A lane line annotation method and device

Abstract

A lane line marking method and device, wherein the method includes: obtaining an entry point where a vehicle enters an intersection and an exit point where the vehicle exits the intersection, determining a first lane line that moves from the entry point to the exit point, and in the case where the first lane line intersects an obstacle in the intersection or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance, instead of marking the first lane line, selecting one of the two side regions of the first lane line as a target obstacle avoidance region, and selecting at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance, and determining and marking a second lane line whose minimum distance from the obstacle is not less than the preset obstacle avoidance distance according to the entry point, at least one control point, and the exit point, so as to improve the marking quality and efficiency of the lane line.

Description

Technical Field

[0001] This application relates to the technical field of vehicle networking, and in particular, to a lane line annotation method and device. Background Art

[0002] In the field of vehicle networking, high-precision maps play a crucial role in vehicle positioning, vehicle navigation, and even vehicle autonomous driving. High-precision maps are usually made in the following way: collecting the surrounding environment information of real roads, obtaining a point cloud map through fusing the surrounding environment information, and annotating the structured data of various traffic entities in the point cloud map to obtain a high-precision map. Among them, traffic entities may include, but are not limited to, lane lines, traffic signs, or traffic lights, etc. The high-precision maps in the field of vehicle networking are mainly used to guide vehicle traffic. To achieve a better guiding effect, the accuracy of the high-precision map should at least reach the lane level. That is to say, how to efficiently and accurately annotate lane lines is very important for quickly obtaining high-quality high-precision maps to accurately guide vehicle traffic.

[0003] There are mainly two existing lane line annotation methods: one is manual annotation, which mainly relies on the human eye of cartographers to judge the surrounding environment of the lane to be annotated in the point cloud map, and manually annotates virtual curves according to the judgment results. However, this annotation method is not only time-consuming and laborious, but also not easy to ensure the smoothness and beauty of the virtual curves; the other is automatic annotation, which mainly uses some existing drawing software to automatically draw curves. However, the drawing software usually only considers the entry point and the exit point, and does not consider whether there are obstacles on the current road. In this case, the lane lines automatically drawn by the drawing software are very likely to intersect with the obstacles on the road, resulting in the lane lines being unavailable. It can be seen that the two existing lane line annotation methods cannot efficiently and accurately annotate lane lines, which is not conducive to improving the annotation efficiency and annotation quality of lane lines on the map. Summary of the Invention

[0004] This application provides a lane line annotation method and device to improve the annotation efficiency and annotation quality of lane lines.

[0005] In a first aspect, the present application provides a lane marking method, which is applicable to a lane marking device. The lane marking device may be a device, component or chip with image processing capabilities, or may also be a vehicle. The method includes: the lane marking device obtains the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection, determines the first lane line moving from the entry point to the exit point, and when the first lane line intersects with an obstacle in the intersection or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance, instead of marking the first lane line on the map, it selects one of the two side regions of the first lane line as the target obstacle avoidance region, and selects at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance. According to the entry point, at least one control point and the exit point, a second lane line with a minimum distance from the obstacle not less than the preset obstacle avoidance distance is determined, and the second lane line is marked on the map.

[0006] In the above design, by re-determining the second lane line that can safely bypass the obstacle in the intersection when the first lane line to be determined cannot safely bypass the obstacle in the intersection, it helps to directly mark the second lane line with accurate obstacle avoidance ability in the intersection of the map through one marking operation. This method neither relies on manual marking nor requires manual secondary adjustment, and can effectively improve the marking quality and efficiency of the lane line. Further, when the first lane line does not meet the marking requirements, by selecting control points within one side region of the first lane line whose distance from the obstacle is greater than or equal to the preset obstacle avoidance distance as the basis for determining the second lane line, it can also increase the probability of determining the second lane line that meets the obstacle avoidance distance requirements and improve the success rate of marking the lane line.

[0007] In a possible design, the lane line to be labeled can be any lane line on the straight lane, left-turn lane or right-turn lane at an intersection, such as one of the two lane side lines on both sides, or the lane center line. In this case, the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance distance, which can include any one of the following: If the first lane line is the lane side line adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance interval; if the first lane line is the lane side line not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance interval and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance interval and half of the preset lane width. Among them, the preset obstacle avoidance interval can be a real number greater than or equal to 0. This design can not only support the lane line labeling device to select a suitable lane line as the lane line to be labeled according to actual needs, but also set different decision conditions for different lane lines. Each lane line will re-determine the second lane line only when it meets its own decision conditions, which helps to balance the accuracy of labeling lane lines while saving computing resources.

[0008] In a possible design, the target obstacle avoidance area can meet at least one of the following conditions:

[0009] Condition 1: The target obstacle avoidance area is located within the obstacle avoidance area indicated by the obstacle with traffic regulation indication function. This condition can label the lane lines that meet traffic regulations within the obstacle avoidance area indicated by the obstacle, effectively reducing the violation risk of vehicles using the map.

[0010] Condition 2: When the first lane line does not intersect with the obstacle, the target obstacle avoidance area does not contain the obstacle. In this condition, the area without the obstacle is better for choosing control points than the area with the obstacle. Therefore, this condition helps to improve the efficiency of selecting control points in the target obstacle avoidance area later.

[0011] Condition 3: When the first lane line intersects with the obstacle, the target obstacle avoidance area contains the obstacle area with the smallest area among the two obstacle areas divided by the first lane line. This condition can quickly select the target obstacle avoidance area by comparing the areas of the obstacle areas on both sides.

[0012] Condition 4: In the case where the first lane line intersects with an obstacle, the target obstacle avoidance area includes the obstacle area with the minimum maximum distance from the first lane line among the two obstacle areas divided by the first lane line. In this condition, by taking the area on the side where the obstacle area with the minimum maximum distance from the first lane line is located as the target obstacle avoidance area, it is possible to obtain the second lane line through a relatively small deformation depending on the positional relationship between the first lane line and the obstacle, which helps to reduce the difficulty of re - determining the second lane line. Moreover, since the second lane line is drawn in the area with the closest maximum distance from the edge of the obstacle, it is also possible for the second lane line to have a shorter length, which helps to indicate that the vehicle can bypass the obstacle as soon as possible through a shorter driving distance, improving the obstacle avoidance efficiency of the vehicle.

[0013] In a possible design, when the first lane line intersects with an obstacle, the lane line marking device selects at least one control point in the target obstacle avoidance area with a distance from the obstacle not less than a preset obstacle avoidance distance, including: The lane line marking device finds the first position point with the maximum distance from the first lane line on the edge of the obstacle area included in the target obstacle avoidance area, and determines a second position point in the target obstacle avoidance area with a distance from the first position point equal to the preset obstacle avoidance distance, and takes the second position point as a control point. Among them, the line connecting the second position point and the first position point is perpendicular to the tangent of the first lane line, or perpendicular to the line segment between the two intersection points of the first lane line and the obstacle. This design, when the first lane line intersects with an obstacle, by taking the point on the obstacle with the maximum distance from the first lane line as the obstacle critical point, can find the lane line critical point that just meets the obstacle avoidance requirement, and by taking this lane line critical point as a control point, helps to draw the critical lane line that can just achieve the obstacle avoidance ability.

[0014] In a possible design, when the first lane line does not intersect with an obstacle, the lane line marking device selects at least one control point in the target obstacle avoidance area with a distance from the obstacle not less than a preset obstacle avoidance distance, including: The lane line marking device finds the third position point with the minimum distance from the first lane line on the edge of the obstacle, and determines a fourth position point in the target obstacle avoidance area with a distance from the third position point equal to the preset obstacle avoidance distance, and takes the fourth position point as a control point. Among them, the line connecting the fourth position point and the third position point is perpendicular to the tangent of the first lane line, or perpendicular to the tangent of the obstacle at the third position point. This design, when the first lane line does not intersect with an obstacle, by taking the point on the obstacle with the minimum distance from the first lane line as the obstacle critical point, can find the lane line critical point that just meets the obstacle avoidance requirement, and by taking this lane line critical point as a control point, helps to draw the critical lane line that can just achieve the obstacle avoidance ability.

[0015] In a possible design, after determining the control points according to the above design, the lane line marking device can also draw a control line in a direction perpendicular to the connection line from the control points, and select at least two fifth position points located on both sides of the control points from the control line, and use the at least two fifth position points as at least two control points. In this way, by re-obtaining safer control points outside the critical point based on the lane line critical point, it helps to draw an obstacle avoidance lane line with a certain safety margin and improve the safety performance of the marked lane line.

[0016] In a possible design, the at least two control points may include at least one of the following: the intersection of the control line and the entry line is used as one control point, and the intersection of the control line and the exit line is used as another control point, where the entry line is a straight line drawn from the entry point along the entry direction, and the exit line is a straight line drawn from the exit point along the opposite direction of the exit direction; two points on the control line whose distances from the control point are equal to the length of the line segment between the two intersections of the first lane line and the obstacle are used as two control points; two points on the control line whose distances from the control point are equal to the length of the first lane line inside the obstacle are used as control points. In this way, by evenly selecting two control points on both sides of the control point on the control line, a relatively smooth second lane line can be drawn based on three relatively evenly distributed control points.

[0017] In a possible design, the lane line marking device can determine the first lane line from the entry point to the exit point in the following way: If the current lane is a straight lane, the lane line marking device can directly connect the entry point and the exit point to obtain the first lane line; if the current lane is a turning lane line, the lane line marking device can first extend from the entry point along the entry direction to obtain the entry line, and extend from the exit point along the opposite direction of the exit direction to obtain the exit line, and then determine the first lane line according to the entry point, the intersection of the entry line and the exit line, and the exit point. In this design, the lane line marking device can select different lane line determination methods according to different types of lanes, which helps to draw lane lines that meet the current lane type more precisely.

[0018] In a second aspect, the present application provides a lane line marking method, which is applicable to a lane line marking device. The lane line marking device can be a device, component or chip with image processing capabilities, or it can also be a vehicle. The method includes: The lane line marking device obtains the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection, selects at least two control points in the intersection, determines at least two first lane lines according to the entry point, the exit point and the at least two control points, and different control points are used for any two of the at least two first lane lines. Then, a target first lane line whose minimum distance from the obstacle in the intersection is not less than a preset obstacle avoidance distance is determined from the at least two first lane lines, and the target first lane line is marked on the map.

[0019] In the above design, by pre-fitting multiple first lane lines in the intersection, the probability that the lane line marking device directly selects a target first lane line that can avoid obstacles in the intersection from the multiple first lane lines can be increased, and it is no longer necessary to re-determine the lane lines. This design not only helps improve the efficiency of lane line marking, but also can mark the target first lane line with obstacle avoidance function on the map, effectively improving the quality and accuracy of lane line marking.

[0020] In a possible design, the lane line to be marked can be any lane line on the straight lane, left-turn lane or right-turn lane in the intersection, such as one of the two side lane boundaries or the lane center line. In this case, the minimum distance between the first lane line and the obstacle is not less than the preset obstacle avoidance distance, and it can include any one of the following: If the first lane line is the lane boundary adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the preset obstacle avoidance interval; if the first lane line is the lane boundary not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance interval and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance interval and half of the preset lane width. Among them, the preset obstacle avoidance interval is a real number greater than or equal to 0.

[0021] In a possible design, the lane line marking device selects at least two control points in the intersection, including: the lane line marking device selects at least two control points in the intersection whose distance from the obstacle is greater than the preset obstacle avoidance distance. In this way, by selecting control points in the intersection whose distance from the obstacle is greater than or equal to the preset obstacle avoidance distance as the reference for determining the first lane line, the probability of determining the first lane line that meets the obstacle avoidance distance requirement can be increased.

[0022] In a possible design, the lane line marking device determines a target first lane line from at least two first lane lines whose minimum distance from the obstacle in the intersection is not less than the preset obstacle avoidance distance, including: If the obstacle is an obstacle with traffic rule indication function, the lane line marking device selects the target first lane line from the first lane lines located in the target obstacle avoidance area indicated by the obstacle, so as to meet the obstacle avoidance rules indicated by the obstacle. If the obstacle is an obstacle without traffic rule indication function, the target first lane line is selected from at least two first lane lines. When the obstacle does not have traffic rule indication function and does not point out the obstacle, it can be selected according to actual needs. Among them, the minimum distance between the target first lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0023] In a possible design, if the lane line marking device determines that there is no target first lane line among at least two first lane lines whose minimum distance from the obstacle is not less than a preset obstacle avoidance distance, it can also select a reference first lane line from the at least two first lane lines, select one of the two side regions of the reference first lane line as the target obstacle avoidance region, and select at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance. According to the entry point, the at least one control point, and the exit point, a second lane line whose minimum distance from the obstacle is not less than the preset obstacle avoidance distance is determined, and then the second lane line is marked on the map. In this design, by re-determining the second lane line that can safely bypass the obstacle in the intersection when multiple first lane lines to be determined cannot safely bypass the obstacle in the intersection, it helps to mark a second lane line with accurate obstacle avoidance ability in the intersection of the map, effectively improving the marking quality and efficiency of the lane line.

[0024] It should be understood that for the specific implementation process of re-determining the second lane line in the second aspect, the corresponding design in the above first aspect can be directly referred to, and will not be repeated here one by one.

[0025] In a third aspect, the present application provides a lane line marking device, including: an acquisition unit for acquiring the entry point of the vehicle entering the intersection and the exit point of the vehicle exiting the intersection; a determination unit for determining a first lane line moving from the entry point to the exit point, where the first lane line intersects with an obstacle in the intersection or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance; a selection unit for selecting one of the two side regions of the first lane line as the target obstacle avoidance region and selecting at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance; the determination unit is further configured to determine a second lane line according to the entry point, the at least one control point, and the exit point, and the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance; a marking unit for marking the second lane line on the map.

[0026] In a possible design, the lane line to be marked can be any lane line on the straight lane, left-turn lane or right-turn lane in an intersection, such as one of the two lane side lines on both sides, or the lane center line. In this case, the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance distance, which can include any one of the following: If the first lane line is the lane side line adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance interval; if the first lane line is the lane side line not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance interval and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance interval and half of the preset lane width. Among them, the preset obstacle avoidance interval can be a real number greater than or equal to 0.

[0027] In a possible design, the target obstacle avoidance area can meet at least one of the following conditions: The target obstacle avoidance area is located within the obstacle avoidance area indicated by the obstacle with traffic rule indication function; when the first lane line does not intersect with the obstacle, the target obstacle avoidance area does not contain the obstacle; when the first lane line intersects with the obstacle, the target obstacle avoidance area contains the obstacle area with the smallest area among the two obstacle areas divided by the first lane line; or, when the first lane line intersects with the obstacle, the target obstacle avoidance area contains the obstacle area with the smallest maximum distance from the first lane line among the two obstacle areas divided by the first lane line.

