Lane data processing methods, devices, equipment, vehicles, and storage media

Abstract

This application provides a lane data processing method, apparatus, device, vehicle, and storage medium. The method includes: if it is determined that the vehicle is currently in a straight-ahead scenario at an intersection, determining a first sampling width sequence for each lane object in the vehicle's current drivable lane data; wherein the first sampling width sequence includes the first lane width of the lane object at each first sampling point; determining a target lane object with an abnormal lane width from among the lane objects based on the first sampling width sequence of the lane objects; correcting the lane centerline and right sideline of the target lane object to obtain a corrected target lane object; and generating and displaying a vehicle guidance surface based on the corrected target lane object. This method can effectively eliminate the protrusion phenomenon of intersection guidance surfaces in the navigation interface, improve the user's intuitive perception of lane boundaries, and optimize lane-level navigation effects.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a lane data processing method, apparatus, equipment, vehicle, and storage medium. Background Technology

[0002] In electronic map navigation systems, lane-level navigation technology is one of the core functions that enhances the user's driving experience. When a user approaches an intersection, the navigation system needs to generate a guidance surface protrusion based on the current lane data that the vehicle can travel in. The guidance surface visually marks the driving path that the vehicle should maintain, such as lane center lines, lane boundary lines, and lane width changes.

[0003] In existing technologies, navigation systems typically generate drivable lane data through a route calculation module, and then directly perform surface smoothing processing by a rendering module to display the guidance surface.

[0004] However, in the above method, at intersections, the lane edge line needs to form an angle difference with the adjacent lane, which causes the guide surface to bulge at the intersection, affecting the lane-level navigation effect. Summary of the Invention

[0005] This application provides a lane data processing method, apparatus, equipment, vehicle, and storage medium, which can effectively eliminate the protrusion phenomenon of intersection guidance surfaces in the navigation interface, improve the user's intuitive perception of lane boundaries, and optimize lane-level navigation effects.

[0006] In a first aspect, this application provides a lane data processing method, including:

[0007] If it is determined that the vehicle is currently in a straight-through scenario at an intersection, then the first sampling width sequence of each lane object in the current drivable lane data of the vehicle is determined; wherein, the first sampling width sequence includes the first lane width of the lane object at each first sampling point;

[0008] Based on the first sampled width sequence of the lane objects, determine the target lane object with abnormal lane width from each of the lane objects;

[0009] The center line and right side line of the target lane object are corrected to obtain the corrected target lane object;

[0010] Based on the modified target lane object, a guide surface for the vehicle is generated and displayed.

[0011] In one possible implementation, determining the target lane object with an abnormal lane width from among the lane objects based on a first sampled width sequence of the lane objects includes:

[0012] If it is determined that the maximum value in the first sampling width sequence of the lane object is greater than a first threshold, and / or if it is determined that the difference between the maximum and minimum values ​​in the first sampling width sequence of the lane object is greater than a second threshold, then the lane object is determined to be the target lane object.

[0013] In one possible implementation, correcting the lane centerline and right sideline of the target lane object to obtain the corrected target lane object includes:

[0014] Based on the topological relationship of the target lane object, an object set corresponding to the target lane object is generated; wherein, the object set includes at least one concentrated lane object; the concentrated lane object includes lane positions with stable lane widths in the target lane object;

[0015] Based on each lane object in the set of objects, the center line and right line of the target lane object are corrected to obtain the corrected target lane object.

[0016] In one possible implementation, generating the object set corresponding to the target lane object based on the topological relationship of the target lane object includes:

[0017] Based on the topological relationship of the target lane object, the target lane object is explored forward along the lane driving direction within a preset distance range starting from the starting position to obtain at least one new lane object corresponding to the target lane object;

[0018] Determine the second sampling width sequence corresponding to the new lane object; wherein, the second sampling width sequence includes the second lane width of the new lane object at each second sampling point;

[0019] Based on the second sampling width sequence corresponding to the new lane object, lane width data that meets the target conditions are determined from the new lane object; wherein, the target conditions include a first condition and a second condition; the first condition is that the difference between the maximum and minimum values ​​in the lane width data is less than or below a third preset threshold; the second condition is that the widths of each second lane in the lane width data do not show a decreasing or increasing trend;

[0020] The lane range corresponding to the lane width data in each new lane object is determined as the concentrated lane object corresponding to the target lane object.

[0021] In one possible implementation, the step of correcting the lane centerline and right sideline of the target lane object based on each lane object in the object set to obtain the corrected target lane object includes:

[0022] Based on the length of the center line of the second lane in the centralized lane object, at least one third sampling point of the center line of the second lane is determined;

[0023] The lane width of the concentrated lane object at the third sampling point is determined based on the distance between the third sampling point and the starting position of the target lane object along the center line of the second lane.

[0024] Based on the coordinates of the third sampling point, determine the coordinates of the perpendicular point from the third sampling point to the left edge of the concentrated lane object;

[0025] Based on the vertical coordinates corresponding to the third sampling point and the lane width of the concentrated lane object at the third sampling point, determine the center point coordinates and right side line coordinates of the concentrated lane object at the third sampling point;

[0026] Based on the coordinates of each center point and the coordinates of each right side line, the center line and right side line of the target lane object are corrected to obtain the corrected target lane object.

