Map evaluation method and device

Abstract

The present disclosure provides a map evaluation method and device, including: determining first deviation information between a map to be evaluated and a high-precision map in a road edge element dimension, and correcting the map to be evaluated based on the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing the geographical features of the same area, determining second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements other than road edge elements, and generating an evaluation result of the map to be evaluated based on the second deviation information, thereby improving the efficiency of map evaluation and improving the accuracy and reliability of map evaluation.

Description

Technical Field

[0001] The present disclosure relates to the field of high-precision map technology, and in particular to a map evaluation method and device. Background Art

[0002] Map elements are important contents in drawing high-precision maps. In order to improve the effectiveness and reliability of high-precision maps, map elements can be evaluated.

[0003] For example, the map elements may be evaluated manually, such as manually creating true values ​​and comparing the map elements with the true values ​​to achieve evaluation of the map elements.

[0004] However, the efficiency of manually producing true values ​​is low, and it is not suitable for scenarios with large amounts of map element data. It is also easily affected by human subjective factors, resulting in technical problems such as low evaluation accuracy. Summary of the Invention

[0005] The present disclosure provides a map evaluation method and device to improve the accuracy and effectiveness of map evaluation.

[0006] In a first aspect, an embodiment of the present disclosure provides a map evaluation method, comprising:

[0007] Determining first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, and correcting the map to be evaluated based on the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area;

[0008] Determining second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map element is at least one of the map elements other than the road edge element;

[0009] An evaluation result of the map to be evaluated is generated according to the second deviation information.

[0010] In one embodiment of the present disclosure, the map element has a type attribute, and the type attribute is used to distinguish different types of map elements; determining the first deviation information of the road edge element dimension between the map to be evaluated and the high-precision map includes:

[0011] Acquire road edge elements from the map to be evaluated based on the type attribute, and acquire road edge elements from the high-precision map based on the type attribute;

[0012] Determining a first correspondence between road edge elements in the map to be evaluated and road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map with the first correspondence represent the same object in an actual road scene;

[0013] The difference between the coordinates of the road edge element in the map to be evaluated having the first corresponding relationship and the coordinates of the road edge element in the high-precision map is calculated to obtain the first deviation information.

[0014] In one embodiment of the present disclosure, determining the second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions includes:

[0015] Determining a second correspondence between other map elements in the high-precision map and other map elements in the revised map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the revised map to be evaluated having the second correspondence represent the same object in an actual road scene;

[0016] The difference between the coordinates of other map elements in the high-precision map having the second corresponding relationship and the coordinates of other map elements in the corrected map to be evaluated is calculated to obtain the second deviation information.

[0017] In one embodiment of the present disclosure, the map element has a directional attribute, the directional attribute including a longitudinal attribute for representing a direction perpendicular to a cross-section of a road on which the map element is located, or a transverse attribute for representing a direction parallel to the cross-section; the calculating the difference between the coordinates of the other map elements in the high-precision map having the second corresponding relationship and the coordinates of the other map elements in the corrected map to be evaluated to obtain the second deviation information includes:

[0018] If the direction attribute of the other map element having the second corresponding relationship is a horizontal attribute, calculating the horizontal coordinate difference between the high-precision map and the corrected map to be evaluated of the map element having the second corresponding relationship to obtain horizontal deviation information;

[0019] If the direction attribute of the other map elements having the second corresponding relationship is a longitudinal attribute, calculating the longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements having the second corresponding relationship to obtain longitudinal deviation information;

[0020] The second deviation information includes the lateral deviation information and / or the longitudinal deviation information.

[0021] In one embodiment of the present disclosure, generating an evaluation result of the map to be evaluated according to the second deviation information includes:

[0022] repositioning the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated;

[0023] Determining a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated having the third correspondence represent the same object in the actual road scene;

[0024] The evaluation result is determined according to the third corresponding relationship.

[0025] In one embodiment of the present disclosure, determining the evaluation result according to the third corresponding relationship includes:

[0026] Calculate the difference between the coordinates of other map elements in the high-precision map having the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information, and determine the evaluation result based on the third deviation information.

[0027] In one embodiment of the present disclosure, the method further includes:

[0028] Obtaining a road surface bounding box of a road described by a preset map, and obtaining a recognition area bounding box of a vehicle traveling on the road, wherein the preset map includes the high-precision map;

[0029] Determine an intersection bounding box between the road surface bounding box and the identification area bounding box, and determine the intersection bounding box as an evaluation area;

[0030] And, the calculation of the difference between the coordinates of other map elements in the high-precision map having the third correspondence and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information includes: calculating the difference between the coordinates of other map elements having the third correspondence in the relocated map to be evaluated within the evaluation area and the coordinates in the high-precision map within the area to be evaluated to obtain the third deviation information.

[0031] In one embodiment of the present disclosure, obtaining a road surface bounding box of a road on a preset map includes:

[0032] Obtaining roads and lane lines in the preset map, and generating a bounding box for selecting a road surface including the roads and lane lines;

[0033] According to the acquired trajectory of the vehicle traveling on the road, a road surface bounding box for selecting the trajectory is acquired from the bounding box.

[0034] In one embodiment of the present disclosure, the map to be evaluated includes a segmented map to be evaluated corresponding to each trajectory segment, and each trajectory segment is obtained by segmenting the trajectory of the vehicle traveling on the road described in the map to be evaluated based on a preset interval mileage length.

[0035] In one embodiment of the present disclosure, the method further includes:

[0036] Obtaining a single-frame map generated based on point cloud data and / or images collected by a vehicle traveling on a road;

[0037] Determining the object represented by the map element represented by the single-frame map in the actual road scene, and obtaining other frame maps including the map element representing the object;

[0038] The single-frame map and the other frame maps are fused to obtain the map to be evaluated.

[0039] In one embodiment of the present disclosure, the fusing of the single-frame map and the other frame maps to obtain the map to be evaluated includes:

[0040] performing clustering processing on the single-frame map and the other frame maps to obtain a cluster map;

[0041] Constructing a topological relationship and a distance relationship between map elements representing objects in an actual road scene based on the single-frame map and the other frame maps;

[0042] The cluster map is preprocessed according to the topological relationship and the distance relationship to obtain the map to be evaluated.

[0043] In one embodiment of the present disclosure, preprocessing the cluster map according to the topological relationship and the distance relationship to obtain the map to be evaluated includes:

[0044] filtering the cluster map according to the topological relationship and the distance relationship to obtain a filtered cluster map;

[0045] fitting a map element model including map elements according to the filtered cluster map, and smoothing the map element model to obtain a smoothed map element model;

[0046] According to the trajectory of the vehicle traveling on the road, the correctness of the map elements in the smoothed map element model is verified, and the verified map element model is determined as the map to be evaluated.

[0047] In a second aspect, an embodiment of the present disclosure provides a map evaluation device, comprising:

[0048] a first determining unit, configured to determine first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area;

[0049] a correction unit, configured to correct the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated;

[0050] a second determining unit, configured to determine second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map element is at least one of the map elements other than the road edge element;

[0051] A generating unit is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.

[0052] In one embodiment of the present disclosure, the map element has a type attribute, and the type attribute is used to distinguish different types of map elements; the first determining unit includes:

[0053] an acquisition subunit, configured to acquire road edge elements from the map to be evaluated based on the type attribute, and to acquire road edge elements from the high-precision map based on the type attribute;

[0054] a first determining subunit, configured to determine a first correspondence between road edge elements in the map to be evaluated and road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map having the first correspondence represent the same object in an actual road scene;

[0055] The first calculation subunit is used to calculate the difference between the coordinates of the road edge element in the map to be evaluated that has the first corresponding relationship and the coordinates of the road edge element in the high-precision map to obtain the first deviation information.

[0056] In one embodiment of the present disclosure, the second determining unit includes:

[0057] a second determining subunit, configured to determine a second correspondence between other map elements in the high-precision map and other map elements in the revised map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the revised map to be evaluated having the second correspondence represent the same object in an actual road scene;

[0058] The second calculation subunit is used to calculate the difference between the coordinates of other map elements in the high-precision map having the second corresponding relationship and the coordinates of other map elements in the corrected map to be evaluated to obtain the second deviation information.

