Virtual lane line generation method, device, equipment, medium and program product

Abstract

The present disclosure relates to a virtual lane line generation method, device, equipment, medium and program product. Including: based on the lane attribute information of the lane in the same traffic direction in the to-be-processed road, determining the lane line hanging point existing in the to-be-processed road; determining the perpendicular distance between the adjacent lane lines on both sides of the lane line hanging point along the traffic direction; based on a preset index, determine the width change index value between the two adjacent perpendicular distances; from the width change index value, filter the target index value that meets the width change convergence condition, wherein the width change convergence condition is used to represent the condition that the lane width change index value converges to a preset change range; based on the lane position in the lane line vertical direction corresponding to the target index value, determine the lane change point of the to-be-processed road; based on the lane line hanging point, the lane change point and the adjacent lane lines on both sides, generate a virtual lane line between the lane hanging point and the lane change point. Improve the smoothness of the virtual lane line.

Description

Technical Field

[0001] This disclosure relates to the field of high-precision map technology, and in particular to a method, apparatus, device, medium and program product for generating virtual lane lines. Background Technology

[0002] In real-world roads, there are areas where lanes merge or separate, and lane lines are not painted. In such areas, human drivers can determine the driving area based on experience. Since high-definition maps can serve as decision-making data for functions such as intelligent driving or advanced driver assistance systems (ADAS), virtual lane lines need to be created during the high-definition map production process for these areas where lane lines are not painted. Because lane lines are not actually painted in the real world in these areas, providing virtual lane lines that meet the required quality is a problem that those skilled in the art need to solve.

[0003] Currently, in areas where lane merging or lane separation is not marked, the solution for creating virtual lane lines can be as follows: Figure 1 As shown. See also Figure 1 In the interrupted lane line L2, among the adjacent lane lines L1 and L3 on both sides along the lane direction, any one lane line (e.g., L1) can be selected. Then, on the selected lane line (L1), at a certain distance (e.g., 10 meters) from the suspension point A of the interrupted lane line L2, a position point B is selected. The suspension point A and the position point B are then connected to form a virtual lane line AB. However, this method of creating a virtual lane line results in abrupt changes and unevenness, affecting the implementation of the aforementioned intelligent driving or advanced driver assistance functions. Summary of the Invention

[0004] To address the technical problem of poor smoothness of virtual lane lines in the aforementioned lane-changing area, this disclosure provides a method, apparatus, device, medium, and program product for generating virtual lane lines.

[0005] In a first aspect, embodiments of this disclosure provide a method for generating virtual lane lines, including:

[0006] Based on the lane attribute information of lanes in the same direction of travel in the road to be processed, determine the lane line suspension points in the road to be processed.

[0007] Determine the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the direction of travel;

[0008] Based on preset indicators, determine the width variation index value between the distances of two adjacent vertical lines;

[0009] Select target index values ​​that meet the width change convergence condition from the width change index values, wherein the width change convergence condition is used to characterize the condition that the width change index value converges to a preset change range;

[0010] Based on the lane position in the vertical direction of the lane line corresponding to the target index value, the lane change point of the road to be processed is determined;

[0011] Based on the lane line suspension point, the lane change point, and the adjacent lane lines on both sides, a virtual lane line is generated between the lane suspension point and the lane change point.

[0012] Secondly, embodiments of this disclosure also provide a virtual lane line generation device, comprising:

[0013] The lane line suspension point determination module is used to determine the lane line suspension points existing in the road to be processed based on the lane attribute information of lanes in the same direction of traffic in the road to be processed.

[0014] The perpendicular distance determination module is used to determine multiple perpendicular distances between adjacent lane lines on both sides of the lane line suspension point along the traffic direction.

[0015] The width change index value determination module is used to determine the width change index value between two adjacent vertical distances based on a preset index.

[0016] The target index value filtering module is used to filter target index values ​​that meet the width change convergence condition from the width change index values, wherein the width change convergence condition is used to characterize the condition that the width change of the road converges to a preset change range.

[0017] The lane change point determination module is used to determine the lane change points of the road to be processed based on the lane position in the direction perpendicular to the lane line corresponding to the target index value.

[0018] The virtual lane line generation module is used to generate a virtual lane line between the lane line suspension point and the lane change point based on the lane line suspension point, the lane change point and the adjacent lane lines on both sides.

[0019] Thirdly, embodiments of this disclosure also provide an electronic device, including:

[0020] A memory and a processor, wherein the memory is used to store executable instructions of the processor;

[0021] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the virtual lane line generation method provided in any embodiment of this disclosure.

[0022] Fourthly, embodiments of this disclosure also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the virtual lane line generation method provided in any embodiment of this disclosure.

[0023] Fifthly, embodiments of this disclosure also provide a computer program product for executing the virtual lane line generation method provided in any embodiment of this disclosure.

[0024] The technical solution provided in this disclosure has at least the following advantages compared with the prior art: Based on the lane attribute information of lanes in the same direction of travel in the road to be processed, lane line suspension points in the road to be processed are determined; the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the direction of travel is determined; based on a preset index, the width change index value between two adjacent perpendicular distances is determined; from the width change index values, target index values ​​that satisfy the width change convergence condition are selected, wherein the width change convergence condition is used to characterize the condition that the width change index value converges to a preset change range; based on the lane position in the direction perpendicular to the lane line corresponding to the target index value, the lane change point of the road to be processed is determined; based on the lane line suspension point, the lane change point and the adjacent lane lines on both sides, a virtual lane line between the lane suspension point and the lane change point is generated. Therefore, based on the lane line suspension point, the width variation between the lane lines on both sides of the lane line suspension point, and specific width constraints, a lane change point that is more in line with the actual situation can be determined. Finally, based on the lane line suspension point, the lane change point, and the adjacent lane lines on both sides of the lane line suspension point, a virtual lane line is generated, which largely avoids abrupt changes in the virtual lane line, thereby improving the smoothness of the virtual lane line and providing more stable and smooth lane line data for subsequent applications of high-precision map data (such as autonomous driving or advanced driver assistance functions). Attached Figure Description

[0025] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0026] Figure 1 This is a schematic diagram of the generation result of virtual lane lines in the prior art;

[0027] Figure 2 A flowchart illustrating a virtual lane line generation method provided in this embodiment of the disclosure;

[0028] Figure 3This is a schematic diagram illustrating the generation principle of virtual lane lines for a road to be processed, provided in an embodiment of this disclosure.