[0027] In one possible implementation, determining that the vehicle is currently in a straight-ahead scenario at an intersection includes:

[0028] The vehicle's current drivable lane data is obtained; and based on the lane data on both sides of the drivable lane data, the vehicle's current scene information is identified.

[0029] If the current scene information of the vehicle indicates that the vehicle is in an intersection scene, then the upstream and downstream lane angle information corresponding to the lane data on both sides is determined; wherein, the upstream and downstream lane angle information includes the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides.

[0030] If it is determined that the upstream and downstream lane angle information, which represents the upstream and downstream lane angles of each lane object, has not changed, then it is determined that the vehicle is currently in a straight-through scenario at the intersection.

[0031] In one possible implementation, determining the first sampling width sequence of each lane object in the vehicle's current drivable lane data includes:

[0032] Determine the first lane centerline of each lane object in the drivable lane data; and determine the distance from each first sampling point in the lane object to the two side boundaries based on the coordinates of each first sampling point in the first lane centerline of the lane object.

[0033] The first sampling width sequence of the lane object is determined based on the sum of the distances from each of the first sampling points in the lane object to the two side boundaries.

[0034] Secondly, this application provides a lane data processing device, comprising:

[0035] The first determining module is configured to determine a first sampling width sequence for each lane object in the current drivable lane data of the vehicle if it is determined that the vehicle is currently in a straight-through scenario at an intersection; wherein the first sampling width sequence includes the first lane width of the lane object at each first sampling point;

[0036] The second determining module is used to determine, based on the first sampling width sequence of the lane objects, a target lane object with an abnormal lane width from each of the lane objects;

[0037] The correction module is used to correct the center line and right line of the target lane object to obtain the corrected target lane object.

[0038] The generation module is used to generate and display the guide surface of the vehicle based on the modified target lane object.

[0039] In one possible implementation, the second determining module is specifically configured to: determine the lane object as the target lane object if it is determined that the maximum value in the first sampling width sequence of the lane object is greater than a first threshold, and / or if it is determined that the difference between the maximum and minimum values ​​in the first sampling width sequence of the lane object is greater than a second threshold.

[0040] In one possible implementation, the correction module is specifically configured to: generate an object set corresponding to the target lane object based on the topological relationship of the target lane object; wherein the object set includes at least one concentrated lane object; the concentrated lane object includes lane positions with stable lane widths in the target lane object; and correct the lane centerline and right side line of the target lane object based on each concentrated lane object in the object set to obtain the corrected target lane object.

[0041] In one possible implementation, the correction module is further configured to: explore the target lane object forward along the lane driving direction within a preset distance range starting from the starting position, based on the topological relationship of the target lane object, to obtain at least one new lane object corresponding to the target lane object; determine a second sampling width sequence corresponding to the new lane object; wherein the second sampling width sequence includes the second lane width of the new lane object at each second sampling point; determine lane width data that meets the target conditions from the new lane objects based on the second sampling width sequence corresponding to the new lane objects; wherein the target conditions include a first condition and a second condition; the first condition is that the difference between the maximum and minimum values ​​in the lane width data is less than or below a third preset threshold; the second condition is that each second lane width in the lane width data does not show a decreasing or increasing trend; and determine the lane range corresponding to the lane width data in each new lane object as the concentrated lane object corresponding to the target lane object.

[0042] In one possible implementation, the correction module is further configured to: determine at least one third sampling point of the second lane centerline based on the length of the second lane centerline in the concentrated lane object; determine the lane width of the concentrated lane object at the third sampling point based on the distance between the third sampling point and the starting position of the target lane object along the second lane centerline; determine the perpendicular coordinates from the third sampling point to the left edge of the concentrated lane object based on the coordinates of the third sampling point; determine the center point coordinates and right edge coordinates of the concentrated lane object at the third sampling point based on the perpendicular point coordinates corresponding to the third sampling point and the lane width of the concentrated lane object at the third sampling point; and correct the lane centerline and right edge of the target lane object based on each of the center point coordinates and each of the right edge coordinates to obtain the corrected target lane object.

[0043] In one possible implementation, the first determining module is specifically configured to: acquire the current drivable lane data of the vehicle; and identify the current scene information of the vehicle based on the lane data on both sides in the drivable lane data; if it is determined that the current scene information of the vehicle indicates that the vehicle is in an intersection scene, then determine the upstream and downstream lane angle information corresponding to the lane data on both sides; wherein, the upstream and downstream lane angle information includes the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides; if it is determined that the upstream and downstream lane angle information indicates that the upstream and downstream lane angles of each lane object have not changed, then determine that the vehicle is currently in a straight-through intersection scene.

[0044] In one possible implementation, the first determining module is further specifically configured to: determine a first lane centerline for each lane object in the drivable lane data; and determine the distance from each first sampling point in the lane object to both side boundaries based on the coordinates of each first sampling point in the first lane centerline of the lane object; and determine a first sampling width sequence for the lane object based on the sum of the distances from each first sampling point in the lane object to both side boundaries.

[0045] Thirdly, this application provides an electronic device, including: a memory and a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the first aspect and / or various possible embodiments of the first aspect as described above.

[0046] Fourthly, this application provides a vehicle comprising: a vehicle body and electronic equipment as described in the third aspect disposed in the vehicle body.

