Abnormal pavement element recognition method, device and equipment and storage medium

By constructing a grid map of pavement elements and identifying abnormal pavement elements based on the grid coverage, the problem of abnormal pavement elements affecting the accuracy of road maps in traditional technology is solved, and an efficient and simple identification process is achieved.

CN119048997APending Publication Date: 2024-11-29SHENYANG MXNAVI CO LTD

Patent Information

Application Number
CN202410420533.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-04-09
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

In traditional technology, the acquisition accuracy and classification algorithm accuracy of pavement elements affect the existence of abnormal pavement elements, affecting the accuracy of road maps.

Method used

By constructing a raster map of pavement elements, determine confidence weights and semantic weights based on the raster coverage, identify abnormal pavement elements, avoid large amounts of operations and dependence on other factors, and make the operation simple.

Benefits of technology

It improves the efficiency and accuracy of abnormal pavement elements recognition, ensures the quality of the road map, and is convenient and fast to operate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048997A_ABST
    Figure CN119048997A_ABST
Patent Text Reader

Abstract

The invention relates to an abnormal road surface element recognition method and device, equipment and a storage medium. The method comprises the steps that at least one road surface element of the same category corresponding to a target road is acquired; constructing a grid map comprising the road surface elements; and according to the grid coverage condition of each road surface element in the grid map, identifying abnormal road surface elements in the at least one road surface element. By adopting the technical scheme, the influence on the quality of the same type of pavement elements corresponding to the target road due to the existence of the abnormal pavement elements in the same type of pavement elements is avoided. Besides, in the abnormal road surface element identification process, only the grid coverage condition of the road surface elements in the grid map including the road surface elements is used, other factors are not needed, the operation is convenient and fast, the calculation amount is small, and the identification efficiency is high.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of map technology, and in particular to a method, device, equipment and storage medium for identifying abnormal road surface elements. Background Art

[0002] Road maps play an important role in the navigation or path planning process of mobile devices. The generation of road maps is inseparable from the collection and analysis of road surface elements.

[0003] In traditional technology, road surface elements are usually classified to divide road surface elements of the same category as the basis for generating road maps.

[0004] However, due to the influence of the accuracy of road surface element collection and the accuracy of the classification algorithm itself, the above method results in the existence of abnormal road surface elements in the same category, which affects the accuracy of the subsequently generated road map. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, equipment and storage medium for identifying abnormal road elements in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for identifying abnormal road surface elements, comprising:

[0007] Acquire at least one road surface element of the same category corresponding to the target road;

[0008] Constructing a grid map including each of the road surface elements;

[0009] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0010] In one of the embodiments, the identifying abnormal road surface elements in the at least one road surface element according to the grid coverage of each road surface element in the grid map includes: determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; determining the semantic weight of each road surface element according to the confidence weight of each grid; and identifying the abnormal road surface elements in the at least one road surface element according to the semantic weight of each road surface element.

[0011] In one of the embodiments, determining the semantic weight of each of the pavement elements based on the confidence weight of each grid includes: identifying abnormal grids in each grid based on the confidence weight of each grid; and determining the semantic weight of the corresponding pavement element based on the proportion of abnormal grids in the grids covered by the pavement element.

[0012] In one of the embodiments, identifying abnormal grids in each grid according to the confidence weight of each grid includes: determining an abnormal weight threshold corresponding to the grid map; and identifying abnormal grids in each grid according to the size relationship between the confidence weight of each grid and the abnormal weight threshold.

[0013] In one of the embodiments, determining the abnormal weight threshold corresponding to the grid map includes: determining the abnormal weight threshold corresponding to the grid map based on the grid coverage of the at least one road surface element in the grid map; or determining the abnormal weight threshold corresponding to the grid map based on the number of elements of the at least one road surface element.

[0014] In one of the embodiments, the confidence weight of each grid in the grid map is determined according to the grid coverage of each road surface element in the grid map, including: setting the confidence weight of each grid in the grid map as an initial weight; taking any unprocessed road surface element among the at least one road surface element as the current road surface element; determining the grid covered by the current road surface element in the grid map according to the grid covered by the element boundary of the current road surface element in the grid map; and updating the confidence weight of the grid covered by the current road surface element in the grid map.