[0028] In a possible design, when the first lane line intersects with the obstacle, the selection unit can find the first position point with the farthest distance from the first lane line on the edge of the obstacle area included in the target obstacle avoidance area, and determine a second position point with a distance of the preset obstacle avoidance distance from the first position point within the target obstacle avoidance area, and use the second position point as a control point. Among them, the line connecting the second position point and the first position point is perpendicular to the tangent of the first lane line, or perpendicular to the line segment between the two intersection points of the first lane line and the obstacle.

[0029] In a possible design, when the first lane line does not intersect with the obstacle, the selection unit can find the third position point with the closest distance from the first lane line on the edge of the obstacle, and determine a fourth position point with a distance of the preset obstacle avoidance distance from the third position point within the target obstacle avoidance area, and use the fourth position point as a control point. Among them, the line connecting the fourth position point and the third position point is perpendicular to the tangent of the first lane line, or perpendicular to the tangent of the obstacle at the third position point.

[0030] In a possible design, after the selection unit determines the control points according to the above design, it can also draw a control line in a direction perpendicular to the connection line from the control points, and select at least two fifth position points located on both sides of the control points from the control line, and use the at least two fifth position points as at least two control points.

[0031] In a possible design, the at least two control points may include at least one of the following: the intersection of the control line and the incoming line is used as one control point, and the intersection of the control line and the outgoing line is used as another control point, where the incoming line is a straight line drawn from the incoming point along the incoming direction, and the outgoing line is a straight line drawn from the outgoing point along the opposite direction of the outgoing direction; two points on the control line whose distances from the control point are equal to the line segment length between the two intersections of the first lane line and the obstacle are used as two control points; or, two points on the control line whose distances from the control point are equal to the length of the first lane line inside the obstacle are used as two control points.

[0032] In a possible design, the determination unit can determine the first lane line from the incoming point to the outgoing point in the following way: If the current lane is a straight lane, the determination unit can directly connect the incoming point and the outgoing point to obtain the first lane line; If the current lane is a turning lane line, the determination unit can extend the incoming line from the incoming point along the incoming direction, and extend the outgoing line from the outgoing point along the opposite direction of the outgoing direction, and determine the first lane line according to the incoming point, the intersection of the incoming line and the outgoing line, and the outgoing point.

[0033] In a fourth aspect, the present application provides a lane line marking device, including: an acquisition unit, configured to acquire the incoming point where the vehicle enters the intersection and the outgoing point where the vehicle exits the intersection; a selection unit, configured to select at least two control points in the intersection; a determination unit, configured to determine at least two first lane lines according to the incoming point, the outgoing point, and the at least two control points, and determine a target first lane line from the at least two first lane lines, where the minimum distance between the target first lane line and the obstacle in the intersection is not less than a preset obstacle avoidance distance; where any two of the at least two first lane lines use different control points; a marking unit, configured to mark the target first lane line on the map.

[0034] In a possible design, the lane line to be marked can be any lane line on the straight lane, left-turn lane or right-turn lane at an intersection, such as one of the two side lane boundaries or the lane center line. In this case, the minimum distance between the first lane line and the obstacle is not less than a preset obstacle avoidance distance, and can include any one of the following: if the first lane line is the lane boundary adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the preset obstacle avoidance interval; if the first lane line is the lane boundary not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance interval and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance interval and half of the preset lane width. Wherein, the preset obstacle avoidance interval can be a real number greater than or equal to 0.

[0035] In a possible design, the selection unit can select at least two control points in the intersection whose distances from the obstacle are greater than the preset obstacle avoidance distance.

[0036] In a possible design, when the obstacle is an obstacle with traffic rule indication function, the determination unit can select a target first lane line from the first lane lines located within the target obstacle avoidance area indicated by the obstacle. Wherein, the minimum distance between the target first lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0037] In a possible design, when the obstacle is an obstacle without traffic rule indication function, the determination unit can select a target first lane line from at least two first lane lines. Wherein, the minimum distance between the target first lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0038] In a possible design, when there is no target first lane line with a minimum distance from the obstacle not less than the preset obstacle avoidance distance among the at least two first lane lines, the selection unit can also select a reference first lane line from the at least two first lane lines, select one of the two side areas of the reference first lane line as the target obstacle avoidance area, select at least one control point within the target obstacle avoidance area whose distance from the obstacle is not less than the preset obstacle avoidance distance, the determination unit can also determine a second lane line according to the entry point, the at least one control point and the exit point, the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance, and the marking unit can also mark the second lane line on the map.

[0039] It should be understood that for the specific implementation process of re-determining the second lane line in the fourth aspect, reference can be directly made to the corresponding design in the first aspect above, and details will not be repeated here.

[0040] Fifth aspect, the present application provides a lane marking device, including a processor, a transceiver and a memory. The processor is connected to the memory, and the memory stores a computer program. When the computer program stored in the memory is executed by the processor, the lane marking device is caused to perform: obtaining an entry point where the vehicle enters the intersection and an exit point where the vehicle exits the intersection, determining a first lane line moving from the entry point to the exit point, and when the first lane line intersects an obstacle in the intersection or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance, instead of marking the first lane line on the map, selecting one of the two side regions of the first lane line as a target obstacle avoidance region, and selecting at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance, determining a second lane line whose minimum distance from the obstacle is not less than the preset obstacle avoidance distance according to the entry point, the at least one control point and the exit point, and marking the second lane line on the map.

[0041] In a possible design, the lane line to be marked can be any lane line on the straight lane, left-turn lane or right-turn lane in the intersection, such as one of the two side lane boundaries or the lane center line. In this case, the minimum distance between the first lane line and the obstacle being less than the preset obstacle avoidance distance can include any one of the following: if the first lane line is the lane boundary adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance spacing; if the first lane line is the lane boundary not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance spacing and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is less than the sum of the preset obstacle avoidance spacing and half of the preset lane width. Among them, the preset obstacle avoidance spacing can be a real number greater than or equal to 0.

[0042] In a possible design, the target obstacle avoidance region can satisfy at least one of the following conditions: the target obstacle avoidance region is located within the obstacle avoidance region indicated by the obstacle with traffic rule indication function; when the first lane line does not intersect the obstacle, the target obstacle avoidance region does not contain the obstacle; when the first lane line intersects the obstacle, the target obstacle avoidance region contains the obstacle region with the smallest area among the two obstacle regions divided by the first lane line; or, when the first lane line intersects the obstacle, the target obstacle avoidance region contains the obstacle region with the smallest maximum distance from the first lane line among the two obstacle regions divided by the first lane line.

[0043] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device is specifically configured to: when the first lane line intersects with an obstacle, find a first position point that is the farthest from the first lane line on the edge of the obstacle area included in the target obstacle avoidance area, and determine a second position point in the target obstacle avoidance area whose distance from the first position point is a preset obstacle avoidance distance, and use the second position point as a control point. Wherein, the line connecting the second position point and the first position point is perpendicular to the tangent of the first lane line, or perpendicular to the line segment between the two intersection points of the first lane line and the obstacle.

[0044] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device is specifically configured to: when the first lane line does not intersect with an obstacle, find a third position point that is the closest to the first lane line on the edge of the obstacle, and determine a fourth position point in the target obstacle avoidance area whose distance from the third position point is a preset obstacle avoidance distance, and use the fourth position point as a control point. Wherein, the line connecting the fourth position point and the third position point is perpendicular to the tangent of the first lane line, or perpendicular to the tangent of the obstacle at the third position point.

[0045] In a possible design, when the computer program stored in the memory is executed by the processor, after the lane line marking device determines the control point according to the above design, it further executes: draw a control line along the direction perpendicular to the connection line from the control point, and select at least two fifth position points located on both sides of the control point from the control line, and use the at least two fifth position points as at least two control points.

[0046] In a possible design, the at least two control points may include at least one of the following: the intersection point of the control line and the entry line is used as a control point, and the intersection point of the control line and the exit line is used as another control point, wherein the entry line is a straight line drawn from the entry point along the entry direction, and the exit line is a straight line drawn from the exit point along the opposite direction of the exit direction; two points on the control line whose distance from the control point is equal to the length of the line segment between the two intersection points of the first lane line and the obstacle are used as two control points; two points on the control line whose distance from the control point is equal to the length of the first lane line inside the obstacle are used as control points.

[0047] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device determines the first lane line from the entry point to the exit point in the following manner: if the current lane is a straight lane, connect the entry point and the exit point to obtain the first lane line; if the current lane is a turning lane line, first extend from the entry point along the entry direction to obtain the entry line, and extend from the exit point along the opposite direction of the exit direction to obtain the exit line, and then determine the first lane line according to the entry point, the intersection point of the entry line and the exit line, and the exit point.

[0048] In a sixth aspect, the present application provides a lane line marking device, including a processor, a transceiver, and a memory. The processor is connected to the memory, and the memory stores a computer program. When the computer program stored in the memory is executed by the processor, the lane line marking device is caused to perform: obtaining an entry point where the vehicle enters the intersection and an exit point where the vehicle exits the intersection, selecting at least two control points in the intersection, and determining at least two first lane lines according to the entry point, the exit point, and the at least two control points. Any two of the at least two first lane lines use different control points. Then, a target first lane line is determined from the at least two first lane lines, where the minimum distance between the target first lane line and an obstacle in the intersection is not less than a preset obstacle avoidance distance, and the target first lane line is marked on the map.

[0049] In a possible design, the lane line to be marked can be any lane line on a straight lane, a left-turn lane, or a right-turn lane in the intersection, such as one of the two side lane boundaries or the lane center line. In this case, the minimum distance between the first lane line and the obstacle being not less than the preset obstacle avoidance distance can include any one of the following: If the first lane line is a lane boundary adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the preset obstacle avoidance spacing; if the first lane line is a lane boundary not adjacent to the obstacle, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance spacing and the preset lane width; or, if the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is not less than the sum of the preset obstacle avoidance spacing and half of the preset lane width. Wherein, the preset obstacle avoidance spacing is a real number greater than or equal to 0.

[0050] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device is specifically caused to perform: selecting at least two control points in the intersection whose distance from the obstacle is greater than the preset obstacle avoidance distance.

[0051] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device is specifically caused to perform: if the obstacle is an obstacle with traffic rule indication function, selecting the target first lane line from the first lane lines located within the target obstacle avoidance area indicated by the obstacle; if the obstacle is an obstacle without traffic rule indication function, selecting the target first lane line from the at least two first lane lines. Wherein, the minimum distance between the target first lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0052] In a possible design, when the computer program stored in the memory is executed by the processor, the lane line marking device can also execute the following: If it is determined that the at least two first lane lines do not include a target first lane line with a minimum distance from an obstacle not less than a preset obstacle avoidance distance, select a reference first lane line from the at least two first lane lines, select one of the two side regions of the reference first lane line as the target obstacle avoidance region, and select at least one control point within the target obstacle avoidance region with a distance from the obstacle not less than the preset obstacle avoidance distance. Determine a second lane line with a minimum distance from the obstacle not less than the preset obstacle avoidance distance based on the entry point, the at least one control point, and the exit point, and then mark the second lane line on the map.

[0053] It should be understood that for the specific implementation process of re-determining the second lane line in the sixth aspect, the corresponding design in the first aspect above can be directly referred to, and will not be repeated here one by one.

[0054] In a seventh aspect, the present application provides a lane line marking device, including a processor and a communication interface. The communication interface is used to receive signals from other communication devices other than the lane line marking device and transmit them to the processor, or send signals from the processor to other communication devices other than the lane line marking device; the processor is used to implement the method described in any one of the designs in the first aspect above through logic circuits or by executing code instructions.

[0055] In an eighth aspect, the present application provides a lane line marking device, including a processor and a communication interface. The communication interface is used to receive signals from other communication devices other than the lane line marking device and transmit them to the processor, or send signals from the processor to other communication devices other than the lane line marking device; the processor is used to implement the method described in any one of the designs in the second aspect above through logic circuits or by executing code instructions.

[0056] In a ninth aspect, the present application provides a lane line marking device, including a processor. The processor is connected to a memory, and the memory is used to store a computer program. The processor is used to execute the computer program stored in the memory so that the lane line marking device executes the method described in any one of the designs in the first aspect above.

[0057] In a tenth aspect, the present application provides a lane line marking device, including a processor. The processor is connected to a memory, and the memory is used to store a computer program. The processor is used to execute the computer program stored in the memory so that the lane line marking device executes the method described in any one of the designs in the second aspect above.

[0058] In an eleventh aspect, the present application provides a lane line annotation device, including a processor and a memory. The memory stores computer program instructions, and the processor runs the computer program instructions to implement the method described in any one of the designs in the first aspect above.

[0059] In a twelfth aspect, the present application provides a lane line annotation device, including a processor and a memory. The memory stores computer program instructions, and the processor runs the computer program instructions to implement the method described in any one of the designs in the second aspect above.

[0060] In a thirteenth aspect, the present application provides a vehicle. After the vehicle collects environmental images, it constructs a point cloud map and annotates lane lines on the point cloud map according to the method described in any one of the designs in the first aspect or the second aspect above.

[0061] In a fourteenth aspect, the present application provides a vehicle networking system, including a vehicle and a mapping device. After the vehicle collects environmental images, it sends them to the mapping device. The mapping device uses the environmental images to construct a point cloud map and annotates lane lines on the point cloud map according to the method described in any one of the designs in the first aspect or the second aspect above.

[0062] In a fifteenth aspect, the present application provides a chip, which may include a processor and an interface. The processor is used to read instructions through the interface to execute the method described in any one of the designs in the first aspect above, or execute the method described in any one of the designs in the second aspect above.

[0063] In a sixteenth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is run, it implements the method described in any one of the designs in the first aspect above, or implements the method described in any one of the designs in the second aspect above.

[0064] In a seventeenth aspect, the present application provides a computer program product. When the computer program product runs on a processor, it implements the method described in any one of the designs in the first aspect above, or implements the method described in any one of the designs in the second aspect above.