[0047] Fifthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0048] In a sixth aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0049] The lane data processing method, apparatus, device, vehicle, and storage medium provided in this application, when a vehicle is currently in a straight-ahead intersection scenario, calculates the first sampling width sequence of each lane object in the vehicle's current drivable lane data. Based on the first sampling width sequence of each lane object, it identifies target lane objects with abnormal lane widths from each lane object, corrects the lane centerline and right sideline of the target lane object, and obtains the corrected target lane object. Based on the corrected target lane object, it generates and displays a guidance surface. Furthermore, by using the sampling width sequence to determine lane width anomalies in a straight-ahead intersection scenario and automatically correcting lanes with abnormal widths to generate continuous guidance surfaces, it can effectively eliminate the protrusion phenomenon of intersection guidance surfaces in the navigation interface, improve the user's intuitive perception of lane boundaries, and ensure that the corrected lane data is consistent with the actual road topology, thus optimizing the navigation effect. Attached Figure Description

[0050] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0051] Figure 1 A schematic diagram illustrating a guide surface protrusion provided in this application;

[0052] Figure 2 A schematic flowchart illustrating a lane data processing method provided in an embodiment of this application;

[0053] Figure 3 A comparative schematic diagram illustrating the lane correction effect provided in an embodiment of this application;

[0054] Figure 4 A schematic flowchart illustrating another lane data processing method provided in an embodiment of this application;

[0055] Figure 5 A schematic diagram illustrating the lane edge width sampling and correction effect provided in an embodiment of this application;

[0056] Figure 6 A schematic diagram illustrating a lane object correction effect provided in an embodiment of this application;

[0057] Figure 7 This is a schematic diagram of the structure of a lane data processing device provided in an embodiment of this application;

[0058] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0059] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0060] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0061] 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, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, they do not violate public order and good morals, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0062] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on user rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0063] This application applies to lane-level navigation scenarios in electronic map navigation systems, especially in the process of generating guide surfaces at intersections. The navigation system's route calculation module is responsible for calculating the lane data that vehicles can pass through, and the rendering module generates guide surfaces (including lane center lines, boundary lines, and lane width changes) based on the route calculation results.

[0064] Based on the above scenarios, it can be seen that, Figure 1 This application provides a schematic diagram of a guide surface protrusion, as shown below. Figure 1 As shown, when a vehicle approaches an intersection, due to the complexity of the lane topology at the intersection, the lane edge lines may form an angle difference due to connection requirements, resulting in a bulge on the guide surface.

[0065] The lane data processing method provided in this application determines lane width anomalies in straight-through scenarios at intersections by using a sampling width sequence and automatically corrects lanes with abnormal widths, generating continuous guide surfaces. This effectively eliminates the protrusion phenomenon of intersection guide surfaces in the navigation interface.

[0066] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0067] Figure 2 This is a flowchart illustrating a lane data processing method provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes:

[0068] 201. If it is determined that the vehicle is currently in a straight-through scenario at an intersection, then determine the first sampling width sequence of each lane object in the current drivable lane data of the vehicle; wherein, the first sampling width sequence includes the first lane width of the lane object at each first sampling point.

[0069] For example, the execution subject of this embodiment may be an electronic device, hereinafter referred to as the device. The device may be a controller or domain controller in a vehicle. The device can obtain the vehicle's scene information through the vehicle's perception system to determine whether the vehicle is currently in a straight-ahead intersection scenario. If it is determined that the vehicle is currently in a straight-ahead intersection scenario, the device obtains the vehicle's current drivable lane data, extracts each lane object from the drivable lane data, and obtains a first sampling width sequence for each lane object by sampling at fixed distance intervals, including the first lane width of each lane object at each first sampling point.

[0070] In one example, the curvature (such as radius of curvature or curvature gradient) of the centerline of the drivable lane in the vehicle's scene information is calculated to identify whether the vehicle is currently in a straight-ahead intersection scenario; for example, if the curvature of the lane centerline does not change abruptly, it is determined to be a straight-ahead intersection scenario.

[0071] In one example, the lane lines parallel to the left edge of each lane object are identified, and sampling points on the lane lines are determined by sampling at fixed intervals, which are the first sampling points. The lane width at each sampling point on the lane lines is then calculated to obtain the first sampling width sequence for each lane object.

[0072] 202. Based on the first sampled width sequence of the lane objects, determine the target lane object with abnormal lane width from each lane object.

[0073] For example, for each lane object, the first sample width sequence of the lane object is analyzed according to preset rules, such as analyzing the changes in the width of each lane in the first sample width sequence, and identifying target lane objects with abnormal lane widths.

[0074] Specifically, if it is determined that the difference between each lane width in the first sampling width sequence (excluding the lane width at the starting point) and the lane width at the starting point is within a preset range, then it is determined that the lane widths in the first sampling width sequence have not changed or have changed little; otherwise, it is determined that the lane widths in the first sampling width sequence have changed significantly, and the lane object corresponding to the first sampling width sequence is determined as the target lane object with abnormal lane width.

[0075] 203. Correct the center line and right line of the target lane object to obtain the corrected target lane object.

[0076] For example, for each target lane object with an abnormal lane width, the coordinate information of the lane centerline and right sideline of the target lane object is extracted. Then, the coordinate information of the lane centerline and right sideline of the target lane object is corrected by linear interpolation or spline interpolation to obtain the corrected lane centerline and right sideline. The lane centerline and right sideline of the target lane object are replaced with the corrected lane centerline and right sideline to obtain the corrected target lane object.

[0077] 204. Generate and display the vehicle's guide surface based on the corrected target lane object.