[0059] In one embodiment of the present disclosure, the map element has a directional attribute, the directional attribute including a longitudinal attribute for representing a direction perpendicular to a cross-section of a road on which the map element is located, or a transverse attribute for representing a direction parallel to the cross-section; the second calculation subunit is configured to, if the directional attribute of the other map element having the second corresponding relationship is a transverse attribute, calculate the transverse coordinate difference between the high-precision map and the corrected map to be evaluated of the map element having the second corresponding relationship, to obtain transverse deviation information;

[0060] The second calculation subunit is configured to calculate, if the direction attribute of the other map elements having the second corresponding relationship is a longitudinal attribute, a longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements having the second corresponding relationship to obtain longitudinal deviation information;

[0061] The second deviation information includes the lateral deviation information and / or the longitudinal deviation information.

[0062] In one embodiment of the present disclosure, the generating unit includes:

[0063] a repositioning subunit, configured to reposition the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated;

[0064] a third determining subunit, configured to determine a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated having the third correspondence represent the same object in an actual road scene;

[0065] The fourth determining subunit is configured to determine the evaluation result according to the third corresponding relationship.

[0066] In one embodiment of the present disclosure, the fourth determining subunit includes:

[0067] a calculation module, configured to calculate the difference between the coordinates of other map elements in the high-precision map having the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated, to obtain third deviation information;

[0068] A first determining module is configured to determine the evaluation result according to the third deviation information.

[0069] In one embodiment of the present disclosure, the fourth determining subunit further includes:

[0070] an acquisition module, configured to acquire a road surface bounding box of a road described by a preset map, and to acquire a recognition area bounding box of a vehicle traveling on the road, wherein the preset map includes the high-precision map;

[0071] A second determining module is configured to determine an intersection bounding box between the road surface bounding box and the identification area bounding box, and determine the intersection bounding box as an evaluation area;

[0072] In addition, the calculation module is used to calculate the difference between the coordinates of other map elements having the third corresponding relationship in the map to be evaluated after repositioning within the evaluation area and the coordinates in the high-precision map within the area to be evaluated, so as to obtain the third deviation information.

[0073] In one embodiment of the present disclosure, the acquisition module includes:

[0074] A first acquisition submodule is used to acquire roads and lane lines in the preset map;

[0075] A generating submodule, configured to generate a bounding box for selecting a road surface including the road and the lane line;

[0076] The second acquisition submodule is configured to acquire, from the enclosing frame, a road surface enclosing frame for selecting the track according to the acquired track of the vehicle traveling on the road.

[0077] In one embodiment of the present disclosure, the map to be evaluated includes a segmented map to be evaluated corresponding to each trajectory segment, and each trajectory segment is obtained by segmenting the trajectory of the vehicle traveling on the road described in the map to be evaluated based on a preset interval mileage length.

[0078] In one embodiment of the present disclosure, the apparatus further includes:

[0079] A first acquisition unit is configured to acquire a single-frame map generated based on point cloud data and / or images collected when a vehicle travels on a road;

[0080] a third determining unit, configured to determine an object represented by the map element represented by the single-frame map in an actual road scene;

[0081] A second acquisition unit is used to acquire other frame maps including map elements representing the object;

[0082] The fusion unit is used to fuse the single-frame map with the other frame maps to obtain the map to be evaluated.

[0083] In one embodiment of the present disclosure, the fusion unit includes:

[0084] a clustering subunit, configured to perform clustering processing on the single-frame map and the other frame maps to obtain a cluster map;

[0085] A construction subunit, configured to construct, based on the single-frame map and the other frame maps, a topological relationship and a distance relationship between map elements representing objects in an actual road scene;

[0086] The processing subunit is configured to pre-process the cluster map according to the topological relationship and the distance relationship to obtain the map to be evaluated.

[0087] In one embodiment of the present disclosure, the processing subunit includes:

[0088] A filtering module, configured to filter the cluster map according to the topological relationship and the distance relationship to obtain a filtered cluster map;

[0089] A fitting module, configured to obtain a map element model including map elements by fitting the filtered cluster map;

[0090] a smoothing module, configured to smooth the map element model to obtain a smoothed map element model;

[0091] a verification module, configured to verify the correctness of the map elements in the smoothed map element model according to the trajectory of the vehicle traveling on the road;

[0092] The third determination module is used to determine the verified map element model as the map to be evaluated.

[0093] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0094] at least one processor; and

[0095] a memory communicatively connected to at least one processor; wherein,

[0096] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the electronic device to execute any one of the methods described in the first aspect of the present disclosure.

[0097] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the methods described in the first aspect of the present disclosure when the computer program is executed by a processor.

[0098] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program, which, when executed by a processor, implements any one of the methods described in the first aspect of the present disclosure.

[0099] The disclosed embodiment provides a map evaluation method and device, including: determining first deviation information between a map to be evaluated and a high-precision map in a road edge element dimension, and correcting the map to be evaluated based on the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing the geographical features of the same area, determining second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements other than the road edge element, and generating an evaluation result of the map to be evaluated based on the second deviation information, wherein determining the characteristics of the first deviation information is equivalent to evaluating the map from the road level. In the above, "coarse matching" of the map to be evaluated with the high-precision map to determine the characteristics of the second deviation information is equivalent to "fine matching" of the corrected map to be evaluated with the high-precision map from the map elements in the road, that is, the lane level. By adopting the "coarse matching + fine matching" method for map evaluation, the disadvantages of low efficiency and accuracy caused by manual evaluation in the above example, the disadvantages of low reliability caused by real-time evaluation in the above example, and the disadvantages of limited scenarios and data volume caused by evaluation based on regions in the above example can be avoided, thereby improving the efficiency of map evaluation and improving the accuracy and reliability of map evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0101] Figure 1 This is a flowchart of a map evaluation method according to an embodiment of the present disclosure;

[0102] Figure 2This is a flowchart of a map evaluation method according to another embodiment of the present disclosure;

[0103] Figure 3 is a schematic diagram of a road edge element according to an embodiment of the present disclosure;

[0104] Figure 4 A schematic diagram of a map evaluation device according to an embodiment of the present disclosure;

[0105] Figure 5 is a schematic diagram of a map evaluation device according to another embodiment of the present disclosure;

[0106] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present disclosure.

[0107] The above drawings illustrate specific embodiments of the present disclosure, which will be described in more detail below. These drawings and textual descriptions are not intended to limit the scope of the present disclosure in any way, but rather to illustrate the concepts of the present disclosure to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0108] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0109] The terms "first," "second," "third," and the like in the specification and claims of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present disclosure described herein can be practiced in orders other than those illustrated or described herein.

[0110] In addition, the terms "comprises" and "having" and any variations thereof are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product or apparatus.

[0111] To facilitate readers' understanding of the present disclosure, at least some of the terms of the present disclosure are explained as follows:

[0112] High-precision maps, also known as high-definition maps (HD maps), refer to maps used for autonomous driving assistance. They have a relative accuracy of centimeters and contain rich lane lines, road signs, traffic signs, traffic lights, lane curvature, slopes, and lane-level real-time traffic dynamics information. They mainly serve the machine's autonomous driving environment judgment, decision-making, and control.

[0113] High-precision base maps refer to the use of images and laser point clouds to extract semantic information and abstractly describe geographic entities and virtual elements.

[0114] Map features are used in HD maps to represent objects in real-world road scenes. Map features have type attributes, such as traffic signs, poles, guardrails, and curbs. They also have directional attributes, such as horizontal and vertical attributes.

[0115] Map elements can be divided into road edge elements and other map elements based on whether they represent the edges of roads in real-world scenarios. Road edge elements represent objects at the edges of roads in real-world scenarios, such as guardrails and curbs. Other map elements are map elements other than road edge elements, representing objects other than the edges of roads in real-world scenarios, such as traffic signs, poles, and lane markings.

[0116] Map evaluation refers to the quality assessment of map elements, that is, the evaluation of the recall rate and / or precision of map elements. Evaluation dimensions may include the recall information of map elements relative to the true value, the recall accuracy information, the absolute precision and relative precision of map elements, etc. Combined with the above explanations of the terms of map elements, it can be seen that the evaluation objects can specifically include lane lines, road edges, ground road components (ground text, arrows, etc.), and non-ground road components (traffic signs, traffic lights, etc.), etc., which will not be listed here one by one.

[0117] Lane line is the abbreviation of lane dividing line, which refers to the traffic marking used to separate traffic flows traveling in the same direction. It is generally a white dotted or solid line or a yellow dotted or solid line.