[0065] For the beneficial effects of each design in the second aspect to the seventeenth aspect above, please specifically refer to the technical effects that can be achieved by the corresponding design in the first aspect above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 Exemplarily shows a schematic diagram of a possible system architecture applicable to an embodiment of the present application;

[0067] Figure 2 Exemplarily shows a schematic flowchart of a lane line annotation method provided in Embodiment 1 of the present application;

[0068] Figure 3 Exemplarily shows a schematic diagram of the intersection situation of an entry point and an exit point provided by an embodiment of the present application;

[0069] Figure 4 Exemplarily shows a schematic flowchart of a lane line marking method provided by the second embodiment of the present application;

[0070] Figure 5 Exemplarily shows a schematic flowchart of the drawing process of a left-turn lane line provided by an embodiment of the present application;

[0071] Figure 6 Exemplarily shows a schematic flowchart of a lane line marking method provided by the third embodiment of the present application;

[0072] Figure 7 Exemplarily shows a schematic flowchart of the drawing process of a left-turn lane line provided by an embodiment of the present application;

[0073] Figure 8 Exemplarily shows a schematic flowchart of the process of marking a turning lane line at an intersection provided by an embodiment of the present application;

[0074] Figure 9 Exemplarily shows another schematic flowchart of the process of marking a turning lane line at an intersection provided by an embodiment of the present application;

[0075] Figure 10 Exemplarily shows a schematic flowchart of the process of marking a straight-through lane line at an intersection provided by an embodiment of the present application;

[0076] Figure 11 Exemplarily shows another schematic flowchart of the process of marking a straight-through lane line at an intersection provided by an embodiment of the present application;

[0077] Figure 12 Exemplarily shows a schematic structural diagram of a lane line marking device provided by an embodiment of the present application;

[0078] Figure 13 Exemplarily shows another schematic structural diagram of a lane line marking device provided by an embodiment of the present application. Detailed implementation manners

[0079] It should be noted that the lane line annotation solution in the embodiments of the present application can be applied to the vehicle networking, such as vehicle to everything (V2X), long term evolution-vehicle (LTE-V), vehicle-vehicle (V2V), etc. For example, it can be applied to vehicles with lane line annotation functions, or other devices in the vehicle with lane line annotation functions. The other devices include but are not limited to: in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle component modules, in-vehicle components, in-vehicle chips, in-vehicle units, in-vehicle radars or in-vehicle cameras and other sensors. The vehicle can implement the lane line annotation method provided by the present application through the in-vehicle terminal, in-vehicle controller, in-vehicle module, in-vehicle component module, in-vehicle component, in-vehicle chip, in-vehicle unit, in-vehicle radar or camera. Of course, the lane line annotation solution in the embodiments of the present application can also be used in other intelligent terminals with lane line annotation functions except vehicles, or be set in other intelligent terminals with lane line annotation functions except vehicles, or be set in the components of the intelligent terminal. The intelligent terminal can be other terminal devices such as intelligent transportation devices, smart home devices, robots, etc. For example, it includes but is not limited to intelligent terminals or controllers, chips, radars or cameras and other sensors, as well as other components in the intelligent terminal.

[0080] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the embodiments described below are only a part of the embodiments of the present application, rather than all of the embodiments. And, in the following description, the mapping device can also be replaced by other devices with lane line annotation functions, or components or chips in other devices. The embodiments of the present application do not make specific limitations on this.

[0081] Figure 1 A schematic diagram of a possible system architecture applicable to the embodiments of the present application, such as Figure 1The system architecture shown includes a data collection vehicle 110 and a mapping device 120. Among them, the data collection vehicle 110 refers to a vehicle with an image collection function, and this image collection function can be implemented by sensor components such as on-vehicle cameras or on-vehicle radars installed on it. The mapping device 120 can refer to a device, component, or chip with image processing functions, such as an entity device including a host or a processor, a virtual device including a virtual machine or a container, or a chip or integrated circuit. Of course, it can also be a vehicle. For example, the data collection vehicle 110 can independently complete the entire process of image collection and map making. In the vehicle networking, the mapping device 120 is usually a vehicle networking server, also known as a cloud server, cloud, cloud end, cloud end server, or cloud controller, etc. This vehicle networking server can be a single server or a server cluster composed of multiple servers, and specific details are not limited.

[0082] It should be understood that the embodiments of the present application do not limit the number of data collection vehicles 110 and the number of mapping devices 120 in the system architecture. Usually, one mapping device 120 can be connected to multiple data collection vehicles 110 simultaneously (for example Figure 1 as shown in the figure, connected to 3 data collection vehicles 110 simultaneously), so that the mapping device 120 can efficiently create a global high-precision map using the different loop data collected in parallel by multiple data collection vehicles 110. In addition, in the system architecture applicable to the embodiments of the present application, in addition to including the data collection vehicle 110 and the mapping device 120, it can also include other devices, such as core network devices, wireless relay devices, and wireless backhaul devices, etc., and the embodiments of the present application also do not limit this. Moreover, the mapping device 120 in the embodiments of the present application can integrate all functions on an independent physical device, or can deploy different functions on multiple independent physical devices, and the embodiments of the present application also do not limit this.

[0083] In implementation, the mapping device 120 may jointly collect a high-precision map for guiding vehicle passage made by the vehicle 110. In implementation, the surveying and mapping personnel first drive or remotely control the vehicle 110 to travel along each loop line in the city. During the travel of the vehicle 110, the in-vehicle camera is called to capture the surrounding environment to obtain camera data, and the lidar is called to sense the surrounding environment to obtain lidar data. The camera data and the lidar data are reported to the mapping device 120 together. The mapping device 120 projects the camera data onto the lidar data. After using the lidar data to refine and remove the outliers in the camera data caused by meteorological information such as light, a point cloud map is constructed by using a three-dimensional modeling algorithm in combination with the processed camera data. Furthermore, the structured information of traffic entities such as lanes, traffic signs, traffic lights, and virtual lane lines is marked on the point cloud map to obtain a high-precision map. Among them, the virtual lane lines marked on the point cloud map may include one or both of the two side lines of the lane, or may include a line located between the two side lines of the lane and parallel to the two side lines, such as the center line of the lane. By marking virtual lane lines on the point cloud map, the vehicle using the high-precision map can be made to travel in the center of the lane as much as possible during passage, avoiding touching the road boundary or lane boundary, and maintaining a safe driving distance as much as possible.

[0084] In an automatic marking scheme for lane lines, the mapping device 120 first calls the drawing software to automatically mark the lane lines according to the entry point and exit point on the point cloud map, and then displays them to the adjustment personnel for inspection. When the adjustment personnel find that the automatically marked lane lines intersect with obstacles, they manually adjust the lane lines so that they do not intersect. It can be seen that although this automatic marking scheme can mark accurate lane lines, at least two steps of marking by the drawing software and manual adjustment need to be performed before marking, which is not conducive to improving the marking efficiency of lane lines. That is to say, this automatic marking scheme cannot take into account both the marking efficiency and marking quality of lane lines at the same time.

[0085] The lane line marking method in the embodiments of the present application is used to automatically mark lane lines that can directly avoid obstacles in the intersection of the point cloud map without manual participation, so as to take into account both the marking efficiency and marking quality of lane lines at the same time. The present application will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific operation methods in the method embodiments can also be applied to the device embodiments or system embodiments. It should be noted that in the description of the present application, "at least one" means one or more, and among them, "a plurality" means two or more. In view of this, "a plurality" can also be understood as "at least two" in the embodiments of the present application. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0086] It should be understood that in the description of the present application, terms such as "first" and "second" are only used for the purpose of distinguishing descriptions and should not be construed as indicating or implying relative importance. For example, the "first lane line" is the lane line to be determined, and the "second lane line" is the lane line re-determined when the distance between the first lane line and the obstacle does not meet the preset obstacle avoidance distance. These two lane lines are just two lane lines determined successively during the process of marking the lane line and should not be construed as having different priorities or importance levels.

[0087] In addition, it should be understood that in the following description, only "marking" is actually drawing on the point cloud map, while "connecting", "fitting", "drawing", "extending" or "extending in reverse" are not actual drawings but only preprocessing steps for the final "marking". And, in the following description, "fitting" means connecting a series of points on a plane with a smooth curve. Common fitting methods include, but are not limited to: least squares curve fitting method, polynomial curve fitting method, interpolation curve fitting method, Bezier curve fitting method or spline curve fitting method, etc.

[0088]

Embodiment 1

[0089] Figure 2 The flowchart of a lane line marking method provided by Embodiment 1 of the present application is exemplarily shown. This method is applicable to a mapping device, such as Figure 1 the mapping device 120 shown. As Figure 2 shown, this process includes the following steps:

[0090] Step 201, the mapping device acquires the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection.

[0091] In the embodiment of the present application, the entry point and the exit point are specifically for the intersection. For example, Figure 3 several possible situations of an entry point and an exit point provided by the embodiment of the present application are exemplarily shown: As Figure 3 shown in (A) therein, the current intersection is a crossroads. The entry point I can be the entrance point where the vehicle enters this crossroads, and the exit point can be the exit point where the vehicle exits this crossroads. For example, it can be the straight-ahead exit point O1, or the left-turn exit point O2, or the right-turn exit point O3; As Figure 3 shown in (B) therein, the current intersection is a Y-shaped intersection. The entry point can be the entrance point where the vehicle enters this Y-shaped intersection. For example, it can be the entrance point I1 on the left branch of the Y-shaped intersection, or the entrance point I2 on the right branch of the Y-shaped intersection. The exit point O can be the exit point where the vehicle exits this Y-shaped intersection; Or, as Figure 3As shown in (C), the current intersection is an L-shaped intersection. The entry point I can be the entrance point where the acquisition vehicle enters the L-shaped intersection, and the exit point O can be the exit point where the acquisition vehicle exits the L-shaped intersection. Or, as Figure 3 shown in (D), the current intersection is a T-shaped intersection. The entry point I can be the entrance point where the acquisition vehicle enters the T-shaped intersection, and the exit point can be the exit point where the acquisition vehicle exits the T-shaped intersection. For example, it can be the straight-ahead exit point O1 or the right-turn exit point O3. Or, as Figure 3 shown in (E), the current intersection is a Z-shaped intersection. The entry point I can be the entrance point where the acquisition vehicle enters the Z-shaped intersection, and the exit point O can be the exit point where the acquisition vehicle exits the Z-shaped intersection. Or, as Figure 3 shown in (F), the current intersection is a 180° sharp-turn intersection. The entry point I can be the entrance point where the acquisition vehicle enters the 180° sharp-turn intersection, and the exit point O can be the exit point where the acquisition vehicle exits the 180° sharp-turn intersection. It should be understood that there are many possible situations for the entry point and the exit point in different intersection scenarios, which are not listed one by one here.

[0092] It should be understood that although the entry point and the exit point in the embodiments of the present application are for intersections, the lane line marking scheme shown in the present application can also be applied to non-intersections, for example, it can also be applied to a certain section of the lane. The present application does not make specific limitations on this.

[0093] Step 202, the mapping device determines the first lane line moving from the entry point to the exit point.

[0094] In the above step 202, the first lane line can correspond to one of the two side lane boundaries, or can correspond to any one of the lane lines within the area formed by the two side lane boundaries, such as the lane center line. In implementation, the mapping device can determine one or more first lane lines according to the entry point and the exit point. Each of the one or more first lane lines can be determined in the following manner:

[0095] Method 1, when the exit direction coincides with the entry direction, the current lane may be a straight-through lane of the intersection as shown in (A) of 3 or as Figure 3 shown in (D). The mapping device can directly connect the entry point and the exit point by a straight line to obtain the first lane line. At this time, the first lane line is a straight lane line.

[0096] Method 2, when the exit direction is parallel to the entry direction but does not coincide, the current lane may be a right-turn sharp-turn lane as Figure 3 shown in (E), or as Figure 3For the left - turn sharp - turn lane illustrated in (F), the mapping device can directly connect the entry point and the exit point by a straight line or a curve to obtain the first lane line. At this time, the first lane line is a straight - line lane line or a curved - line lane line. Exemplarily, considering that directly connecting the entry point and the exit point by a straight line may cause the first lane line to intersect with the lane boundary, resulting in the unavailability of the first lane line, it is preferably possible to connect the entry point and the exit point by a curve located inside the lane to reduce the probability of the first lane line intersecting with the lane boundary.

[0097] Method 3: When the exit direction and the entry direction are not parallel, the current lane may be a left - turn lane or a right - turn lane as illustrated in Figure 3 (A), Figure 3 (B), or Figure 3 (C) or as illustrated in Figure 3 (D), and the vehicle turns left or right in the current lane. Taking the left - turn scenario at a cross - road illustrated in Figure 3 (A) as an example, the mapping device can first extend the virtual entry line (L1) along the entry direction from the entry point I, extend the virtual exit line (L2) along the opposite direction of the exit direction from the exit point O2, determine the intersection point (P) of the virtual entry line L1 and the virtual exit line L2, and then fit the first lane line according to the entry point I, the intersection point P, and the exit point O2. Among them, the fitting methods include but are not limited to: randomly drawing a straight line or a curve within the area formed by the entry point I, the intersection point P, and the exit point O2; drawing a second - order Bezier curve or a second - order spline curve according to the entry point I, the intersection point P, and the exit point O2; randomly selecting W control points within the area formed by the entry point I, the intersection point P, and the exit point O2, and drawing a (W + 1) - order Bezier curve or a (W + 1) - order spline curve according to the entry point I, the W control points, and the exit point O2, where W is a positive integer. Preferably, the W control points can be selected as points located outside the obstacles as much as possible to increase the probability that the first lane line does not intersect with the obstacles.

[0098] It should be noted that the above content only exemplarily introduces several ways to determine the first lane line. Any way that can determine one or more first lane lines moving from the entry point to the exit point according to the entry point and the exit point is within the protection scope of this application, and this application will not list them one by one.

[0099] Step 203: The mapping device determines whether the minimum distance between the first lane line and the obstacles in the intersection is greater than or equal to a preset obstacle - avoidance distance. If not, it executes step 204; if so, it executes step 206.

[0100] In step 203 above, the mapping device may calculate the minimum distance between each of the one or more first lane lines determined and the obstacle. When the minimum distance between at least one of the one or more first lane lines and the obstacle is greater than or equal to a preset obstacle avoidance distance, it means that there is a target first lane line among the one or more first lane lines that can safely avoid the obstacle. Therefore, the mapping device may mark the target first lane line on the map in the manner of step 206 below. When the distances between all of the one or more first lane lines and the obstacle are not greater than or equal to the preset obstacle avoidance distance, it means that none of the one or more first lane lines can safely avoid the obstacle. Therefore, the mapping device may re-determine a second lane line that can safely avoid the obstacle in the manner of steps 204 to 205 below.