[0029] Figure 4 for Figure 2 A detailed flowchart of S240 in the virtual lane line generation method is shown.

[0030] Figure 5 A schematic diagram illustrating the generation principle of virtual lane lines for another road to be processed, provided in an embodiment of this disclosure;

[0031] Figure 6 for Figure 2 A detailed flowchart of S250 in the virtual lane line generation method is shown.

[0032] Figure 7 This is a schematic diagram of the structure of a virtual lane line generation device provided in an embodiment of the present disclosure;

[0033] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0034] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0035] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0036] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0037] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0038] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0039] In related technologies, lane line suspension points on interrupted lane lines and fixed empirical values ​​are often used to determine lane change points on adjacent lane lines on either side of the lane direction. Then, the lane line suspension points and lane change points are connected to generate virtual lane lines. This method of generating virtual lane lines does not take into account the actual situation of lanes on high-precision maps, resulting in relatively rigid virtual lane lines that are prone to abrupt lane line changes and lane line imbalances.

[0040] To avoid abrupt changes in the generated virtual lane lines, this disclosure provides a method for generating virtual lane lines. The method determines lane change points that better meet the requirements for safe driving based on the changes in lane width around the interrupted lane line. Then, it draws undrawn lane lines using the lane suspension point at the interrupted lane line, the lane change point, and the lane lines already drawn around the terminal lane line, thereby improving the smoothness of the virtual lane lines.

[0041] Figure 2 This is a flowchart illustrating a virtual lane line generation method provided in an embodiment of the present disclosure. It can be applied to situations where virtual lane lines are generated at lane change locations during the creation or updating of high-precision maps. This virtual lane line generation method can be executed by a virtual lane line generation device, which can be implemented using software and / or hardware and integrated into an electronic device with a certain computing power. This electronic device can be, for example, a laptop computer, a desktop computer, a mobile workstation, or a server.

[0042] like Figure 2 As shown, the virtual lane line generation method provided in this embodiment may include:

[0043] S210. Based on the lane attribute information of lanes in the same direction of travel in the road to be processed, determine the lane line suspension points existing in the road to be processed.

[0044] In this embodiment, when generating virtual lane lines on a high-precision map, for any road to be processed, the lane attribute information of the road to be processed is obtained, and the lane line suspension point is detected from the lane to be processed based on the lane attribute information, so that the virtual lane line is generated based on the lane line suspension point.

[0045] The road to be processed refers to any road on the high-precision map that requires the drawing of virtual lane lines. Optionally, the road to be processed can be a highway or a country road; there is no limitation on this.

[0046] Among them, lane attribute information can characterize the topology information of each lane in the same direction of travel in the lane to be processed.

[0047] In some embodiments, lane attribute information includes lane connection relationships and lane line information. S210 specifically includes: determining the location of lanes in the road to be processed where the number of lanes changes based on each lane and lane connection relationship; if, based on the lane line information of each lane, it is determined that there is a suspension point at the location of the lane where the number of lanes changes, then the suspension point is determined as a lane line suspension point.

[0048] Lane connectivity refers to the topological connectivity between lanes in different road segments of the road to be processed. For example, the connectivity between two lanes before and after lane separation.

[0049] The lane line information may include the location information of each lane point.

[0050] The lane positions where the number of lanes changes in the road to be processed refer to the locations where the number of lanes increases or decreases, and are defined on the lane lines in a direction perpendicular to the lane lines. Specifically, multiple perpendicular lines are drawn along the direction perpendicular to the lane lines, and the number of intersections between each perpendicular line and the lane lines is determined. If the number of intersections corresponding to a certain perpendicular line changes, it is determined that the number of lanes in the road to be processed has changed, and the intersections where the number of intersections has changed are identified as the lane positions on the corresponding lane lines.

[0051] The suspension point refers to a point where at least one end is not connected to the lane line.

[0052] Specifically, if the number of lanes in the road to be processed changes based on lane connectivity, the location of the lane with the changed lane number is determined. Then, it is determined whether the lane position on each lane line is a suspension point. If not, it means there are no interrupted lane lines in the road to be processed, and there is no need to perform virtual lane line generation. If so, the suspension point is used as the lane line suspension point.

[0053] For ease of understanding, Figure 3 A schematic diagram illustrating the generation principle of virtual lane lines for a road to be processed, provided in an embodiment of this disclosure, is shown. For example... Figure 3 As shown, to the left of point C, the road to be processed includes lane 2 and lane 3. To the right of point C, the road to be processed includes lane 1, lane 2 and lane 3. That is, in the same direction of traffic in the road to be processed, starting from point C (endpoint) of the left lane line of lane 1, the number of lanes in the road to be processed changes, and there is no lane line connected to the left of point C. Therefore, point C is recorded as the lane line suspension point in the road to be processed.

[0054] In some other embodiments, S210 specifically includes: if it is determined that there is a suspension point identifier for the virtual lane line to be generated in each lane attribute information, then the suspension point corresponding to the suspension point identifier is determined as the lane line suspension point.

[0055] Among them, suspension point markings refer to the marking information generated in advance by manual means for the suspension points of the virtual lane lines to be generated.

[0056] Specifically, if there are suspension point identifiers for virtual lane lines to be generated in the attribute information of each lane, the suspension points carrying suspension point identifiers are directly identified from the lane points of the road to be processed and used as lane line suspension points.

[0057] Therefore, for the road to be processed, the lane position can be determined based on the lane connection relationship and lane line information contained in the lane attribute information, and the lane line suspension point in the road to be processed can be automatically determined. Alternatively, the lane line suspension point to be generated can be selected from the suspension point identifiers that are manually marked in advance, so as to adapt to the situation of determining the lane line suspension point in different scenarios.

[0058] S220. Determine the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the direction of traffic.

[0059] In this embodiment, along the direction of travel, based on the correspondence between lanes and lane lines, the adjacent lanes to which the lane line suspension point belongs are detected, and the two lane lines in the adjacent lanes other than the existing lane line where the lane line suspension point is located are determined as the adjacent lane lines on both sides of the lane line suspension point. See also... Figure 3 Following the direction of traffic, we can first determine the adjacent lanes, namely lane 1 and lane 2, based on the lane line suspension point C. Then, based on the correspondence between lanes and lane lines, we can determine lane line L4 and its connected lane lines L1 and L2, which are the adjacent lane lines on both sides of lane line suspension point C.

