The target location can be obtained after image recognition and localization of landmarks in the visual image.

[0061] S120 obtains road surface data corresponding to the vehicle based on the vehicle's location.

[0062] Obtain road surface data corresponding to the vehicle's current location. It should be understood that road surface data refers to point cloud data of the current road surface area corresponding to the vehicle's location. Specifically, the road surface can be the drivable area composed of all lanes traveling in the same direction connected to the left and right sides of the vehicle's location.

[0063] S130, based on the vehicle position and the target position, determine the query lane line corresponding to the target and the vehicle's driving direction in the road surface data.

[0064] By comparing the vehicle's location with the target's location, the query lane line corresponding to the target and the vehicle's travel direction are determined from the acquired road surface data. The query lane line refers to the lane line corresponding to the point cloud data with the highest correlation to the target location. The vehicle's travel direction is determined based on the lane direction corresponding to the vehicle's location.

[0065] Before obtaining the road surface data corresponding to the vehicle, it is also possible to query the lane line data of the preset surrounding area of ​​the target location; and obtain the road surface data corresponding to the vehicle from the lane line data of the preset area according to the vehicle location.

[0066] S140: Based on the vehicle location, the lane line to be queried, and the vehicle's direction of travel, obtain the range of the lane area to be queried.

[0067] Based on the vehicle's location, the lane lines, and the vehicle's direction of travel, obtain the range of lane areas heading towards the target location.

[0068] S150, calculate the intersection range between the query lane area range and the preset target area range of the target location.

[0069] The query lane area range corresponds to the distribution range of point cloud data in the road surface data that is associated with the target location. The preset target area range is the range of point cloud data centered on the target location, queried according to actual needs. By calculating the intersection range of the lane area range and the preset target area range of the target location, the point cloud data within the intersection range is the point cloud data with a high correlation to the target location.

[0070] S160 outputs the query point cloud data corresponding to the intersection range.

[0071] The query point cloud data corresponding to the intersection range is obtained through calculation, and the query point cloud data is output. The output process can include returning the query results to the query initiator.

[0072] In this embodiment, the point cloud data matching method of this application determines the query lane line and vehicle driving direction from the road surface data corresponding to the vehicle by using the vehicle position and target position. The query lane area range is calculated by using the vehicle position, query lane line and vehicle driving direction. The query point cloud data is obtained by using the intersection of the query lane area range and the preset target area range. This enables the rapid search for point cloud data with higher relevance to the target object, reduces noise data, reduces data processing volume, and improves computational efficiency.

[0073] Figure 2 This is another schematic diagram of the point cloud data matching method shown in the embodiments of this application.

[0074] See Figure 2 The point cloud data matching method of this application includes:

[0075] S210, obtain the vehicle location and target location based on the query request.

[0076] The query request can be initiated by the server or a local client. Upon receiving the query request, the vehicle location and target location are obtained. The vehicle location can be obtained using an onboard positioning device. The target location can be obtained by image recognition and localization of landmarks in the visual image.

[0077] Both the vehicle position and the target position can include coordinate parameters.

[0078] S220: Query lane line data within a preset area surrounding the target location.

[0079] The system queries the database for lane line data within a preset surrounding area of ​​the target location. This lane line data is used for point cloud data matching in the method described in this application.

[0080] It should be understood that lane line data consists of multiple lane lines, each of which is composed of a continuous point cloud, where the point cloud is directional coordinate data. The lane line data within the preset perimeter of the target location can correspond to the lane line data of the drivable area within that preset perimeter.

[0081] This initial screening of lane line data ensures a stable range of values ​​for subsequent point cloud data matching, reduces interference from point cloud data from other ranges, and improves the stability of the matching process.

[0082] In some embodiments, the preset surrounding range is obtained as follows: the preset surrounding range is obtained based on the distance relationship between the target location and the vehicle location. The distance relationship between the target location and the vehicle location corresponds to the distance between the sign and the vehicle, and the preset surrounding range is set based on the distance between the two. However, when the distance between the vehicle and the sign is too large, the sign appears small in the acquired visual image. Increasing the search range beyond the distance between the sign and the vehicle can easily increase interference data.

[0083] In some embodiments, the preset distance threshold can be defined as the preset surrounding radius based on the distance between the target location and the vehicle location being less than or equal to a preset distance threshold; or the distance between the target location and the vehicle location can be defined as the preset surrounding radius based on the distance between the target location and the vehicle location being greater than the preset distance threshold.