[0101] In the embodiments of the present application, the minimum distance between a first lane line and an obstacle being greater than or equal to the preset obstacle avoidance distance may include any one of the following: when the first lane line is the lane boundary line (also referred to as the critical boundary line) on the side close to the obstacle, the minimum distance between the first lane line and the obstacle is greater than or equal to the preset minimum obstacle avoidance interval; when the first lane line is the lane boundary line on the side far from the obstacle, the minimum distance between the first lane line and the obstacle is greater than or equal to the sum of the preset minimum obstacle avoidance interval and the preset lane width; when the first lane line is the lane center line, the minimum distance between the first lane line and the obstacle is greater than or equal to the sum of the preset minimum obstacle avoidance interval and half of the preset lane width. Among them, the preset minimum obstacle avoidance interval is used to indicate the minimum interval distance between the vehicle and the obstacle during driving and may be set to a value greater than or equal to 0. When the preset minimum obstacle avoidance interval is 0, that is, the map requires that the driving area does not intersect with the obstacle. When the preset minimum obstacle avoidance interval is greater than 0, that is, the map not only requires that the driving area does not intersect with the obstacle, but also requires that the critical boundary line of the driving area is spaced from the obstacle by a certain safe distance.

[0102] Corresponding to the above content, the minimum distance between a first lane line and an obstacle being not greater than or equal to the preset obstacle avoidance distance may include any one of the following: in the case where the preset minimum obstacle avoidance interval is 0, the first lane line intersects with the obstacle; or in the case where the obstacle avoidance interval is greater than 0, the first lane line intersects with the obstacle, or the first lane line does not intersect with the obstacle but the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance distance.

[0103] For example, continuing to refer to Figure 3As shown in (A), assuming that the preset minimum obstacle avoidance distance is 30 cm and the preset lane width is 750 cm, in the case of avoiding the obstacle on the left side at the intersection: the right lane boundary line of the left-turn lane is the critical boundary line, and the minimum distance between the right lane boundary line and the obstacle should be greater than or equal to 30 cm. If the first determined right lane boundary line intersects with the obstacle or the distance from the obstacle is less than 30 cm, then the second right lane boundary line needs to be re-determined; the minimum distance between the left lane boundary line and the obstacle should be greater than or equal to 780 cm (i.e., 30 cm + 750 cm). If the first determined left lane boundary line intersects with the obstacle or the distance from the obstacle is less than 780 cm, then the second left lane boundary line needs to be re-determined; the minimum distance between the center lane line and the obstacle should be greater than or equal to 405 cm (i.e., 30 cm + 750 / 2 cm). If the first determined center lane line intersects with the obstacle or the distance from the obstacle is less than 405 cm, then the second center lane line needs to be re-determined. In the case of avoiding the obstacle on the right side at the intersection: the left lane boundary line of the left-turn lane is the critical boundary line, that is, the minimum distance between the left lane boundary line and the obstacle should be greater than or equal to 30 cm. If the first determined left lane boundary line intersects with the obstacle or the distance from the obstacle is less than 30 cm, then the second left lane boundary line needs to be re-determined; the minimum distance between the right lane boundary line and the obstacle should be greater than or equal to 780 cm (i.e., 30 cm + 750 cm). If the first determined right lane boundary line intersects with the obstacle or the distance from the obstacle is less than 780 cm, then the second right lane boundary line needs to be re-determined; the minimum distance between the center lane line and the obstacle should be greater than or equal to 405 cm (i.e., 30 cm + 750 / 2 cm). If the first determined center lane line intersects with the obstacle or the distance from the obstacle is less than 405 cm, then the second center lane line needs to be re-determined.

[0104] Step 204, the mapping device selects one of the two side areas of the first lane line as the target obstacle avoidance area, selects at least one control point within the target obstacle avoidance area whose distance from the obstacle is not less than the preset obstacle avoidance distance, and determines the second lane line according to the entry point, at least one control point, and the exit point. The minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0105] In the above step 204, the target obstacle avoidance area can be randomly selected from the areas on both sides of the first lane line, or it can be the side of the areas on both sides of the first lane line that is farther from the obstacle, so as to quickly determine the second lane line again on the side where the first lane line is biased. Of course, it can also be indicated by the obstacle, and the specific method is not limited. By selecting points in the intersection that are at a distance greater than the preset obstacle avoidance distance from the obstacle as control points, it helps to increase the success probability of determining the second lane line that meets the obstacle avoidance requirements at one time and reduce the number of times of re-determining the second lane line. For the specific implementation process of determining the second lane line, please refer to the following Embodiment 3, and no specific introduction will be made here for the time being.

[0106] It should be understood that selecting control points in the intersection to re-determine the second lane line is only an optional implementation method. In another optional implementation method, the mapping device can also offset the first lane line towards a certain side area of the first lane line until the minimum distance between the offset first lane line and the obstacle is not less than the preset obstacle avoidance distance, and then use the offset first lane line as the second lane line. Among them, offsetting the first lane line can refer to offsetting the entire first lane line between the entry point and the exit point, or it can refer to only offsetting the part of the first lane line that intersects with the obstacle or has a distance less than the preset obstacle avoidance distance, and the specific method is not limited.

[0107] Step 205, the mapping device marks the second lane line on the map.

[0108] Exemplarily, after the mapping device determines the second lane line, it can also determine other lane boundaries or lane centerlines outside the second lane line according to the preset lane width, and mark the second lane line, other lane boundaries and lane centerlines on the map. For example, continue to refer to Figure 3As shown in (A), assuming that the second lane line is the center line of the lane, after determining the second lane line, the mapping device can also translate the second lane line 1 / 2 times the preset lane width to the left of the second lane line (with certain adjustments) to obtain the left lane boundary line, and translate the second lane line 1 / 2 times the preset lane width to the right of the second lane line (with certain adjustments) to obtain the right lane boundary line, and mark the second lane line, the left lane boundary line and the right lane boundary line on the map. Or, in the case where the second lane line is re-fitted according to one or more control points, the mapping device can also translate one or more control points 1 / 2 times the preset lane width to the left to obtain one or more control points corresponding to the left lane boundary line, fit the left lane boundary line according to the entry point, one or more control points and the exit point corresponding to the left lane line, and translate one or more control points 1 / 2 times the preset lane width to the right to determine one or more control points corresponding to the right lane boundary line, fit the right lane boundary line according to the entry point, one or more control points and the exit point corresponding to the right lane line, and mark the first lane line, the left lane boundary line and the right lane boundary line on the map.

[0109] Step 206, the mapping device marks the first lane line on the map.

[0110] In the above step 206, when the minimum distance between at least two first lane lines and the obstacle is greater than or equal to the preset obstacle avoidance distance among the one or more first lane lines determined by the mapping device, the mapping device can randomly or according to a certain rule select one of the at least two first lane lines as the target first lane line, determine other lane boundary lines or the center line of the lane according to the target first lane line and the preset lane width, and then mark the target first lane line, other lane boundary lines and the center line of the lane on the map together. For the specific implementation process of selecting the target first lane line, please refer to Embodiment 2 below and will not be introduced here first.

[0111] In the above Embodiment 1, by re-determining the second lane line that can safely bypass the obstacle when the first lane line to be determined cannot safely bypass the obstacle, it helps to directly mark the second lane line with accurate obstacle avoidance ability on the map. This method neither relies on manual marking nor requires manual secondary adjustment, and can effectively improve the marking quality and efficiency of the lane line. Further, in the case where the first lane line does not meet the marking requirements, by selecting control points with a distance greater than or equal to the preset obstacle avoidance distance from the obstacle in the area on one side of the first lane line as the basis for determining the second lane line, it can also increase the probability of determining the second lane line that meets the obstacle avoidance distance requirement and improve the success rate of marking the lane line.

[0112] It should be noted that the above Example 1 is only introduced by taking a common obstacle as an example. In another alternative implementation, the obstacle may also be an obstacle with traffic rule indication function, and the obstacle with traffic rule indication function indicates that the vehicle should avoid the obstacle on one side of the target obstacle avoidance area. That is to say, the lane lines marked on the map also need to be located on one side of the target obstacle avoidance area. In this case, the mapping device can also complete the lane line marking scheme in the above Example 1 in combination with the type of the obstacle. The specific implementation process includes any of the following:

[0113] Solution 1: The mapping device first identifies the type of the obstacle. If it is an obstacle with traffic rule indication function, then: determine the first lane line on one side of the target obstacle avoidance area indicated by the obstacle with traffic rule indication function. When the first lane line intersects with the obstacle or the minimum distance from the obstacle is less than the preset obstacle avoidance distance, re-determine the second lane line on one side of the target obstacle avoidance area with the minimum distance from the obstacle greater than or equal to the preset obstacle avoidance distance, and mark the second lane line on the map; when the minimum distance between the first lane line and the obstacle is greater than or equal to the preset obstacle avoidance distance, directly mark the first lane line on the map. If it is a common obstacle, then: randomly determine the first lane line, and judge whether the first lane line intersects with the obstacle or the minimum distance from the obstacle is less than the preset obstacle avoidance distance. If either is yes, re-determine the second lane line on one side of the two side areas of the first lane line with the minimum distance from the obstacle greater than or equal to the preset obstacle avoidance distance, and mark the second lane line on the map. If both are no, directly mark the first lane line on the map.

[0114] Solution 2: The mapping device first randomly fits the first lane line, and then identifies the type of the obstacle. If it is an obstacle with traffic rule indication function, then: judge whether the first lane line is located on one side of the target obstacle avoidance area and the minimum distance from the obstacle is greater than or equal to the preset obstacle avoidance distance. If so, mark the first lane line on the map. If not, re-determine the second lane line on one side of the target obstacle avoidance area with the minimum distance from the obstacle greater than or equal to the preset obstacle avoidance distance, and mark the second lane line on the map. If it is a common obstacle, then: judge whether the minimum distance between the first lane line and the obstacle is greater than or equal to the preset obstacle avoidance distance. If not, re-determine the second lane line on one side of the two side areas of the first lane line with the minimum distance from the obstacle greater than or equal to the preset obstacle avoidance distance, and mark the second lane line on the map. If so, mark the first lane line on the map.

[0115] Next, taking the above Solution 2 as an example, based on Example 2 and Example 3, the specific implementation process of the lane line marking method is further introduced.

[0116]

Example 2

[0117] Figure 4 The flowchart of a lane line annotation method provided by the second embodiment of the present application is exemplarily shown. This method is applicable to a mapping device, such as Figure 1 the mapping device 120 shown. As Figure 4 shown, the process includes the following steps:

[0118] Step 401, the mapping device obtains the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection.

[0119] Step 402, the mapping device selects at least two control points in the intersection. According to the entry point, the exit point, and the at least two control points, Q first lane lines for moving from the entry point to the exit point are determined, where Q is an integer greater than or equal to 2, and any two of the Q first lane lines use different control points.

[0120] Exemplarily, the mapping device can randomly select Q control points from the intersection, and draw second-order Bezier curves or second-order spline curves according to the entry point, each of the Q control points, and the exit point to obtain Q first lane lines. Among them, more control points can be selected as much as possible, for example, 5 or more are selected at a time, and points with a distance greater than or equal to a preset obstacle avoidance distance from the edge of the obstacle can also be selected as much as possible, so as to fit the first lane lines that meet the requirements of the preset obstacle avoidance distance as much as possible and improve the annotation efficiency of the lane lines. In addition, considering that the finally annotated lane lines also need to match the type of the obstacle, Q first lane lines can also be evenly distributed in the two side areas of the obstacle as much as possible, so as to increase the probability of selecting a target first lane line that meets the target obstacle avoidance area indicated by any type of obstacle from the Q first lane lines, reduce the probability of re-determining the second lane line, and further improve the annotation efficiency of the lane lines.

[0121] For example, Figure 5 The flowchart of a mapping process for a left-turn lane line provided by the embodiment of the present application is exemplarily shown. As shown in reference to Figure 5 shown, the left-turn lane line in this example corresponds to the right lane boundary line of the left-turn lane. In implementation, the mapping device can first draw a virtual entry line L1 along the entry direction from the entry point I, draw a virtual exit line L2 along the opposite direction of the exit direction from the exit point O, and use the intersection point P of the virtual entry line L1 and the virtual exit line L2 as a control point, and draw the first lane line K according to the entry point I, the control point P, and the exit point O 11 . Then, the mapping device can randomly select control points on both sides of the first lane line K 11 to draw other first lane lines. For example, three control points are randomly selected from the left side of the first lane line K 11 , and the first lane line K is respectively drawn according to the entry point I, these three control points, and the exit point O 12, the first lane line K 13 and the first lane line K 14 , randomly select two control points from the right side of the first lane line K 11 , and respectively draw the first lane line K 15 and the first lane line K 16 according to the entry point I, these two control points and the exit point O. So far, the mapping device has drawn a total of 6 first lane lines K 11 ~K 16 .

[0122] Step 403, the mapping device determines the type of obstacles in the intersection:

[0123] If the obstacle in the intersection is an obstacle with traffic rule indication function, then execute step 404;

[0124] If the obstacle in the intersection is an obstacle without traffic rule indication function, then execute step 405.

[0125] Step 404, the mapping device determines whether there is a target first lane line among the Q first lane lines that is located within the target obstacle avoidance area indicated by the obstacle with traffic rule indication function and the distance from the obstacle is not less than the preset obstacle avoidance distance. If so, then execute step 406; if not, then execute step 407.

[0126] In the above steps 403 and 404, the obstacles with traffic rule indication function can include, for example, traffic circles, sentry boxes, roundabouts or rotaries, etc. For example, a traffic circle usually indicates that a vehicle waiting to turn left turns left on the left side of the traffic circle, and indicates that a vehicle waiting to turn right turns right on the right side of the traffic circle: if the first lane line corresponds to a left-turn lane line, the mapping device can select the first lane line located on the left side of the obstacle and the minimum distance from the obstacle is greater than or equal to the preset obstacle avoidance distance from the Q first lane lines as the target first lane line; if the first lane line corresponds to a right-turn lane line, the mapping device can select the first lane line located on the right side of the obstacle and the minimum distance from the obstacle is greater than or equal to the preset obstacle avoidance distance from the Q first lane lines as the target first lane line. Another example is that a rotary indicates that a vehicle drives around the rotary in a counterclockwise direction and exits at the exit. Therefore, regardless of whether the first lane line is a left-turn lane line, a right-turn lane line or a straight-through lane line, the mapping device needs to select the first lane line located on the right side of the obstacle and the minimum distance from the obstacle is greater than or equal to the preset obstacle avoidance distance from the Q first lane lines as the target first lane line.