[0060] Then, within a certain range around the lane line suspension point, based on the positions of points on the adjacent lane lines on both sides of the lane line suspension point, calculate multiple perpendicular distances between the adjacent lane lines on both sides of the lane line suspension point.

[0061] In some embodiments, the adjacent lane lines on both sides of the lane line suspension point are uniformly interpolated, and the vertical distance is determined based on the interpolation points. Accordingly, S220 specifically includes: determining multiple interpolation points on any adjacent lane line at preset intervals; and determining the vertical distance between the adjacent lane lines on both sides at each interpolation point.

[0062] Specifically, determining multiple interpolation points on any adjacent lane line according to a preset interval includes: determining an interpolation area on each lane line of the adjacent lane lines based on a preset distance range corresponding to the lane line suspension point; determining multiple interpolation points in the interpolation area according to a preset interval; and determining the perpendicular distance between adjacent lane lines at each interpolation point.

[0063] The preset distance range is used to determine the interpolation area on each lane line in the adjacent lane lines on both sides.

[0064] The preset interval distance can be understood as a uniform interpolation distance. Specifically, the preset interval distance can be determined based on the processing speed and the accuracy of the lane change points. Optionally, the preset interval distance can be 1m, 2m, or other parameters.

[0065] See also Figure 3 Based on the traffic direction of the lane, taking the lane line suspension point C as the midpoint, a rectangular area (this is just an example, it could also be a circular area, etc.) is defined by extending a preset distance on one side (such as the left or right side) or both sides of the perpendicular line V. The area where this rectangular area intersects with the adjacent lane lines (lane line L2, lane line L4 and their connected lane line L1) is used as the interpolation area for each adjacent lane line. Then, according to the preset interval, a new lane point (e.g., lane line L2) is inserted on any adjacent lane line (such as lane line L2) in the interpolation area. Figure 3 Points represented by triangles on lane L2 are used as multiple interpolation points. Then, a perpendicular line to the lane line is drawn at each interpolation point, and the distance between the perpendicular lines of the adjacent lane lines on both sides (lane line L2, lane line L4 and the lane line L1 connected to them) is calculated, thus obtaining multiple perpendicular distances between the adjacent lane lines on both sides.

[0066] Therefore, interpolation is performed based on uniform intervals to determine the perpendicular distance between adjacent lane lines on both sides. This makes it less likely to miss the actual lane point changes and ensures the accuracy of the distance calculation.

[0067] In other embodiments, non-uniform interpolation is performed on adjacent lane lines on both sides of the lane line suspension point, and the vertical distance is determined based on the interpolation point. Accordingly, S220 specifically includes: along the traffic direction, determining the lane segment to be processed from adjacent lane lines based on the lane line suspension point and a preset lane length; and determining the vertical distance between adjacent lane lines on both sides of the lane segment to be processed according to a preset number.

[0068] Among them, the lane line suspension point and the preset lane length are used to determine the length of the lane segment to be processed in the adjacent lane lines.

[0069] The preset quantity refers to the number of interpolation points.

[0070] Specifically, along the direction of traffic, based on the lane line suspension point and the preset lane length, the interpolation length is determined from the adjacent lane lines to obtain the lane segment to be processed. Then, a preset number of interpolation points are inserted into the lane segment to be processed. Finally, at each interpolation point, the perpendicular distance between adjacent lane lines is determined. Specifically, the distance between any two interpolation points in the adjacent lane lines on both sides is calculated, and the minimum distance is selected as the perpendicular distance between the adjacent lane lines on both sides.

[0071] Therefore, interpolation is performed based on the method of calculating the perpendicular distance at non-uniform intervals to calculate the perpendicular distance between adjacent lane lines on both sides, which improves the flexibility of interpolation.

[0072] In summary, interpolation can be performed using either uniform or non-uniform interval calculation of perpendicular distances, thus adapting to various calculation needs, such as calculating the perpendicular distance between adjacent lane lines on both sides.

[0073] S230. Based on preset indicators, determine the width change index value between the distances of two adjacent vertical lines.

[0074] In this embodiment, the perpendicular distance between two adjacent lane lines is taken as the width between the two adjacent lane lines, and the width change index value of the two adjacent lane lines is calculated from each width according to the calculation method of the preset index.

[0075] For better understanding, please continue to refer to [link / reference]. Figure 3 For two adjacent lane lines (lane line L2, lane line L4 and their connected lane line L1) at lane line suspension point C, the width change index value between each pair of adjacent perpendicular distances (such as V1 and V2, V2 and V3, V3 and V4, V4 and V5, V5 and V6) can be calculated according to preset indexes.

[0076] Optionally, the preset index can be any one of width difference, width ratio, and width change rate. That is, if the preset index is a width difference calculation index, then the difference between the distances of two adjacent perpendicular lines is calculated in a certain direction (same traversal direction) as the corresponding width change index value; if the preset index is a width ratio calculation index, then the ratio between the distances of two adjacent perpendicular lines is calculated in a certain direction (same traversal direction) as the corresponding width change index value; if the preset index is a change rate calculation index, then the ratio between the difference between the distances of two adjacent perpendicular lines and the distance of the preceding perpendicular line in a certain direction (same traversal direction) is calculated as the corresponding width change index value.

[0077] S240. From the width change index values, select target index values ​​that meet the width change convergence condition, wherein the width change convergence condition is used to characterize the condition that the width change of the road converges to a preset change range.

[0078] In this embodiment, a suitable width change convergence condition is determined based on a preset index corresponding to the width change index value; that is, the condition under which the road width change converges to a preset range is determined. Then, width change index values ​​that satisfy the width change convergence condition are selected from all width change index values ​​and used as target index values.

[0079] The width change convergence condition is used to characterize the stabilization of the width between two adjacent lane lines, i.e., the convergence of the width change index value. In this embodiment, a preset variation range can be used to limit the fluctuation range of the width change index value during convergence. The preset variation range refers to the tolerable error range during numerical convergence, which is a small numerical range Δ. For example, when the width change index is the width difference, the target convergence index value is in the range of 0 ± Δ; when the width change index is the width ratio, the target convergence index value is in the range of 1 ± Δ.