[0015] In one of the embodiments, for non-surface road surface elements, before constructing a grid map including each of the road surface elements, the method further includes: expanding the road surface elements according to a grid size of the grid map and acquisition parameters of the road surface elements to update the road surface elements.

[0016] In a second aspect, the present application also provides a device for identifying abnormal road surface elements, comprising:

[0017] An acquisition module, used for acquiring at least one road surface element of the same category corresponding to the target road;

[0018] A construction module, used for constructing a grid map including each of the road surface elements;

[0019] The identification module is used to identify abnormal road surface elements in the at least one road surface element according to the grid coverage of each road surface element in the grid map.

[0020] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0021] Acquire at least one road surface element of the same category corresponding to the target road;

[0022] Constructing a grid map including each of the road surface elements;

[0023] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0024] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0025] Acquire at least one road surface element of the same category corresponding to the target road;

[0026] Constructing a grid map including each of the road surface elements;

[0027] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0028] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0029] Acquire at least one road surface element of the same category corresponding to the target road;

[0030] Constructing a grid map including each of the road surface elements;

[0031] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0032] The above-mentioned abnormal road surface element identification method, device, equipment and storage medium, by constructing a grid map including at least one road surface element of the same category corresponding to the target road, and identifying abnormal road surface elements in each road surface element according to the grid coverage of different road surface elements in the grid map, avoids the existence of abnormal road surface elements in the same category affecting the quality of road surface elements of the same category corresponding to the target road. In addition, in the process of abnormal road surface element identification, only the grid coverage of the road surface elements in the grid map including each road surface element is used, without the need to use other factors, the operation is convenient and fast, the amount of calculation is small, and the identification efficiency is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A schematic diagram of a flow chart of a method for identifying abnormal road surface elements in one embodiment;

[0035] Figure 2 A schematic diagram of a flow chart of an abnormal road surface element identification step in one embodiment;

[0036] Figure 3 A flowchart of a step of determining a semantic weight in one embodiment;

[0037] Figure 4 A schematic diagram of a flow chart of a method for identifying abnormal road surface elements in another embodiment;

[0038] Figure 5 is a structural block diagram of an abnormal road surface element identification device in one embodiment;

[0039] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] In an exemplary embodiment, Figure 1 As shown, a method for identifying abnormal road surface elements is provided. This embodiment uses the method applied to a terminal as an example. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. This application does not make any limitation on this. In this embodiment, the method includes the following steps:

[0042] S110: Acquire at least one road surface element of the same category corresponding to the target road.

[0043] The target road may be understood as a road on which abnormal road surface elements need to be identified. The road surface elements may be understood as elements with certain semantics on the road surface, such as lane lines and guide signs. The guide signs may include guide arrows.

[0044] Among them, the category of pavement elements is used to distinguish pavement elements of different attributes in different sections of the target road. Exemplarily, the category of pavement elements can be obtained by classifying pavement elements of different attributes (such as guide signs and lane lines, etc.) in different sections of the target road. It should be noted that the present application does not impose any limitation on the classification method. For example, cluster analysis can be used to classify pavement elements of different attributes in different sections to obtain pavement elements with the same attributes in the same section and corresponding to the same location area.

[0045] The pavement elements may be surface-type pavement elements or non-surface-type pavement elements. For non-surface-type pavement elements, such as one-dimensional pavement elements corresponding to linear pavement elements, in order to ensure the accuracy of the recognition results of subsequent abnormal pavement element recognition, the non-surface-type pavement elements may also be converted into surface-type pavement elements.

[0046] In an optional embodiment, the road surface elements may be expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements, thereby converting the non-surface road surface elements into two-dimensional surface road surface elements.

[0047] The grid size of the grid map can be set by the technicians according to their needs or experience, or determined repeatedly through a large number of experiments, and this application does not impose any restrictions on this. The acquisition parameters of the road surface elements may include acquisition accuracy and acquisition distance; the acquisition distance is used to characterize the spatial distance between the acquisition device corresponding to the road surface element and the actual road surface element. In a specific example, the grid size can be 0.2m×0.2m.

[0048] In an optional embodiment, the collection distance may be determined according to the spatial distance between the driving track of the collection device and the collected road surface elements, wherein the larger the collection distance, the lower the collection accuracy.