[0084] The distance between the target location and the vehicle location is compared with a preset distance threshold. A preset perimeter radius is defined based on the comparison result. If the distance between the target location and the vehicle location is less than or equal to the preset distance threshold, it indicates that the distance between them is small or within a reasonable range, and the preset perimeter radius is defined according to the preset distance threshold. This ensures that the lane line data has a sufficient range of values. If the distance between the target location and the vehicle location is greater than the preset distance threshold, it indicates that the distance between them is large, and the preset perimeter radius is defined according to the distance between them. This reduces irrelevant lane line data, lowers computational load, and reduces noise interference. Using this method to define the preset perimeter radius allows for different methods to define the data value range based on different distances between the target location and the vehicle location, thus ensuring the stability of the data value range.

[0085] S230 retrieves the road surface data corresponding to the vehicle from the lane line data within a preset surrounding area based on the vehicle's location.

[0086] The system obtains road surface data corresponding to the vehicle based on the vehicle's location, starting from lane line data within a preset surrounding area. This road surface data refers to the drivable area comprised of all lanes traveling in the same direction adjacent to the vehicle's left and right sides.

[0087] It can be understood that step S220 is equivalent to performing an initial screening from the database, and step 230 is equivalent to further filtering the point cloud data corresponding to the vehicles from the screening results of step S220. This method achieves a secondary screening of the data, thereby further reducing the amount of data used for point cloud data matching and enhancing the correlation of point cloud data among the selected data.

[0088] In some embodiments, the acquired road surface data may also undergo data filtering. Filtering refers to deleting data within a specified range or that meets filtering criteria. Further data filtering of the acquired road surface data reduces the interference of noise data on the matching process.

[0089] In some embodiments, the data objects for data filtering can include at least U-turn lane line data, reverse lane line data, and auxiliary road lane line data. Of course, the data objects for data filtering can also be other data elements with low relevance to the vehicle or target or that are unnecessary. Specifically, U-turn lane line data refers to the lane line data corresponding to the U-turn lane. U-turn lanes generally connect the vehicle's current lane to the opposite lane (reverse lane). Filtering out U-turn lane line data avoids introducing point cloud data from the reverse lane. Reverse lane line data refers to the lane line data corresponding to the lane opposite to the vehicle's current lane; the reverse lane travels in the opposite direction to the vehicle's current lane. Auxiliary road lane line data refers to the lane line data corresponding to the auxiliary road, which generally does not have markers. By filtering out the aforementioned data objects with low relevance to the vehicle or target, the amount of data to be processed during the matching process is effectively reduced, while also decreasing the possibility of mismatches caused by low-relevance data.

[0090] S240 determines the driving lane data corresponding to the vehicle in the road surface data based on the vehicle's location.

[0091] The vehicle's lane is determined based on its location, and the driving lane data for that lane is determined from the road surface data.

[0092] In some embodiments, after determining the lane where the vehicle is located, the lane line data in the road surface data undergoes connectivity and merging processing. Specifically, connectivity and merging processing refers to connecting related lane lines into a single lane line. This connectivity and merging processing can be performed on only the two lane lines corresponding to the driving lane data of the vehicle's lane, or it can be performed on all lane line data in the road surface data. This allows the point cloud data to be connected to form straight lines, facilitating subsequent calculation of the distance between the target location and the lane lines. In some embodiments, the two lane lines of the vehicle's lane can be marked.

[0093] S250: Based on the driving lane data, obtain the lane line closest to the target location and the vehicle's driving direction in the lane where the vehicle is located, and define the lane line closest to the target location in the lane where the vehicle is located as the query lane line.

[0094] The algorithm iterates through the lane data to determine the lane line closest to the target location for the vehicle's current lane. This can be understood as the lane line closest to the target location corresponding to the vehicle's direction of travel. For example, if the target location is to the left of the vehicle's direction of travel, the closest lane line will also be to the left of the vehicle. This closest lane line is defined as the query lane line. The vehicle's direction of travel is determined based on the lane direction corresponding to the vehicle's location.

[0095] S260: Based on the vehicle location, the lane line being queried, and the vehicle's direction of travel, obtain the range of the lane area to be queried.

[0096] Based on the vehicle's location, the lane lines, and the vehicle's direction of travel, obtain the range of lane areas heading towards the target location.

[0097] For example, the vehicle's location can be used as the starting cross-section to query the lane area range by extending a preset lane range in the direction of vehicle travel.

[0098] The query lane area can cover the query lane line alone, or it can cover the query lane line and the lane lines adjacent to the query lane line.

[0099] In some embodiments, the size of the query lane area can be limited by preset constraints. These preset constraints may include a length not exceeding a preset value, such as three times the distance from the target location to the perpendicular line of the query lane. The query lane area can be a rectangular area or an area matching the shape of the lane extension.

[0100] In some embodiments, the defined query lane lines can be one or two, and correspondingly, the query lane area range can also be one or two. For example, if the target location is at the center of the two lane lines of the lane corresponding to the vehicle's location, then the two lane lines closest to the target location in the vehicle's lane are defined as two query lane lines, and the corresponding query lane area range can be two. Of course, when there are two query lane lines, the same query lane area range can also be used.