[0078] For example, Figure 3 This application provides a comparative illustration of lane correction effects, as shown in the following diagram. Figure 3 As shown, the original target lane object is replaced with a corrected target lane object. Based on this corrected target lane object, a vehicle guidance surface is calculated through road calculation. This guidance surface is then displayed using rendering technology to achieve the vehicle's intersection navigation guidance function. Through a dual mechanism of scene recognition and dynamic correction, the corrected lane data is ensured to satisfy both topological rationality and eliminate visual anomalies caused by abrupt width changes.

[0079] This embodiment provides a lane data processing method that effectively solves the problem of bulging guidance surfaces at intersections in navigation systems through a dual mechanism of scene recognition and lane data correction. Specifically, the scene recognition stage accurately locates the lane objects that need correction, reducing invalid corrections; the lane data correction stage uses a width interpolation algorithm to dynamically reconstruct the lane edge coordinates, ensuring that the corrected lane data conforms to the actual road topology and generates a continuous guidance surface. Ultimately, the corrected guidance surface eliminates the visual bulge phenomenon, improves the user's intuitive perception of lane boundaries, and ensures the accuracy and reliability of navigation system guidance in complex intersection scenarios.

[0080] Figure 4 A flowchart illustrating another lane data processing method provided in this application embodiment is shown below. Figure 4 As shown, the method includes:

[0081] 301. Obtain the current drivable lane data of the vehicle; and identify the current scene information of the vehicle based on the lane data on both sides of the drivable lane data.

[0082] For example, the device obtains the vehicle's current drivable lane data from the road calculation module, and extracts the lane data on both sides from the drivable lane data (including centerline coordinates, edge coordinates, and topological relationships). The lane data on both sides is processed by a scene recognition algorithm, such as a deep learning model (e.g., a convolutional network), to identify the vehicle's current scene information and determine whether the vehicle is currently in an intersection scene. For example, the lane topology is used to determine whether a lane in set A is an intersection lane; if not, it is ignored.

[0083] 302. If the current scene information of the vehicle indicates that the vehicle is in an intersection scene, then determine the upstream and downstream lane angle information corresponding to the lane data on both sides; wherein, the upstream and downstream lane angle information includes the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides.

[0084] For example, if it is determined that the vehicle is currently in an intersection scenario, the upstream and downstream lane angle information is extracted from the lane data on both sides, including the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides. For example, the changes in the upstream and downstream lane angles of each lane object are too large, too small, or have not changed.

[0085] 303. If it is determined that the upstream and downstream lane angle information representing the upstream and downstream lane angles of each lane object has not changed, then it is determined that the vehicle is currently in a straight-through scenario at the intersection.

[0086] For example, based on the upstream and downstream lane angle information, if it is determined that the upstream and downstream lane angles of each lane object have not changed, then it is determined that the vehicle is currently in a straight-ahead scenario at the intersection. For instance, in a T-junction, the system only retains the straight-ahead lane as a candidate object, ignoring the correction requirements for the turning lane. This process achieves accurate identification of different scenarios (such as straight-ahead and turning) through the classification logic of topological relationships.

[0087] For example, iterate through the set of drivable lanes to find the sets of lanes A on both sides. Iterate through lane a in set A and determine if it is an intersection lane. If it is not an intersection lane, ignore it. Check the angle change of the upstream and downstream lanes of lane a. If there is no change, it is a straight-ahead lane; otherwise, ignore it.

[0088] By jointly analyzing the changes in lane angles at intersections and the upstream and downstream angles, accurate identification of different scenarios (such as straight-ahead and turning) is achieved. This technique avoids the ineffective processing caused by the uniform correction strategy in existing technologies, significantly improves the scenario adaptability of the correction effect, and ensures the continuity of guidance of the navigation system in diverse intersection scenarios.

[0089] 304. Determine the first lane centerline of each lane object in the drivable lane data; and determine the distance from each first sampling point in the lane object to the two side boundaries based on the coordinates of each first sampling point in the first lane centerline of the lane object.

[0090] For example, for each lane object in the drivable lane data, the first lane centerline of each lane object is determined using the coordinate data in the drivable lane data. The first lane centerline is sampled at fixed intervals to determine the coordinates of each first sampling point in the first lane centerline of the lane object, and the distance from each first sampling point to the two side boundaries of the lane object is calculated using a distance formula.

[0091] 305. Determine the first sampling width sequence of the lane object based on the sum of the distances from each first sampling point in the lane object to the two side boundaries.

[0092] For example, for each first sampling point in the lane object, the sum of the distances from each first sampling point to the two side boundaries is calculated, and the first lane width at each first sampling point in the lane object is obtained based on the sum of the distances, thereby obtaining the first sampling width sequence of the lane object.

[0093] 306. If the maximum value in the first sampling width sequence of the lane object is greater than a first threshold, and / or if the difference between the maximum and minimum values ​​in the first sampling width sequence of the lane object is greater than a second threshold, then the lane object is determined to be the target lane object.

[0094] For example, for each lane object, the maximum and minimum values ​​of each lane width in the first sampled width sequence of the lane object are determined, and the difference between the maximum and minimum values ​​is calculated. The maximum value is compared with a first threshold, and / or the difference is compared with a second threshold. If it is determined that the maximum value is greater than the first threshold, and / or if it is determined that the difference is greater than the second threshold, then it is determined that there is a lane width anomaly in the first sampled width sequence of the lane object, that is, the lane object is identified as a target lane object with an abnormal lane width.

