A lane line data fusion method and system with virtual and real attributes

Abstract

This invention relates to a method and system for fusion of lane line data with real and virtual attributes. The method corrects solid lines misidentified as dashed lines in a lane line dataset Ω using a clustering approach. A threshold for lane line length is set, and the lane line dataset Ω is divided into long lane line datasets and short lane line datasets based on this threshold. The method then corrects dashed lines misidentified as solid lines in the short lane line data using a clustering approach. The corrected lane line dataset Ω is further divided into dashed lane line datasets and solid lane line datasets. The lane lines in the dashed and solid lane line datasets are then fused and optimized separately before being merged. By accumulating multiple data collections in the cloud and using algorithms to correct the real and virtual attributes of lane lines, the subsequent fusion of lane lines and the construction of topology layers produce better results.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving, and in particular to a method and system for fusing lane line data with virtual and real attributes. Background Technology

[0002] In the field of autonomous driving, during the high-precision map creation process, the lane line data collected by the data acquisition vehicle is processed by the on-board equipment. Each vehicle's lane line data for each trip is segmented into individual lane lines, and each lane line is identified to determine its solid / phasic attribute. However, due to various factors such as vehicle occlusion, lane line paint wear, and local road repairs, the on-board equipment may misjudge the solid / phasic attribute of the lane lines. After full-map pose optimization, subsequent lane line fusion and mapping processes will produce fusion attribute errors, thus affecting the construction of the topology layer. Since the on-board equipment identifies the solid / phasic attribute of lane lines in real time during data acquisition, it lacks an effective solution to this problem. Summary of the Invention

[0003] This invention addresses the technical problems existing in the prior art by providing a method and system for fusion of lane line data with virtual and real attributes. It solves the problem that various situations, such as vehicle occlusion, lane line paint wear, and local road maintenance, can lead to incorrect judgments of the virtual and real attributes of lane lines by the vehicle-side equipment during lane line data collection. Furthermore, the problem of misidentification cannot be resolved by a single-pass data collection by the vehicle-side equipment. By accumulating multiple data collections in the cloud and using algorithms to correct the virtual and real attributes of lane lines, the subsequent fusion of lane lines and the construction of topology layers produce better results.

[0004] According to a first aspect of the present invention, a method for fusion of lane line data with virtual and real attributes is provided, comprising:

[0005] Step 1: Correct the solid lines in the lane line dataset Ω that are misidentified as dashed lines using a clustering method;

[0006] Step 2: Set a threshold for lane line length, and divide the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold.

[0007] Step 3: Correct the dashed lines that are misidentified as solid lines in the short lane line data using a clustering method;

[0008] Step 4: Divide the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset. Then, perform fusion optimization on the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0009] Based on the above technical solution, the present invention can also be improved as follows.

[0010] Optionally, step 1 includes:

[0011] Step 101: Mark each lane point of each lane line in the lane line dataset Ω with virtual and real attributes according to the initial virtual and real attributes of the lane line in which it belongs; each lane line has a globally unique identifier ID, and each lane point has coordinate position information;

[0012] Step 102: Set the Eps neighborhood value and the lower limit value of the number of category data, and perform DBSCAN clustering on each lane line point based on the coordinate position information of each lane line point to obtain the lane line cluster set φ1;

[0013] Step 103: For any lane line cluster in the lane line cluster set φ1, if the proportion of lane line points marked with solid line attribute in the lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark the solid or virtual attribute of all lane line points corresponding to all lane line IDs in the lane line dataset Ω as solid line.

[0014] Optionally, in step 2, the length of each lane line is L = N * D, where N is the number of lane line points contained in the lane line and D is the spacing between the lane line points.

[0015] Optionally, step 3 includes:

[0016] Step 301: Set the Eps neighborhood value and the lower limit value of the number of category data, and perform DBSCAN clustering on each lane line point in the short lane line dataset based on the coordinate position information of each lane line point to obtain the lane line cluster set φ2.

[0017] Step 302: For any lane line cluster in the lane line cluster set φ2, if the proportion of lane line points marked with solid line attribute in the cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark the solid / dark attribute of all lane line points corresponding to all lane line IDs in the short lane line dataset as dashed lines.

