Method and device for determining lane center line

Abstract

The present invention provides a method and device for determining a lane centerline, wherein the method comprises: obtaining position data of a first lane line and a second lane line located on both sides of a target lane in map data, wherein the position data includes at least one positioning point position; and sequentially determining the midpoint position of a connecting line between each positioning point of the first lane and all positioning points of the second lane; and then determining the lane centerline data of the target lane according to the determined midpoint position. The method and device for determining a lane centerline provided by the present invention can improve the work efficiency when determining a lane centerline.

Description

Technical Field

[0001] The present invention relates to map data processing technology, and in particular to a method and device for determining a lane centerline. Background Art

[0002] At present, with the continuous development of electronic technology, the content that maps can present to people is becoming more and more abundant. In addition to flat maps, the emergence of 3D maps, satellite maps and real-life maps has brought people a richer experience in the perception of maps, and can provide users and vehicles with more services such as assisted navigation and automatic driving. Maps with rich content also pose a lot of challenges to map data providers. For example, in addition to the relevant location data of each lane, the map data also needs to mark the center line of the lane, so that during assisted navigation or automatic driving, the center line of the lane can indicate to the user or vehicle the best position of the vehicle on the lane.

[0003] In the prior art, since there is no actual marking on the lane center line on the road, in order to obtain the lane center line, relevant technical personnel are required to manually mark and draw the lane center line between two lane lines on both sides of the lane based on the lane line data on the road collected by the map collection vehicle.

[0004] Therefore, the existing technology is not intelligent enough when determining the lane centerline, and the work efficiency when determining the lane centerline is low because it relies solely on manual marking. Summary of the invention

[0005] The present invention provides a method and device for determining a lane centerline, so as to improve the working efficiency of determining the lane centerline.

[0006] A first aspect of the present invention provides a method for determining a lane centerline, comprising:

[0007] Acquire position data of a first lane line and a second lane line located on both sides of a target lane in the map data, wherein the position data includes a position of at least one positioning point;

[0008] Determine in sequence the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line;

[0009] According to the midpoint position, lane centerline data of the target lane is determined.

[0010] A second aspect of the present invention provides a device for determining a lane centerline, comprising:

[0011] An acquisition module, used for acquiring position data of a first lane line and a second lane located on both sides of a target lane in map data, wherein the position data includes at least one positioning point position;

[0012] A determination module, used to sequentially determine the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line;

[0013] A processing module is used to determine lane centerline data of the target lane according to the midpoint position.

[0014] A third aspect of the present invention provides a storage medium storing a computer program, which, when executed on a computer, causes the computer to execute the method described in the first aspect.

[0015] In summary, the present invention provides a method and device for determining the center line of a lane, wherein the method comprises: obtaining the position data of the first lane line and the second lane line located on both sides of the target lane in the map data, wherein the position data includes at least one positioning point position; and sequentially determining the midpoint position of the connecting line between each positioning point of the first lane and all positioning points of the second lane; and then determining the lane center line data of the target lane according to the determined midpoint position. The method and device for determining the center line of a lane provided by the present invention can determine the midpoint position of the connecting line of each positioning point between the first lane line and the second lane line on both sides of the target lane according to the position data of the first lane line and the second lane line, and the lane center line between the first lane line and the second lane line can be obtained by sequentially connecting the midpoint positions. This improves the intelligence level in determining the center line of the lane, and further improves the work efficiency of determining the center line of the lane. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for determining a lane centerline provided by the present invention;

[0018] Figure 2 A structural schematic diagram of a first lane line and a second lane line in a method for determining a lane center line provided by the present invention;

[0019] Figure 3 A structural schematic diagram of a second embodiment of the first lane line and the second lane line in the method for determining the lane center line provided by the present invention;

[0020] Figure 4 A schematic diagram of the structure of a third embodiment of the first lane line and the second lane line in the method for determining the lane center line provided by the present invention;

[0021] Figure 5 A schematic diagram of lane elevation data in the method for determining the lane centerline provided by the present invention;