[0049] In a specific implementation, the following formula can be used to expand non-surface road elements to obtain surface road elements: buffer = grid + accuracy × VD. Wherein, buffer is the expansion length of the sampling points in the road element; grid is the grid size of the grid map; accuracy is the acquisition accuracy of the acquisition device corresponding to the road element; VD is the acquisition distance corresponding to the sampling points in the road element. Wherein, the expansion lengths corresponding to different sampling points in the same road element can be the same or different, and this application does not impose any limitation on this.

[0050] S120: Construct a grid map including various road surface elements.

[0051] For example, a grid map including various road elements can be constructed according to a preset direction. The preset direction can be set or adjusted by a technician according to needs or experience, and this application does not impose any limitation on this. In an optional embodiment, the preset direction can be the positive direction corresponding to the view display interface.

[0052] In a specific implementation, an image composed of road surface elements of the same category can be used as a reference image; based on the grid size of the grid map, the minimum circumscribed rectangle of the reference image in a preset direction is constructed to obtain a grid map including each road surface element. It is worth noting that the grid here is a square grid.

[0053] Optionally, a minimum bounding rectangle of the reference image in a preset direction may be constructed; the minimum bounding rectangle is divided according to the grid size of the grid map to obtain a grid map. In the end, the grid that is less than the grid size is padded according to the grid size. Alternatively, the length and width of the minimum bounding rectangle may be expanded to integer multiples of the grid size in advance, and then the expanded minimum bounding rectangle may be divided according to the grid size of the grid map to obtain a grid map.

[0054] S130: Identify an abnormal road surface element in at least one road surface element according to the grid coverage of each road surface element in the grid map.

[0055] Since the road surface elements of the same category correspond to the same road element in the real space, the grid coverage of the road surface elements of the same category in the grid map should be relatively concentrated or similar. Therefore, the grid coverage of each road surface element in the grid map can be introduced to identify abnormal road surface elements among the road surface elements of the same category.

[0056] In an optional embodiment, abnormal road surface elements among different road surface elements may be determined based on the distribution of grids covered by different road surface elements in the grid map.

[0057] The embodiment of the present application constructs a grid map including at least one road surface element of the same category corresponding to the target road, and identifies abnormal road surface elements in each road surface element according to the grid coverage of different road surface elements in the grid map, thereby avoiding the situation that the quality of road surface elements of the same category corresponding to the target road is affected by the existence of abnormal road surface elements in the road surface elements of the same category. In addition, in the process of identifying abnormal road surface elements, only the grid coverage of the road surface elements in the grid map including each road surface element is used, without the need to use other factors, the operation is convenient and fast, the amount of calculation is small, and the recognition efficiency is high.

[0058] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment. In this optional embodiment, the abnormal road surface element identification step of S130 is refined.

[0059] See also Figure 2 The steps for identifying abnormal road surface elements shown include:

[0060] S210 : Determine the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map.

[0061] The confidence weight of the grid can be understood as the numerical quantification result of the coverage credibility of the same category of road elements in the grid, which is used to characterize the probability of whether the actual space area corresponding to the grid contains credible semantics. The larger the confidence weight of the grid, the greater the distribution possibility of the road elements of this category corresponding to the grid position in the actual space.

[0062] For example, for any road surface element, the grid covered can be determined according to the grid coverage of the road surface element in the grid map; for any covered grid, the cumulative number of times different road surface elements are covered is counted; and the confidence weight of the corresponding grid is determined according to the cumulative number, wherein the confidence weight increases with the increase of the cumulative number.

[0063] Optionally, based on the first preset function, the confidence weight of the corresponding grid is determined according to the cumulative number of times. The first preset function is an increasing function with the cumulative number of times as the independent variable and the confidence weight as the dependent variable. The present application does not impose any restrictions on the specific content of the first preset function. In a specific implementation, the cumulative number of times corresponding to the grid can be directly used as the confidence weight of the corresponding grid.

[0064] In an optional embodiment, the confidence weight of each grid in the grid map can be set as an initial weight; any unprocessed road surface element in at least one road surface element is used as the current road surface element; the grid covered by the current road surface element in the grid map is determined based on the grid covered by the element boundary of the current road surface element in the grid map; and the confidence weight of the grid covered by the current road surface element in the grid map is updated.