[0018] Optionally, step 4, the process of fusing and optimizing lane lines in the lane line dashed line dataset, includes:

[0019] Step 401: Set the Eps neighborhood value and the lower limit value of the number of category data, and perform DBSCAN clustering on all lane line data in the lane line dashed line dataset based on their coordinate points to obtain the lane line cluster set φ3;

[0020] Step 402: Perform linear fitting optimization on each lane cluster in the lane cluster set φ3.

[0021] Optionally, the process of merging the optimized lane lines in step 4 further includes:

[0022] Step 403: Traverse all lane lines and change the lane line ID to a number that starts from 1 and increments by 1 each time.

[0023] According to a second aspect of the present invention, a lane line data fusion system with solid and dashed attributes is provided, comprising: a solid line correction module, a dashed line correction module, and a merging module;

[0024] The solid line correction module is used to correct solid lines that are misidentified as dashed lines in the lane line dataset Ω based on a clustering method.

[0025] The dashed line correction module is used to set a threshold for lane line length, and to divide the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold; and to correct dashed lines that are misidentified as solid lines in the short lane line data based on a clustering method.

[0026] The merging module is used to divide the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset, and then perform fusion optimization on the lane lines of the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0027] According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the processor is configured to implement a method for fusion of lane line data with virtual and real attributes when executing a computer management program stored in the memory.

[0028] According to a fourth aspect of the present invention, a computer-readable storage medium is provided having a computer management class program stored thereon, which, when executed by a processor, implements the steps of a lane line data fusion method with virtual and real attributes.

[0029] This invention provides a method, system, electronic device, and storage medium for fusing lane line data with virtual and real attributes. It achieves the correction of virtual and real attributes based on multiple acquisitions of lane line data with virtual and real attributes through methods such as clustering and classification, and then uses different fusion optimization methods to construct maps from virtual and real lane lines. This solves the problems caused by various situations during vehicle-based lane line data acquisition, such as vehicle occlusion, lane line paint wear, and local road maintenance, which can lead to incorrect identification of the virtual and real attributes of lane lines by vehicle-side devices. Furthermore, it addresses the issue that single-pass acquisition by vehicle-side devices cannot resolve misidentification problems, resulting in better subsequent lane line fusion and topology layer construction. Attached Figure Description

[0030] Figure 1A flowchart of a lane line data fusion method with virtual and real attributes provided by the present invention;

[0031] Figure 2 A schematic diagram of lane lines in a lane line data fusion process with virtual and real attributes provided in an embodiment of the present invention;

[0032] Figure 3 A structural block diagram of a lane line data fusion system with virtual and real attributes provided by the present invention;

[0033] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0034] Figure 5 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation

[0035] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0036] Figure 1 A flowchart of a lane line data fusion method with virtual and real attributes provided by the present invention is shown below. Figure 1 As shown, the method includes:

[0037] Step 1: Correct the solid lines in the lane line dataset Ω that are misidentified as dashed lines using a clustering method.

[0038] Step 2: Set a threshold for lane line length, and split the lane line dataset Ω into a long lane line dataset and a short lane line dataset based on the threshold.

[0039] Step 3: Correct the dashed lines that are misidentified as solid lines in the short lane line data using a clustering method.

[0040] Step 4: Divide the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset. Then, perform fusion optimization on the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0041] This invention provides a lane line data fusion method with virtual and real attributes. This method addresses the issues that arise during vehicle-to-vehicle lane line data collection, such as vehicle occlusion, lane line paint wear, and local road repairs. These factors can lead to incorrect judgments of the virtual and real attributes of lane lines by the vehicle-side equipment, and the inability of a single-pass collection by the vehicle-side equipment to resolve these misidentifications. By accumulating multiple data collections in the cloud and using an algorithm to correct the virtual and real attributes of lane lines, the method achieves better results in subsequent lane line fusion and topology layer construction.

[0042] Example 1

[0043] Embodiment 1 provided by this invention is an embodiment of a lane line data fusion method with virtual and real attributes provided by this invention, combined with... Figure 1 It can be seen that embodiments of this lane line data fusion method include:

[0044] Step 1: Correct the solid lines in the lane line dataset Ω that are misidentified as dashed lines using a clustering method.

[0045] In one possible embodiment, step 1 includes:

[0046] Step 101: Mark the virtual and real attributes of each lane point in the lane line dataset Ω according to the initial virtual and real attributes of the lane line it belongs to; each lane line has a globally unique identifier ID, and each lane point has coordinate position information.