[0127] Exemplarily, continue to refer to Figure 5 shown, among the 6 first lane lines, the first lane line K 11 , the first lane line K 12 and the first lane line K 15All intersect with the obstacle. The minimum distances between these three first lane lines and the obstacle must be less than the preset obstacle avoidance distance. Therefore, the mapping device can first exclude these three lane lines. Among the remaining three first lane lines, the first lane line K 13 and the first lane line K 14 are on the left side of the obstacle, and the first lane line K 16 is on the right side of the obstacle. Assume that the minimum distance between the first lane line K 13 and the obstacle is less than the preset obstacle avoidance distance, while the minimum distances between the first lane line K 14 and the first lane line K 16 and the obstacle are greater than the preset obstacle avoidance distance. Then: When the obstacle is a traffic circle, since the first lane line is a left-turn lane line, the mapping device can select from the first lane line K 13 and the first lane line K 14 on the left side of the obstacle the first lane line K 14 whose minimum distance from the obstacle is greater than the preset obstacle avoidance distance as the target first lane line; when the obstacle is a roundabout, the mapping device can use the first lane line K 16 on the right side of the obstacle and whose minimum distance from the obstacle is greater than the preset obstacle avoidance distance as the target first lane line.

[0128] Step 405, the mapping device determines whether there is a target first lane line among the Q first lane lines whose distance from the obstacle is not less than the preset obstacle avoidance distance. If so, it executes Step 406; if not, it executes Step 407.

[0129] In the above Steps 403 and 405, obstacles without traffic rule indication functions can include, for example, ordinary obstacles that impede vehicle travel, center circles that prohibit vehicle travel, road markings, or highway fences. Vehicles only need to bypass these obstacles during driving and do not need to consider the bypass direction. In this case, continuing to refer to Figure 5 shown, the mapping device can first exclude the first lane lines K 11 , K 12 and K 15 that intersect with the obstacle, and then calculate the minimum distances between the remaining three first lane lines K 13 , K 14 and K 16 and the obstacle respectively, and compare the three calculated minimum distances with the preset obstacle avoidance distance. It is found that the minimum distances between the first lane line K 14 and the obstacle and between the first lane line K 16 and the obstacle are both greater than the preset obstacle avoidance distance, while the minimum distance between the first lane line K 13 and the obstacle is less than the preset obstacle avoidance distance. Therefore, the mapping device can select from the first lane line K 14and the first lane line K 16 Select a target first lane line from them.

[0130] Step 406, the mapping device marks the target first lane line on the map.

[0131] In the above step 406, continue to refer to Figure 5 As shown, assume that the determined target lane line is the first lane line K 14 , then the target lane line actually corresponds to the right lane boundary line of the left-turn lane. In order to mark the most detailed and comprehensive lane lines on the map, the mapping device can also translate the first lane line K 14 to the left by a preset lane width to obtain the left lane boundary line of the left-turn lane ( Figure 5 not shown in the figure), and then mark both the left lane boundary line and the first lane line K 14 on the map. Alternatively, the mapping device can also determine the center lane line of the left-turn lane according to the left lane boundary line and the first lane line K 14 , and mark the left lane boundary line, the first lane line K 14 and the center lane line on the map.

[0132] In an optional implementation manner, if there are at least two first lane lines in the target obstacle avoidance area in step 404 above whose minimum distance is greater than or equal to the preset obstacle avoidance distance, or if there are at least two first lane lines in the Q first lane lines in step 405 above whose minimum distance is greater than or equal to the preset obstacle avoidance distance, the mapping device can select a suitable first lane line from the at least two first lane lines as the target first lane line. Among them, the selection methods include but are not limited to: selecting the first lane line with the shortest distance, so that the vehicle can bypass the obstacle as soon as possible; selecting the first lane line farthest from the obstacle to further reduce the risk of the vehicle colliding with the obstacle during the process of bypassing the obstacle; selecting the first lane line closest to the obstacle to reduce the probability of the vehicle colliding with the vehicle on the same side or the opposite side during the process of bypassing the obstacle; randomly selecting a first lane line; selecting the first lane line in the middle, etc. It should be understood that this application does not limit only the above several selection methods. In actual operation, the mapping device can also decide which selection method to use according to the specific traffic conditions. For example, when marking the left-turn lane line at the intersection of two-way lanes on the map, the mapping device can also try to select the first lane line on the right side of the obstacle as the second lane line to reduce the probability of the vehicle colliding with the oncoming straight vehicle during the left-turn process and improve the safety of the left-turn.

[0133] Step 407, the mapping device re-determines the second lane line and marks the second lane line on the map, where the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance.

[0134] In implementation, if there is no first lane line in the target obstacle avoidance area in step 404 above, or all the first lane lines in the target obstacle avoidance area in step 404 above intersect with the obstacle or the minimum distance from the obstacle is less than the preset obstacle avoidance distance, or the Q first lane lines in step 405 above intersect with the obstacle or the minimum distance from the obstacle is less than the preset obstacle avoidance distance, the mapping device may use any one of the Q first lane lines as the reference first lane line and re-determine the second lane line depending on the reference first lane line. Among them, the reference first lane line may preferably select a first lane line with less severe conditions to improve the effective reference of the reference first lane line. For the specific implementation process of re-determining the second lane line, please refer to Embodiment 3 below and will not be introduced here first.

[0135] In the above Embodiment 2, by pre-fitting multiple first lane lines, the probability that the mapping device directly selects a target first lane line that meets the requirements from the multiple first lane lines can be increased, and the second lane line does not need to be re-determined. This method not only helps to improve the efficiency of lane line annotation, but also can annotate the target first lane line with obstacle avoidance function on the map, effectively improving the quality and accuracy of lane line annotation. Moreover, by using different annotation methods for different types of obstacles, the target first lane lines annotated on the map can also meet the obstacle avoidance requirements of the corresponding obstacles, effectively improving the accuracy of map annotation.

[0136]

Embodiment 3

[0137] Figure 6 Exemplarily shows a schematic flowchart of a lane line annotation method provided by Embodiment 3 of the present application. This method is applicable to a mapping device, such as Figure 1 the mapping device 120 shown. As Figure 6 shown, this process includes the following steps:

[0138] Step 601, the mapping device obtains the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection.

[0139] Step 602, the mapping device determines the first lane line moving from the entry point to the exit point.

[0140] In the above step 602, the mapping device may only fit one first lane line. Figure 7 Exemplarily shows a schematic flowchart of the mapping process of a left-turn lane line provided by an embodiment of the present application. As Figure 7 in (A) and Figure 7As shown in (B), the first lane line in this example corresponds to the right lane boundary line of the left-turn lane. In implementation, the mapping device can first draw a virtual entry line L1 along the entry direction from the entry point I, draw a virtual exit line L2 along the opposite direction of the exit direction from the exit point O, and draw a second-order Bezier curve or a second-order spline curve based on the entry point I, the intersection point P of the virtual entry line L1 and the virtual exit line L2, and the exit point O to obtain the first lane line K1. It should be noted that when the position of the obstacle is different, the positional relationship between the first lane line K1 and the obstacle may also be different. For example: Figure 7 The obstacle J1 shown in (A) is more to the left than Figure 7 the obstacle J2 shown in (B), which causes the same first lane line K1 to intersect with Figure 7 the obstacle J1 shown in (A), while not intersecting with Figure 7 the obstacle J2 shown in (B).

[0141] Step 603, the mapping device determines the type of the obstacle in the intersection:

[0142] If the obstacle in the intersection is an obstacle without traffic rule indication function, step 604 is executed;

[0143] If the obstacle in the intersection is an obstacle with traffic rule indication function, step 606 is executed.

[0144] Step 604, the mapping device determines whether the minimum distance between the first lane line and the obstacle is less than the preset obstacle avoidance distance. If so, step 605 is executed; if not, step 609 is executed.

[0145] In the above step 604, when the preset obstacle avoidance distance is 0, the minimum distance between the first lane line and the obstacle being less than the preset obstacle avoidance distance means that the first lane line intersects with the obstacle, as shown in Figure 7 (A). When the preset obstacle avoidance distance is greater than 0 (for example, 30 cm), the minimum distance between the first lane line and the obstacle being less than the preset obstacle avoidance distance means that the first lane line intersects with the obstacle, as shown in Figure 7 (A); or, the first lane line does not intersect with the obstacle but the minimum distance is less than 30 cm, as shown in Figure 7 (B).

[0146] Step 605, the mapping device selects one side area in the two-side areas of the first lane line as the target obstacle avoidance area, and then step 607 is executed.

[0147] In the above step 605, the mapping device can select the target obstacle avoidance area in any of the following ways:

[0148] Method 1: In the case where the first lane line intersects with an obstacle, the first lane line divides the obstacle into two obstacle regions. The mapping device can select the region where the obstacle region with the minimum maximum distance from the first lane line is located from the two regions on both sides of the first lane line as the target obstacle avoidance region. The implementation process is as follows: Continuing to refer to Figure 7 As shown in (A) of Figure 7 , assume that the left region of the first lane line K1 is D1, the right region is D2, the two intersection points of the first lane line K1 and the obstacle J1 are points E1 and E2, and the first lane line K1 divides the obstacle J1 into the obstacle region S and the obstacle region R. Then the mapping device can first find the point M on the edge of the obstacle region S that is farthest from the line segment E1E2 (in this article, the line segment E1E2 can refer to that part of the first lane line located between points E1 and E2, or it can refer to the straight line segment connecting points E1 and E2, and the specific is not limited). S Assume that the point M S The foot of the perpendicular from the point M to the line segment E1E2 is the point F. Then, the maximum distance between the obstacle region S and the first lane line K1 is the length of the line segment M S F. Correspondingly, the mapping device can find the point M on the edge of the obstacle region R that is farthest from the line segment E1E2 R Assume that the point M R The foot of the perpendicular from the point M to the line segment E1E2 is the point G. Then, the maximum distance between the obstacle region R and the first lane line K1 is the length of the line segment M R G. Since the length of the line segment M S F is less than the length of the line segment M R G, therefore, the obstacle region S is the obstacle region with the minimum maximum distance from the first lane line K1 among the two obstacle regions. The mapping device selects the region D1 on the side where the target obstacle region S is located from the two regions D1 and D2 on both sides of the first lane line K1 as the target obstacle avoidance region.

[0149] In the above Method 1, by using the region on the side where the obstacle region with the minimum maximum distance from the first lane line is located as the target obstacle avoidance region, it is possible to obtain the second lane line through a relatively small deformation depending on the positional relationship between the first lane line and the obstacle, which helps to reduce the difficulty of re-fitting the second lane line. Moreover, since the second lane line is drawn in the region where the maximum distance from the edge of the obstacle is the closest, it is also possible for the second lane line to have a shorter length, which helps to indicate that the vehicle can bypass the obstacle as soon as possible through a shorter driving distance and improve the obstacle avoidance efficiency of the vehicle.

[0150] Method 2: In the case where the first lane line does not intersect with the obstacle but the minimum distance is less than the preset obstacle avoidance distance, the mapping device can use the regions on both sides of the first lane line that do not contain the obstacle as the target obstacle avoidance regions. For example Figure 7 The region D1 shown in (B) of Figure 7 .

[0151] It should be noted that the above content only exemplarily introduces two optional implementation manners. In other optional implementation manners, the mapping device may also randomly select one side area of the two side areas of the first lane line as the target obstacle avoidance area, or may also use the side area with the smallest area of the obstacle areas included in the two side areas of the first lane line as the target obstacle avoidance area, or may also adopt different strategies according to specific traffic scenarios. For example, considering that when a straight-going vehicle avoids an obstacle on the left side, it is very likely to collide with an oncoming straight-going vehicle, so the mapping device may also use the right side area of the second lane line as the target obstacle avoidance area, so as to mark the second lane line that bypasses the obstacle on the right side in the map, reducing the probability of collision between the straight-going vehicle and the oncoming straight-going vehicle.

[0152] Step 606, the mapping device determines whether the first lane line is within the target obstacle avoidance area indicated by the obstacle with traffic rule indication function and the minimum distance from the obstacle is not less than the preset obstacle avoidance distance. If not, step 607 is executed; if so, step 609 is executed.

[0153] Exemplarily, continuing to refer to Figure 7 as shown in (A) in, assuming that the obstacle J1 is a traffic circle, then: currently it corresponds to a left-turn lane, and the traffic circle indicates that the vehicle to be turned left turns left on the left side of the traffic circle, that is, the target obstacle avoidance area indicated by the traffic circle is the left side area of the obstacle J1. The first lane line K1 does not lie in the left side area of the obstacle J1 but intersects with the obstacle J1. Therefore, the first lane line K1 is not within the target obstacle avoidance area; and, since the first lane line K1 intersects with the obstacle J1, the minimum distance between the first lane line K1 and the obstacle J1 is less than the preset obstacle avoidance distance, and the mapping device needs to re-determine the second lane line. Continuing to refer to Figure 7 as shown in (B) in, assuming that the obstacle J2 is a roundabout, then: currently it corresponds to a left-turn lane, and the roundabout indicates that all vehicles move counterclockwise along the roundabout to the exit position. Therefore, the target obstacle avoidance area indicated by the roundabout is the right side area of the obstacle J2, while the first lane line K1 lies in the left side area of the obstacle J2. Therefore, the first lane line K1 is not within the target obstacle avoidance area. Therefore, even if the first lane line K1 does not intersect with the obstacle J2, the mapping device has to re-determine the second lane line.

[0154] Step 607, the mapping device selects at least one control point within the target obstacle avoidance area whose minimum distance from the obstacle is not less than the preset obstacle avoidance distance, and fits the second lane line according to the entry point, the at least one control point, and the exit point.

[0155] In step 607 above, at least one control point may be as follows: including one control point, the mapping device draws a second-order Bezier curve or a second-order spline curve based on the entry point, this one control point, and the exit point to obtain the second lane line; or, including at least two control points, the mapping device draws a high-order Bezier curve or a high-order spline curve based on the entry point, at least two control points, and the exit point to obtain the second lane line.