[0065] Exemplarily, determining the grid covered by the current pavement element in the grid map based on the grid covered by the element boundary of the current pavement element in the grid map may include: determining the boundary grid corresponding to the element boundary of the current pavement element based on the grid covered by the current pavement element; using the grid within the closed area formed by the boundary grid as the filling grid; and using the boundary grid and the filling grid corresponding to the current pavement element as the grid covered by the current pavement element.

[0066] Specifically, the grid index of the grid covered by the element boundary of the current road surface element is determined; the grid index within the area surrounded by the grid index is determined; and the grids corresponding to all grid indexes corresponding to the current road surface element are used as the grids covered by the current road surface element.

[0067] Exemplarily, the confidence weight of the grid covered by the current road surface element in the grid map is updated by increasing the confidence weight of the grid covered by the current road surface element in the grid map according to the preset weight step length to update the confidence weight of the corresponding grid. The preset weight step length can be set or adjusted by the technician according to needs or experience, and this application does not impose any limitation on this, for example, it can be 1.

[0068] It can be understood that by introducing the grids covered by the element boundaries of the current road surface element in the grid map, all the grids covered by the current road surface element in the grid map are further determined, without having to compare whether each grid is covered, thereby improving the efficiency of determining the grids covered by the current road surface element in the grid map.

[0069] The following will take the 5*5 grid map constructed by the same category of road surface elements A~D as an example to explain the process of determining the confidence weight in detail. Among them, the grids covered by road surface element A include G 31 , G 21 , G 12 , G 13 and G 14 ; The grids covered by the road surface element B include G 42 , G 41 , G 31 , G 21 , G 22 , G 23 and G 13 ; The grids covered by the pavement element C include G 41 , G 31 , G 32 , G 33 , G 23 and G 24 ; The grids covered by the road surface element D include G 42 , G 32 , G 22 , G 23 and G 24 .

[0070] Each grid G ​​in the grid map is pre-set ij The confidence weight of the grid G ​​is set to the initial weight 0. 12 , G 14 and G 33All of them are covered once by road surface elements A~D, so the confidence weights of the corresponding grids are adjusted to 1, that is, w(G 12 )=1, w(G 14 )=1 and w(G 33 )=1. Among them, the grid G 13 , G 21 , G 22 , G 24 , G 32 , G 41 and G 42 All of them are covered by road surface elements A~D for 2 times cumulatively, so the confidence weights of the corresponding grids are adjusted to 2, that is, w(G 13 )=2, w(G 21 )=2, w(G 22 )=2, w(G 24 )=2, w(G 32 )=2, w(G 41 )=2 and w(G 42 )=2. Among them, the grid G 23 and G 31 All of them are covered by road surface elements A~D for 3 times cumulatively. Therefore, the confidence weights of the corresponding grids are adjusted to 3, that is, w(G 23 )=3 and w(G 31 ) = 3. The remaining uncovered grids G 11 , G 15 , G 25 , G 34 , G 35 , G 43 , G 44 , G 45 , G 51 , G 52 , G 53 , G 54 and G 55 Its confidence weight remains unchanged, that is, 0.

[0071] S220: Determine the semantic weight of each road surface element according to the confidence weight of each grid.

[0072] The semantic weight of a road surface element can be understood as a numerical quantification of the possibility that the road surface element corresponds to the road semantics in the actual space. The higher the semantic weight, the greater the possibility that the road surface element actually corresponds to a road element in the actual space.

[0073] In an optional embodiment, for any pavement element, the semantic weight of the pavement element can be determined based on the ratio between the cumulative weight value of the confidence weights of the grids covered by the pavement element in the grid map and the cumulative weight value of the confidence weights of the grids covered by pavement elements of the same category.

[0074] In another optional embodiment, abnormal grids may be identified based on confidence weights of different grids, and the semantic weights of corresponding road surface elements may be determined based on the proportion of abnormal grids in the road surface elements.

[0075] S230: Identify an abnormal road surface element in at least one road surface element according to the semantic weight of each road surface element.