[0047] In specific implementation, such as Figure 2 The diagram shown is a schematic representation of lane lines in a lane line data fusion process with virtual and real attributes, provided by an embodiment of the present invention. Figure 2 As can be seen, the globally optimized lane line dataset Ω consists of several independent lane lines, each with a globally unique identifier (ID). Each ID lane line consists of several lane line points (≥2 lane line points), with a spacing of 0.5m between the points. The points are arranged in the order of the vehicle's travel direction, and each lane line point is represented by its coordinates (x, y, z). Each ID lane line has an initial dashed / solid attribute. In specific implementation, all coordinate points in dashed lane lines can be marked as 0, and all coordinate points in solid lane lines can be marked as 1.

[0048] Step 102: Set the Eps neighborhood value and the lower limit of the number of category data points, and perform DBSCAN clustering on each lane line point based on the coordinate position information of each lane line point to obtain the lane line cluster set φ1.

[0049] Step 103: For any lane line cluster in the lane line cluster set φ1, if the proportion of lane line points marked with solid line attribute in the lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark the solid or virtual attribute of all lane line points corresponding to all lane line IDs in the lane line dataset Ω as solid line.

[0050] In specific implementation, the number of lane line points with real and virtual attributes in each lane line cluster in the lane line cluster set φ1 is counted. The total number of lane line points with real and virtual attributes marked as 0 is denoted as A, the total number of lane line points with real and virtual attributes marked as 1 is denoted as B, and the total number of lane line points in the lane line cluster is denoted as T.

[0051] In each lane cluster, if B / T is greater than or equal to a certain threshold, all lane IDs in that lane cluster are recorded, and the virtual / real attribute of all lane points with the corresponding ID in Ω is updated to 1; otherwise, Ω is not updated.

[0052] Step 2: Set a threshold for lane line length, and split the lane line dataset Ω into a long lane line dataset and a short lane line dataset based on the threshold.

[0053] In one possible embodiment, the length of each lane line in step 2 is L = N * D, where N is the number of lane line points contained in the lane line and D is the spacing between the lane line points.

[0054] In practice, step 2 includes:

[0055] Calculate the length of each lane line in the updated lane line dataset Ω from step 103. The number of points within each lane line ID is N, so N*D is the length L of the lane line. The spacing D between lane line points can be 0.5 meters.

[0056] Remember Ω L For a long lane line dataset, let Ω be... S This is a short lane line dataset. For each ID, determine the lane line length L. If L is greater than or equal to a certain threshold, add the lane line data for that ID to the long lane line dataset Ω. L Otherwise, add it to the short lane line dataset Ω. S .

[0057] Step 3: Correct the dashed lines that are misidentified as solid lines in the short lane line data using a clustering method.

[0058] In one possible embodiment, step 3 includes:

[0059] Step 301: Set the Eps neighborhood value and the lower limit of the number of category data points, and perform a short lane line dataset Ω based on the coordinate location information of each lane line point. S DBSCAN clustering is performed on each lane line point to obtain a lane line cluster set φ2.

[0060] Step 302: For any lane line cluster in the lane line cluster set φ2, if the proportion of lane line points marked with solid line attributes in that lane line cluster is not less than a set threshold, record all lane line IDs in that lane line cluster, and then convert the short lane line dataset Ω... S In this context, all lane line points corresponding to all lane line IDs are marked with dashed lines.

[0061] In practice, similar to step 103, within each lane cluster, if B / T is greater than or equal to a certain threshold, then all lane IDs in that lane cluster are recorded, and Ω is updated. S In the short lane line dataset Ω, the virtual / real attribute of all lane line points corresponding to the lane line ID is 0; otherwise, no virtual / real attribute is assigned to the short lane line dataset Ω. s Update.

[0062] Step 4: Divide the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset. Then, perform fusion optimization on the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0063] In specific implementation, let Ω0 be the dashed lane line dataset and Ω1 be the solid lane line dataset. l All lane line data are added to Ω1, and Ω s All lane line data with a point coordinate marked as 1 are added to the solid lane line dataset Ω1, and Ω is... S All lane line data with coordinates marked as 0 are added to the lane line dashed line dataset Ω0.

[0064] In specific implementation, for the solid lane line dataset Ω1, the method of the invention patent entitled "A Fast Fusion and Optimization Method for Crowdsourced Data of Multiple Road Segments of Lane Lines" (Publication No.: CN111222418B) can be used to perform fusion optimization of solid lane lines.