[0156] In an alternative implementation, continuing to refer to Figure 7 as shown in (A) of [reference], when the left area D1 of the first lane line K1 is the target obstacle avoidance area, the mapping device may first find the point M that is the farthest from the first lane line K1 on the obstacle area S within the target obstacle avoidance area D1 S (i.e., the first position point), and find the foot of the perpendicular F from point M S to the first lane line K1. Starting from point M S , extend the line segment MF in the reverse direction to point N (i.e., the second position point), and make the length of the line segment MN S exactly equal to the preset obstacle avoidance distance. Through the above steps, the mapping device uses the point M on the obstacle area S that is the farthest from the first lane line K1 S as a reference to find the point N whose distance from the obstacle J1 is exactly equal to the preset obstacle avoidance distance. After that, the mapping device may fit to obtain the second lane line based on the entry point I, point N, and the exit point O in any of the following ways: S

[0157]

[0158] Figure 7

[0159] Method 1: The mapping device may directly use point N as a control point and draw a second-order Bezier curve or a second-order spline curve based on the entry point I, control point N, and the exit point O to obtain the second lane line. Method 2: Continuing to refer to Figure 7 as shown in (A) of [reference], the mapping device may draw a straight line L3 (i.e., the control line) perpendicular to the line segment FN in both directions starting from point N. The intersection of this straight line L3 and the virtual entry line L1 is C1 (a fifth position point), and the intersection with the virtual exit line L2 is C2 (another fifth position point). The mapping device may use point C1, point N, and point C2 as three control points and fit to obtain the second lane line based on the entry point I, control point C1, control point N, control point C2, and the exit point O. For example, it may directly draw a fourth-order Bezier curve or a fourth-order spline curve based on the entry point I, control point C1, control point N, control point C2, and the exit point O to obtain the second lane line, or draw a second-order Bezier curve or a second-order spline curve based on the entry point I, control point C1, and control point N as the first segment of the second lane line, and draw a second-order Bezier curve or a second-order spline curve based on control point N, control point C2, and the exit point O as the second segment of the second lane line.Method 3: After drawing the straight line L3 perpendicular to the line segment NF according to the method in Method 2, the mapping device can also select two points V1 and V2 (two fifth position points) located on both sides of point N from the straight line L3, use point V1, point N, and point V2 as three control points, and draw a fourth-order Bezier curve or a fourth-order spline curve based on the entry point I, control point V1, control point N, control point V2, and the exit point O to obtain the second lane line, or draw a second-order Bezier curve or a second-order spline curve based on the entry point I, control point V1, and control point N as the first segment of the second lane line, and draw a second-order Bezier curve or a second-order spline curve based on control point N, control point V2, and the exit point O as the second segment of the second lane line. Among them, control points V1 and V2 can be evenly selected from both sides of point N, that is, ensure that the length of line segment V1N is equal to the length of line segment V2N, so that the mapping device can draw a relatively smooth second lane line based on three relatively evenly distributed control points. Exemplarily, the method of uniform selection may include but is not limited to: selecting a point on the straight line segment L3 on the left side of control point N whose distance from control point N is exactly equal to the length of line segment E1E2 as control point V1, and selecting a point on the straight line segment L3 on the right side of control point N whose distance from control point N is exactly equal to the length of line segment E1E2 as control point V2; selecting the midpoint of line segment NC1 as control point V1, and selecting the midpoint of line segment NC2 as control point V2. Of course, other selection methods can also be used, which will not be listed one by one here.

[0160] Method 4: After selecting control points V1 and V2 located on both sides of point N according to the method in Method 3, if the smoothness of the second lane line is not considered, a second-order Bezier curve or a second-order spline curve can also be drawn based on the entry point I, control point C1, and control point V1 as the first segment of the second lane line, use the line segment of control points V1, control point N, and control point V2 as the second segment of the second lane line, and draw a second-order Bezier curve or a second-order spline curve based on control point V2, control point C2, and the exit point O as the third segment of the second lane line. This method can obtain a second lane line that combines curve segments and straight line segments.

[0161] In another alternative implementation, continue to refer to Figure 7 as shown in (B) in U (i.e., the third position point), and find the foot of the perpendicular X from point M U to the first lane line K1. Starting from point M U extend the line segment M U X in the reverse direction to point N (i.e., the fourth position point), and make the line segment M UThe length of N is exactly equal to the preset obstacle avoidance distance. Through the above steps, the mapping device uses the point M on the obstacle J2 that is closest to the first lane line K1 U as a reference to find the point N whose distance from the obstacle J2 is exactly equal to the preset obstacle avoidance distance. After that, the mapping device can fit the second lane line based on the entry point I, the point N, and the exit point O in any of the above ways.

[0162] It should be noted that the above is only an exemplary introduction of several possible fitting methods, and the present application does not limit that only these several fitting methods can be used. For example, in another possible fitting method, continue to refer to Figure 7 as shown in (A) therein, the mapping device can also select a point (such as S T in S ) on the extension line of the line segment FM whose distance from the point M Figure 7 is greater than the preset obstacle avoidance distance as the control point N in the above four cases, and draw the second lane line according to one of the above four cases. Or, in yet another possible fitting method, the mapping device can also directly randomly select one or more control points within the area formed by the entry point I, the control point M S and the exit point O whose distance from the obstacle is greater than or equal to the preset obstacle avoidance distance to draw the second lane line. There are many possible fitting methods, which will not be listed one by one here.

[0163] Step 608, the mapping device marks the second lane line on the map.

[0164] Exemplarily, continue to refer to Figure 7 as shown in (A) therein. The currently determined second lane line corresponds to the right lane boundary line of the left-turn lane. The mapping device can also determine at least one control point corresponding to the left lane boundary line according to the preset lane width and at least one control point corresponding to the second lane line, and draw the left lane boundary line using the entry point corresponding to the left lane boundary line, at least one control point, and the exit point. Among them, the preset lane width can refer to the lane width of the entry lane or the exit lane, or it can be a gradually variable quantity that gradually transitions from the lane width of the entry lane to the lane width of the exit lane, so that the marked lane line can be applicable to the lane after the vehicle exits.

[0165] Step 609, the mapping device marks the first lane line on the map.

[0166] In the above-mentioned third embodiment, when the first lane line does not meet the marking requirements, by selecting a control point in the area on one side of the first lane line whose distance from the obstacle is greater than or equal to the preset obstacle avoidance distance as the basis for fitting the second lane line, the probability of fitting the second lane line that meets the obstacle avoidance distance requirements can be increased, and the success rate of marking the lane line can be increased. Moreover, by selecting different target obstacle avoidance areas for different types of obstacles, the second lane line can be placed in the area corresponding to the obstacle as much as possible, effectively improving the accuracy of marking the lane line.

[0167] The following is an illustrative introduction to some applications of the lane marking method based on different intersection conditions. It is assumed that all obstacles at the intersection are ordinary obstacles.

[0168] Intersection situation 1

[0169] Figure 8 A schematic diagram of a process for marking a turning lane line at an intersection provided by an embodiment of the present application is exemplarily shown, such as Figure 8 As shown in the figure, the blank area in this example represents the intersection, the strip area represents the crosswalk, and there is a rectangular obstacle at the bottom right of the intersection:

[0170] In one case, this example can be regarded as marking the left turn lane line, that is, the vehicle enters the intersection from the left side of the diagram and exits the intersection from the top of the diagram. In implementation, the mapping device can first mark the left turn lane line according to the entry point B of the left lane in the diagram. 11 and exit point B at the top of the exit lane in the diagram 21 Draw out Figure 8 The right lane edge line L of the left turn lane shown in (A) 11 , and follow the left lane entry point B as shown in the figure 12 and exit point B at the top of the exit lane in the diagram 22 Draw out Figure 8 The left lane edge line L of the left turn lane shown in (A) 12 , by comparison, it is found that the right lane edge line L 11 Intersecting with the obstacle and the left lane edge L 12 Does not intersect with obstacles, right lane edge L 11 is the critical edge in this case, so the mapping device can convert the right lane edge L 11 As the first lane line. Further, according to the obstacle being the first lane line L 11 The area of ​​the two obstacle areas is known to be located at the first lane line L 11 The area of ​​the obstacle region on the left is smaller than the area of ​​the obstacle region on the right side of the first lane line, so the mapping device determines that the first lane line L 11 The left area is the target obstacle avoidance area, starting from the first lane line L11 Select at least one control point in the left area whose minimum distance to the obstacle is not less than the preset obstacle avoidance distance (such as 30 cm) ( Figure 8 (not shown in the figure), follow the entry point B for the left lane as shown in the figure 11 , the at least one control point and the exit point B of the exit lane shown above 21 Draw out Figure 8 The second lane line L shown in (B) 21 , the second lane line L 21 The right lane line L corresponds to the left turn lane. 21 At least one control point corresponding to the left lane edge of the left turn lane is determined by using the entry point B of the left lane in the figure. 12 , at least one control point corresponding to the left lane edge and the exit point B of the exit lane above the diagram 22 , draw as Figure 8 The left lane edge L shown in (B) 22 The right lane edge line L in this example 21 and the left lane edge L 22 Can instruct left-turning vehicles to avoid obstacles on the left side of the obstacles.

[0171] In another case, this example can also be regarded as marking the right turn lane line, that is, the vehicle enters the intersection from the top of the diagram and exits the intersection from the left side of the diagram. In implementation, the mapping device can first mark the right turn lane line according to the entry point B of the lane at the top of the diagram. 21 and exit point B for the left exit lane in the diagram 11 Draw out Figure 8 The left lane edge line L of the right turn lane shown in (A) 11 , and enter the lane according to the entry point B on the diagram above 22 and exit point B for the left exit lane in the diagram 12 Draw out Figure 8 The right lane edge line L of the right turn lane shown in (A) 12 , by comparison, it is found that the left lane edge L 11 Intersecting with the obstacle and the right lane edge L 12 It does not intersect with the obstacle, so the left lane edge L 11 As the first lane line. According to the obstacle, the first lane line L 11 The area of ​​the two obstacle areas is known to be located at the first lane line L 11 The area of ​​the obstacle area on the right is larger than that on the first lane line L 11 The obstacle area on the left is small, so the mapping device determines the first lane line L11 The right - hand area is the target obstacle - avoidance area. Select at least one control point from the right - hand area of the first lane line L 11 such that the minimum distance from the obstacle is not less than a preset obstacle - avoidance distance. According to the entry point B of the incoming lane above the figure 21 and the at least one control point, and the exit point B of the outgoing lane on the left - hand side of the figure 11 draw the second lane line L Figure 8 as shown in (B) of 21 . This second lane line L 21 corresponds to the left - hand lane boundary of the right - turn lane. Then, using the at least one control point corresponding to this left - hand lane boundary L 21 , and the width of the incoming lane or the width of the outgoing lane, determine at least one control point corresponding to the right - hand lane boundary of the right - turn lane. According to the entry point B of the incoming lane above the figure 22 , the at least one control point corresponding to the right - hand lane boundary, and the exit point B of the outgoing lane on the left - hand side of the figure 12 draw the right - hand lane boundary L Figure 8 as shown in (B) of 22 . In this example, the left - hand lane boundary L 21 and the right - hand lane boundary L 22 can indicate that a right - turning vehicle avoids the obstacle on the right side of the obstacle.

[0172] Intersection situation two

[0173] Figure 9 Exemplarily shows another flow diagram for marking a turning lane line at an intersection provided by an embodiment of the present application. As shown in Figure 9 , the blank area in this example represents the intersection, the strip - shaped area represents the crosswalk, and there is a rectangular obstacle at the upper - middle position of the intersection:

[0174] In one case, this example can be regarded as marking a left - turn lane line, that is, the vehicle enters the intersection from the left - hand side of the figure and exits the intersection from above the figure. In implementation, the mapping device can first draw the right - hand lane boundary L 11 of the left - turn lane as shown in (A) of 21 according to the entry point B of the incoming lane on the left - hand side of the figure and the exit point B of the outgoing lane above the figure, and draw the left - hand lane boundary L Figure 9 of the left - turn lane as shown in (A) of 11 according to the entry point B of the incoming lane on the left - hand side of the figure and the exit point B of the outgoing lane above the figure. By comparison, it is found that the left - hand lane boundary L 12 intersects with the obstacle while the right - hand lane boundary L 22 is as shown in (A) of Figure 9 and draw the left - hand lane boundary L 12 of the left - turn lane. By comparison, it is found that the left - hand lane boundary L 12 intersects with the obstacle while the right - hand lane boundary L11 Does not intersect with the obstacle, and the left lane boundary line L 12 is the critical boundary line in this case. Therefore, the mapping device can use the left lane boundary line L 12 as the first lane line. Further, according to the areas of the two obstacle regions divided by the first lane line L 12 , it can be known that the area of the obstacle region on the right side of the first lane line L 12 is smaller than the area of the obstacle region on the left side of the first lane line L 12 . Therefore, the mapping device determines that the right side region of the first lane line L 12 is the target obstacle avoidance region. According to the entry point B 12 of the left incoming lane shown in the figure, a control point selected from the right side region of the first lane line L 12 , and the exit point B 22 of the upper exit lane shown in the figure, draw the second lane line L Figure 9 as shown in (B) of 22 . This second lane line L 22 corresponds to the left lane boundary line of the left-turn lane. Then, using the control point corresponding to this left lane boundary line L 22 and the preset lane width, determine the control point corresponding to the right lane boundary line of the left-turn lane. According to the entry point B 11 of the left incoming lane shown in the figure, the control point corresponding to the right lane boundary line, and the exit point B 21 of the upper exit lane shown in the figure, draw the right lane boundary line L Figure 9 as shown in (B) of 21 . The right lane boundary line L 21 and the left lane boundary line L 22 in this example can indicate that the left-turning vehicle avoids the obstacle on the right side of the obstacle.

[0175] In another case, this example can also be regarded as marking the right-turn lane line, that is, the vehicle enters the intersection from the upper part shown in the figure and exits the intersection from the left side shown in the figure. In implementation, the mapping device can first draw the left lane boundary line L 21 of the right-turn lane as shown in (A) of 11 according to the entry point B Figure 9 of the upper incoming lane shown in the figure and the exit point B 11 of the left exit lane shown in the figure, and draw the right lane boundary line L 22 of the right-turn lane as shown in (A) of 12 according to the entry point B Figure 9 of the upper incoming lane shown in the figure and the exit point B 12 of the left exit lane shown in the figure. By comparison, it is found that the right lane boundary line L 12 intersects with the obstacle while the left lane boundary line L 11Does not intersect with the obstacle, so the right lane boundary line L 12 can be used as the first lane line. According to the areas of the two obstacle regions into which the obstacle is divided by the first lane line L 12 , it can be known that the area of the obstacle region located on the left side of the first lane line L 12左侧 is smaller than the area of the obstacle region located on the right side of the first lane line L 12 . Therefore, the mapping device determines the left region of the first lane line L 12 as the target obstacle avoidance region. According to the entry point B 22 of the incoming lane above the figure, the control point selected from the left region of the first lane line L 12 and the exit point B 12 of the exit lane on the left side of the figure, draw the second lane line L Figure 9 as shown in (B) of 22 . This second lane line L 22 corresponds to the right lane boundary line of the right-turn lane. After that, using at least one control point corresponding to this right lane boundary line L 22 and the preset lane width, determine the control points corresponding to the left lane boundary line of the right-turn lane. According to the entry point B 21 of the incoming lane above the figure, the control points corresponding to the right lane boundary line, and the exit point B 11 of the exit lane on the left side of the figure, draw the left lane boundary line L Figure 9 as shown in (B) of 21 . The left lane boundary line L 21 and the right lane boundary line L 22 in this example can indicate that the right-turn vehicle avoids the obstacle on the left side of the obstacle.