[0076] Exemplarily, according to the semantic weight of each road surface element and the relationship between the preset semantic weight threshold, an abnormal road surface element in at least one road surface element is determined. The preset semantic weight threshold can be set by a technician according to needs or experience, or determined repeatedly through a large number of experiments, and this application does not impose any limitation on this. For example, the preset semantic weight threshold can be 0.3.

[0077] In a specific implementation, if the semantic weight of a pavement element is less than a preset semantic weight threshold, the pavement element is determined to be an abnormal pavement element; if the semantic weight of a pavement element is not less than the preset semantic weight threshold, the pavement element is determined to be a normal pavement element.

[0078] The embodiment of the present application introduces the confidence weight of the grid to numerically quantify the grid coverage of the road surface elements in the grid map, and determines the semantic weight of each road surface element according to the confidence weight of each grid, thereby realizing the numerical quantification of the semantic carrying of different road surface elements, and then identifying abnormal road surface elements according to the semantic weight of each road surface element. The recognition process is convenient to operate and requires little data calculation, thereby improving the recognition efficiency of abnormal road surface elements and the accuracy of recognition results.

[0079] On the basis of the technical solutions of the above-mentioned embodiments, the present application further provides an optional embodiment. In this optional embodiment, the step of determining the semantic weights of the road surface elements in S220 is refined.

[0080] See also Figure 3 The steps for determining the semantic weight shown include:

[0081] S310 , identifying abnormal grids in each grid according to the confidence weight of each grid.

[0082] In an optional embodiment, abnormal grids in each grid are identified based on the distribution of confidence weights of different grids.

[0083] Exemplarily, an abnormal weight threshold corresponding to the grid map may be determined; and abnormal grids in each grid may be identified based on the size relationship between the confidence weight thresholds of each grid.

[0084] Specifically, if the confidence weight of the grid is less than the confidence weight threshold, the grid is determined to be an abnormal grid; if the confidence weight of the grid is not less than the confidence weight threshold, the grid is determined to be a normal grid, that is, not an abnormal grid.

[0085] Optionally, the abnormal weight threshold can be set or adjusted by technicians according to needs or experience, and this application does not impose any limitation on this.

[0086] Or, optionally, the abnormal weight threshold may be determined according to a grid coverage condition of at least one road surface element in the grid map.

[0087] Exemplarily, the confidence weight of each grid can be determined according to the grid coverage of different road surface elements in the grid map; and the abnormal weight threshold corresponding to the grid map can be determined according to the statistical data of the confidence weight.

[0088] Specifically, the statistical data of the confidence weights may include a weight mean and a weight standard deviation of the confidence weights; and the difference between the weight mean and the corresponding standard deviation of the confidence weights is used as the abnormal weight threshold corresponding to the grid map.

[0089] Or optionally, the abnormal weight threshold corresponding to the grid map may be determined according to the number of elements of at least one road surface element.

[0090] Exemplarily, the same or different abnormal weight thresholds may be set in advance for different numbers of elements based on experience or test conditions.

[0091] It can be understood that by determining the abnormal weight threshold through at least one of the above methods, the richness and diversity of the abnormal weight threshold are improved, which helps to improve the diversity of abnormal road surface element identification methods.

[0092] S320: Determine the semantic weight of the corresponding road surface element according to the proportion of abnormal grids in the grids covered by the road surface element.

[0093] Exemplarily, based on the second preset function, the semantic weight of the corresponding road surface element is determined according to the proportion of abnormal grids in the grid covered by the road surface element. The second preset function is a decreasing function with the proportion of abnormal grids in the grid covered by the road surface element as the independent variable and the semantic weight as the dependent variable. The present application does not impose any limitation on the specific content of the second preset function. In a specific implementation method, the difference between the preset value (such as 1) and the above proportion can be directly used as the semantic weight of the corresponding road surface element.

[0094] For example, if the grids occupied by road element A in the grid map include G 31 , G 21 , G 12 , G 13 and G 14 , the abnormal grids in the grid map include G 21 , G 22 and G 23 , accordingly, the semantic weight of pavement element A is: . Where W(A) is the semantic weight of road surface element A; Determines the number of elements in a collection.

[0095] The embodiment of the present application introduces abnormal grids based on the confidence weights of each grid, and determines the semantic weight of the pavement element according to the proportion of abnormal grids in the grids covered by the pavement element. This allows the semantic weight determination process of the pavement element to fully consider the proportion of abnormal grids, making the subsequent recognition results of abnormal pavement elements more reasonable and accurate, while avoiding the misidentification of pavement elements with abnormal grids as abnormal pavement elements.