[0080] S250 determines the lane change point of the lane to be processed based on the lane position in the direction perpendicular to the lane line corresponding to the target index value.

[0081] In this embodiment, a perpendicular line to the travel direction of the lane line is determined at the target index value, and the intersection points of this perpendicular line with the adjacent lane lines on both sides of the lane line suspension point are determined. This intersection point is the lane position corresponding to the target index value. This lane position is used as the lane change point of the lane to be processed.

[0082] For better understanding, please continue to refer to [link / reference]. Figure 3 If the determined target index value corresponds to the vertical line V2, then the intersection points D and E of the vertical line V2 with the adjacent lane lines on both sides (lane line L2, lane line L4 and the lane line L1 connected to it) can be used as lane change points.

[0083] Therefore, based on the lane line suspension point, the actual lane width, and specific width constraints, lane change points that better reflect the actual situation can be determined, which facilitates the subsequent generation of virtual lane lines that conform to the actual situation.

[0084] S260. Based on the lane line suspension point, lane change point, and adjacent lane lines on both sides, generate a virtual lane line between the lane suspension point and the lane change point.

[0085] In this embodiment, virtual lane lines that are not actually drawn on the road are drawn, starting from the lane line suspension point, ending at the lane change point, and using the adjacent lane lines on both sides as range constraints. Because the location of the lane change point is more in line with actual road conditions, the virtual lane lines generated here will better meet actual driving guidance needs.

[0086] In some embodiments, a virtual lane line between the lane suspension point and the lane change point is generated based on the boundary copying method. Here, the boundary copying method refers to a curve generation method that copies the line shape of any one of the adjacent lane lines on both sides. For details on generating virtual lane lines based on the boundary copying method, please refer to the description of subsequent embodiments.

[0087] In other embodiments, virtual lane lines are generated by drawing curves based on lane line suspension points, lane change points, and adjacent lane lines on both sides. Details of this curve-drawing method for generating virtual lane lines can be found in the descriptions of subsequent embodiments.

[0088] In some other embodiments, virtual lane lines are generated by curve fitting based on lane line suspension points, lane change points, and adjacent lane lines on both sides. Details of this curve fitting-based method for generating virtual lane lines can be found in the descriptions of subsequent embodiments.

[0089] In other embodiments, candidate lane lines corresponding to the reference line are first generated based on the lane line suspension point, lane change point, and adjacent lane lines on both sides. Then, the final virtual lane line is determined from the candidate lane lines by combining the angle change at each point, whether it intersects with an obstacle, and whether it intersects with an adjacent lane line.

[0090] In some embodiments, the convergence condition for width variation is characterized by a preset threshold range. For each calculated width variation index value, it is determined whether the width variation value falls within the preset threshold range according to a specific direction, and the target index value is determined based on the determination result. This process is easy to implement and can also ensure the accuracy of target index value selection. Figure 4 As shown, Figure 2 A detailed flowchart of step S240 in the virtual lane line generation method is shown. (See also...) Figure 4 S240 "Select target index values ​​that meet the convergence condition of width change from the width change index values", including:

[0091] S410. Compare the width change index values ​​with the preset threshold range along the preset traversal direction.

[0092] In this embodiment, the identification order of each width change index value is predetermined as a preset traversal direction. Then, the width change index values ​​are identified one by one according to the preset traversal direction, and each width change index value is compared with a preset threshold range to identify the width change index values ​​within the preset threshold range. S420 or S430 can then be executed.

[0093] The preset traversal direction can be understood as an empirically set direction for identifying width change index values. Specifically, it can be consistent with the direction of lane movement and is not limited to the direction of traffic. For example, the preset traversal direction can be from left to right or from right to left.

[0094] The preset threshold range is the range of width change index values ​​that satisfy the convergence condition for width change. The preset threshold range is constructed based on the width change baseline value and the preset change range. Here, the width change baseline value is the ideal value of the width change index. For example, for the preset index of width difference, the width change baseline value can be 0, and the preset threshold range can be 0 ± Δ; for the preset index of width ratio, the width change baseline value can be 1, and the preset threshold range can be 1 ± Δ.

[0095] S420. The first width change index value that falls within the preset threshold range is determined as the target index value.

[0096] It is understandable that there are multiple width change index values. Therefore, the first width change index value that falls within the preset threshold range is selected from the multiple width change index values ​​as the target index value.

[0097] S430. If there are a preset number of width change index values ​​that fall within a preset threshold range, the first width change index value that falls within the preset threshold range will be determined as the target index value.

[0098] It is understandable that when a sudden change occurs in a local position of a lane, the width change index value corresponding to the lane position at the location of the sudden change will also change suddenly. This width change index value may also be within the preset threshold range. If this width change index value happens to be the first width change index value within the preset threshold range, it is obviously inaccurate to use this width change index value as the target index value, which further leads to the unreliability of the determined lane change point.

[0099] To avoid inaccurate lane change point determination due to a single comparison result, in this embodiment, during the comparison of each width change index value with a preset threshold range, a preset number (e.g., 3 or 5) of width change index values ​​falling within the preset threshold range, and where these width change index values ​​are consecutive, can be used to filter out the aforementioned lane abrupt changes. Thus, during the comparison of each width change index value with the preset threshold range, if a preset number of consecutive width change index values ​​fall within the preset threshold range, the first width change index value falling within the preset threshold range is taken as the target index value.

[0100] Therefore, when a sudden change occurs in the local position of a lane, the first width change index value that falls within the preset threshold range is selected from a preset number of consecutive width change index values ​​that fall within the preset threshold range. This eliminates the impact of the sudden change in the local position of the lane and ensures the reliability of the lane change point determined based on the target index value.

[0101] In a situation different from S240, after identifying the lane line suspension point, if the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point remains constant, the lane line width change index value remains constant. In this case, none of the width change index values ​​meet the width change convergence condition, making it impossible to determine the lane change point based on the lane line width change index value. To solve this problem, after S230, the method also includes a method parallel to S240, specifically including: if none of the width change index values ​​meet the width change convergence condition, determining the required length of the virtual lane line based on the lane width, lateral driving speed, and lane speed limit; and determining the lane change point on any adjacent lane line on the side of the existing lane line far from the lane line suspension point based on the lane line suspension point and the required length.