[0022] Figure 6 A schematic diagram of a first embodiment of a lane connection curve in a method for determining a lane centerline provided by the present invention;

[0023] Figure 7 A schematic diagram of a second embodiment of a lane connection curve in a method for determining a lane centerline provided by the present invention;

[0024] Figure 8 A schematic diagram of the structure of a first embodiment of a lane centerline determination device provided by the present invention;

[0025] Fig. 9 This is a structural schematic diagram of Embodiment 2 of the device for determining the lane centerline provided by the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0029] The execution subject of this embodiment may be any electronic device with relevant data processing functions, such as a mobile phone, a tablet computer, a laptop computer, a desktop computer, and a server. Alternatively, the execution subject of this embodiment may also be a chip in the electronic device, such as a CPU or a GPU. In the embodiments of the present invention, the execution subject is described as an electronic device, but is not limited thereto.

[0030] The lane centerline determination method provided in this embodiment can be applied to map data providers in the process of making map data, to determine the lane centerline according to the collected lane data of the target lane and add it to the map data. Alternatively, in some possible applications, the lane centerline determination method provided in this embodiment can also be used by autonomous driving vehicles in the process of autonomous driving, to determine the lane centerline of the target lane according to the lane lines on both sides of the target lane to assist autonomous driving.

[0031] Figure 1 A flow chart of an embodiment of a method for determining a lane centerline provided by the present invention is shown in FIG. Figure 1 As shown, the method for determining the lane centerline provided in this embodiment includes:

[0032] S101: Acquire position data of a first lane line and a second lane line on both sides of a target lane in map data.

[0033] Specifically, in S101, in order to determine the lane center line between two lane lines located on both sides of the target lane, the electronic device first needs to obtain position data of the two lane lines on both sides of the lane, recorded as the position data of the first lane line and the position data of the second lane line.

[0034] The position data described in this embodiment includes the latitude and longitude coordinate data of the lane line recorded in the map data, wherein a continuous lane line is represented by discrete positioning points in the map data. Therefore, the position data of the lane line includes the position of at least one positioning point, and the position of each positioning point is represented by the latitude and longitude coordinates of the actual position of the positioning point.

[0035] For example: Figure 2 FIG. 1 is a schematic diagram of a first lane line and a second lane line in a method for determining a lane center line provided by the present invention; Figure 2 In the example shown, the first lane line L1 is represented by discrete lane positioning points A, B, C, D and E; the second lane line L2 is represented by discrete lane positioning points F, G, H, I and J. Then the position data of the first lane line in the map data includes the longitude and latitude coordinates of the lane positioning points A, B, C, D and E, and the position data of the second lane line includes the longitude and latitude coordinates of the lane positioning points F, G, H, I and J.

[0036] S102: sequentially determine the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line.

[0037] Specifically, in S102, the electronic device sequentially connects all the first lane line positioning points and all the second lane line positioning points to obtain connecting lines based on the first lane line positioning points and the second lane line positioning points acquired in S101, and then determines the midpoint positions of all the connecting lines.

[0038] For example, in Figure 2 In the example shown, first, for the positioning point A of the first lane line, according to the position of the positioning point A in the position data of the first lane line and the position data of the second lane line, the connection line between the positioning point A and the positioning point F is recorded as AF, the connection line between the positioning point A and the positioning point G is recorded as AG, the connection line between the positioning point A and the positioning point H is recorded as AH, the connection line between the positioning point A and the positioning point I is recorded as AI, and the connection line between the positioning point A and the positioning point J is recorded as AJ. Subsequently, the connection lines between the positioning point B of the first lane line and all the positioning points of the second lane line are determined in turn as: BF, BG, BH, BI and BJ, as well as the connection lines between the positioning points C, D and E and all the positioning points of the second lane line. Therefore, for Figure 2 In the example shown, when the number of positioning points of the first lane line is 5 and the number of positioning points of the second lane line is 5, 5*5=25 connecting lines can be determined.