[0065] In one possible embodiment, step 4, the process of fusing and optimizing lane lines in the lane line dashed line dataset, includes:

[0066] Step 401: Set the Eps neighborhood value and the lower limit value of the number of category data, and perform DBSCAN clustering on all lane line data in the lane line dashed line dataset Ω0 based on their coordinate points to obtain the lane line cluster set φ3.

[0067] Step 402: Perform linear fitting optimization on each lane cluster in the lane cluster set φ3.

[0068] In practice, linear regression problems can use robust regression algorithms such as general linear least squares or random consistency sampling (RANSAC) algorithm, and the coordinates of the first point after fitting are kept unchanged during fitting optimization.

[0069] In one possible embodiment, step 4, merging the optimized lane lines, further includes:

[0070] Step 403: For lane lines in the solid line dataset and dashed line dataset after fusion optimization, traverse all lane lines and change the lane line ID to a number that starts from 1 and increments by 1 each time, making the solid lines globally unique.

[0071] Example 2

[0072] Embodiment 2 provided by this invention is an embodiment of a lane line data fusion system with virtual and real attributes provided by this invention. Figure 3 This invention provides a structural diagram of a lane line data fusion system with virtual and real attributes, combined with... Figure 3 It is known that the implementation of the lane line data fusion system includes: a solid line correction module, a dashed line correction module, and a merging module.

[0073] The solid line correction module is used to correct solid lines in the lane line dataset Ω that are misidentified as dashed lines based on a clustering method.

[0074] The dashed line correction module is used to set a threshold for lane line length and divide the lane line dataset Ω into long lane line datasets and short lane line datasets based on the threshold. A clustering-based method is used to correct dashed lines in the short lane line data that are misidentified as solid lines.

[0075] The merging module is used to divide the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset. The lane lines in the dashed lane line dataset and the solid lane line dataset are fused and optimized separately before being merged.

[0076] It is understood that the lane line data fusion system with virtual and real attributes provided by the present invention corresponds to the lane line data fusion method with virtual and real attributes provided in the foregoing embodiments. The relevant technical features of the lane line data fusion system with virtual and real attributes can be referred to the relevant technical features of the lane line data fusion method with virtual and real attributes, and will not be repeated here.

[0077] Please see Figure 4 , Figure 4 This is a schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 4 As shown, this embodiment of the invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, it performs the following steps: correcting solid lines misidentified as dashed lines in the lane line dataset Ω based on a clustering method; setting a threshold for lane line length, and dividing the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold; correcting dashed lines misidentified as solid lines in the short lane line data based on a clustering method; dividing the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset, and then merging and optimizing the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0078] Please see Figure 5 , Figure 5 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. (See diagram below.) Figure 5 As shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, it performs the following steps: correcting solid lines that are misidentified as dashed lines in the lane line dataset Ω based on a clustering method; setting a threshold for lane line length, and dividing the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold; correcting dashed lines that are misidentified as solid lines in the short lane line data based on a clustering method; dividing the corrected lane dataset Ω into a dashed lane line dataset and a solid lane line dataset, and then merging and optimizing the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them.

[0079] This invention provides a method, system, electronic device, and storage medium for fusing lane line data with virtual and real attributes. It achieves correction of virtual and real attributes based on multiple acquisitions of lane line data with virtual and real attributes through methods such as clustering and classification, and then uses different fusion optimization methods to construct maps from virtual and real lane lines. This solves the problem that various situations, such as vehicle occlusion, lane line paint wear, and local road repairs, can lead to incorrect judgments of the virtual and real attributes of lane lines by vehicle-side devices during lane line data acquisition. Furthermore, it addresses the issue that single-pass acquisition by vehicle-side devices cannot resolve misidentification problems, resulting in better subsequent lane line fusion and topology layer construction.