[0095] For example, if the maximum value of the sampling width sequence is greater than 5 meters, the width change is considered abnormal; if the difference between the maximum and minimum values ​​is greater than 0.5 meters, the width change is considered abnormal.

[0096] By traversing the lane set and analyzing the sampling width sequence, accurate identification of lane objects requiring correction was achieved. This technique reduces invalid corrections, significantly improves the accuracy of scene recognition, and ensures that the correction process is only performed on lane objects with actual width abrupt changes.

[0097] 307. Generate a set of objects corresponding to the target lane objects based on the topological relationship of the target lane objects; wherein the set of objects includes at least one centralized lane object; the centralized lane object includes lane positions with stable lane widths in the target lane objects.

[0098] For example, for each target lane object, the topological relationship of the target lane object is obtained, including the connection relationship between lanes, such as the connection direction (straight, turning) of upstream and downstream lanes and geometric adaptability. Based on the topological relationship, along the driving direction in the topological relationship of the target lane object, according to the sampled width sequence of the target lane object, the target lane object is traversed to find the object set corresponding to the target lane object, including at least one lane position with stable lane width in the target lane object, which is the concentrated lane object.

[0099] Specifically, by sliding the analysis sampling width data through a fixed window length (e.g., 30 meters), data points that meet stability are filtered out. For example, sampling points where the difference between the maximum and minimum values ​​is less than 0.5 meters within a continuous 30-meter range are retained to obtain concentrated lane objects.

[0100] In one possible implementation, step 307 includes the following steps:

[0101] The first step is to explore the target lane object forward along the lane driving direction within a preset distance range starting from the starting position, based on the topological relationship of the target lane object, to obtain at least one new lane object corresponding to the target lane object.

[0102] The second step is to determine the second sampling width sequence corresponding to the new lane object; wherein, the second sampling width sequence includes the second lane width of the new lane object at each second sampling point.

[0103] The third step is to determine the lane width data that meets the target conditions from the new lane objects based on the second sampling width sequence corresponding to the new lane objects. The target conditions include the first condition and the second condition. The first condition is that the difference between the maximum and minimum values ​​in the lane width data is less than or below a third preset threshold. The second condition is that the widths of the included second lanes do not show a decreasing or increasing trend.

[0104] The fourth step is to determine the lane range corresponding to the lane width data in each new lane object as the concentrated lane object corresponding to the target lane object.

[0105] Specifically, for each target lane object, based on the topological relationships of the target lane object, including analyzing lane connection logic along the lane driving direction and topological data related to the correction range in the target lane object, a preset distance range (e.g., 100 meters) is determined. The target lane object is then explored forward along the lane driving direction within this preset distance range from its starting position to obtain at least one new lane object corresponding to the target lane object. For each new lane object, each second sampling point of the new lane object is determined by sampling at fixed distance intervals. The second lane width of the new lane object at each second sampling point is obtained by calculating the sum of the vertical distances from each second sampling point to the two side lines of the new lane object, thus obtaining the second sampling width sequence corresponding to each new lane object. Preset target conditions are invoked, including a first condition and a second condition; wherein the first condition is that the difference between the maximum and minimum values ​​of each second lane width is less than or equal to a third preset threshold; the second condition is that the included second lane widths do not show a decreasing or increasing trend. Based on the preset target conditions, each second lane width in the second sampling width sequence corresponding to each new lane object is analyzed to select lane width data that meets the target conditions from each new lane object. Each new lane object is compared with the lane width data in that new lane object that meets the target condition, and the lane range corresponding to the lane width data in that new lane object that meets the target condition is extracted. This lane range is then identified as a centralized lane object for use in the subsequent lane object correction process.

[0106] By combining topological relationship exploration with sliding window filtering, lane width stability analysis within the correction range was achieved. This technique reduces topological conflicts caused by correction ranges that are too small or too large, and significantly improves the topological rationality of the correction results.

[0107] In one example, during the topology exploration phase, the correction range is dynamically adjusted based on the severity of lane width anomalies. For instance, when the difference between the maximum and minimum values ​​of the sampled width sequence exceeds 0.5 meters, the topology exploration range is expanded from a fixed 100 meters to 200 meters; when the difference is small, the range remains at 100 meters. Simultaneously, the correction intensity is dynamically adjusted based on the upstream and downstream topological connections of the lanes (e.g., whether they are bifurcations), such as applying higher correction priority to bifurcated lanes. This dynamic parameter adjustment ensures the correction range matches the severity of the actual problem, reducing over-correction or under-correction. In severe anomaly scenarios, the exploration range is expanded to ensure coverage of all relevant lane data; in minor anomaly scenarios, the correction range remains compact to reduce interference with non-critical areas, improving the flexibility of the correction strategy and ensuring that the corrected lane data satisfies both topological rationality and accurately eliminates protrusion problems.

[0108] 308. Based on each lane object in the object set, correct the center line and right line of the target lane object to obtain the corrected target lane object.

[0109] For example, lane width data for each set of lane objects in the object set is determined, including multiple data points that satisfy stability. A preset algorithm is used to calculate the lane width data for each set of lane objects in the object set to obtain a target lane width. Using this target lane width, the coordinate information of the lane centerline and right lane line of the target lane object is corrected to obtain a corrected target lane object, ensuring that the lane width data of the corrected target lane object is consistent with the actual road topology.