[0102] Lane width can be determined based on the vertical distance between adjacent lane lines on either side of the lane line suspension point. Lateral speed is the average speed component of a vehicle traveling across lanes at the lane speed limit, expressed along the lane width. The lane speed limit refers to the maximum speed allowed in a lane.

[0103] Optionally, lane width and lateral speed can be obtained from high-precision map data.

[0104] In this context, the side of the existing lane line furthest from the lane line suspension point can be understood as the road segment where the number of lane lines changes. See also... Figure 3 The side of the existing lane line that is far from the lane line suspension point can be understood as the road segment to the left of the perpendicular line V at the lane line suspension point C.

[0105] It is understandable that if the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point remains fixed, it can be determined that none of the width change index values ​​meet the width change convergence condition. Therefore, there is no width change index value that converges within the preset change range, and thus it is impossible to determine the target index value and the lane change point based on the target index value. Based on this, in this embodiment, optionally, the required length of the virtual lane line is determined based on the lane width, lateral driving speed, and lane speed limit, including: calculating the ratio between the lane width and the lateral driving speed, and then multiplying the ratio by the lane speed limit, and taking the product as the required length of the virtual lane line; correspondingly, based on the lane line suspension point and the required length, the lane change point is determined on any adjacent lane line on the side of the existing lane line away from the lane line suspension point, including: taking the position of the lane line suspension point as the starting point, and based on the starting point and the required length, determining the target position on any adjacent lane line on the side of the existing lane line away from the lane line suspension point, and taking the lane point corresponding to the target position as the lane change point.

[0106] For ease of understanding, see Figure 5 The diagram illustrates the generation principle of virtual lane lines for another type of road. A perpendicular line V is drawn from the lane line suspension point F, and within a preset distance range to the left of perpendicular line V, the perpendicular distances V1, V2, and V3 between adjacent lane lines L1 and L3 are determined. Since adjacent lane lines L1 and L3 are parallel, the perpendicular distances V1, V2, and V3 are all equal. Thus, the width variation index values ​​calculated from the multiple perpendicular distances between adjacent lane lines on both sides of the lane line suspension point F are equal (e.g., width difference is 0, width ratio is 1), and they do not gradually converge to the preset variation range Δ. In this case, none of the width variation index values ​​meet the width variation convergence condition. At this point, the required length of the virtual lane line that meets safe driving requirements can be calculated using the formula: Required length = Lateral variation distance / Lateral average speed * Lane speed limit. Then, based on the lane line suspension point F and the required length, determine the lane change point G on any adjacent lane line (such as L1) on the side of the existing lane line far from the lane line suspension point. Afterwards, according to the method for drawing virtual lane lines, use the lane line suspension point F, the lane change point G, the adjacent lane line L1, and the adjacent lane line L3 to generate the virtual lane line FG.

[0107] Therefore, for cases where the width change index value does not meet the width change convergence condition, the required length of the virtual lane line is determined, and then the lane change point is determined based on the lane line suspension point and the required length. This expands the method for determining lane change points, making it suitable for flexibly and accurately identifying lane change points on lanes with different width changes.

[0108] In some embodiments, after determining the lane change point, adjacent lane lines can be used as reference lines, and candidate lane lines are drawn based on the lane line suspension points and lane change points to avoid abrupt changes in the virtual lane lines. Furthermore, based on the smoothness of the lane lines, a virtual lane line is selected from the candidate lane lines to ensure high smoothness of the virtual lane lines. Figure 6 As shown, Figure 6 A detailed flowchart of step S260 in the virtual lane line generation method is shown. (See also...) Figure 6 S260 includes:

[0109] S610. Using adjacent lane lines as reference lines, generate candidate lane lines corresponding to the reference lines based on lane line suspension points and lane change points.

[0110] In some embodiments, a boundary copying method can be used to generate candidate lane lines. Accordingly, S610 includes: for any reference line, using the lane line suspension point and lane change point as endpoints, copying the line shape of the reference line to generate a candidate lane line corresponding to the reference line.

[0111] For details, please refer to [link / reference]. Figure 3 Using lane line L2 from one of the adjacent lane lines on both sides as a reference line, starting from lane line suspension point C and ending at lane change point D, the alignment of reference line L2 is copied to generate candidate lane line CD. Similarly, using lane line L4 from the other of the adjacent lane lines on both sides and its connected lane line L1 as reference lines, starting from lane line suspension point C and ending at lane change point E, the alignment of reference line L4 is copied to generate candidate lane line CE. Candidate lane lines CD and CE are then treated as two distinct candidate lane lines.

[0112] In other embodiments, a curve drawing method can be used to generate candidate lane lines. Accordingly, S610 includes: using the travel direction at the lane line suspension point as the directional constraint of the lane line suspension point; using the travel direction of any reference line at the lane change point as the directional constraint of the lane change point; and performing curve drawing processing based on the lane line suspension point, the directional constraint of the lane line suspension point, the lane change point, and the directional constraint of the lane change point to generate candidate lane lines corresponding to the reference lines.

[0113] The directional constraint of the lane line suspension point can be understood as the trend of the candidate lane line at the starting point, and the directional constraint of the lane change point can be understood as the trend of the candidate lane line at the ending point, thus obtaining the trend of the two ends of the candidate lane line.

[0114] Specifically, using the lane line suspension point and lane change point as endpoints, the directional constraint of the lane line suspension point is used as the trend of the candidate lane line at the starting point, and the directional constraint of the lane change point is used as the trend of the candidate lane line at the ending point. Using a curve drawing algorithm, curve drawing processing is performed to generate candidate lane lines corresponding to the reference line.

[0115] Optionally, the curve plotting algorithm can be Hermitian curve, B-spline curve, quintic polynomial curve, etc.

[0116] In some other embodiments, curve fitting can be used to generate candidate lane lines. Accordingly, S610 includes: determining multiple lane line sampling points from the existing lane lines where the lane line suspension point is located; for any reference line: starting from the lane position in the direction perpendicular to the lane line corresponding to the lane change point, determining multiple lane line sampling points on the reference line on the side away from the existing lane line where the lane line suspension point is located; using the adjacent lane lines on both sides as range constraints, performing curve fitting on each lane line sampling point, lane line suspension point, and lane change point to generate candidate lane lines corresponding to the reference line.

