A high-precision map lane line update method and system

Abstract

The present invention provides a method and system for updating lane lines of a high-precision map. The method includes: projecting the vector data of lane lines and road outer lines in the high-precision map master library onto a two-dimensional image, filtering oncoming lane lines based on the road outer lines, retaining the lane lines of the current road and numbering them; acquiring lane line images collected by an in-vehicle camera, filtering oncoming lane lines based on the left and right road outer lines recognized by perception, retaining the lane lines of the current road and numbering them; matching the perceived lane lines with the lane lines in the master library, determining the lane lines in the master library that are not matched as deleted, determining the lane lines in the perceived lane lines that are not matched as newly added, and determining the lane lines with attribute differences as modified; marking the starting points, ending points, and difference types of the differences in the lane line images according to the matching results to update the lane lines of the high-precision map. Through this solution, the cost of updating the lane lines of the high-precision map can be reduced, manpower and material resources can be saved, and the update efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of high-precision maps, and particularly relates to a method and system for updating lane lines of a high-precision map. Background Art

[0002] In the process of making a high-precision map, lane lines are one of the extremely important elements. Due to the frequent changes of lane lines on the road, it is necessary to update the made high-precision map in real time. If the changed map part is remade according to the high-precision map production process, it will be very costly in terms of manpower and material resources. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and system for updating lane lines of a high-precision map, which are used to solve the problem of high costs of manpower and material resources for updating lane lines of a high-precision map.

[0004] In the first aspect of the embodiments of the present invention, a method for updating lane lines of a high-precision map is provided, including:

[0005] Projecting the lane line and road outer line vector data of the high-precision map master library onto a two-dimensional image, filtering the oncoming lane lines based on the road outer line, retaining the lane lines of the current road and numbering them as the first lane line data;

[0006] Obtaining the lane line image collected by the vehicle-mounted camera, filtering the oncoming lane lines based on the left and right road outer lines recognized by perception, retaining the lane lines of the current road and numbering them as the second lane line data;

[0007] Matching the first lane line data with the second lane line, determining the lane lines not matched in the first lane line data as deleted, determining the lane lines not matched in the second lane line data as newly added, and determining that there are matching attribute differences between the corresponding numbered lane lines in the first lane line data and the second lane line data as modified;

[0008] Marking the starting point, ending point and difference type of the difference in the lane line image according to the matching result to update the lane lines of the high-precision map.

[0009] In the second aspect of the embodiments of the present invention, a system for updating lane lines of a high-precision map is provided, including:

[0010] A first lane line extraction module, which is used to project the lane line and road outer line vector data of the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, retain the lane lines of the current road and number them as the first lane line data;

[0011] The second lane line extraction module is used to obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the left and right road outer lines identified by perception, retain the lane lines of the current road and number them as the second lane line data;

[0012] The lane line matching module is used to match the first lane line data with the second lane line, determine the lane lines that are not matched in the first lane line data as deleted, determine the lane lines that are not matched in the second lane line data as newly added, and determine that there is a difference in the matching attributes of the lane lines with the corresponding numbers in the first lane line data and the second lane line data as modified;

[0013] The marking update module is used to mark the starting point, ending point and difference type of the difference in the lane line image according to the matching result, so as to update the lane lines of the high-precision map.

[0014] In the third aspect of the embodiments of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect of the embodiments of the present invention are implemented.

[0015] In the fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiments of the present invention are implemented.

[0016] In the embodiments of the present invention, by comparing the lane lines in the current image with the high-precision master library, the difference points of the lane lines are accurately located, the position numbers of the difference points and the image frame intervals are obtained, so that it is possible to avoid remaking the map of the different parts, realize the automatic update of the lane lines, effectively save time and labor costs, and improve the update efficiency of the lane lines of the high-precision map. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0018] Figure 1 It is a schematic flowchart of a method for updating lane lines of a high-precision map provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic structural diagram of a system for updating lane lines of a high-precision map provided by an embodiment of the present invention;

[0020] Figure 3 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0021] In order to make the object, features, and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] It should be understood that the term "including" and other similar expressions in the specification or claims of the present invention and the above-mentioned drawings mean covering non-exclusive inclusion. For example, a process, method, system, or device including a series of steps or units is not limited to the listed steps or units. In addition, "first" and "second" are used to distinguish different objects, rather than to describe a specific order.