[0096] On the basis of the technical solutions of the above embodiments, further, the abnormal road surface elements in at least one road surface element of the same category can be eliminated; the eliminated road surface elements are fitted to obtain the target road surface elements. The advantage of this is that the accuracy of the target road surface elements is improved, which helps to improve the accuracy of the high-precision map constructed based on the target road surface elements.

[0097] In an optional embodiment, the similarity between different road surface elements can also be determined based on the semantic weight of the road surface element and other attributes of the road surface element. The other attributes of the road surface element may include at least one of element type, position, length, width, and running direction, etc., which is not limited in this application. The element type may be a lane line or a guide arrow, etc.

[0098] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0099] Based on the same inventive concept, the embodiment of the present application also provides an abnormal road surface element identification device for implementing the abnormal road surface element identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more abnormal road surface element identification device embodiments provided below can refer to the limitations of the abnormal road surface element identification method above, and will not be repeated here.

[0100] Based on the technical solutions of the above embodiments, the present application also provides an optional embodiment, in which the abnormal road surface element identification process is described in detail.

[0101] See also Figure 4 The abnormal road surface element identification method shown includes:

[0102] S401: Acquire at least one road surface element of the same category corresponding to a target road.

[0103] S402: For non-surface road surface elements, the road surface elements are expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements.

[0104] S403: Construct a grid map including various road surface elements.

[0105] S404: setting the confidence weight of each grid in the grid map as an initial weight.

[0106] S405: Use any unprocessed road surface element among the at least one road surface element as the current road surface element.

[0107] S406: Determine the grids covered by the current road surface element in the grid map according to the grids covered by the element boundary of the current road surface element in the grid map.

[0108] S407: Update the confidence weight of the grid covered by the current road surface element in the grid map.

[0109] S408. Determine whether there are unprocessed road surface elements; if so, return to execute S405; otherwise, continue to execute S409A or S409B.

[0110] S409A, determine the abnormal weight threshold corresponding to the grid map according to the statistical data of the confidence weight of each grid; and continue to execute S410.

[0111] S409B, determining an abnormal weight threshold corresponding to the grid map according to the number of elements of at least one road surface element; and continuing to execute S410.

[0112] S410 , identifying abnormal grids in each grid according to the relationship between the confidence weight of each grid and the abnormal weight threshold.

[0113] S411. Determine the semantic weight of the corresponding road surface element according to the proportion of abnormal grids in the grids covered by the road surface element.

[0114] S412: Identify an abnormal road surface element in at least one road surface element according to the semantic weight of each road surface element.

[0115] In an exemplary embodiment, Figure 5 As shown, a device for identifying abnormal road surface elements is provided, including: an acquisition module 510, a construction module 520 and an identification module 530. Among them,

[0116] An acquisition module 510, configured to acquire at least one road surface element of the same category corresponding to the target road;

[0117] A construction module 520, configured to construct a grid map including each of the road surface elements;

[0118] The identification module 530 is used to identify abnormal road surface elements in the at least one road surface element according to the grid coverage of each road surface element in the grid map.

[0119] In one embodiment, the identification module 530 includes: a confidence weight determination unit, used to determine the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; a semantic weight determination unit, used to determine the semantic weight of each road surface element according to the confidence weight of each grid; an abnormal element identification unit, used to identify abnormal road surface elements in at least one road surface element according to the semantic weight of each road surface element.

[0120] In one of the embodiments, the semantic weight determination unit includes: an abnormal grid identification subunit, which is used to identify abnormal grids in each grid according to the confidence weight of each grid; and a semantic weight determination subunit, which is used to determine the semantic weight of the corresponding pavement element according to the proportion of abnormal grids in the grid covered by the pavement element.

[0121] In one of the embodiments, the abnormal grid identification subunit is specifically used to: determine the abnormal weight threshold corresponding to the grid map; and identify the abnormal grids in each grid according to the size relationship between the confidence weight of each grid and the abnormal weight threshold.