[0117] Specifically, the adjacent lane lines on both sides are used as the range constraints for fitting candidate lane lines, so that the candidate lane lines will not exceed the adjacent lane lines on both sides. The lane line suspension point, lane change point and lane line sampling point are used as fitting points to perform curve fitting and generate candidate lane lines corresponding to the reference line.

[0118] Optionally, curve fitting methods may include, but are not limited to, the least squares method, and other algorithms may also be used for curve fitting.

[0119] Therefore, different generation methods are used to generate virtual lane lines, ensuring the flexibility and reliability of the virtual lane line generation method.

[0120] S620. Based on the smoothness of the lane lines corresponding to each candidate lane line, determine the virtual lane line from each candidate lane line.

[0121] To make the generated virtual lane lines smoother and avoid large steering and turbulence during autonomous driving, after determining each candidate lane line, the smoothness of each candidate lane line can be obtained, and then the lane line with higher smoothness can be selected as the virtual lane line.

[0122] In this embodiment, optionally, the method for determining lane line smoothness includes: for any candidate lane line: determining the in-line smoothness of the candidate lane line based on the angle change at each point on the candidate lane line, whether the candidate lane line intersects with an obstacle, and whether the candidate lane line intersects with adjacent lane lines on both sides; determining the inter-line smoothness between the candidate lane line and the reference line based on the angle between the candidate lane line and the reference line corresponding to the candidate lane line; and determining the lane line smoothness based on the in-line smoothness and the inter-line smoothness.

[0123] The angle change at each point can be determined based on the angle between multiple consecutive lane points on the candidate lane line and the existing lane line. It is understandable that a larger angle change at each point on the candidate lane line indicates a greater range of angle change, resulting in a larger range of directional changes for the autonomous vehicle during operation.

[0124] Understandably, if a candidate lane line intersects with an obstacle, it indicates that there is an obstacle on the candidate lane line. If the autonomous vehicle travels along the candidate lane line, there is a high probability that the autonomous vehicle will collide with the obstacle, posing a safety hazard. Conversely, if a candidate lane line does not intersect with an obstacle, it indicates that there is no obstacle on the candidate lane line. If the autonomous vehicle travels along the candidate lane line, the autonomous vehicle will not collide with the obstacle.

[0125] Understandably, if a candidate lane line intersects with an adjacent lane line, it means that there is a lane mark on the adjacent lane line. If an autonomous vehicle drives along this candidate lane line, it may cross the adjacent lane line, resulting in a lane-changing-like driving behavior, which poses a certain safety hazard. Conversely, if a candidate lane line does not intersect with an adjacent lane line, it means that there is no lane mark on the adjacent lane line. If an autonomous vehicle drives along this candidate lane line, the driving safety of the autonomous vehicle is relatively low.

[0126] Specifically, different weights are assigned to the angle change, whether the candidate lane line intersects with an obstacle, and whether the candidate lane line intersects with an adjacent lane line. The angle change at each point on the candidate lane line, whether the candidate lane line intersects with an obstacle, whether the candidate lane line intersects with an adjacent lane line, and their respective weights are weighted and summed. The weighted sum is used as the in-line smoothness of the candidate lane line.

[0127] The angle between the candidate lane line and at least one reference line is used to characterize the smoothness of the connection between them. In other words, the larger the angle, the lower the smoothness of the connection; conversely, the smaller the angle, the higher the smoothness. Understandably, lower smoothness results in poorer driving stability for the autonomous vehicle, while higher smoothness leads to better driving stability.

[0128] After determining the in-line smoothness and inter-line smoothness, the lane line smoothness can be obtained by weighted summation based on the in-line smoothness, inter-line smoothness and their respective weights.

[0129] Furthermore, S620 specifically includes: selecting lane lines from candidate lane lines whose lane line smoothness is greater than or equal to a preset threshold, and using them as virtual lane lines.

[0130] For better understanding, please continue to refer to [link / reference]. Figure 3 If candidate lane line CD and candidate lane line CE are determined using the different methods described above, and the smoothness of candidate lane line CD is greater than or equal to a preset threshold, while the smoothness of candidate lane line CE is less than a preset threshold, then candidate lane line CD will be used as a virtual lane line.

[0131] Therefore, after determining the lane change point, the adjacent lane lines are used as reference lines, and candidate lane lines are drawn based on the lane line suspension point and lane change point to avoid abrupt changes in the virtual lane lines. Furthermore, based on the smoothness of the lane lines, the virtual lane lines are selected from the candidate lane lines to ensure that the virtual lane lines have high smoothness. This allows the autonomous vehicle to drive along the virtual lane lines without frequently changing its driving direction, ultimately ensuring the stability of the autonomous vehicle's driving process.

[0132] Figure 7 This is a schematic diagram of a virtual lane line generation device provided in an embodiment of this disclosure. Figure 7 As shown, the virtual lane line generation device 700 provided in this embodiment may include:

[0133] The lane line suspension point determination module 710 is used to determine the lane line suspension points existing in the road to be processed based on the lane attribute information of lanes in the same direction of traffic in the road to be processed.

[0134] The perpendicular distance determination module 720 is used to determine the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the direction of traffic.

[0135] The width change index value determination module 730 is used to determine the width change index value between two adjacent vertical lines based on a preset index.

[0136] The target index value filtering module 740 is used to filter target index values ​​that meet the width change convergence condition from the width change index values. The width change convergence condition is used to characterize the condition that the width change of the road converges to a preset change range.

[0137] The lane change point determination module 750 is used to determine the lane change points of the road to be processed based on the lane position in the direction perpendicular to the lane line corresponding to the target index value.

[0138] The virtual lane line generation module 760 is used to generate a virtual lane line between the lane line suspension point and the lane change point based on the lane line suspension point, the lane change point and the adjacent lane lines on both sides.

[0139] In some embodiments, the convergence condition for width variation is characterized by a preset threshold range, and the target index value filtering module 740 includes:

[0140] The comparison unit is used to compare the width change index values ​​with the preset threshold range along the preset traversal direction;

[0141] The target indicator value determination unit is used to determine the first width change indicator value that falls within the preset threshold range as the target indicator value.