[0118] Traffic signs are the abbreviation of traffic signs or traffic signs. They refer to facilities that use graphic symbols and text to convey specific information, manage traffic, indicate driving directions to ensure smooth roads and driving safety. They are mainly applicable to highways, urban roads and special highways, and vehicles and pedestrians must comply with them.

[0119] Traffic lights are signals composed of three colors of red, yellow and green (green is blue-green) used to direct traffic.

[0120] Map elements are crucial for producing high-precision maps. With the advancement of autonomous driving technology, users are increasingly concerned about the safety and reliability of autonomous driving. During the map element production process, that is, when the collected point clouds and / or images are vectorized, these vectorized map elements need to be evaluated to check their accuracy and precision. This ensures the quality of these elements, resulting in high-quality high-precision maps and, in turn, improves the safety and reliability of vehicles driving autonomously based on these maps.

[0121] In some embodiments, map elements may be evaluated manually, such as by manually creating true values ​​and comparing the values ​​of map elements (such as the coordinates of map elements) with the true values ​​to achieve evaluation of the map elements.

[0122] However, the efficiency of manually producing true values ​​is low, and it is not suitable for scenarios with large amounts of map element data. It is also easily affected by human subjective factors, resulting in technical problems such as low evaluation accuracy.

[0123] In other embodiments, the real-time trajectory of the collection vehicle may be obtained, such as the real-time position (eg, coordinates), real-time speed, and real-time acceleration of the collection vehicle, and map elements may be evaluated based on the real-time trajectory.

[0124] However, the error accuracy and reliability of real-time trajectories are relatively poor. Real-time evaluation generates poor map element accuracy and recall, which leads to technical problems such as low reliability of the evaluation.

[0125] In some other embodiments, the map elements within a region can be evaluated in units of regions. However, the evaluation scenarios are limited, and the amount of data for evaluation is limited.

[0126] In order to avoid at least one of the above-mentioned technical problems, the inventors of the present disclosure have obtained the inventive concept of the present disclosure through creative work: using a "coarse matching + fine matching" method for evaluation, such as "coarse matching" can be a road-level matching between the map to be evaluated and the high-precision map determined based on the road edge element dimensions, and the map to be evaluated is corrected based on the result obtained by the matching; "fine matching" can be a matching of other map elements in the high-precision map with other map elements in the modified map to be evaluated, and the evaluation result is determined based on the deviation information of other map elements between the high-precision map and the modified map to be evaluated determined based on the matching result.

[0127] The technical solution of the present disclosure is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0128] See also Figure 1 , Figure 1 This is a flow chart of a map evaluation method according to an embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0129] S101: Determine first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, and correct the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated.

[0130] Among them, the map to be evaluated and the high-precision map are maps that describe the geographical features of the same area.

[0131] Exemplarily, the executor of the map evaluation method of the embodiment of the present disclosure may be a map evaluation device, which may be a server (such as a cloud server, a local server, or a server cluster), a computer, a terminal device, a processor, a chip, etc., which are not listed one by one here.

[0132] This embodiment does not limit the method of obtaining the map to be evaluated and the high-precision map. Taking the acquisition of the map to be evaluated (or high-precision map) as an example, the following method can be used:

[0133] In one example, the map evaluation device can be connected to a data transmission device and receive the map to be evaluated (or high-precision map) sent by the data transmission device.

[0134] In another example, the map evaluation device may provide a tool for loading the map to be evaluated (or high-precision map), and the user may use the tool to transfer the map to be evaluated (or high-precision map) to the map evaluation device.

[0135] Among them, the tool for loading the map to be evaluated (or high-precision map) can be an interface for connecting to an external device, such as an interface for connecting to other storage devices, through which the map to be evaluated (or high-precision map) transmitted by the external device is obtained; the tool for loading the map to be evaluated (or high-precision map) can also be a display device, such as a map evaluation device can input an interface for loading the map to be evaluated (or high-precision map) function on the display device, and the user can import the map to be evaluated (or high-precision map) into the evaluation device through the interface, and the map evaluation device obtains the imported map to be evaluated (or high-precision map).

[0136] The method for obtaining the map to be evaluated and the high-precision map may be the same or different, and this embodiment does not limit this.

[0137] The first deviation information can be understood as the deviation information between the map to be evaluated and the high-precision map determined from the road edge element dimension. The deviation information can be deviation information on coordinates.

[0138] For example, in combination with the above analysis, the road edge element is a type of map element and is used to represent objects at the edge of the road in an actual road scene, such as guardrails and curbs.

[0139] Accordingly, the map to be evaluated includes a road edge element, so as to represent the edge object of the road in the actual road scene based on the road edge element. For the sake of distinction, the road edge element in the map to be evaluated is referred to as the first road edge element.

[0140] Similarly, HD maps include road edge elements, which are used to represent objects at the edge of roads in actual road scenes. For ease of distinction, the road edge elements in HD maps are referred to as second road edge elements.

[0141] The difference information between the first road edge element and the second road edge element may be determined by a matching method such as a coordinate matching method, and the difference information may be referred to as first deviation information.

[0142] In other words, the first deviation information reflects the deviation between the map to be evaluated and the high-precision map from the road edge element dimension, that is, taking the high-precision map as a reference benchmark, the map to be evaluated deviates from the position information of the high-precision map in the road edge element dimension.

[0143] In order to improve the accuracy and reliability of the map to be evaluated, the map to be evaluated may be corrected based on the first deviation information.

[0144] The correction process may be understood as adjusting the map to be evaluated based on the first deviation information, such as adjusting the coordinates of map elements in the map to be evaluated, so as to correct the deviation of the map to be evaluated.

[0145] S102: Determine second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions.

[0146] Among them, other map elements are at least one of the map elements except the road edge elements.

[0147] Combined with the above analysis, other map elements are a type of map elements and are used to represent other objects in actual road scenes except for objects on the edge of the road, such as traffic signs.

[0148] Accordingly, the map to be evaluated includes other map elements so as to represent other objects in the actual road scene, except for objects at the edge of the road, based on the other map elements. For ease of distinction, the other map elements in the map to be evaluated are referred to as first other map elements.

[0149] Similarly, high-precision maps include other map elements, so that other map elements can be used to represent other places in the actual road scene, except for objects at the edge of the road. For ease of distinction, other map elements in high-precision maps are referred to as second other map elements.

[0150] The difference information between the first other map element and the second other map element may be determined by a matching method such as a coordinate matching method. The difference information may be referred to as second deviation information.

[0151] That is to say, the second deviation information reflects the deviation between the high-precision map and the revised map to be evaluated from the dimensions of other map elements, that is, with the high-precision map as the reference benchmark, the revised map to be evaluated deviates from the information of the high-precision map in the dimensions of other map elements.

[0152] It is worth noting that by determining the first deviation information and correcting the map to be evaluated based on the first deviation information, the deviation between the corrected map to be evaluated and the high-precision map can be relatively reduced. Further determining the second deviation information on this basis can avoid errors in the determined second deviation information as much as possible, thereby improving the accuracy and reliability of the second deviation information.

[0153] S103: Generate an evaluation result of the map to be evaluated according to the second deviation information.

[0154] Based on the above analysis, the present disclosure provides a map evaluation method, including: determining first deviation information between the map to be evaluated and the high-precision map in the road edge element dimension, and correcting the map to be evaluated based on the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing the geographical features of the same area, determining second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions, wherein the other map elements are at least one of the map elements other than the road edge elements, and generating an evaluation result of the map to be evaluated based on the second deviation information. In this embodiment, determining the characteristics of the first deviation information is equivalent to obtaining the road edge element from the road edge element. At the lane level, the "coarse matching" of the map to be evaluated with the high-precision map to determine the characteristics of the second deviation information is equivalent to the map elements in the road, that is, the "fine matching" of the corrected map to be evaluated with the high-precision map. By adopting the "coarse matching + fine matching" method for map evaluation, the disadvantages of low efficiency and accuracy caused by manual evaluation in the above example, the disadvantages of low reliability caused by real-time evaluation in the above example, and the disadvantages of limited scenarios and data volume caused by evaluation based on regions in the above example can be avoided, thereby improving the efficiency of map evaluation and improving the accuracy and reliability of map evaluation.

[0155] In order to make readers more deeply understand the implementation principle of this disclosure, Figure 2 The implementation principle of the present disclosure is described in more detail. Figure 2 FIG. 1 is a flow chart of a map evaluation method according to another embodiment of the present disclosure. Figure 2 As shown, the method includes:

[0156] S201: Obtain a map to be evaluated and a high-precision map corresponding to the map to be evaluated.