[0122] In one of the embodiments, the abnormal grid identification subunit, when executing the determination of the abnormal weight threshold corresponding to the grid map, is specifically used to: determine the abnormal weight threshold corresponding to the grid map based on the grid coverage of the at least one road surface element in the grid map; or determine the abnormal weight threshold corresponding to the grid map based on the number of elements of the at least one road surface element.

[0123] In one of the embodiments, the confidence weight determination unit includes: a weight initialization subunit, used to set the confidence weight of each grid in the grid map as an initial weight; a pavement element selection subunit, used to take any unprocessed pavement element of the at least one pavement element as the current pavement element; a covered grid determination subunit, used to determine the grid covered by the current pavement element in the grid map based on the grid covered by the element boundary of the current pavement element in the grid map; and a confidence weight update subunit, used to update the confidence weight of the grid covered by the current pavement element in the grid map.

[0124] In one of the embodiments, the device also includes a pavement element updating module, which is used to expand the pavement elements for non-surface pavement elements according to the grid size of the grid map and the acquisition parameters of the pavement elements before constructing the grid map including each of the pavement elements, so as to update the pavement elements.

[0125] Each module in the abnormal road element identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0126] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for identifying abnormal road surface elements is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0127] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0129] Acquire at least one road surface element of the same category corresponding to the target road;

[0130] Constructing a grid map including each of the road surface elements;

[0131] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0132] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; determining the semantic weight of each road surface element according to the confidence weight of each grid; and identifying abnormal road surface elements in at least one road surface element according to the semantic weight of each road surface element.

[0133] In one embodiment, when the processor executes the computer program, the following steps are also implemented: identifying abnormal grids in each grid according to the confidence weight of each grid; and determining the semantic weight of the corresponding road surface element according to the proportion of abnormal grids in the grids covered by the road surface element.

[0134] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determining an abnormal weight threshold corresponding to the grid map; and identifying abnormal grids in each grid according to a size relationship between the confidence weight of each grid and the abnormal weight threshold.

[0135] In one embodiment, when the processor executes the computer program, the following steps are also implemented: determining the abnormal weight threshold corresponding to the grid map based on the grid coverage of the at least one road surface element in the grid map; or determining the abnormal weight threshold corresponding to the grid map based on the number of elements of the at least one road surface element.

[0136] In one embodiment, when the processor executes the computer program, the following steps are also implemented: setting the confidence weight of each grid in the grid map as an initial weight; taking any unprocessed road surface element among the at least one road surface element as the current road surface element; determining the grid covered by the current road surface element in the grid map based on the grid covered by the element boundary of the current road surface element in the grid map; and updating the confidence weight of the grid covered by the current road surface element in the grid map.

[0137] In one embodiment, when the processor executes the computer program, the following steps are also implemented: for non-surface road surface elements, before constructing a grid map including each of the road surface elements, the road surface elements are expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements.

[0138] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0139] Acquire at least one road surface element of the same category corresponding to the target road;

[0140] Constructing a grid map including each of the road surface elements;

[0141] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0142] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; determining the semantic weight of each road surface element according to the confidence weight of each grid; and identifying abnormal road surface elements in at least one road surface element according to the semantic weight of each road surface element.

[0143] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying abnormal grids in each grid according to the confidence weight of each grid; and determining the semantic weight of the corresponding road surface element according to the proportion of abnormal grids in the grids covered by the road surface element.

[0144] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining an abnormal weight threshold corresponding to the grid map; and identifying abnormal grids in each grid according to the size relationship between the confidence weight of each grid and the abnormal weight threshold.

[0145] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the abnormal weight threshold corresponding to the grid map based on the grid coverage of the at least one road surface element in the grid map; or determining the abnormal weight threshold corresponding to the grid map based on the number of elements of the at least one road surface element.

[0146] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: setting the confidence weight of each grid in the grid map as an initial weight; taking any unprocessed road surface element among the at least one road surface element as the current road surface element; determining the grid covered by the current road surface element in the grid map based on the grid covered by the element boundary of the current road surface element in the grid map; and updating the confidence weight of the grid covered by the current road surface element in the grid map.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for non-surface road surface elements, before constructing a grid map including each of the road surface elements, the road surface elements are expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements.