[0142] Furthermore, the target indicator value determination unit is also used for:

[0143] If there are consecutive preset number of width change index values ​​that fall within the preset threshold range and the comparison result is the target result, then the width change index value corresponding to the first comparison result that falls within the preset threshold range in the consecutive preset number of comparison results is determined as the target index value.

[0144] In some embodiments, the device further includes:

[0145] The requirement length determination module is used to determine the required length of the virtual lane line based on the lane width, lateral driving speed, and lane speed limit if none of the width change index values ​​meet the width change convergence condition; wherein, the lateral driving speed is the speed component of the average speed of the vehicle when crossing the lane at the lane speed limit in the lane width direction.

[0146] The lane change point determination module is used to determine the lane change point on any adjacent lane line on the side of the existing lane line far from the lane line suspension point, based on the lane line suspension point and the required length.

[0147] In some embodiments, the virtual lane line generation module 760 includes:

[0148] The candidate lane line generation unit is used to generate candidate lane lines corresponding to the reference lines based on the lane line suspension point and the lane change point, respectively, using the adjacent lane lines as reference lines.

[0149] The virtual lane line determination unit is used to determine virtual lane lines from each candidate lane line based on the lane line smoothness corresponding to each candidate lane line.

[0150] In some embodiments, the candidate lane line generation unit is specifically used for:

[0151] For any reference line, using the lane line suspension point and lane change point as endpoints, the line shape of the reference line is copied to generate candidate lane lines corresponding to the reference line.

[0152] In some embodiments, the candidate lane line generation unit is specifically used for:

[0153] The direction of travel at the lane line suspension point is used as the directional constraint for the lane line suspension point.

[0154] The direction of travel of any reference line at the lane change point is used as the directional constraint of the lane change point.

[0155] Based on the lane line suspension point, the direction constraint of the lane line suspension point, the lane change point, and the direction constraint of the lane change point, curve drawing processing is performed to generate candidate lane lines corresponding to the reference line.

[0156] In some embodiments, the candidate lane line generation unit is specifically used for:

[0157] Multiple lane line sampling points are determined from the existing lane lines where the lane line suspension points are located;

[0158] For any reference line:

[0159] Starting from the lane position perpendicular to the lane line at the lane change point, multiple lane line sampling points are determined on the reference line on the side of the existing lane line away from the lane line suspension point.

[0160] Using the adjacent lane lines on both sides as range constraints, curve fitting is performed on the sampling points, suspension points, and lane change points of each lane line to generate candidate lane lines corresponding to the reference line.

[0161] In some embodiments, the virtual lane line generation module 760 further includes:

[0162] For any candidate lane line:

[0163] The in-line smoothness determination unit is used to determine the in-line smoothness of the candidate lane line based on the angle change at each point on the candidate lane line, whether the candidate lane line intersects with obstacles, and whether the candidate lane line intersects with the adjacent lane lines on both sides.

[0164] The line smoothness determination unit is used to determine the line smoothness between the candidate lane line and the reference line based on the angle between the candidate lane line and the reference line corresponding to the candidate lane line.

[0165] The lane line smoothness determination unit is used to determine the lane line smoothness based on the in-line smoothness and the inter-line smoothness.

[0166] In some embodiments, the perpendicular distance determination module 720 includes:

[0167] The interpolation point determination unit is used to determine multiple interpolation points on any adjacent lane line according to a preset interval distance;

[0168] The first perpendicular distance determination unit is used to determine the perpendicular distance between adjacent lane lines on both sides at each interpolation point.

[0169] In some embodiments, the perpendicular distance determination module 720 includes:

[0170] The lane segment determination unit is used to determine the lane segment to be processed from adjacent lane lines along the direction of travel, based on the lane line suspension point and the preset lane length.

[0171] The second perpendicular distance determination unit is used to determine the perpendicular distance between adjacent lane lines on both sides in the lane segment to be processed according to a preset number.

[0172] In some embodiments, lane attribute information includes lane connectivity and lane line information; the lane line suspension point determination module 710 includes:

[0173] The lane position determination unit is used to determine the position of lanes in the road to be processed where the number of lanes changes, based on each lane and the lane connection relationship.

[0174] The lane line suspension point determination unit is used to determine the suspension point as the lane line suspension point if, based on the lane line information of each lane, a suspension point exists at the location of the lane where the number of lanes changes.

[0175] In some embodiments, the lane line suspension point determination module 710 is specifically used for:

[0176] If it is determined that there is a suspension point identifier for the virtual lane line to be generated in each lane attribute information, then the suspension point corresponding to the suspension point identifier is determined as the lane line suspension point.

[0177] The virtual lane line generation device provided in this disclosure can execute the virtual lane line generation method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method. Content not described in detail in the device embodiments of this disclosure can be referred to the description in any method embodiment of this disclosure.

[0178] This disclosure also provides an electronic device, which may include at least a processor and a memory, the memory being used to store executable instructions. The processor may be used to read the executable instructions from the memory and execute the executable instructions to implement the virtual lane line generation method in any of the above embodiments.

[0179] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Figure 8 As shown, the electronic device 800 may include a processor 801 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device 800. The processor 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0180] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touch screens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data.

[0181] It should be noted that, Figure 8 The illustrated electronic device 800 is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein. That is, although... Figure 8 An electronic device 800 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0182] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by the processor 801, it can perform the functions defined in the virtual lane line generation method provided in any embodiment of this disclosure.

[0183] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0184] In some implementations, the client and server can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0185] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0186] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the virtual lane line generation method provided in any embodiment of this disclosure.

[0187] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on a computer, partially on a computer, as a standalone software package, partially on a computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0188] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0189] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules are not, in some cases, intended to limit the functionality of the module itself.

[0190] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0191] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0192] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0193] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0194] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for generating virtual lane lines, characterized in that, include: Based on the lane attribute information of lanes in the same direction of travel in the road to be processed, determine the lane line suspension points in the road to be processed. Determine the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the direction of travel; Based on preset indicators, determine the width variation index value between the distances of two adjacent vertical lines; From the width change index values, target index values ​​that meet the width change convergence condition are selected, wherein the width change convergence condition is used to characterize the condition that the width change of the road converges to a preset change range. Based on the lane position in the direction perpendicular to the lane line corresponding to the target index value, determine the lane change point of the road to be processed; Based on the lane line suspension point, the lane change point, and the adjacent lane lines on both sides, a virtual lane line is generated between the lane line suspension point and the lane change point.