[0157] It should be understood that, in order to avoid cumbersome descriptions, the technical features of this embodiment that are the same as those in the above embodiments will not be described in detail in this embodiment.

[0158] The high-precision base map includes a high-precision map. For example, the high-precision map can be a map obtained from the high-precision base map that corresponds to the map to be evaluated. The term "correspondence" here can be understood as regional correspondence. That is, the map to be evaluated and the high-precision map describe the geographical features of the same area.

[0159] In some embodiments, obtaining a map to be evaluated may include the following steps:

[0160] The first step is to obtain a single-frame map generated based on point cloud data and / or images collected when the vehicle is driving on the road.

[0161] Exemplarily, an image is used as an example to illustrate as follows: a current frame image is acquired, and vectorization is performed on the current frame image to obtain a single-frame map.

[0162] The second step is to determine the object represented by the map element in the single-frame map in the actual road scene, and obtain other frame maps including the map element representing the object.

[0163] For example, if the object represented by the map elements in a single-frame map in the actual road scene is a traffic sign, then other frame maps including the map elements for representing the traffic sign are obtained.

[0164] In some embodiments, a single-frame map has attribute information, and the attribute information is used to identify whether there are other frame maps that represent the same object as the single-frame map in the actual road scene. If so, the other frame maps are obtained; if not, the map to be evaluated can be a single-frame map.

[0165] Step 3: Fuse the single-frame map with other frame maps to obtain the map to be evaluated.

[0166] Accordingly, if there are other map frames that represent the same object in the actual road scene as the map elements in the single-frame map, the single-frame map and the other map frames are fused to obtain the map to be evaluated. In other words, the map to be evaluated can be obtained by fusion processing multiple map frames containing map elements that represent the same object in the actual road scene.

[0167] In this embodiment, a single-frame map and other frame maps including map elements representing the same object in an actual road scene are fused to obtain a map to be evaluated. This can make the map to be evaluated more comprehensive, thereby improving the accuracy and reliability of the evaluation.

[0168] In some embodiments, the third step may include the following sub-steps:

[0169] The first sub-step: clustering the single-frame map and other frame maps to obtain a cluster map.

[0170] Clustering can be understood as dividing a dataset, including single-frame maps and other frame maps, into different classes or clusters, so that data objects within the same cluster are as similar as possible, while data objects in different clusters are as different as possible. In other words, after clustering, data of the same class is clustered together as much as possible, while data of different classes is separated as much as possible.

[0171] This embodiment does not limit the clustering processing method. For example, partition-based methods can be used for clustering processing, density-based methods can be used for clustering processing, hierarchical methods can be used for clustering processing, and so on.

[0172] Second sub-step: constructing the topological relationship and distance relationship between map elements representing objects in the actual road scene based on the single-frame map and other frame maps.

[0173] For example, an object in an actual road scene may be represented by multiple map elements, and certain associations exist between the map elements, such as associations in topological structures (which can be understood as associations in positions) and associations in distances.

[0174] The third sub-step: pre-process the cluster map according to the topological relationship and distance relationship to obtain the map to be evaluated.

[0175] For example, based on the topological relationship and distance relationship, noise removal processing can be performed on the map elements in the cluster map to obtain the map to be evaluated. Alternatively, based on the topological relationship and distance relationship, smoothing processing can be performed on the map elements in the cluster map to obtain the map to be evaluated, and so on.

[0176] In this embodiment, by combining the “clustering processing + preprocessing” method to obtain the map to be evaluated, redundant data and noise data of the map to be evaluated can be avoided, thereby improving the effectiveness of the map to be evaluated and further improving the accuracy of map evaluation.

[0177] In some embodiments, the third sub-step may include the following refinement steps:

[0178] The first refinement step: filtering the map elements in the cluster map according to the topological relationship and the distance relationship to obtain a filtered cluster map.

[0179] Exemplarily, based on the topological relationship and the distance relationship, noise map elements and redundant map elements in the cluster map are filtered out to obtain a filtered cluster map.

[0180] The second refinement step: obtaining a map element model including map elements according to the filtered cluster map fitting, and performing smoothing processing on the map element model to obtain a smoothed map element model.

[0181] The map feature model can be understood as a curve equation obtained by fitting the filtered cluster map. Correspondingly, the smoothing process can be understood as smoothing the curve equation to remove noise data in the curve equation, making the curve equation smoother.

[0182] The third refinement step: verifying the correctness of the map elements in the smoothed map element model according to the trajectory of the vehicle traveling on the road, and determining the map element model that passes the verification as the map to be evaluated.

[0183] For example, when a vehicle travels on a road to collect point cloud data and / or images, a trajectory can be formed, such as the vehicle's speed, position, direction, elevation, and acceleration. The map elements in the smoothed map element model can be verified based on at least one of the trajectories to verify the correctness of the map elements in the smoothed map element model. If the verification result is incorrect, the incorrect map element is removed from the smoothed map element model to obtain the map to be evaluated.

[0184] In this embodiment, by combining the "filtering + smoothing + verification" process, the redundant data and noise data in the map to be evaluated can be reduced as much as possible, so as to improve the correctness of the map elements in the map to be evaluated as much as possible, thereby improving the accuracy and effectiveness of the map to be evaluated, and further improving the reliability of the evaluation.

[0185] S202: Obtain road edge elements from the map to be evaluated based on the type attribute, and obtain road edge elements from the high-precision map based on the type attribute.

[0186] Among them, the map elements have a type attribute, which is used to distinguish different types of map elements.

[0187] Combined with the above analysis, map elements can be divided into road edge elements and other map elements based on whether they are used to represent road edges in actual road scenes. Therefore, the type attribute can include the type of road edge elements and the type of other map elements.

[0188] Alternatively, based on the above analysis, it can be seen that the type attributes of map elements include traffic sign type, pole type, guardrail type, curb type, etc.

[0189] In this embodiment, road edge elements of the type attribute of road edge elements can be obtained from the map to be evaluated, or road edge elements of the type attribute of road edge elements can be obtained from the high-precision map. For example, curbs and / or road edges can be obtained from the map to be evaluated and the high-precision map respectively.

[0190] S203: Determine a first correspondence between road edge elements in the map to be evaluated and road edge elements in the high-precision map.

[0191] Among them, the road edge elements in the map to be evaluated and the road edge elements in the high-precision map that have a first corresponding relationship represent the same object in the actual road scene.

[0192] For example, since the collected data may contain errors, on the one hand, the road edge elements in the map to be evaluated may be more than the road edge elements in the high-precision map. For example, the road edge elements in the map to be evaluated include curbs and road sidelines, while the road edge elements in the high-precision map only include road sidelines.

[0193] On the other hand, the road edge elements in the map to be evaluated and the high-precision map are both road sidelines, but the number of road sidelines in the map to be evaluated is greater than the number of road sidelines in the high-precision map.

[0194] This step can be understood as establishing a correspondence (i.e., a first correspondence) between the road edge elements in the map to be evaluated and the road edge elements in the high-precision map that represent the same object in the actual road scene.

[0195] For example, Figure 3 As shown, the road in the map to be evaluated is labeled Road 1, which includes road edgelines 11 and 12. The road in the HD map is labeled Road 2, which includes road edgelines 21 and 22. Based on the above analysis, we can see that Road 1 and Road 2 represent the same road in the actual road scene.

[0196] If road edge line 11 and road edge line 21 are the same road edge line in the actual road scene, a first correspondence relationship is established between road edge line 11 and road edge line 21. If road edge line 12 and road edge line 22 are the same road edge line in the actual road scene, a first correspondence relationship is established between road edge line 12 and road edge line 22.

[0197] In some embodiments, the first correspondence may be determined based on the “overall residual minimum principle”, for example:

[0198] The deviation between the set roadside line 11 and the road sideline 21 is calculated, such as the distance between the set roadside line 11 and the road sideline 21 (for ease of distinction, this distance is referred to as the first distance); the deviation between the set roadside line 12 and the road sideline 22 is calculated, such as the distance between the set roadside line 12 and the road sideline 22 (for ease of distinction, this distance is referred to as the second distance); and the sum of the first distance and the second distance is calculated.