[0148] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0149] Acquire at least one road surface element of the same category corresponding to the target road;

[0150] Constructing a grid map including each of the road surface elements;

[0151] According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

[0152] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; determining the semantic weight of each road surface element according to the confidence weight of each grid; and identifying abnormal road surface elements in at least one road surface element according to the semantic weight of each road surface element.

[0153] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: identifying abnormal grids in each grid according to the confidence weight of each grid; and determining the semantic weight of the corresponding road surface element according to the proportion of abnormal grids in the grids covered by the road surface element.

[0154] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining an abnormal weight threshold corresponding to the grid map; and identifying abnormal grids in each grid according to the size relationship between the confidence weight of each grid and the abnormal weight threshold.

[0155] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: determining the abnormal weight threshold corresponding to the grid map based on the grid coverage of the at least one road surface element in the grid map; or determining the abnormal weight threshold corresponding to the grid map based on the number of elements of the at least one road surface element.

[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: setting the confidence weight of each grid in the grid map as an initial weight; taking any unprocessed road surface element among the at least one road surface element as the current road surface element; determining the grid covered by the current road surface element in the grid map based on the grid covered by the element boundary of the current road surface element in the grid map; and updating the confidence weight of the grid covered by the current road surface element in the grid map.

[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: for non-surface road surface elements, before constructing a grid map including each of the road surface elements, the road surface elements are expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0160] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying abnormal road surface elements, characterized in that: include: Acquire at least one road surface element of the same category corresponding to the target road; Constructing a grid map including each of the road surface elements; According to the grid coverage of each of the road surface elements in the grid map, an abnormal road surface element in the at least one road surface element is identified.

2. The method according to claim 1, characterized in that The step of identifying an abnormal road surface element in the at least one road surface element according to the grid coverage of each road surface element in the grid map comprises: Determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map; Determining the semantic weight of each of the road surface elements according to the confidence weight of each grid; According to the semantic weight of each of the road surface elements, an abnormal road surface element in the at least one road surface element is identified.

3. The method according to claim 2, characterized in that Determining the semantic weight of each road surface element according to the confidence weight of each grid includes: According to the confidence weight of each grid, identify the abnormal grid in each grid; The semantic weight of the corresponding road surface element is determined according to the proportion of abnormal grids in the grids covered by the road surface element.

4. The method according to claim 3, characterized in that The step of identifying abnormal grids in each grid according to the confidence weight of each grid includes: Determine an abnormal weight threshold corresponding to the grid map; According to the size relationship between the confidence weight of each grid and the abnormal weight threshold, the abnormal grid in each grid is identified.

5. The method according to claim 4, characterized in that The determining of the abnormal weight threshold corresponding to the grid map includes: Determining an abnormal weight threshold corresponding to the grid map according to the grid coverage of the at least one road surface element in the grid map; or, An abnormal weight threshold corresponding to the grid map is determined according to the element quantity of the at least one road surface element.

6. The method according to claim 2, characterized in that Determining the confidence weight of each grid in the grid map according to the grid coverage of each road surface element in the grid map includes: Setting the confidence weight of each grid in the grid map as an initial weight; Taking any unprocessed pavement element among the at least one pavement element as a current pavement element; Determining the grid covered by the current road surface element in the grid map according to the grid covered by the element boundary of the current road surface element in the grid map; The confidence weight of the grid covered by the current road surface element in the grid map is updated.

7. The method according to any one of claims 1 to 6, characterized in that: For non-surface road surface elements, before constructing the grid map including each of the road surface elements, the method further includes: The road surface elements are expanded according to the grid size of the grid map and the acquisition parameters of the road surface elements to update the road surface elements.

8. An abnormal road surface element identification device, characterized in that: include: An acquisition module, used for acquiring at least one road surface element of the same category corresponding to the target road; A construction module, used for constructing a grid map including each of the road surface elements; The identification module is used to identify abnormal road surface elements in the at least one road surface element according to the grid coverage of each road surface element in the grid map.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Method and device for generating traffic sign line map and storage medium

    CN113298910A

  • Lane line detection method and device

    CN115187944A

  • Crowdsourcing map evaluation method and device based on lane lines

    CN116109576A

  • Map construction method and device

    CN118365812A

Cited By

  • Neural network and point cloud spatial feature-based road center line determination method and system

    CN120808115A