[0176] Intersection situation three

[0177] Figure 10 Exemplarily shows a schematic flow chart of marking a straight lane line at an intersection provided by an embodiment of the present application. As shown in Figure 10 , the blank area in this example represents the intersection, the strip area represents the crosswalk, there are two adjacent straight lanes in the intersection, and there is a rectangular obstacle in the center of the intersection:

[0178] In one case, this example can be regarded as marking two straight lane lines indicating driving from left to right, that is, the vehicle enters the intersection from the left side of the figure and exits the intersection from the right side of the figure. When drawing the straight lane line of the straight lane below the figure, the mapping device can first draw the right lane boundary line L 11 of the straight lane as shown in (A) of 21 according to the entry point B Figure 10 on the left side of the figure and the exit point B 11 on the right side of the figure. According to the entry point B12 and the right-side exit point B shown in the figure 22 Draw as shown in Figure 10 the left lane boundary line L of the straight lane as shown in (A) therein 12 , it can be found by comparison that although the right lane boundary line L 11 and the left lane boundary line L 12 both intersect with the obstacle, but: if the obstacle is avoided on the left side of the obstacle, then the right lane boundary line L 11 is the critical boundary line, and the maximum distance between the right lane boundary line L 11 and the left obstacle is D1. If the obstacle is avoided on the right side of the obstacle, then the left lane boundary line L 12 is the critical boundary line, and the maximum distance between the left lane boundary line L 12 and the right obstacle is D2. Obviously, D1 is greater than D2. Based on the principle that the side with the minimum maximum distance is the target obstacle avoidance area, the mapping device can use the left lane boundary line L 12 as the first lane line, and use the right side of the first lane line L 12 as the target obstacle avoidance area. According to the left-side entry point B shown in the figure 12 , the control point selected from the right-side area of the first lane line L 12 and the right-side exit point B shown in the figure 22 draw the second lane line L as shown in (B) therein Figure 10 , and this second lane line L 221 corresponds to the left lane boundary line L of the lower straight lane 221 , and then draw the right lane boundary line L of the lower straight lane as shown in (B) therein according to the preset lane width 221 . When drawing the straight lane line of the upper straight lane shown in the figure, the mapping device can first draw the right lane boundary line L of the straight lane as shown in (A) therein according to the left-side entry point B shown in the figure Figure 10 and the right-side exit point B shown in the figure 21 . When drawing the straight lane line of the upper straight lane shown in the figure, the mapping device can first draw the right lane boundary line L of the straight lane as shown in (A) therein according to the left-side entry point B shown in the figure 12 and the right-side exit point B shown in the figure 22 , draw as shown in Figure 10 the right lane boundary line L of the straight lane as shown in (A) therein 12 , draw the left lane boundary line L of the straight lane as shown in (A) therein according to the left-side entry point B shown in the figure 13 and the right-side exit point B shown in the figure 23 , draw as shown in Figure 10 the left lane boundary line L of the straight lane as shown in (A) therein 13 , it can be found by comparison that the right lane boundary line L 12 intersects with the obstacle while the left lane boundary line L 13 does not intersect with the obstacle. Therefore, the mapping device can use the right lane boundary line L 12 as the first lane line. According to the areas of the two obstacle areas divided by the first lane line L 12 for the obstacle, it can be known that the one located on the first lane line L12 The area of the obstacle area on the left side is smaller than that of the obstacle area on the right side of the first lane line L 12 Therefore, the mapping device determines that the left area of the first lane line L 12 is the target obstacle avoidance area. According to the entry point B of the vehicle entering the lane on the left side shown in the figure 12 , a control point selected from the left area of the first lane line L 12 and the exit point B of the vehicle exiting the lane on the right side shown in the figure 22 draw the second lane line as shown in Figure 10 (B) in the figure. This second lane line L 222 corresponds to the right lane boundary line of the straight-ahead lane above. Then, according to the preset lane width, draw the left lane boundary line L Figure 10 of the straight-ahead lane above as shown in 23 .

[0179] In another case, this example can also be regarded as marking two straight-ahead lane lines indicating driving from right to left, that is, the vehicle enters the intersection from the right side shown in the figure and exits the intersection from the left side shown in the figure. When drawing the straight-ahead lane lines of the straight-ahead lane below the figure, the mapping device can first draw the left lane boundary line L 21 of the straight-ahead lane as shown in 11 (A) in the figure according to the entry point B on the right side shown in the figure Figure 10 and the exit point B on the left side shown in the figure 11 . Then, draw the right lane boundary line L 22 of the straight-ahead lane as shown in 12 (A) in the figure according to the entry point B on the right side shown in the figure Figure 10 and the exit point B on the left side shown in the figure 12 . By comparison, it is found that although both the left lane boundary line L 11 and the right lane boundary line L 12 intersect with the obstacle, however: if avoiding the obstacle on the right side of the obstacle, then the left lane boundary line L 11 is the critical boundary line, and the maximum distance between the left lane boundary line L 11 and the right obstacle is D1. If avoiding the obstacle on the left side of the obstacle, then the right lane boundary line L 12 is the critical boundary line, and the maximum distance between the right lane boundary line L 12 and the left obstacle is D2. Obviously, D1 is greater than D2. Based on the principle that the side with the minimum maximum distance is the target obstacle avoidance area, the mapping device can use the right lane boundary line L 12 as the first lane line, and use the left side of the first lane line L 12 as the target obstacle avoidance area. According to the entry point B on the right side shown in the figure 22 , a control point selected from the left area of the first lane line L 12 and the exit point B on the left side shown in the figure12 Draw out Figure 10 The second lane line L shown in (B) 221 , the second lane line L 221 The corresponding lane line L is the right lane line of the straight lane below. 221 , and then draw the following according to the preset lane width Figure 10 The left lane edge line L of the lower straight lane shown in (B) 21 When drawing the straight lane line of the straight lane above the diagram, the mapping equipment can first draw the line according to the right entry point B in the diagram. 22 and exit point B on the left side of the diagram 12 Draw out Figure 10 The left lane edge line L of the through lane shown in (A) 12 , follow the diagram to the right and enter point B 23 and exit point B on the left side of the diagram 13 Draw out Figure 10 The right lane edge line L of the through lane shown in (A) 13 , by comparison, it is found that the left lane edge line L 12 Intersecting with the obstacle and the right lane edge L 13 does not intersect with the obstacle, so the mapping equipment can 12 As the first lane line. According to the obstacle, the first lane line L 12 The area of ​​the two obstacle areas is known to be located at the first lane line L 12 The area of ​​the obstacle area on the right is larger than that on the first lane line L 12 The obstacle area on the left is small, so the mapping device determines the first lane line L 12 The right side of the target obstacle avoidance area is the entry point B of the right lane. 22 , from the first lane line L 12 The control point selected in the right area of ​​​​the figure and the exit point B of the left exit lane 12 Draw out Figure 10 The second lane line L is shown in (B). 222 The left lane edge line of the upper straight lane is corresponding, and then the following is drawn according to the preset lane width: Figure 10 The right lane edge line L of the upper through lane shown in (B) 23 .

[0180] The above example allows vehicles in two adjacent through lanes to avoid the obstacle on both sides of the obstacle.

[0181] Intersection situation 4

[0182] Figure 11Another schematic flowchart for marking the straight - through lane lines at an intersection provided by an embodiment of the present application is exemplarily shown. As Figure 11 shown, the blank area in this example represents the intersection, the strip - shaped area represents the crosswalk, there are two adjacent straight - through lanes in the intersection, and there is a rectangular obstacle at a position slightly below the center of the intersection:

[0183] In one case, this example can be regarded as marking two straight - through lane lines indicating driving from left to right, that is, vehicles enter the intersection from the left side of the figure and exit the intersection from the right side of the figure. When drawing the straight - through lane line of the straight - through lane below the figure, the mapping device can first draw the right - hand lane boundary line L of the straight - through lane as shown in (A) of 11 point B where vehicles enter from the left side of the figure 21 and point B where vehicles exit from the right side of the figure Figure 11 as shown in (A) of 11 point B where vehicles enter from the left side of the figure 12 and point B where vehicles exit from the right side of the figure 22 draw the left - hand lane boundary line L of the straight - through lane as shown in (A) of Figure 11 . By comparison, it is found that although both the right - hand lane boundary line L 12 and the left - hand lane boundary line L 11 intersect with the obstacle, however: If avoiding the obstacle on the left side of the obstacle, the right - hand lane boundary line L 12 is the critical boundary line, and the maximum distance between the right - hand lane boundary line L 11 and the left - hand obstacle is D3. If avoiding the obstacle on the right side of the obstacle, the left - hand lane boundary line L 11 is the critical boundary line, and the maximum distance between the left - hand lane boundary line L 12 and the right - hand obstacle is D4. Obviously, D3 is less than D4. Based on the principle that the side with the minimum maximum distance is the target obstacle - avoiding area, the mapping device can use the right - hand lane boundary line L 12 as the first lane line, use the left - hand area of the first lane line L 11 as the target obstacle - avoiding area, and draw the second lane line L as shown in (B) of 11 point B where vehicles enter from the left side of the figure 11 , a control point selected from the left - hand area of the first lane line L 11 and point B where vehicles exit from the right side of the figure 21 as shown in (B) of Figure 11 . This second lane line L 21 corresponds to the right - hand lane boundary line of the straight - through lane below, and then draw the left - hand lane boundary line L of the straight - through lane below as shown in (B) of 21 according to the preset lane width as shown in (B) of Figure 11 . When drawing the straight - through lane line of the straight - through lane above the figure, the mapping device can first draw according to point B where vehicles enter from the left side of the figure 22 12 ​and the right exit point B shown in the figure 22 Draw as Figure 11 the right lane boundary line L of the straight lane as shown in (A) in 12 , according to the left entry point B shown in the figure 13 and the right exit point B shown in the figure 23 Draw as Figure 11 the left lane boundary line L of the straight lane as shown in (A) in 13 , it is found by comparison that the right lane boundary line L 12 intersects with the obstacle while the left lane boundary line L 13 does not intersect with the obstacle. Therefore, the mapping device can use the right lane boundary line L 12 as the first lane line. According to the areas of the two obstacle regions divided by the first lane line L 12 for the obstacle, it can be known that the area of the obstacle region on the left side of the first lane line L 12 is smaller than the area of the obstacle region on the right side of the first lane line L 12 . Therefore, the mapping device determines the left region of the first lane line L 12 as the target obstacle avoidance region. Since the lower straight lane line adjacent to the upper straight lane line is also on the left side of the obstacle, the right lane boundary line of the upper straight lane can directly refer to the left lane boundary line L 22 of the already drawn lower straight lane. On this basis, the mapping device can directly determine the control points corresponding to the left lane boundary line of the upper straight lane according to the control points used when drawing the left lane boundary line L 22 and the preset lane width. According to the entry point B 13 of the left entry lane shown in the figure, the determined control points and the exit point B 23 of the right exit lane shown in the figure, draw as Figure 11 the left lane boundary line L of the upper straight lane as shown in (B) in 23 .

[0184] In another case, this example can also be regarded as marking two straight lane lines indicating driving from right to left, that is, the vehicle enters the intersection from the right side shown in the figure and exits the intersection from the left side shown in the figure. When drawing the straight lane lines of the lower straight lane shown in the figure, the mapping device can first draw according to the right entry point B 21 shown in the figure and the left exit point B 11 shown in the figure as Figure 11 the left lane boundary line L of the straight lane as shown in (A) in 11 , and draw according to the right entry point B 22 shown in the figure and the left exit point B 12 shown in the figure as Figure 11 the right lane boundary line L of the straight lane as shown in (A) in 12, by comparison, it is found that although the left lane boundary line L 11 and the right lane boundary line L 12 both intersect with the obstacle, however: if avoiding the obstacle on the right side of the obstacle, then the left lane boundary line L 11 is the critical boundary line, and the maximum distance between the left lane boundary line L 11 and the right obstacle is D3. If avoiding the obstacle on the left side of the obstacle, then the right lane boundary line L 12 is the critical boundary line, and the maximum distance between the right lane boundary line L 12 and the left obstacle is D4. Obviously, D3 is less than D4. Based on the principle that the side with the minimum maximum distance is the target obstacle avoidance area, the mapping device can use the left lane boundary line L 11 as the first lane line, and use the area on the right side of the first lane line L 11 as the target obstacle avoidance area. According to the illustrated right entry point B 21 , the control point selected from the area on the right side of the first lane line L 11 and the illustrated left exit point B 11 to draw the second lane line L Figure 11 as shown in (B), and this second lane line L 21 corresponds to the left lane boundary line of the lower straight lane, and then draw the right lane boundary line L 21 of the lower straight lane as shown in (B) according to the preset lane width Figure 11 . When drawing the straight lane line of the upper straight lane in the illustration, the mapping device can first draw the left lane boundary line L 22 of the straight lane as shown in (A) according to the illustrated right entry point B 22 and the illustrated left exit point B 12 , draw the right lane boundary line L Figure 11 of the straight lane as shown in (A) according to the illustrated right entry point B 12 and the illustrated left exit point B 23 and the illustrated left exit point B 13 . By comparison, it is found that the left lane boundary line L Figure 11 intersects with the obstacle while the right lane boundary line L 13 does not intersect with the obstacle. Therefore, the mapping device can use the left lane boundary line L 12 as the first lane line. According to the area of the two obstacle areas divided by the first lane line L 13 by the obstacle, it can be known that the area of the obstacle area on the right side of the first lane line L 12 is smaller than the area of the obstacle area on the left side of the first lane line L 12 . Therefore, the mapping device determines the first lane line L 12 on the right side of the first lane line L 12 is smaller than the area of the obstacle area on the left side of the first lane line L 12The right area is the target obstacle avoidance area. Since the lower straight lane line adjacent to the upper straight lane line is also on the right side of the obstacle, the left lane boundary line of the upper straight lane can directly refer to the right lane boundary line L of the already drawn lower straight lane. 22 On this basis, the mapping device can directly determine the control points corresponding to the right lane boundary line of the upper straight lane according to the control points used when drawing the right lane boundary line L 22 and the preset lane width, and determine the entry point B of the right lane shown in the figure 23 of the entry lane, the determined control points and the exit point B of the left exit lane shown in the figure 13 to draw the right lane boundary line L of the upper straight lane as shown in Figure 11 (B) in the figure. 23 .

[0185] The above example enables vehicles in two adjacent straight lanes to avoid obstacles on the same side of the obstacle.

[0186] It should be noted that the above is only an exemplary introduction to several ways of marking obstacle avoidance lane lines at intersections. In actual traffic scenarios, there may be more intersection situations, which are not listed one by one in this application.