[0101] S270, calculate the intersection range between the query lane area range and the preset target area range of the target location.

[0102] By calculating the intersection of the lane area and the preset target area of ​​the target location, the point cloud data within the intersection area is the point cloud data that is highly correlated with the target location.

[0103] In some embodiments, the preset target area range can be set according to the identifiable distance of the target. The target location is obtained by identifying the marker in the visual image, wherein the marker has an identifiable distance range in the visual image, that is, the range of distance values ​​within which the marker can be captured by the visual image acquisition device and has a good recognition effect. The preset target area range can be the identifiable distance of the marker. For example, if the identifiable distance of the marker is 10m, then the preset target area range can be a circular area with a radius of 10m centered on the target location.

[0104] S280 outputs the query point cloud data corresponding to the intersection range.

[0105] The query point cloud data corresponding to the intersection range is obtained based on the calculation, and the query point cloud data is output to the query request initiator.

[0106] In this embodiment, the point cloud data matching method of this application defines the data value range in different ways according to the different distances between the target location and the vehicle location, thereby ensuring the stability of the data value range. It adopts a multi-step filtering method to filter the point cloud data obtained from the database, reducing the amount of data used for point cloud data matching, and enhancing the correlation of point cloud data in the selected data, so as to match point cloud data with higher relevance to the target object, and effectively reducing noise data in the matching process, reducing data processing volume, and improving computational efficiency.

[0107] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a point cloud data matching device, electronic device, and corresponding embodiments.

[0108] Figure 3 This is a schematic diagram of the point cloud data matching device shown in the embodiments of this application.

[0109] See Figure 3 The point cloud data matching device 300 of this application includes a positioning module 310, a data acquisition module 320, a data determination module 330, a query area range module 340, a calculation module 350, and an output module 360.

[0110] The positioning module 310 is used to obtain the vehicle location and the target location.

[0111] The vehicle's location can be obtained using an onboard positioning device. The target location can be obtained by image recognition and localization of landmarks in the visual image.

[0112] The data acquisition module 320 is used to acquire road surface data corresponding to the vehicle based on the vehicle's location.

[0113] In some embodiments, the data acquisition module 320 can also be used to query lane line data within a preset surrounding range of the target location, and then the data acquisition module 320 obtains the road surface data corresponding to the vehicle from the lane line data within the preset surrounding range according to the vehicle location.

[0114] In some embodiments, the preset surrounding range of the data acquisition module 320 is obtained in the following manner: the preset surrounding range is obtained based on the distance relationship between the target location and the vehicle location.

[0115] In some embodiments, the data acquisition module 320 may define the preset distance threshold as the preset surrounding radius based on the distance between the target location and the vehicle location being less than or equal to a preset distance threshold; or define the distance between the target location and the vehicle location as the preset surrounding radius based on the distance between the target location and the vehicle location being greater than the preset distance threshold.

[0116] In some embodiments, the data acquisition module 320 can also perform data filtering on the acquired road surface data.

[0117] In some embodiments, the data objects for data filtering processing may include at least U-turn lane line data, reverse lane line data, and auxiliary road lane line data.

[0118] The data determination module 330 is used to determine the query lane line corresponding to the target and the vehicle driving direction corresponding to the vehicle in the road surface data based on the vehicle position and the target position.

[0119] In some embodiments, the data determination module 330 can be used to determine the driving lane data corresponding to the vehicle in the road surface data based on the vehicle position; obtain the lane line closest to the target position of the vehicle's lane and the vehicle's driving direction based on the driving lane data, and define the lane line closest to the target position of the vehicle's lane as the query lane line.

[0120] In some embodiments, after determining the lane where the vehicle is located, the data determination module 330 performs a connectivity and merging process on the lane line data in the road surface data. Specifically, the connectivity and merging process refers to connecting related lane lines into a single, continuous lane line.

[0121] The query area range module 340 is used to obtain the query lane area range based on the vehicle location, the query lane line, and the vehicle's driving direction.

[0122] In some embodiments, the query lane area range of the query area range module 340 can be limited in size by preset constraints.

[0123] In some embodiments, the query lane lines determined by the query area range module 340 can be one or two, and correspondingly, the query lane area range can also be one or two.

[0124] The calculation module 350 is used to calculate the intersection range of the query lane area range and the preset target area range of the target location.

[0125] In some embodiments, the preset target area range of the calculation module 350 can be set according to the identifiable distance of the target.

[0126] The output module 360 ​​is used to output the query point cloud data corresponding to the intersection range.