[0110] For example, Figure 5 This is a schematic diagram illustrating the lane edge width sampling and correction effect provided in an embodiment of this application, as shown below. Figure 5 As shown, abnormal lane objects in intersection scenarios are identified; through sampling point interpolation algorithms, the lane edge shape of the lane objects is dynamically corrected to ensure that the corrected lane data not only conforms to the actual road topology but also generates continuous guide surfaces.

[0111] By combining topological relationship exploration with sliding window filtering, lane width stability analysis within the correction range is achieved, ensuring the navigation system's guidance accuracy in complex intersection scenarios.

[0112] In one possible implementation, step 308 includes:

[0113] Step 1: Based on the length of the center line of the second lane in the concentrated lane object, determine at least one third sampling point of the center line of the second lane.

[0114] Step 2: Determine the lane width of the concentrated lane object at the third sampling point based on the distance between the third sampling point and the starting position of the target lane object along the center line of the second lane.

[0115] Step 3: Based on the coordinates of the third sampling point, determine the coordinates of the perpendicular point from the third sampling point to the left edge of the concentrated lane object.

[0116] Step 4: Based on the vertical coordinates of the third sampling point and the lane width of the concentrated lane object at the third sampling point, determine the center point coordinates and right side line coordinates of the concentrated lane object at the third sampling point.

[0117] Step 5: Based on the coordinates of each center point and each right-side line, correct the center line and right-side line of the target lane object to obtain the corrected target lane object.

[0118] Specifically, for each lane group, the length of the lane centerline (i.e., the second lane centerline) within the lane group is calculated. Based on this length, at least one third sampling point of the second lane centerline is obtained using sampling at fixed distance intervals. For each third sampling point along the second lane centerline, the distance to the starting position of the target lane object is calculated. Based on this distance, the initial lane width of the lane group at each third sampling point is interpolated to obtain the lane width of each lane group at each third sampling point. The coordinates of each third sampling point in each lane group are calculated, and based on the coordinates of each third sampling point, the coordinates of the perpendicular point from each third sampling point to the left edge line of the lane group are calculated. Based on the vertical coordinates corresponding to each third sampling point, the system moves along the left edge perpendicularly towards the right edge of the concentrated lane object. The moving distance is the lane width at each third sampling point. The final position reached is the coordinate of each vertical point on the right edge of the concentrated lane object. When the moving distance is half the lane width at each third sampling point, the final position reached is the center point coordinate of each vertical point in the concentrated lane object. Thus, the coordinates of each center point and each right edge are obtained. Based on the obtained center point coordinates and right edge coordinates, a new lane center line and a new right edge of the target lane object are generated. The target lane object is then corrected based on the new lane center line and the new right edge, resulting in the corrected target lane object.

[0119] For example, for a target lane object a with an abnormal width, calculate the lane width w1 at the starting position s of a. Based on the topological relationship of a, find the position where the lane width is stable in the direction of travel of a. Specifically, along the direction of travel of the lane, explore forward a maximum of 100 meters according to the topological relationship to obtain the Lane set A1. Traverse the set A1, obtain the sampled width for the Lane object a1 (new lane object) in the set A1, and add it to the set L1. Find the starting index in the set L1 that meets the following conditions using a sliding window: (1) the maximum and minimum values ​​of the sampling widths over a continuous 30-meter length are less than 0.5 meters; (2) the sampling widths in the continuous width do not show a decreasing trend; (3) the sampling widths in the continuous width do not show an increasing trend. Record the Lane object a1 that meets the conditions and its range, and obtain the set B, in which object a is also in the set B. At the same time, calculate the width w2 at the ending position e. Calculate the length m from s to e, passing through the center line of the lane. Iterate through each lane object b in set B, sampling the centerline of lane b at 2-meter intervals, and calculate the lane width w3 at the sampling point based on the distance from the sampling point along the centerline to the starting point a (interpolating the width). Calculate the perpendicular coordinates from the centerline sampling point to the left lane. Based on the perpendicular coordinates and lane width w3, recalculate the center point coordinates and right lane coordinates. Replace the re-generated center point coordinates and right lane coordinates in the road calculation results. Figure 6 This is a schematic diagram illustrating a lane object correction effect provided in an embodiment of this application, as shown below. Figure 6 As shown, the corrected target lane object is obtained, which affects the subsequent generation of wide lane surfaces / lines.

[0120] By calculating the perpendicular point coordinates and comparing them with the data, the topological compatibility between the corrected lane edge lines and the original data was verified. This technique reduces lane connection breaks caused by correction errors, significantly improves the reliability of the correction results, and ensures the continuity of navigation system guidance in complex intersection scenarios.

[0121] In one example, a multi-dimensional data verification mechanism is introduced, combining real-time traffic signs, historical user trajectory data, and the correction status of adjacent lanes to cross-validate the corrected target lane object. For instance, in a straight-ahead scenario, the system verifies whether the corrected target lane object matches the guide line sign, while ensuring that the correction result is consistent with the user's historical trajectory. This process ensures the reliability of the correction result through joint verification from multiple data sources.

[0122] 309. Generate and display the vehicle's guide surface based on the corrected target lane object.

[0123] For example, this step can be referred to as step 204, which will not be repeated here.