[0187] In addition, it should be noted that each of the above embodiments is only introduced by taking the existence of one obstacle in the lane or intersection as an example. In the real scenario, there may also be multiple obstacles in the lane or intersection. In this case, the mapping device can directly select the points whose minimum distances from multiple obstacles are greater than or equal to the preset obstacle avoidance distance as control points to draw the second lane line, or first draw the second lane line based on a certain obstacle, and then determine whether the second lane line meets the obstacle avoidance requirements of other obstacles. When it meets, mark the second lane line; when it does not meet, redraw a new second lane line based on the second lane line, and repeat the above process until the target second lane line that meets the obstacle avoidance requirements of all obstacles is found, and mark the target second lane line on the map. Among them, the first selected obstacle can be randomly selected from multiple obstacles or selected in sequence according to the position order, or the one with the most severe position relationship among multiple obstacles, which is not specifically limited.

[0188] It should be noted that the names of the above various information are only examples. With the evolution of communication technology, any of the above information may change its name, but no matter how its name changes, as long as its meaning is the same as the meaning of the above information in this application, it shall fall within the protection scope of this application.

[0189] The above mainly introduces the solution provided by this application from the perspective of the interaction between each network element. It can be understood that in order to implement the above functions, each of the above network elements includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described function for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0190] According to the foregoing method, Figure 12 An exemplary structural schematic diagram of a lane line annotation device provided by an embodiment of this application is shown, as Figure 12 shown. This device can be a mapping device, or a chip or circuit, such as a chip or circuit that can be arranged in a mapping device. Exemplarily, it can be a mapping device as described in any one of Figures 1 to 11 the above.

[0191] As Figure 12 shown, the lane line annotation device 1201 can include a processor 1202, a memory 1204, and a transceiver 1203, and can further include a bus system. Among them, the processor 1202, the memory 1204, and the transceiver 1203 can be connected through the bus system.

[0192] It should be understood that the above processor 1202 can be a chip. For example, the processor 1202 can be a field programmable gate array (FPGA), can be an application specific integrated circuit (ASIC), can also be a system on chip (SoC), can also be a central processor unit (CPU), can also be a network processor (NP), can also be a digital signal processing circuit (DSP), can also be a micro controller unit (MCU), can also be a programmable logic device (PLD), or other integrated chips.

[0193] In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 1202 or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by the hardware processor, or executed by a combination of the hardware and software modules in the processor 1202. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory 1204, and the processor 1202 reads the information in the memory 1204 and combines its hardware to complete the steps of the above method.

[0194] It should be noted that the processor 1202 in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiments can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by the hardware decoding processor, or executed by a combination of the hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0195] It can be understood that the memory 1204 in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0196] When the lane line marking device 1201 corresponds to the mapping device, the lane line marking device may include a processor 1202, a transceiver 1203, and a memory 1204. The memory 1204 is used to store instructions, and the processor 1202 is used to execute the instructions stored in the memory 1204 to implement the relevant solutions of the mapping device in any one or any combination of the methods corresponding to those shown above Figures 1 to 11 or execute the method executed by the mapping device in any one of the embodiments shown in Embodiments 1 to 3 above.

[0197] When the lane line marking device 1201 is a mapping device and implements Embodiment 1: The transceiver 1203 can receive the environmental images reported by the acquisition vehicle. The processor 1202 can construct a point cloud map based on the environmental images, obtain the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection on the point cloud map, determine the first lane line moving from the entry point to the exit point. When the first lane line intersects with the obstacles in the intersection or the minimum distance between the first lane line and the obstacles is less than the preset obstacle avoidance distance, select one of the two side regions of the first lane line as the target obstacle avoidance region, select at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance, determine the second lane line whose minimum distance from the obstacle is not less than the preset obstacle avoidance distance according to the entry point, at least one control point and the exit point, and mark the second lane line on the map.

[0198] When the lane line marking device 1201 is a mapping device and implements Embodiment 2: The transceiver 1203 can receive the environmental images reported by the acquisition vehicle. The processor 1202 can construct a point cloud map based on the environmental images, obtain the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection on the point cloud map, select at least two control points in the intersection, determine at least two first lane lines according to the entry point, the exit point and at least two control points, and any two of the at least two first lane lines use different control points. Then, determine the target first lane line whose minimum distance from the obstacles in the intersection is not less than the preset obstacle avoidance distance from the at least two first lane lines, and mark the target first lane line on the map.

[0199] For the concepts, explanations, detailed descriptions and other steps related to the technical solutions of the mapping device provided in the embodiments of the present application involved in the lane line marking device 1201, please refer to the descriptions of these contents in the foregoing method or other embodiments, and will not be elaborated here.

[0200] Based on the above embodiments and the same concept, Figure 13 Exemplarily shows a schematic structural diagram of another lane line marking device provided in the embodiments of the present application. As Figure 13 shown, the lane line marking device 1301 can be a mapping device, and can be, for example, any one of the mapping devices described in Figures 1 to 11 , or can be a chip or a circuit, such as a chip or a circuit that can be arranged in a mapping device. The lane line marking device can implement the steps executed by the mapping device in any one or any combination of the corresponding methods shown in Figures 1 to 11 , or execute the methods executed by the mapping device in any one of the first to third embodiments shown above. As Figure 13As shown, the lane line marking device 1301 may include an acquisition unit 1302, a determination unit 1303, a selection unit 1304, and a marking unit 1305.

[0201] When the lane line marking device 1301 is a mapping device and executes the first embodiment: The acquisition unit 1302 may acquire the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection. When the first lane line intersects with an obstacle in the intersection or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance, the determination unit 1303 may determine the first lane line from the entry point to the exit point. The selection unit 1304 may select one of the two side regions of the first lane line as the target obstacle avoidance region, and select at least one control point within the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance. The determination unit 1303 may further determine a second lane line based on the entry point, at least one control point, and the exit point, where the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance. Then, the marking unit 1305 marks the second lane line on the map.

[0202] When the lane line marking device 1301 is a mapping device and executes the second embodiment: The acquisition unit 1302 may acquire the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection. The selection unit 1304 may select at least two control points in the intersection. The determination unit 1303 may determine at least two first lane lines based on the entry point, the exit point, and at least two control points, and determine a target first lane line whose minimum distance from the obstacle in the intersection is not less than the preset obstacle avoidance distance, where any two of the at least two first lane lines use different control points. Then, the marking unit 1305 marks the target first lane line on the map.

[0203] It should be understood that the division of the units of the above lane line marking device 1301 is only a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or physically separated. For the concepts, explanations, detailed descriptions, and other steps related to the technical solutions provided in the embodiments of the present application involved in the lane line marking device 1301, please refer to the descriptions of these contents in the foregoing methods or other embodiments, and will not be elaborated here.

[0204] According to the method provided in the embodiments of the present application, the present application also provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, it causes the computer to execute Figures 1 to 11 the method of any one of the embodiments shown.

[0205] According to the method provided by the embodiments of the present application, the present application further provides a computer-readable storage medium storing program codes, which when run on a computer, cause the computer to execute Figures 1 to 11 the method of any one of the embodiments shown.

[0206] According to the method provided by the embodiments of the present application, the present application further provides a vehicle that can collect environmental images, construct a point cloud map based on the environmental images, and then execute the steps performed by the mapping device in any one or any combination of the methods shown above Figures 1 to 11 to mark lane lines that can avoid obstacles on the point cloud map.

[0207] According to the method provided by the embodiments of the present application, the present application further provides a vehicle networking system including the aforementioned vehicle and a mapping device. The vehicle can collect environmental images and send them to the mapping device. The mapping device can construct a point cloud map based on the environmental images and execute the steps performed by the mapping device in any one or any combination of the methods shown above Figures 1 to 11 to mark lane lines that can avoid obstacles on the point cloud map.

[0208] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a high-density digital video disc (DVD)), or a semiconductor medium (such as a solid state drive (SSD)), etc.

[0209] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. A lane line annotation method, characterized in that, The method includes: Obtaining the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection; Determining a first lane line that moves from the entry point to the exit point, where the first lane line intersects an obstacle in the intersection, or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance; Selecting one of the two side regions of the first lane line as the target obstacle avoidance region; Selecting at least one control point within the target obstacle avoidance region that is not less than the preset obstacle avoidance distance from the obstacle; Determining a second lane line based on the entry point, the at least one control point, and the exit point, where the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance; Marking the second lane line on the map; Wherein, the target obstacle avoidance region satisfies at least one of the following conditions: Located within the obstacle avoidance region indicated by the obstacle with traffic rule indication function; When the first lane line does not intersect the obstacle, it does not include the obstacle; When the first lane line intersects the obstacle, it includes the obstacle region with the smallest area among the two obstacle regions divided by the first lane line; Or, When the first lane line intersects the obstacle, it includes the obstacle region with the smallest maximum distance from the first lane line among the two obstacle regions divided by the first lane line.

2. The method according to claim 1, wherein When the first lane line intersects the obstacle: The step of selecting at least one control point within the target obstacle avoidance region that is not less than the preset obstacle avoidance distance from the obstacle includes: Finding the first position point that is farthest from the first lane line on the edge of the obstacle region included in the target obstacle avoidance region; Determining a second position point within the target obstacle avoidance region whose distance from the first position point is the preset obstacle avoidance distance, and the line connecting the second position point and the first position point is perpendicular to the tangent of the first lane line, or perpendicular to the line segment between the two intersection points of the first lane line and the obstacle; Taking the second position point as one of the control points.

3. The method according to claim 1, characterized in that When the first lane line does not intersect the obstacle: The step of selecting at least one control point within the target obstacle avoidance region that is not less than the preset obstacle avoidance distance from the obstacle includes: Finding the third position point that is closest to the first lane line on the edge of the obstacle; Determining a fourth position point within the target obstacle avoidance region whose distance from the third position point is the preset obstacle avoidance distance, and the line connecting the fourth position point and the third position point is perpendicular to the tangent of the first lane line, or perpendicular to the tangent of the obstacle at the third position point; Taking the fourth position point as one of the control points.

4. The method according to claim 2 or 3, characterized in that The method further includes: Drawing a control line in a direction perpendicular to the connection line from the control point; Selecting at least two fifth position points respectively located on both sides of the control point from the control line; Taking the at least two fifth position points as at least two of the control points.

5. The method according to claim 4, characterized in that, The at least two control points include at least one of the following: The intersection points of the control line and the entry line, and the intersection points of the control line and the exit line, where the entry line is a straight line drawn from the entry point along the entry direction, and the exit line is a straight line drawn from the exit point along the opposite direction of the exit; Two points on the control line whose distances from the control point are equal to the length of the line segment between the two intersection points of the first lane line and the obstacle; Or, Two points on the control line whose distances from the control point are equal to the length of the first lane line inside the obstacle.

6. The method according to any one of claims 1 to 5, characterized in that Determining the first lane line moving from the entry point to the exit point includes: Extending from the entry point along the entry direction to obtain the entry line; Extending from the exit point along the opposite direction of the exit direction to obtain the exit line; Determining the first lane line according to the entry point, the intersection point of the entry line and the exit line, and the exit point.

7. A lane marking device, characterized in that, Including: An acquisition unit for acquiring the entry point where the vehicle enters the intersection and the exit point where the vehicle exits the intersection; A determination unit for determining the first lane line moving from the entry point to the exit point, where the first lane line intersects with the obstacle in the intersection, or the minimum distance between the first lane line and the obstacle is less than a preset obstacle avoidance distance; A selection unit for selecting one of the two side regions of the first lane line as the target obstacle avoidance region, and selecting at least one control point in the target obstacle avoidance region whose distance from the obstacle is not less than the preset obstacle avoidance distance; The determination unit is further configured to determine a second lane line according to the entry point, the at least one control point, and the exit point, where the minimum distance between the second lane line and the obstacle is not less than the preset obstacle avoidance distance; A marking unit for marking the second lane line on the map; Wherein, the target obstacle avoidance region satisfies at least one of the following conditions: Located within the obstacle avoidance region indicated by the obstacle with traffic rule indication function; When the first lane line does not intersect with the obstacle, it does not include the obstacle; When the first lane line intersects with the obstacle, it includes the obstacle region with the smallest area among the two obstacle regions divided by the first lane line; Or, When the first lane line intersects with the obstacle, it includes the obstacle region with the smallest maximum distance from the first lane line among the two obstacle regions divided by the first lane line.

8. The device according to claim 7, wherein When the first lane line intersects with the obstacle, the selection unit is specifically configured to: Find the first position point with the farthest distance from the first lane line on the edge of the obstacle region included in the target obstacle avoidance region; Determine a second position point in the target obstacle avoidance region whose distance from the first position point is the preset obstacle avoidance distance, and the line connecting the second position point and the first position point is perpendicular to the tangent of the first lane line, or perpendicular to the line segment between the two intersection points of the first lane line and the obstacle; Taking the second position point as one of the control points.

9. The device according to claim 7, characterized in that When the first lane line does not intersect with the obstacle, the selection unit is specifically configured to: find a third position point on the edge of the obstacle that is closest to the first lane line; determine a fourth position point within the target obstacle avoidance area that is at the preset obstacle avoidance distance from the third position point, and the line connecting the fourth position point and the third position point is perpendicular to the tangent of the first lane line or perpendicular to the tangent of the obstacle at the third position point; use the fourth position point as one of the control points.

10. The device according to claim 8 or 9, characterized in that The selection unit is further configured to: draw a control line in a direction perpendicular to the connecting line from the control point; select at least two fifth position points on the control line that are located on both sides of the control point respectively; use the at least two fifth position points as at least two of the control points.

11. The device according to claim 10, characterized in that The at least two control points include at least one of the following: the intersection point of the control line and the entry line, and the intersection point of the control line and the exit line, where the entry line is a straight line drawn from the entry point along the entry direction, and the exit line is a straight line drawn from the exit point along the opposite direction of the exit; two points on the control line whose distances from the control point are equal to the length of the line segment between the two intersection points of the first lane line and the obstacle; or, two points on the control line whose distances from the control point are equal to the length of the first lane line within the obstacle.

12. The device according to any one of claims 7 to 11, characterized in that The determination unit is specifically configured to: extend from the entry point along the entry direction to obtain an entry line; extend from the exit point along the opposite direction of the exit direction to obtain an exit line; determine the first lane line based on the entry point, the intersection point of the entry line and the exit line, and the exit point.

13. A lane line marking device, characterized in that, It includes a processor and a memory, the memory stores a computer program, and the processor runs the computer program to implement the method according to any one of claims 1 to 6 above.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is run, it implements the method according to any one of claims 1 to 6 above.

Images