[0127] In this embodiment, the point cloud data matching device of this application determines the query lane line and vehicle driving direction from the road surface data corresponding to the vehicle by using the vehicle position and target position. It calculates and obtains the query lane area range by using the vehicle position, query lane line and vehicle driving direction. It obtains the query point cloud data by using the intersection of the query lane area range and the preset target area range. This enables the rapid search for point cloud data with higher relevance to the target object, reduces noise data, reduces data processing volume, and improves computing efficiency.

[0128] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.

[0129] Figure 4 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.

[0130] See Figure 4 The electronic device 1000 includes a memory 1010 and a processor 1020.

[0131] The processor 1020 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0132] Memory 1010 may include various types of storage units, such as device memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1020 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices employ mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). Device memory may be read-write storage devices or volatile read-write storage devices, such as dynamic random access memory. Device memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital multifunction optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, a high-density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.

[0133] The memory 1010 stores executable code, which, when processed by the processor 1020, can cause the processor 1020 to execute part or all of the methods described above.

[0134] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.

[0135] Alternatively, this application may be implemented as a computer-readable storage medium (or a non-transitory machine-readable storage medium or a machine-readable storage medium) storing executable code (or computer program or computer instruction code) thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the methods described above according to this application.

[0136] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A point cloud data matching method, characterized in that, include: Obtain the vehicle location and target location; Obtain road surface data corresponding to the vehicle based on the vehicle's location; Based on the vehicle location and the target location, determine the query lane line corresponding to the target and the vehicle's driving direction in the road surface data; wherein, the process includes: determining the driving lane data corresponding to the vehicle in the road surface data based on the vehicle location; obtaining the lane line closest to the target location in the vehicle's lane and the vehicle's driving direction based on the driving lane data, and defining the lane line closest to the target location in the vehicle's lane as the query lane line; wherein, the query lane line is the lane line corresponding to the point cloud data with the highest correlation to the target location; Based on the vehicle location, the lane lines, and the vehicle's direction of travel, the range of the query lane area is obtained; Calculate the intersection range between the query lane area range and the preset target area range of the target location; wherein, the query lane area range is the distribution range of point cloud data associated with the target location in the road surface data; output the query point cloud data corresponding to the intersection range.

2. The method according to claim 1, characterized in that, Before obtaining the road surface data corresponding to the vehicle based on the vehicle location, the method further includes: Query the lane line data within a preset area surrounding the target location; The step of obtaining road surface data corresponding to the vehicle based on the vehicle's location includes: Based on the vehicle's location, obtain the road surface data corresponding to the vehicle from the lane line data within the preset surrounding area.

3. The method according to claim 2, characterized in that, The preset surrounding range is obtained in the following way: Based on the distance relationship between the target location and the vehicle location, a preset surrounding range is obtained.

4. The method according to claim 3, characterized in that, The step of obtaining a preset surrounding range based on the distance relationship between the target location and the vehicle location includes: Based on the condition that the distance between the target location and the vehicle location is less than or equal to a preset distance threshold, the preset distance threshold is defined as a preset surrounding radius; or The distance between the target location and the vehicle location is defined as the preset surrounding radius based on the fact that the distance between the target location and the vehicle location is greater than a preset distance threshold.

5. The method according to claim 2, characterized in that, The method also includes: The acquired road surface data is subjected to data filtering processing; The data objects undergoing the data filtering process include at least: lane line data for U-turn lanes, lane line data for reverse lanes, and lane line data for auxiliary lanes.

6. The method according to claim 1, characterized in that, The preset target area range is set according to the target's identifiable distance.

7. A point cloud data matching device, characterized in that, include: The positioning module is used to obtain the vehicle's location and the target's location; The data acquisition module is used to acquire road surface data corresponding to the vehicle based on the vehicle's location; The data determination module is used to determine the distance relationship between the vehicle position and the target position, and to determine the query lane line corresponding to the target and the vehicle driving direction corresponding to the vehicle in the road surface data; The query area range module is used to obtain the query lane area range based on the vehicle location, the query lane line, and the vehicle's driving direction. This includes: determining the driving lane data corresponding to the vehicle in the road surface data based on the vehicle's location; obtaining the lane line closest to the target location and the vehicle's driving direction based on the driving lane data, and defining the lane line closest to the target location as the query lane line; wherein the query lane line is the lane line corresponding to the point cloud data with the highest correlation to the target location. The calculation module is used to calculate the intersection range of the query lane area range and the preset target area range of the target location; wherein, the query lane area range is the distribution range of point cloud data associated with the target location in the corresponding road surface data; The output module is used to output the query point cloud data corresponding to the intersection range.

8. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium having executable code stored thereon, characterized in that: When the executable code is executed by the processor of the electronic device, the processor performs the method as described in any one of claims 1-6.

Images