[0080] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0081] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0085] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0086] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for fusing lane line data with both real and virtual attributes, characterized in that, The lane line data fusion method includes: Step 1: Correct the solid lines in the lane line dataset Ω that are misidentified as dashed lines using a clustering method; Step 2: Set a threshold for lane line length, and divide the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold. Step 3: Correct the dashed lines that are misidentified as solid lines in the short lane line data using a clustering method; Step 4: Divide the corrected lane line dataset Ω into a dashed lane line dataset and a solid lane line dataset. Then, perform fusion optimization on the lane lines in the dashed lane line dataset and the solid lane line dataset respectively before merging them. Step 1 includes: Step 101: Mark each lane point of each lane line in the lane line dataset Ω with virtual and real attributes according to the initial virtual and real attributes of the lane line in which it belongs; each lane line has a globally unique identifier ID, and each lane point has coordinate position information; Step 102: Set the Eps neighborhood value and the lower limit value of the number of category data points, and perform DBSCAN clustering on each lane line point based on the coordinate position information of each lane line point to obtain a set of lane line clusters. ; Step 103, for the lane line cluster set If the proportion of lane line points marked as solid lines in any lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark the solid or virtual line attribute of all lane line points corresponding to all lane line IDs in the lane line dataset Ω as solid lines. Step 3 includes: Step 301: Set the Eps neighborhood value and the lower limit value of the number of category data points. Based on the coordinate position information of each lane line point, perform DBSCAN clustering on each lane line point in the short lane line dataset to obtain a lane line cluster set. ; Step 302, for the lane line cluster set If the proportion of lane line points marked as solid lines in any lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark all lane line points corresponding to all lane line IDs in the short lane line dataset as dashed lines.

2. The lane line data fusion method according to claim 1, characterized in that, In step 2, the length of each lane line is L = N * D, where N is the number of lane line points contained in the lane line and D is the spacing between the lane line points.

3. The lane line data fusion method according to claim 1, characterized in that, Step 4 involves fusing and optimizing the lane lines in the dashed lane line dataset, including: Step 401: Set the Eps neighborhood value and the lower limit value of the number of category data, and perform DBSCAN clustering on all lane line data in the lane line dashed line dataset based on their coordinate points to obtain a lane line cluster set. ; Step 402, for the lane line cluster set Linear fitting optimization is performed on each lane cluster.

4. The lane line data fusion method according to claim 1, characterized in that, The process of merging the optimized lane lines in step 4 also includes: Step 403: Traverse all lane lines and change the lane line ID to a number that starts from 1 and increments by 1 each time.

5. A lane line data fusion system with virtual and real attributes, characterized in that, The lane line data fusion system includes: a solid line correction module, a dashed line correction module, and a merging module; The solid line correction module is used to correct solid lines that are misidentified as dashed lines in the lane line dataset Ω based on a clustering method. The dashed line correction module is used to set a threshold for lane line length, and to divide the lane line dataset Ω into a long lane line dataset and a short lane line dataset according to the threshold; and to correct dashed lines that are misidentified as solid lines in the short lane line data based on a clustering method. The merging module is used to divide the corrected lane line dataset Ω into a lane line dashed line dataset and a lane line solid line dataset, and then perform fusion optimization on the lane lines of the lane line dashed line dataset and the lane line solid line dataset respectively before merging them. The solid line correction module includes: Step 101: Mark each lane point of each lane line in the lane line dataset Ω with virtual and real attributes according to the initial virtual and real attributes of the lane line in which it belongs; each lane line has a globally unique identifier ID, and each lane point has coordinate position information; Step 102: Set the Eps neighborhood value and the lower limit value of the number of category data points, and perform DBSCAN clustering on each lane line point based on the coordinate position information of each lane line point to obtain a set of lane line clusters. ; Step 103, for the lane line cluster set If the proportion of lane line points marked as solid lines in any lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster and mark the solid / virtual attributes of all lane line points corresponding to all lane line IDs in the lane line dataset Ω as solid lines. The dashed line correction module includes: Step 301: Set the Eps neighborhood value and the lower limit value of the number of category data points. Based on the coordinate position information of each lane line point, perform DBSCAN clustering on each lane line point in the short lane line dataset to obtain a lane line cluster set. ; Step 302, for the lane line cluster set If the proportion of lane line points marked as solid lines in any lane line cluster is not less than a set threshold, record all lane line IDs in the lane line cluster, and mark all lane line points corresponding to all lane line IDs in the short lane line dataset as dashed lines.

6. An electronic device, characterized in that, The system includes a memory and a processor, wherein the processor is used to execute computer management programs stored in the memory to implement the steps of the lane line data fusion method with virtual and real attributes as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, It stores a computer management program, which, when executed by a processor, implements the steps of the lane line data fusion method with virtual and real attributes as described in any one of claims 1-4.

Images