[0199] The deviation between the set roadside line 11 and the road sideline 22 is calculated, such as the distance between the set roadside line 11 and the road sideline 22 (for ease of distinction, this distance is referred to as the third distance); the deviation between the set roadside line 12 and the road sideline 21 is calculated, such as the distance between the set roadside line 12 and the road sideline 21 (for ease of distinction, this distance is referred to as the fourth distance); and the sum of the third distance and the fourth distance is calculated.

[0200] If the first distance+the second distance>the third distance+the fourth distance, a first corresponding relationship between the road sideline 11 and the road sideline 21 and a first corresponding relationship between the road sideline 12 and the road sideline 22 are established.

[0201] If the first distance+the second distance<the third distance+the fourth distance, a first corresponding relationship between the road sideline 11 and the road sideline 22 and a first corresponding relationship between the road sideline 12 and the road sideline 21 are established.

[0202] S204: Calculate the difference between the coordinates of the road edge element in the map to be evaluated and the coordinates of the road edge element in the high-precision map, which have a first corresponding relationship, to obtain first deviation information.

[0203] For example, in combination with the above analysis, if there is a first corresponding relationship between road sideline 11 and road sideline 21, and there is a first corresponding relationship between road sideline 12 and road sideline 22, then the deviation distance from road sideline 11 to road sideline 21 can be calculated based on the coordinates of road sideline 11 and the coordinates of road sideline 21 to obtain first deviation information.

[0204] Alternatively, the deviation distance between the road sideline 12 and the road sideline 22 may be calculated according to the coordinates of the road sideline 12 and the coordinates of the road sideline 22 to obtain the first deviation information.

[0205] Alternatively, after calculating the deviation distance between the road sideline 11 and the road sideline 21 and the deviation distance between the road sideline 12 and the road sideline 22 , the average of the two calculated deviation distances is determined as the first deviation information.

[0206] In this embodiment, by determining the road edge elements that correspond to the map to be evaluated and the high-precision map respectively, and determining the first correspondence between the road edge elements representing the same object in the actual road scene, the coordinate difference between the road edge elements with the first correspondence is calculated to obtain the first deviation information, so that the first deviation information can more accurately reflect the offset of the road edge representing the same object in the actual road scene between the map to be evaluated and the high-precision map.

[0207] S205: Correcting the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated.

[0208] For example, the first deviation information is added to the high-precision map to correct the map to be evaluated, thereby obtaining a corrected map to be evaluated. Alternatively, the first deviation information is subtracted from the high-precision map to correct the map to be evaluated, thereby obtaining a corrected map to be evaluated.

[0209] S206: Determine a second correspondence between other map elements in the high-precision map and other map elements in the corrected map to be evaluated.

[0210] The other map elements are at least one of the map elements other than the road edge elements. The other map elements in the high-precision map with the second corresponding relationship and the other map elements in the corrected map to be evaluated represent the same object in the actual road scene.

[0211] For example, other map elements in the high-precision map may include at least one of lane lines, traffic signs, and traffic lights, and other map elements in the revised map to be evaluated may also include at least one of lane lines, traffic signs, and traffic lights.

[0212] Similarly, the types of other map elements in the high-precision map may be more than the types of other map elements in the revised map to be evaluated, or may be less than the types of other map elements in the revised map to be evaluated, or may be equal to the types of other map elements in the revised map to be evaluated.

[0213] In terms of quantity, the other map elements in the high-precision map may be more than the other map elements in the revised map to be evaluated, or may be less than the other map elements in the revised map to be evaluated, or may be equal to the other map elements in the revised map to be evaluated.

[0214] This step can be understood as comparing other map elements in the high-precision map with other map elements in the revised map to be evaluated to determine other map elements in the high-precision map and other map elements in the revised map to be evaluated that represent the same object in the actual road scene.

[0215] Based on the above analysis, it can be seen that map elements have type attributes. Accordingly, in some embodiments, other map elements with the same type attributes in the high-precision map and the revised map to be evaluated can be first determined based on the type attributes, and then based on the "minimum distance principle", other map elements representing the same object in the actual road scene can be determined from other map elements with the same type, that is, the second corresponding relationship can be determined.

[0216] Among them, the "minimum distance principle" can be understood as: if there are multiple other map elements with the same type attributes in the high-precision map and the revised map to be evaluated, then the coordinate difference of any other map elements with the same type attributes in the high-precision map and the revised map to be evaluated is calculated, and the other map element in the high-precision map corresponding to the smallest coordinate difference among the coordinate differences and the other map element in the revised map to be evaluated are determined as the other map elements with a second corresponding relationship.

[0217] For example, taking traffic signs as an example, if a traffic sign is obtained from a high-precision map and a traffic sign is obtained from a revised map to be evaluated, and if there are two traffic signs in the high-precision map, namely the first and second traffic signs, then there are two traffic signs in the revised map to be evaluated, namely the third and fourth traffic signs.

[0218] The distances between the first traffic sign and the third traffic sign and the fourth traffic sign are calculated. If the distance between the first traffic sign and the third traffic sign is smaller than the distance between the first traffic sign and the fourth traffic sign, it is determined that the first traffic sign and the third traffic sign have a second corresponding relationship.

[0219] S207: Calculate the difference between the coordinates of other map elements in the high-precision map having the second corresponding relationship and the coordinates of other map elements in the corrected map to be evaluated to obtain second deviation information.

[0220] For example, the first traffic sign in the high-precision map has a second corresponding relationship with the third traffic sign in the corrected map to be evaluated, that is, the first traffic sign and the third traffic sign represent the same traffic sign in the actual road scene, then the second deviation information is determined based on the coordinates of the first traffic sign and the coordinates of the third traffic sign.

[0221] Similarly, in this embodiment, by determining that other map elements representing the actual scene correspond to other map elements in the revised map to be evaluated and the high-precision map, and determining a second correspondence between other map elements representing the same object in the actual road scene, the coordinate difference between the other map elements with the second correspondence is calculated to obtain the second deviation information. This can make the second deviation information more accurately reflect the offset of other map elements representing the same object in the actual road scene between the map to be evaluated and the high-precision map.

[0222] In some embodiments, the map element has a direction attribute, which includes a longitudinal attribute for representing a direction perpendicular to a cross-section of the road on which the map element is located, or a transverse attribute for representing a direction parallel to the cross-section; S207 may include:

[0223] If the direction attribute of the other map elements with the second corresponding relationship is a horizontal attribute, the horizontal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relationship is calculated to obtain the horizontal deviation information.

[0224] If the direction attribute of the other map elements with the second corresponding relationship is a longitudinal attribute, the longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements with the second corresponding relationship is calculated to obtain longitudinal deviation information.

[0225] The second deviation information includes lateral deviation information and / or longitudinal deviation information.

[0226] Exemplarily, the difference between the lateral coordinates of the lane line having the second corresponding relationship in the high-precision map and the lateral coordinates of the corrected map to be evaluated is calculated to obtain lateral deviation information.

[0227] The difference between the longitudinal coordinates of the traffic sign having the second corresponding relationship in the corrected map to be evaluated and the longitudinal coordinates in the high-precision map is calculated to obtain longitudinal deviation information. For example, the longitudinal deviation information can be determined based on the four corner points of the traffic sign.

[0228] In this embodiment, by combining the horizontal and vertical attributes of other map elements and determining the second deviation information from both horizontal and vertical dimensions, the diversity and completeness of the second deviation information can be improved, thereby improving the accuracy and reliability of map evaluation.

[0229] In some embodiments, other map elements have weight attributes, such as lane lines and traffic signs, and the weight attributes of lane lines and traffic signs may be the same or different.

[0230] Accordingly, based on the above analysis, it can be seen that there may be multiple map elements with a second correspondence, such as the first traffic sign and the third traffic sign having a second correspondence, the second traffic sign and the fourth traffic sign having a second correspondence. There may also be multiple map elements with a second correspondence, such as the first traffic sign and the third traffic sign having a second correspondence, the first lane line and the second lane line having a second correspondence, and so on.

[0231] Accordingly, the lateral deviation information can be determined in combination with the weighted attribute of the lane line. If, in a scenario where only the lane line is other map elements with lateral attributes, the weighted attribute of the lane line represents that the weight of the lane line is 1.

[0232] If other map elements with longitudinal attributes include traffic lights and traffic signs in a scenario, the longitudinal deviation information can be determined by combining the weight ratio attributes corresponding to the traffic sign and the traffic light. For example, the weight ratio attribute of the traffic sign indicates that the weight ratio of the traffic sign is 0.8, and the weight ratio attribute of the traffic light indicates that the weight ratio of the traffic light is 0.2. Then, after determining the longitudinal deviation information corresponding to each traffic sign and traffic light respectively, the final longitudinal deviation information can be determined by combining the weight ratios of the two and the corresponding longitudinal deviation information.