[0023] Please refer to Figure 1 , a schematic flowchart of a method for updating lane lines of a high-precision map provided by an embodiment of the present invention, including:

[0024] S101. Project the lane line and road outer line vector data in the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, and retain the lane lines of the current road and number them as the first lane line data;

[0025] The high-precision map master library is a high-precision map database, which contains high-precision map lane line data, road outer line data, etc. The road outer line is the marking of the outermost passable area of the road, which is generally located on the outermost side of the road surface and close to the physical isolation facilities on both sides of the road.

[0026] Among the lane lines projected onto the two-dimensional image, there are both the lane lines of the current road and the lane lines of the oncoming road. Therefore, it is necessary to filter out the oncoming lane lines through the left and right road outer lines and retain all the lane lines of the current road.

[0027] The outer road lines are divided into left and right sides based on the slopes of the outer lines in the two-dimensional image. The left and right outer road lines are saved in left_dege_lane and right_edge_lane respectively. If there is only one line in both left_dege_lane and right_edge_lane, they are respectively the left and right outer road lines of the current road. If there is more than one line in left_dege_lane or right_edge_lane, it is determined by the x coordinate of the center point. For example, if there are two lines L1 and L2 in left_dege_lane, and the x coordinates of the center points of L1 and L2 are x1 and x2 respectively, if x1 is less than x2, then L1 represents the left outer road line of the current road.

[0028] Among them, the number of equally divided points on the lane line within the polygon contour formed by the endpoints of the outer road line is obtained. When the number exceeds a predetermined value, it is determined that the lane line belongs to the current driving road.

[0029] Exemplarily, the four endpoints of the left and right outer road lines are connected to form a polygon contour. Seven points are equally spaced on all lane lines. If at least five of the seven points are within the contour, it is determined that the lane line belongs to the current driving road.

[0030] S102: Obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the sensed left and right outer road lines, and retain the lane lines of the current road and number them as the second lane line data;

[0031] The lane lines and outer road lines in the lane line image can be sensed and recognized through the corresponding image recognition model.

[0032] Among them, the attributes of the lane lines are judged. The attributes of the lane lines are at least divided into dotted lines and solid lines. The dotted lines (such as white dotted lines, yellow dotted lines, etc.) in the lane lines can be extracted through the corresponding dotted line segment segmentation model.

[0033] Construct a lane line segmentation model and a dotted line segment segmentation model. Input the picture into the two models to obtain the segmentation result of the lane lines and the segmentation result of the dotted line blocks respectively. Combining the two can determine the solid and dotted attributes of the lane lines.

[0034] Extract the outer road lines in the lane line image through the outer road line recognition model, locate the left and right outer road lines of the current road, filter out the oncoming lane lines through the left and right outer road lines, and retain all the lane lines of the current road.

[0035] Among them, the central axis of the lane line is extracted to facilitate subsequent matching with the data in the high-precision map master database.

[0036] After extracting the lane lines of the current road, it is necessary to sort the lane lines. The sorting rule is the same as the lane line numbering rule in the master database, that is, numbering and sorting are carried out in sequence from left to right.

[0037] Exemplarily, it is judged whether there is a common interval in the y coordinates of the retained lane lines. If so, for the same y coordinate, the x coordinates corresponding to different lane lines are sorted. The lane line with the smallest x coordinate is the leftmost lane line, with id = 0, and from left to right, the id increases; if there is no common interval, the sorting is carried out according to the x coordinate of the midpoint of the lane line.

[0038] S103. Match the first lane line data with the second lane line. Determine the lane lines that are not matched in the first lane line data as deleted, determine the lane lines that are not matched in the second lane line data as newly added, and determine that there is a difference in the matching attributes of the lane lines with corresponding numbers in the first lane line data and the second lane line data as modified;

[0039] When performing lane line matching, it is necessary to locate the lane line data in the master database to the current vehicle position, and compare and match the lane lines currently collected by the vehicle with the lane lines in the master database in sequence according to the numbers, and record the difference types, id numbers, and geometric points of the above lane lines.

[0040] On a single-frame image, compare and match the lane lines in the master database with the perceived lane lines. If there are lane lines in the master database that are not matched, they are determined as deleted; if there are lane lines in the perceived lane lines that are not matched, they are determined as added; if the attributes of the perceived lane lines are changed, they are determined as modified.

[0041] Among them, if the distance between the lane lines with corresponding numbers in the first lane line data and the second lane line data is less than a preset threshold, it is determined that the two lane lines are successfully matched. That is, if the distance between the perceived lane line and the lane line in the master database map is less than a certain threshold thresh, it is determined that the two lane lines are successfully matched.