[0124] In this embodiment, based on the above embodiments, on the one hand, the scene recognition stage accurately locates the lane objects that need correction through lane topology relationship and sampling width sequence analysis, reducing invalid corrections caused by global smoothing processing; on the other hand, the lane data correction stage dynamically reconstructs the lane edge coordinates through topology relationship exploration and width interpolation algorithms, ensuring that the corrected lane data not only conforms to the actual road topology structure but also generates continuous guidance surfaces. Ultimately, the corrected guidance surfaces eliminate visual bulges, improve the user's intuitive perception of lane boundaries, and ensure the accuracy and reliability of the navigation system in complex intersection scenarios.

[0125] Figure 7 This is a schematic diagram of the structure of a lane data processing device provided in an embodiment of this application, as shown below. Figure 7 As shown, the device includes:

[0126] The first determining module 401 is used to determine the first sampling width sequence of each lane object in the current drivable lane data of the vehicle if it is determined that the vehicle is currently in a straight-through scenario at an intersection; wherein the first sampling width sequence includes the first lane width of the lane object at each first sampling point;

[0127] The second determining module 402 is used to determine the target lane object with abnormal lane width from each lane object based on the first sampled width sequence of the lane objects.

[0128] The correction module 403 is used to correct the center line and right line of the target lane object to obtain the corrected target lane object.

[0129] The generation module 404 is used to generate and display the vehicle's guide surface based on the corrected target lane object.

[0130] In one possible implementation, the second determining module 402 is specifically used to: determine the lane object as the target lane object if the maximum value in the first sampling width sequence of the determined lane object is greater than a first threshold, and / or if the difference between the maximum and minimum values ​​in the first sampling width sequence of the determined lane object is greater than a second threshold.

[0131] In one possible implementation, the correction module 403 is specifically used to: generate an object set corresponding to the target lane object based on the topological relationship of the target lane object; wherein the object set includes at least one concentrated lane object; the concentrated lane object includes lane positions with stable lane widths in the target lane object; and correct the lane center line and right side line of the target lane object based on each concentrated lane object in the object set to obtain the corrected target lane object.

[0132] In one possible implementation, the correction module 403 is further specifically configured to: explore forward along the lane driving direction within a preset distance range starting from the starting position of the target lane object according to the topological relationship of the target lane object, to obtain at least one new lane object corresponding to the target lane object; determine a second sampling width sequence corresponding to the new lane object; wherein the second sampling width sequence includes the second lane width of the new lane object at each second sampling point; determine lane width data that meets the target conditions from the new lane objects according to the second sampling width sequence corresponding to the new lane object; wherein the target conditions include a first condition and a second condition; the first condition is that the difference between the maximum and minimum values ​​in the lane width data is less than or below a third preset threshold; the second condition is that each second lane width in the lane width data does not show a decreasing trend or an increasing trend; and determine the lane range corresponding to the lane width data in each new lane object as the concentrated lane object corresponding to the target lane object.

[0133] In one possible implementation, the correction module 403 is further specifically configured to: determine at least one third sampling point of the second lane centerline based on the length of the second lane centerline in the concentrated lane object; determine the lane width of the concentrated lane object at the third sampling point based on the distance between the third sampling point along the second lane centerline and the starting position of the target lane object; determine the perpendicular coordinates from the third sampling point to the left edge of the concentrated lane object based on the coordinates of the third sampling point; determine the center point coordinates and right edge coordinates of the concentrated lane object at the third sampling point based on the perpendicular point coordinates corresponding to the third sampling point and the lane width of the concentrated lane object at the third sampling point; and correct the lane centerline and right edge of the target lane object based on the coordinates of each center point and each right edge coordinate to obtain the corrected target lane object.

[0134] In one possible implementation, the first determining module 401 is specifically used to: acquire the current drivable lane data of the vehicle; and identify the current scene information of the vehicle based on the lane data on both sides in the drivable lane data; if the current scene information of the vehicle indicates that the vehicle is in an intersection scene, then determine the upstream and downstream lane angle information corresponding to the lane data on both sides; wherein, the upstream and downstream lane angle information includes the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides; if the upstream and downstream lane angle information indicates that the upstream and downstream lane angles of each lane object have not changed, then determine that the vehicle is currently in a straight-through scene at an intersection.

[0135] In one possible implementation, the first determining module 401 is further specifically configured to: determine the first lane centerline of each lane object in the drivable lane data; and determine the distance from each first sampling point in the lane object to the two side boundaries based on the coordinates of each first sampling point in the first lane centerline of the lane object; and determine the first sampling width sequence of the lane object based on the sum of the distances from each first sampling point in the lane object to the two side boundaries.

[0136] The apparatus in this embodiment can execute the technical solutions in the above method. Its specific implementation process and technical principles are the same, and will not be repeated here.

[0137] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, the electronic device includes: a memory 501 and a processor 502; the memory 501 is a memory used to store instructions executable by the processor 502.

[0138] The processor 502 is configured to perform the method provided in the above embodiments.

[0139] The electronic device also includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0140] The specific implementation process of the processor can be found in the above method embodiments, and its implementation principle and technical effect are similar, so it will not be repeated here.

[0141] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0142] This application provides a vehicle, which includes: a vehicle body and an electronic device disposed in the vehicle body as described in the above embodiments, to perform the technical solutions of the above embodiments.

[0143] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed on a computer, cause the computer to perform the technical solutions described above.

[0144] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0145] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. The readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in a device.

[0146] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, it can implement the technical solutions in the above embodiments.