[0233] Among them, the weight ratio of the weight ratio attribute representation can be determined based on the accuracy of other map elements. Relatively speaking, the higher the accuracy of other map elements, the greater the weight ratio of the weight ratio attribute representation of the other map elements. Conversely, the lower the accuracy of other map elements, the smaller the weight ratio of the weight ratio attribute representation of the other map elements.

[0234] In some embodiments, the aforementioned operations of correcting the map to be evaluated and determining the second deviation information may be iterated to improve the accuracy and reliability of the determined second deviation information, such as to obtain the optimal second deviation information. The number of iterations may be determined based on requirements, historical records, and experiments. Alternatively, if the deviation value of the second deviation information of the current iteration is less than a preset threshold (which may similarly be determined based on requirements, historical records, and experiments), the second deviation information of the current iteration may be determined as the final second deviation information.

[0235] S208: repositioning the corrected map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated.

[0236] Exemplarily, this step can be understood as calculating the coordinates of other map elements in the corrected map to be evaluated based on the second deviation information, and determining the calculated coordinates of other map elements as the coordinates of other map elements in the relocated map to be evaluated.

[0237] For example, the coordinates of other map elements in the high-precision map can be used as a reference, and the deviation value represented by the second deviation information can be added or subtracted to obtain the coordinates of other map elements in the relocated map to be evaluated.

[0238] Combined with the above analysis, there may be a second correspondence between other map elements in the high-precision map and other map elements in the revised map to be evaluated. Based on the second correspondence, the coordinates of other map elements in the revised map to be evaluated are relocated to obtain the relocated map to be evaluated.

[0239] For example, if the first traffic sign in the high-precision map has a second corresponding relationship with the third traffic sign in the map to be evaluated, the coordinates of the third traffic sign are determined based on the second deviation information and the coordinates of the first traffic sign.

[0240] S209: Determine a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated.

[0241] Among them, other map elements in the high-precision map with the third correspondence and other map elements in the relocated map to be evaluated represent the same object in the actual road scene.

[0242] For example, the high-precision map includes a lane line, the relocated map to be evaluated includes a lane line, and the lane line represents the same lane line in the actual road scene, then it is determined that the two vehicle lines have a third corresponding relationship.

[0243] S210: Determine an evaluation result according to the third corresponding relationship.

[0244] In this embodiment, other map elements in the high-precision map with a third correspondence and other map elements in the relocated map to be evaluated represent the same object in the actual road scene. When the relocated map to be evaluated is evaluated based on the third correspondence, the evaluation can have a more reliable evaluation benchmark, thereby improving the accuracy and reliability of the evaluation.

[0245] In some embodiments, S210 may include the following steps:

[0246] Step 1: Calculate the difference between the coordinates of other map elements in the high-precision map with the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information.

[0247] In some embodiments, in order to further improve the validity and reliability of the third deviation information, an evaluation area may be determined first, so as to determine the third deviation information within the evaluation area.

[0248] Exemplarily, determining the evaluation area may include the following steps:

[0249] Step 1: Obtain a road surface bounding box of a road described by a preset map, wherein the preset map includes a high-precision map.

[0250] For example, the road surface bounding box may be determined based on association information of roads and lane lines in a preset map.

[0251] In some embodiments, the first step may include the following sub-steps:

[0252] The first sub-step is to obtain the roads and lane lines in the preset map, and generate a bounding box for selecting the road surface based on the roads and lane lines.

[0253] Second sub-step: according to the acquired trajectory of the vehicle traveling on the road, a road surface bounding box for selecting the trajectory is obtained from the bounding box.

[0254] Exemplarily, this embodiment can be understood as first determining a bounding box within a large range (i.e., a bounding box for selecting the road surface), and then determining a relatively more accurate bounding box within a small range (i.e., a road surface bounding box for selecting the trajectory) within the large range.

[0255] In other words, the road surface bounding box is the area covered by the trajectory, that is, the area where the vehicle actually travels. By adopting the "large range + small range" method to determine the road surface bounding box, the effectiveness of the road surface bounding box can be improved, thereby improving the effectiveness and efficiency of the evaluation.

[0256] Step 2: Obtain the bounding box of the recognition area where the vehicle is traveling on the road.

[0257] The recognition area bounding box can be understood as the bounding box corresponding to the effective recognition range. For example, if the device used to capture images on a vehicle is an image collector (such as a camera), the image collector has a recognition range, such as a recognition range determined based on the field of view of the image collector. The area within the recognition range is the effective recognition area, and accordingly, the bounding box used to select the effective recognition area can be called the recognition area bounding box.

[0258] The third step: determine the intersection bounding box of the road surface bounding box and the recognition area bounding box, and determine the intersection bounding box as the evaluation area.

[0259] Combined with the above understanding of the road surface bounding box and the identification area bounding box, it can be seen that the evaluation area is the area where the trajectory is located and is the effective identification area. Therefore, by determining the intersection bounding box of the road surface bounding box and the identification area bounding box as the evaluation area, the evaluation area can be made more effective and reliable.

[0260] Correspondingly, the third deviation information is obtained by calculating the difference between the coordinates of other map elements in the high-precision map with the third correspondence and the coordinates of other map elements in the relocated map to be evaluated. This can be replaced by: calculating the third deviation information by calculating the difference between the coordinates of the map elements with the third correspondence in the relocated map to be evaluated within the evaluation area and the coordinates in the high-precision map within the evaluation area.

[0261] Since the evaluation area has high validity and reliability, the third deviation information determined based on the third corresponding relationship has high validity and reliability within the evaluation area.

[0262] In some embodiments, the relocated map to be evaluated of the evaluation area can also be filtered based on the trajectory to filter out abnormal map elements and other map elements not acting in the evaluation area in the relocated map to be evaluated.

[0263] For example, the relocated map to be evaluated in the evaluation area can be filtered based on the direction and elevation in the trajectory, so as to determine the deviations between other map elements in the filtered map to be evaluated in the evaluation area and other map elements in the high-precision map in the evaluation area according to the third correspondence, thereby improving the efficiency and reliability of determining the third deviation information.

[0264] Combined with the above analysis, it can be seen that map elements have directional attributes. Accordingly, the third deviation information includes lateral deviation information and longitudinal deviation information. The lateral deviation information is determined based on other map elements with a third corresponding relationship based on the lateral attribute, and the longitudinal deviation information is determined based on other map elements with a third corresponding relationship based on the longitudinal attribute.

[0265] For example, the high-precision map within the evaluation area includes lane lines and traffic signs, the relocated map to be evaluated within the evaluation area includes lane lines and traffic signs, the lane lines in the high-precision map within the evaluation area and the lane lines in the relocated map to be evaluated within the evaluation area have a third correspondence, and the traffic signs in the high-precision map within the evaluation area and the traffic signs in the relocated map to be evaluated within the evaluation area have a third correspondence.

[0266] Accordingly, calculating the difference between the coordinates of other map elements having the third correspondence in the map to be evaluated after relocation within the evaluation area and the coordinates in the high-precision map within the evaluation area may include:

[0267] The difference between the coordinates of the lane line in the relocated map to be evaluated within the evaluation area and the coordinates of the lane line in the high-precision map within the evaluation area is calculated, and the difference is determined as the lateral deviation information.

[0268] The difference between the coordinates of the traffic sign in the relocated map to be evaluated within the evaluation area and the coordinates of the traffic sign in the high-precision map within the evaluation area is calculated, and the difference is determined as the longitudinal deviation information.

[0269] Among them, the calculated lateral deviation information can be understood as generating the relationship between the points and lines representing the lane lines in the relocated map to be evaluated within the evaluation area and the lane lines in the high-precision map within the evaluation area. For example, for the lane lines in the relocated map to be evaluated within the evaluation area, determine the vertical distance between the lane lines and the lane lines in the high-precision map within the evaluation area, and determine the distance as the lateral deviation information.

[0270] Among them, calculating the longitudinal deviation information can be understood as calculating the three-dimensional coordinate deviation between the corner points of the traffic signs in the relocated map to be evaluated within the evaluation area and the corner points of the traffic signs in the high-precision map within the evaluation area. The three-dimensional coordinate deviation can be determined as the longitudinal deviation information.