[0042] S104. Mark the starting point, ending point, and difference type of the difference in the lane line image according to the matching result to update the lane lines in the high-precision map.

[0043] Among them, if the number of lane lines marked as modified in consecutive lane line image frames for the same numbered lane line exceeds a predetermined ratio, the lane line with the corresponding number is marked as modified, and the starting frame and ending frame of the lane line image marked as modified are recorded.

[0044] Since the lane line is a chain-like target, comprehensive judgment needs to be carried out through consecutive frames. For example, if the difference type of more than 1 / 2*N frames from the first frame to the Nth frame is modification, then the difference type of the entire interval is modification; then count the ids and their numbers of the lane line labels with modification in the entire interval. If the number of the same id is greater than 1 / 2*N, then the type of this lane line id is modification, and the start label is marked at the frame where the lane line first appears, and the end label is marked at the frame where the lane line last appears. The marked coordinates should be on the lane line.

[0045] In this embodiment, by accurately locating the difference points on the lane line and marking the start and end positions of the difference interval, the lane line production and update can be carried out targeted, effectively reducing the update cost, saving manpower and material resources, and improving the update efficiency of the lane line in the high-precision map.

[0046] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0047] Figure 2 FIG. is a schematic structural diagram of a system for updating lane lines in a high-precision map provided by an embodiment of the present invention. The system includes:

[0048] The first lane line extraction module 210 is used to project the lane line and the vector data of the road outer line in the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, retain the lane lines of the current road and number them as the first lane line data;

[0049] Among them, the first lane line extraction module 210 includes:

[0050] A judgment unit is used to obtain the number of equally divided points on the lane line within the polygon contour formed by the endpoints of the road outer line. When the number exceeds a predetermined value, it is determined that the lane line belongs to the current driving road.

[0051] The second lane line extraction module 220 is used to obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the left and right road outer lines recognized by perception, retain the lane lines of the current road and number them as the second lane line data;

[0052] Among them, judge the attribute of the lane line, and the attribute of the lane line is at least divided into dotted line and solid line.

[0053] The lane line matching module 230 is used to match the first lane line data with the second lane line, determine the lane lines not matched in the first lane line data as deleted, determine the lane lines not matched in the second lane line data as newly added, and determine that there is a difference in the matching attributes of the corresponding numbered lane lines in the first lane line data and the second lane line data as modified;

[0054] Optionally, if the distance between the lane lines with corresponding numbers in the first lane line data and the second lane line data is less than a preset threshold, it is determined that the two lane lines are successfully matched.

[0055] The marking update module 240 is configured to mark the starting point, ending point, and difference type of the difference in the lane line image according to the matching result, so as to update the lane lines of the high-precision map.

[0056] Among them, marking the starting point, ending point, and difference type of the difference in the lane line image according to the matching result includes:

[0057] If the number of lanes marked as modified in consecutive lane line image frames for the same numbered lane line exceeds a predetermined ratio, the lane line corresponding to the number is marked as modified, and the starting frame and ending frame of the lane line image marked as modified are recorded.

[0058] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0059] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device is used for updating the lane lines of a high-precision map. As Figure 3 shown, the electronic device 3 of this embodiment includes: a memory 310, a processor 320, and a system bus 330. The memory 310 includes a program 3101 that can run thereon. Those skilled in the art can understand that Figure 3 the shown structure of the electronic device does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0060] Next, Figure 3 specific introductions will be made to the various components of the electronic device:

[0061] The memory 310 can be used to store software programs and modules. The processor 320 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 310. The memory 310 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the electronic device (such as cached data, etc.). In addition, the memory 310 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0062] A runnable program 3101 including a network request method is stored on a memory 310. The runnable program 3101 can be divided into one or more modules / units, which are stored in the memory 310 and executed by a processor 320 to implement functions such as lane line update. The one or more modules / units can be a series of computer program instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program 3101 in the electronic device 3. For example, the computer program 3101 can be divided into functional modules such as a first lane line extraction module, a second lane line extraction module, a lane line matching module, and a marker update module.

[0063] The processor 320 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory 310, and by invoking data stored in the memory 310, it executes various functions of the electronic device and processes data, thereby monitoring the overall state of the electronic device. Optionally, the processor 320 can include one or more processing units; preferably, the processor 320 can integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 320.