[0147] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as magnetic disks or optical disks.

[0148] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A lane data processing method, characterized in that, include: If it is determined that the vehicle is currently in a straight-through scenario at an intersection, then the first sampling width sequence of each lane object in the current drivable lane data of the vehicle is determined; wherein, the first sampling width sequence includes the first lane width of the lane object at each first sampling point; Based on the first sampled width sequence of the lane objects, determine the target lane object with abnormal lane width from each of the lane objects; The center line and right side line of the target lane object are corrected to obtain the corrected target lane object; Based on the modified target lane object, a guide surface for the vehicle is generated and displayed.

2. The method according to claim 1, characterized in that, The step of determining the target lane object with abnormal lane width from each of the lane objects based on the first sampled width sequence of the lane objects includes: If it is determined that the maximum value in the first sampling width sequence of the lane object is greater than a first threshold, and / or if it is determined that the difference between the maximum and minimum values ​​in the first sampling width sequence of the lane object is greater than a second threshold, then the lane object is determined to be the target lane object.

3. The method according to claim 1, characterized in that, The step of correcting the center line and right side line of the target lane object to obtain the corrected target lane object includes: Based on the topological relationship of the target lane object, an object set corresponding to the target lane object is generated; wherein, the object set includes at least one concentrated lane object; the concentrated lane object includes lane positions with stable lane widths in the target lane object; Based on each lane object in the set of objects, the center line and right line of the target lane object are corrected to obtain the corrected target lane object.

4. The method according to claim 3, characterized in that, The step of generating a set of objects corresponding to the target lane object based on the topological relationship of the target lane object includes: Based on the topological relationship of the target lane object, the target lane object is explored forward along the lane driving direction within a preset distance range starting from the starting position to obtain at least one new lane object corresponding to the target lane object; Determine the second sampling width sequence corresponding to the new lane object; wherein, the second sampling width sequence includes the second lane width of the new lane object at each second sampling point; Based on the second sampling width sequence corresponding to the new lane object, lane width data that meets the target conditions are determined from the new lane object; wherein, the target conditions include a first condition and a second condition; the first condition is that the difference between the maximum and minimum values ​​in the lane width data is less than or below a third preset threshold; the second condition is that the widths of each second lane in the lane width data do not show a decreasing or increasing trend; The lane range corresponding to the lane width data in each new lane object is determined as the concentrated lane object corresponding to the target lane object.

5. The method according to claim 3, characterized in that, The step of correcting the center line and right side line of the target lane object based on each lane object in the object set to obtain the corrected target lane object includes: Based on the length of the center line of the second lane in the centralized lane object, at least one third sampling point of the center line of the second lane is determined; The lane width of the concentrated lane object at the third sampling point is determined based on the distance between the third sampling point and the starting position of the target lane object along the center line of the second lane. Based on the coordinates of the third sampling point, determine the coordinates of the perpendicular point from the third sampling point to the left edge of the concentrated lane object; Based on the vertical coordinates corresponding to the third sampling point and the lane width of the concentrated lane object at the third sampling point, determine the center point coordinates and right side line coordinates of the concentrated lane object at the third sampling point; Based on the coordinates of each center point and the coordinates of each right side line, the center line and right side line of the target lane object are corrected to obtain the corrected target lane object.

6. The method according to claim 1, characterized in that, The determination that the vehicle is currently in a straight-ahead scenario at an intersection includes: The vehicle's current drivable lane data is obtained; and based on the lane data on both sides of the drivable lane data, the vehicle's current scene information is identified. If the current scene information of the vehicle indicates that the vehicle is in an intersection scene, then the upstream and downstream lane angle information corresponding to the lane data on both sides is determined; wherein, the upstream and downstream lane angle information includes the changes in the upstream and downstream lane angles of each lane object in the lane data on both sides. If it is determined that the upstream and downstream lane angle information, which represents the upstream and downstream lane angles of each lane object, has not changed, then it is determined that the vehicle is currently in a straight-through scenario at the intersection.

7. The method according to any one of claims 1-6, characterized in that, The step of determining the first sampling width sequence of each lane object in the current drivable lane data of the vehicle includes: Determine the first lane centerline of each lane object in the drivable lane data; and determine the distance from each first sampling point in the lane object to the two side boundaries based on the coordinates of each first sampling point in the first lane centerline of the lane object. The first sampling width sequence of the lane object is determined based on the sum of the distances from each of the first sampling points in the lane object to the two side boundaries.

8. A lane data processing device, characterized in that, include: The first determining module is configured to determine a first sampling width sequence for each lane object in the current drivable lane data of the vehicle if it is determined that the vehicle is currently in a straight-through scenario at an intersection; wherein the first sampling width sequence includes the first lane width of the lane object at each first sampling point; The second determining module is used to determine, based on the first sampling width sequence of the lane objects, a target lane object with an abnormal lane width from each of the lane objects; The correction module is used to correct the center line and right line of the target lane object to obtain the corrected target lane object. The generation module is used to generate and display the guide surface of the vehicle based on the modified target lane object.

9. An electronic device, characterized in that, include: Memory and processor; The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A vehicle, characterized in that, The vehicle includes: a vehicle body and an electronic device as described in claim 9 disposed in the vehicle body.

11. A computer-readable storage medium / computer program product, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7; and / or, the computer program product includes a computer program, which, when executed by a processor, implements the method as described in any one of claims 1-7.

Images