[0271] Calculating the longitudinal deviation information can also be understood as calculating the three-dimensional coordinate deviation between the center point of the traffic sign in the relocated map to be evaluated within the evaluation area and the center point of the traffic sign in the high-precision map within the evaluation area. The three-dimensional coordinate deviation can be determined as the longitudinal deviation information.

[0272] That is, the longitudinal deviation information can be determined based on the corner point of the traffic sign, or based on the center point of the traffic sign, which is not limited in this embodiment.

[0273] Step 2: Determine the evaluation result according to the third deviation information.

[0274] For example, the evaluation results may include content in two dimensions, such as the recall dimension and the precision dimension.

[0275] In some embodiments, an evaluation result of the map to be evaluated may be generated based on a preset evaluation index and the third deviation information, wherein the evaluation index may be a recall rate of 85%, a precision of 95%, or the like.

[0276] Based on the above analysis, it can be seen that the third deviation information may include lateral deviation information determined based on other map elements with lateral attributes, such as lateral deviation information determined based on lane lines with the third corresponding relationship.

[0277] Accordingly, the recall rate and precision can be determined based on the mileage and lateral deviation information. Taking the recall rate as an example, the evaluation result can indicate that the recall rate within XX mileage is Y%. The recall rate and precision can be determined based on the number and longitudinal deviation information.

[0278] Based on the above analysis, it can be seen that in some embodiments, the map to be evaluated can be taken as a whole to determine the evaluation results by combining the whole and the corresponding high-precision map. In other embodiments, partial evaluation results of part of the map to be evaluated can be determined first, and then the evaluation results of the map to be evaluated can be determined by combining the evaluation results of each part.

[0279] Illustratively, the map to be evaluated includes a segmented map to be evaluated corresponding to each trajectory segment, and each trajectory segment is obtained by segmenting the acquired trajectory of the vehicle traveling on the road based on a preset interval mileage length.

[0280] The interval mileage length can be determined based on demand, historical records, and testing, and is not limited in this embodiment. For example, the trajectory can be segmented based on the interval mileage length to obtain N (N is a positive integer greater than 1) trajectory segments. The map to be evaluated in each trajectory segment is a segmented map to be evaluated, that is, the map to be evaluated includes N segmented maps to be evaluated.

[0281] In some embodiments, for each trajectory segment, a three-dimensional coordinate bounding box can be generated according to the trajectory coordinates of the trajectory segment, and the map within the three-dimensional coordinate bounding box can be intercepted from the map to be evaluated to determine it as the segmented map to be evaluated for the trajectory segment.

[0282] Accordingly, for each segmented map to be evaluated, a segmented high-precision map corresponding to the segmented map to be evaluated is obtained from the high-precision map. A segmented evaluation result is determined based on the segmented map to be evaluated and the segmented high-precision map, thereby obtaining N segmented evaluation results. Furthermore, the evaluation result of the map to be evaluated can be determined based on the N segmented evaluation results.

[0283] In this embodiment, the segmented evaluation results of each segment are determined in a segmented manner, so that each segmented evaluation result can relatively more accurately represent the evaluation result corresponding to the segmented map to be evaluated. Therefore, when the evaluation result of the map to be evaluated is obtained by combining the segmented evaluation results, the accuracy and reliability of the determined evaluation result can be improved.

[0284] See also Figure 4 , Figure 4 A schematic diagram of a map evaluation device according to an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the map evaluation device 400 includes:

[0285] The first determining unit 401 is configured to determine first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area.

[0286] The correction unit 402 is configured to correct the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated.

[0287] The second determining unit 403 is configured to determine second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map elements are at least one of the map elements except the road edge element.

[0288] The generating unit 404 is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.

[0289] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram of a map evaluation device according to another embodiment of the present disclosure. Figure 5 As shown, the map evaluation device 500 includes:

[0290] The first acquisition unit 501 is configured to acquire a single-frame map generated based on point cloud data and / or images collected when a vehicle travels on a road.

[0291] The third determining unit 502 is configured to determine the object represented by the map element represented by the single-frame map in the actual road scene.

[0292] The second acquisition unit 503 is configured to acquire other frame maps including map elements representing the object.

[0293] The fusion unit 504 is configured to fuse the single-frame map with the other frame maps to obtain the map to be evaluated.

[0294] In some embodiments, combined Figure 5 It can be seen that the fusion unit 504 includes:

[0295] A clustering subunit 5041 is configured to perform clustering processing on the single-frame map and the other frame maps to obtain a cluster map;

[0296] A construction subunit 5042 is configured to construct a topological relationship and a distance relationship between map elements representing objects in an actual road scene based on the single-frame map and the other frame maps;

[0297] The processing subunit 5043 is configured to pre-process the cluster map according to the topological relationship and the distance relationship to obtain the map to be evaluated.

[0298] In some embodiments, the processing subunit 5043 includes:

[0299] The filtering module is used to filter the cluster map according to the topological relationship and the distance relationship to obtain a filtered cluster map.

[0300] A fitting module is used to obtain a map element model including map elements according to the filtered cluster map.

[0301] The smoothing module is used to perform smoothing processing on the map element model to obtain a smoothed map element model.

[0302] The verification module is used to verify the correctness of the map elements in the smoothed map element model according to the trajectory of the vehicle traveling on the road.

[0303] The third determination module is used to determine the verified map element model as the map to be evaluated.

[0304] The first determining unit 505 is configured to determine first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area.

[0305] In some embodiments, the map elements have a type attribute, and the type attribute is used to distinguish different types of map elements. Figure 5 It can be seen that the first determining unit 505 includes:

[0306] The acquisition subunit 5051 is used to acquire road edge elements from the map to be evaluated based on the type attribute, and to acquire road edge elements from the high-precision map based on the type attribute.

[0307] The first determination subunit 5052 is used to determine a first correspondence between the road edge elements in the map to be evaluated and the road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map with the first correspondence represent the same object in the actual road scene.

[0308] The first calculation subunit 5053 is used to calculate the difference between the coordinates of the road edge element in the map to be evaluated that has the first corresponding relationship and the coordinates of the road edge element in the high-precision map to obtain the first deviation information.

[0309] The correction unit 506 is configured to correct the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated.

[0310] The second determining unit 507 is configured to determine second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map elements are at least one of the map elements other than the road edge element.

[0311] In some embodiments, combined Figure 5 It can be seen that the second determining unit 507 includes:

[0312] The second determining subunit 5071 is used to determine a second correspondence between other map elements in the high-precision map and other map elements in the revised map to be evaluated, wherein the other map elements in the high-precision map with the second correspondence and the other map elements in the revised map to be evaluated represent the same object in the actual road scene.

[0313] The second calculation subunit 5072 is used to calculate the difference between the coordinates of other map elements in the high-precision map having the second corresponding relationship and the coordinates of other map elements in the corrected map to be evaluated to obtain the second deviation information.

[0314] In some embodiments, the map element has a directional attribute, and the directional attribute includes a longitudinal attribute for representing a cross-section perpendicular to the road where the map element is located, or a lateral attribute for representing a cross-section parallel to the cross-section; the second calculation subunit 5072 is used to calculate the lateral coordinate difference between the high-precision map and the corrected map to be evaluated of the map element with the second corresponding relationship if the directional attribute of the other map elements with the second corresponding relationship is a lateral attribute, to obtain lateral deviation information.

[0315] The second calculation subunit 5072 is used to calculate the longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements having the second corresponding relationship if the direction attribute of the other map elements having the second corresponding relationship is a longitudinal attribute, to obtain longitudinal deviation information.

[0316] The second deviation information includes the lateral deviation information and / or the longitudinal deviation information.

[0317] The generating unit 508 is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.

[0318] In some embodiments, combined Figure 5 It can be seen that the generating unit 508 includes:

[0319] The relocation subunit 5081 is configured to relocate the map to be evaluated according to the second deviation information to obtain a relocated map to be evaluated.

[0320] The third determining subunit 5082 is used to determine a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map with the third correspondence and the other map elements in the relocated map to be evaluated represent the same object in the actual road scene.

[0321] The fourth determining subunit 5083 is configured to determine the evaluation result according to the third corresponding relationship.

[0322] In some embodiments, the fourth determining subunit 5083 includes:

[0323] The calculation module is used to calculate the difference between the coordinates of other map elements in the high-precision map having the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information.

[0324] A first determining module is configured to determine the evaluation result according to the third deviation information.