[0064] The system bus 330 is used to connect various functional components inside the computer, and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, CAN bus, etc. Instructions from the processor 320 are transmitted to the memory 310 through the bus, and the memory 310 feeds back data to the processor 320. The system bus 330 is responsible for the data and instruction interaction between the processor 320 and the memory 310. Of course, the system bus 330 can also be connected to other devices, such as a network interface, a display device, etc.

[0065] In an embodiment of the present invention, the runnable program executed by the processor 320 included in the electronic device includes:

[0066] Project the lane line and road outer line vector data of the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, and retain the lane lines of the current road and number them as the first lane line data;

[0067] Obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the left and right road outer lines identified by perception, and retain the lane lines of the current road and number them as the second lane line data;

[0068] Match the first lane line data with the second lane line. Determine the lane lines in the first lane line data that are not matched as deleted, the lane lines in the second lane line data that are not matched as newly added, and the lane lines with matching attribute differences in the corresponding numbered lane lines between the first lane line data and the second lane line data as modified;

[0069] Mark the starting point, ending point, and difference type of the differences in the lane line image according to the matching results to update the lane lines in the high-precision map.

[0070] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0071] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0072] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for updating lane lines of a high-precision map, characterized in that, Including: Project the lane line and road outer line vector data in the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, retain the lane lines of the current road and number them as the first lane line data; Obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the left and right road outer lines identified by perception, retain the lane lines of the current road and number them as the second lane line data; Match the first lane line data with the second lane line, determine the lane lines not matched in the first lane line data as deleted, determine the lane lines not matched in the second lane line data as newly added, and determine that there is a matching attribute difference between the corresponding numbered lane lines in the first lane line data and the second lane line data as modified; Mark the starting point, ending point and difference type of the difference in the lane line image according to the matching result to update the lane lines of the high-precision map.

2. The method according to claim 1, wherein The step of projecting the lane line and road outer line vector data in the high-precision map master library onto a two-dimensional image and filtering the oncoming lane lines based on the road outer line further includes: Obtain the number of equally divided points on the lane line within the polygon contour formed by the endpoints of the road outer line. When the number exceeds a predetermined value, it is determined that the lane line belongs to the current driving road.

3. The method according to claim 1, characterized in that The step of filtering the oncoming lane lines based on the left and right road outer lines identified by perception further includes: Judge the attribute of the lane line, and the attribute of the lane line is at least divided into dotted line and solid line.

4. The method according to claim 1, wherein The step of matching the first lane line data with the second lane line includes: If the distance between the corresponding numbered lane lines in the first lane line data and the second lane line data is less than a preset threshold, it is determined that the two lane lines are successfully matched.

5. The method according to claim 1, wherein The step of marking the starting point, ending point and difference type of the difference in the lane line image according to the matching result includes: If the number of lanes marked as modified in consecutive lane line image frames for the same numbered lane line exceeds a predetermined ratio, mark the corresponding numbered lane line as modified, and record the starting frame and ending frame of the lane line image marked as modified.

6. A system for updating lane lines of a high-precision map, characterized in that, Including: The first lane line extraction module is used to project the lane line and road outer line vector data in the high-precision map master library onto a two-dimensional image, filter the oncoming lane lines based on the road outer line, retain the lane lines of the current road and number them as the first lane line data; The second lane line extraction module is used to obtain the lane line image collected by the vehicle-mounted camera, filter the oncoming lane lines based on the left and right road outer lines identified by perception, retain the lane lines of the current road and number them as the second lane line data; The lane line matching module is used to match the first lane line data with the second lane line, determine the lane lines not matched in the first lane line data as deleted, determine the lane lines not matched in the second lane line data as newly added, and determine that there is a matching attribute difference between the corresponding numbered lane lines in the first lane line data and the second lane line data as modified; The marking and updating module is used to mark the starting point, ending point and difference type of the difference in the lane line image according to the matching result to update the lane lines of the high-precision map.

7. The system according to claim 6, wherein The first lane line extraction module includes: A judgment unit is configured to obtain the number of equally divided points on the lane line within the polygon contour formed by the end points of the outer road line. When the number exceeds a predetermined value, it is determined that the lane line belongs to the current driving road.

8. The system according to claim 6, wherein The marking of the starting point, ending point and difference type of the difference in the lane line image according to the matching result includes: If the number of lanes with the same number marked as modified in consecutive lane line image frames exceeds a predetermined ratio, the lane line with the corresponding number is marked as modified, and the starting frame and ending frame of the lane line image marked as modified are recorded.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a high-precision map lane line update method according to any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of a high-precision map lane line update method according to any one of claims 1 to 5.

Images