2. The method according to claim 1, wherein, The convergence condition for width change is characterized by a preset threshold range, and the selection of target index values ​​that satisfy the convergence condition for width change from the width change index values ​​includes: Compare the width change index values ​​with the preset threshold range along the preset traversal direction; The first width change index value that falls within the preset threshold range is determined as the target index value.

3. The method according to claim 2, wherein, After comparing each of the width change index values ​​with a preset threshold range along the preset traversal direction, the method further includes: If a predetermined number of consecutive width change index values ​​fall within the predetermined threshold range, the first width change index value to fall within the predetermined threshold range is determined as the target index value.

4. The method according to claim 1, wherein, After determining the width variation index value between two adjacent vertical distances based on a preset index, the method further includes: If none of the width change index values ​​meet the width change convergence condition, the required length of the virtual lane line is determined based on the lane width, lateral travel speed, and lane speed limit; wherein, the lateral travel speed is the speed component in the lane width direction of the average speed of the vehicle when crossing lanes at the lane speed limit. Based on the lane line suspension point and the required length, the lane change point is determined on any adjacent lane line on the side away from the existing lane line where the lane line suspension point is located.

5. The method according to any one of claims 1-4, wherein, The process of generating a virtual lane line between the lane suspension point and the lane change point based on the lane line suspension point, the lane change point, and the adjacent lane lines on both sides includes: Using the adjacent lane lines as reference lines, candidate lane lines corresponding to the reference lines are generated based on the lane line suspension points and the lane change points. The virtual lane line is determined from the candidate lane lines based on the lane line smoothness corresponding to each candidate lane line.

6. The method according to claim 5, wherein, The step of generating candidate lane lines corresponding to the reference lines based on the lane line suspension points and the lane change points, using the adjacent lane lines as reference lines respectively, includes: For any of the reference lines, using the lane line suspension point and the lane change point as endpoints, the line shape of the reference line is copied to generate the candidate lane line corresponding to the reference line.

7. The method according to claim 5, wherein, The step of generating candidate lane lines corresponding to the reference lines based on the lane line suspension points and the lane change points, using the adjacent lane lines as reference lines respectively, includes: The direction of travel at the lane line suspension point is used as the directional constraint of the lane line suspension point. The reference line at the lane change point is used as the directional constraint of the lane change point. Based on the lane line suspension point, the direction constraint of the lane line suspension point, the lane change point, and the direction constraint of the lane change point, curve drawing processing is performed to generate the candidate lane line corresponding to the reference line.

8. The method according to claim 5, wherein, The step of generating candidate lane lines corresponding to the reference lines based on the lane line suspension points and the lane change points, using the adjacent lane lines as reference lines respectively, includes: Multiple lane line sampling points are determined from the existing lane lines where the lane line suspension points are located; For any of the reference lines mentioned: Starting from the lane position in the direction perpendicular to the lane line corresponding to the lane change point, multiple lane line sampling points are determined on the reference line on the side away from the existing lane line where the lane line suspension point is located. Using the adjacent lane lines on both sides as range constraints, curve fitting is performed on each lane line sampling point, lane line suspension point, and lane change point to generate the candidate lane line corresponding to the reference line.

9. The method according to claim 5, wherein, Before determining the virtual lane line from the candidate lane lines based on the lane line smoothness corresponding to each candidate lane line, the method further includes: For any of the candidate lane lines: The in-line smoothness of the candidate lane line is determined based on the angle change at each point on the candidate lane line, whether the candidate lane line intersects with an obstacle, and whether the candidate lane line intersects with the adjacent lane lines on both sides. Based on the angle between the candidate lane line and the reference line corresponding to the candidate lane line, the line smoothness between the candidate lane line and the reference line is determined; The lane line smoothness is determined based on the in-line smoothness and the inter-line smoothness.

10. The method according to any one of claims 1-4, wherein, Determining the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the traffic direction includes: On any of the adjacent lane lines, multiple interpolation points are determined at preset intervals. At each of the interpolation points, the perpendicular distance between the adjacent lane lines on both sides is determined.

11. The method according to any one of claims 1-4, wherein, Determining the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the traffic direction includes: Along the direction of travel, based on the lane line suspension point and the preset lane length, determine the lane segment to be processed from the adjacent lane lines; According to a preset number, the perpendicular distance between the adjacent lane lines on both sides is determined in the lane segment to be processed.

12. The method according to any one of claims 1-4, wherein, The lane attribute information includes lane connection relationships and lane line information; determining the lane line suspension points in the road to be processed based on the lane attribute information of lanes with the same traffic direction includes: Based on each lane and the lane connection relationship, determine the location of the lane where the number of lanes changes in the road to be processed; If, based on the lane line information of each lane, it is determined that there is a suspension point at the location of the lane where the number of lanes changes, then the suspension point is determined as the lane line suspension point.

13. The method according to any one of claims 1-4, wherein, The process of determining lane line suspension points in the road to be processed based on lane attribute information of lanes traveling in the same direction includes: If it is determined that there is a suspension point identifier for the virtual lane line to be generated in each of the lane attribute information, then the suspension point corresponding to the suspension point identifier is determined as the lane line suspension point.

14. A virtual lane line generation device, characterized in that, include: The lane line suspension point determination module is used to determine the lane line suspension points existing in the road to be processed based on the lane attribute information of lanes in the same direction of traffic in the road to be processed. The perpendicular distance determination module is used to determine the perpendicular distance between adjacent lane lines on both sides of the lane line suspension point along the traffic direction. The width change index value determination module is used to determine the width change index value between two adjacent vertical distances based on a preset index. The target indicator value filtering module is used to filter target indicator values ​​that meet the width change convergence condition from the width change indicator values, wherein the width change convergence condition is used to characterize the condition that the width change of the road converges to a preset change range. The lane change point determination module is used to determine the lane change point of the road to be processed based on the lane position in the direction perpendicular to the lane line corresponding to the target index value. The virtual lane line generation module is used to generate a virtual lane line between the lane line suspension point and the lane change point based on the lane line suspension point, the lane change point and the adjacent lane lines on both sides.

15. A computer program product, characterized in that, The computer program product is used to execute the virtual lane line generation method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that cause a computer to perform the virtual lane line generation method according to any one of claims 1 to 13.

Images