[0325] In some embodiments, the fourth determining subunit 5083 further includes:

[0326] an acquisition module, configured to acquire a road surface bounding box of a road described by a preset map, and to acquire a recognition area bounding box of a vehicle traveling on the road, wherein the preset map includes the high-precision map;

[0327] The second determining module is configured to determine an intersection bounding box between the road surface bounding box and the identification area bounding box, and determine the intersection bounding box as an evaluation area.

[0328] In some embodiments, the acquisition module includes:

[0329] The first acquisition submodule is used to acquire the roads and lane lines in the preset map.

[0330] A generating submodule is used to generate a bounding box for selecting a road surface including the road and the lane line.

[0331] The second acquisition submodule is configured to acquire, from the enclosing frame, a road surface enclosing frame for selecting the track according to the acquired track of the vehicle traveling on the road.

[0332] In addition, the calculation module is used to calculate the difference between the coordinates of other map elements having the third corresponding relationship in the map to be evaluated after repositioning within the evaluation area and the coordinates in the high-precision map within the area to be evaluated, so as to obtain the third deviation information.

[0333] In some embodiments, the map to be evaluated includes a segmented map to be evaluated corresponding to each trajectory segment, and each trajectory segment is obtained by segmenting the trajectory of the vehicle traveling on the road described in the map to be evaluated based on a preset interval mileage length.

[0334] Figure 6 Schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present disclosure. Figure 6 As shown, the electronic device 600 of the embodiment of the present disclosure may include: at least one processor 601 ( Figure 6Only one processor is shown); and a memory 602 in communication with the at least one processor. Memory 602 stores instructions executable by at least one processor 601. The instructions are executed by at least one processor 601 to enable electronic device 600 to implement the technical solution of any of the aforementioned method embodiments.

[0335] Optionally, the memory 602 may be independent or integrated with the processor 601 .

[0336] When the memory 602 is a device independent of the processor 601 , the electronic device 600 further includes a bus 603 for connecting the memory 602 and the processor 601 .

[0337] The electronic device provided by the embodiments of the present disclosure can execute the technical solution of any of the aforementioned method embodiments, and its implementation principles and technical effects are similar, which will not be repeated here.

[0338] The embodiments of the present disclosure further provide a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the technical solution in any of the aforementioned method embodiments.

[0339] An embodiment of the present disclosure provides a computer program product, including a computer program, which implements the technical solution of any of the aforementioned method embodiments when executed by a processor.

[0340] The embodiment of the present disclosure further provides a chip, including: a processing module and a communication interface, wherein the processing module can execute the technical solution in the aforementioned method embodiment.

[0341] Furthermore, the chip also includes a storage module (such as a memory), the storage module is used to store instructions, the processing module is used to execute the instructions stored in the storage module, and the execution of the instructions stored in the storage module enables the processing module to execute the technical solution in the aforementioned method embodiment.

[0342] It should be understood that the processor described above may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), or application-specific integrated circuits (ASICs). A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0343] The memory may include a high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk.

[0344] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the figures of this disclosure are not limited to just one bus or just one type of bus.

[0345] The storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0346] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an application-specific integrated circuit (ASIC). Of course, the processor and storage medium can also exist as discrete components in an electronic device.

[0347] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A map evaluation method, characterized in that: include: Determining first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, and correcting the map to be evaluated based on the first deviation information to obtain a corrected map to be evaluated, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area, and the road edge element includes a curb or a guardrail; Determining second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map element is at least one of the map elements other than the road edge element; An evaluation result of the map to be evaluated is generated according to the second deviation information.

2. The method according to claim 1, characterized in that The map element has a type attribute, and the type attribute is used to distinguish different types of map elements. The first deviation information of the road edge element dimension between the map to be evaluated and the high-precision map is determined, including: Acquire road edge elements from the map to be evaluated based on the type attribute, and acquire road edge elements from the high-precision map based on the type attribute; Determining a first correspondence between road edge elements in the map to be evaluated and road edge elements in the high-precision map, wherein the road edge elements in the map to be evaluated and the road edge elements in the high-precision map with the first correspondence represent the same object in an actual road scene; The difference between the coordinates of the road edge element in the map to be evaluated having the first corresponding relationship and the coordinates of the road edge element in the high-precision map is calculated to obtain the first deviation information.

3. The method according to claim 1 or 2, characterized in that Determining the second deviation information between the high-precision map and the corrected map to be evaluated in other map element dimensions includes: Determining a second correspondence between other map elements in the high-precision map and other map elements in the revised map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the revised map to be evaluated having the second correspondence represent the same object in an actual road scene; The difference between the coordinates of other map elements in the high-precision map having the second corresponding relationship and the coordinates of other map elements in the corrected map to be evaluated is calculated to obtain the second deviation information.

4. The method according to claim 3, characterized in that The map element has a direction attribute, the direction attribute including a longitudinal attribute for representing a cross-section perpendicular to the road on which the map element is located, or a transverse attribute for representing a cross-section parallel to the cross-section; the calculating the difference between the coordinates of the other map elements in the high-precision map having the second corresponding relationship and the coordinates of the other map elements in the corrected map to be evaluated to obtain the second deviation information includes: If the direction attribute of the other map element having the second corresponding relationship is a horizontal attribute, calculating the horizontal coordinate difference between the high-precision map and the corrected map to be evaluated of the map element having the second corresponding relationship to obtain horizontal deviation information; If the direction attribute of the other map elements having the second corresponding relationship is a longitudinal attribute, calculating the longitudinal coordinate difference between the high-precision map and the corrected map to be evaluated of the other map elements having the second corresponding relationship to obtain longitudinal deviation information; The second deviation information includes the lateral deviation information and / or the longitudinal deviation information.

5. The method according to any one of claims 1 to 4, characterized in that Generating an evaluation result of the map to be evaluated according to the second deviation information includes: repositioning the map to be evaluated according to the second deviation information to obtain a repositioned map to be evaluated; Determining a third correspondence between other map elements in the high-precision map and other map elements in the relocated map to be evaluated, wherein the other map elements in the high-precision map and the other map elements in the relocated map to be evaluated having the third correspondence represent the same object in the actual road scene; The evaluation result is determined according to the third corresponding relationship.

6. The method according to claim 5, characterized in that Determining the evaluation result according to the third corresponding relationship includes: Calculate the difference between the coordinates of other map elements in the high-precision map having the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information, and determine the evaluation result based on the third deviation information.

7. The method according to claim 6, characterized in that The method further comprises: Obtaining a road surface bounding box of a road described by a preset map, and obtaining a recognition area bounding box of a vehicle traveling on the road, wherein the preset map includes the high-precision map; Determine an intersection bounding box between the road surface bounding box and the identification area bounding box, and determine the intersection bounding box as an evaluation area; And, the calculation of the difference between the coordinates of other map elements in the high-precision map having the third corresponding relationship and the coordinates of other map elements in the relocated map to be evaluated to obtain third deviation information includes: calculating the difference between the coordinates of other map elements having the third corresponding relationship in the relocated map to be evaluated within the evaluation area and the coordinates in the high-precision map within the evaluation area to obtain the third deviation information.

8. The method according to claim 7, characterized in that The method of obtaining a road surface bounding box of a road on a preset map includes: Obtaining roads and lane lines in the preset map, and generating a bounding box for selecting a road surface including the roads and lane lines; According to the acquired trajectory of the vehicle traveling on the road, a road surface bounding box for selecting the trajectory is acquired from the bounding box.

9. The method according to any one of claims 1 to 8, characterized in that The map to be evaluated includes a segmented map to be evaluated corresponding to each trajectory segment. Each trajectory segment is obtained by segmenting the acquired trajectory of the vehicle traveling on the road described in the map to be evaluated based on a preset interval mileage length.

10. A map evaluation device comprising: a first determining unit, configured to determine first deviation information between the map to be evaluated and the high-precision map in a road edge element dimension, wherein the map to be evaluated and the high-precision map are maps describing geographical features of the same area, and the road edge element includes a curb or a guardrail; a correction unit, configured to correct the map to be evaluated according to the first deviation information to obtain a corrected map to be evaluated; a second determining unit, configured to determine second deviation information between the high-precision map and the corrected map to be evaluated in dimensions of other map elements, wherein the other map element is at least one of the map elements other than the road edge element; A generating unit is configured to generate an evaluation result of the map to be evaluated according to the second deviation information.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images