[0039] Then, in S102, the electronic device also needs to determine the midpoint positions of all the above-mentioned connecting lines. Figure 2 In the example shown, the midpoint of the connecting line AF is ①, the midpoint of the connecting line AG is ②, the midpoint of the connecting line AH is ③, the midpoint of the connecting line AI is ④, and the midpoint of the connecting line AJ is ⑤. Figure 2 The midpoint positions of the connecting lines BF, BG, etc. not shown all need to be determined, and a total of 25 midpoint positions corresponding to the 25 connecting lines are obtained.

[0040] Optionally, in a possible specific implementation of this step, when determining the connecting line, the electronic device can obtain the connecting line in the form of longitude and latitude coordinate equations based on the longitude and latitude coordinates of the two endpoints of the connecting line, and determine the midpoint position of the connecting line based on the longitude and latitude coordinate equations of the connecting line, and the midpoint position is also represented by longitude and latitude coordinates.

[0041] S103: Connect in sequence according to the midpoint positions to determine the lane centerline data of the target lane.

[0042] Then, in S103, the electronic device as the execution subject sequentially connects the midpoint positions obtained in S102, and the obtained connection line can be used as the lane centerline of the target lane, that is, the sequentially connected midpoint positions can be used as the lane centerline data of the target lane. Figure 2 In the example shown, after the determined 25 midpoint positions are connected in sequence, the connection line obtained is the lane center line between the first lane line L1 and the second lane line L2 of the target lane.

[0043] However, the lane lines of actual lanes are not always Figure 2 The standard straight line shown, therefore, in S103, the midpoint position determined in S102 also needs to be screened, and for all midpoint positions, it is necessary to determine whether each midpoint position is an available midpoint position, that is, whether it can be used to determine the centerline data of the lane; and it is necessary to determine the lane centerline data between the first lane line and the second lane line of the target lane based on the available midpoint positions in the midpoint positions.

[0044] Among them, in a specific method for determining whether the midpoint position is an available midpoint position provided in the present embodiment, first, based on the position data of the first lane line and the position data of the second lane line, a target area surrounded by the first lane line, the second lane line, and the connecting line between the end points of the first lane line and the second lane line in the same direction is determined; then, based on whether the midpoint position is within the target area, the midpoint position within the target area is determined to be an available midpoint position, while the midpoint position outside the target area is determined to be an unavailable midpoint position.

[0045] For example, Figure 3 FIG. 1 is a schematic diagram of a structure of a second embodiment of a first lane line and a second lane line in a method for determining a lane center line provided by the present invention. Figure 3 In the example shown, the first lane line L1 and the second lane line L2 of the curved road are shown, wherein the connecting lines between the positioning point A of the first lane line and the positioning point of the second lane line obtained according to the above steps include AE, AF, AG and AH, wherein the midpoint ④ of the connecting line AH is located outside the two lanes, so the midpoint ④ cannot be used to determine the lane centerline data. Then, the connecting line AE and the connecting line DH can be obtained by connecting the two end points of the first lane line L1 and the second lane line L2 in the same direction. Subsequently, the first lane line L1, the second lane line L2, the connecting line AE and the connecting line DH can form a closed target area, the midpoint of the connecting line located in the target area is the available midpoint position, and the midpoint of the connecting line located outside the target area is the unavailable midpoint position.

[0046] Optionally, in the specific implementation described in this embodiment, the longitude and latitude coordinate range of the target area can be determined based on the longitude and latitude coordinates of the endpoints of the target area, and then, based on whether the longitude and latitude coordinates of the midpoint position of the connecting line are within the longitude and latitude coordinate range of the target area, it is determined whether the midpoint position is within the target area.

[0047] In another specific method of determining whether a midpoint position is an available midpoint position provided in this embodiment, clustering features in all midpoint positions are calculated by a clustering algorithm to obtain clustering points, and the clustering points are used as available midpoint positions.

[0048] For example, Figure 4 FIG. 1 is a schematic diagram of a structure of a first lane line and a second lane line in a third embodiment of a method for determining a lane center line provided by the present invention. Figure 4 In the example shown, each dot represents the midpoint position of a connecting line determined in the above steps. It can be seen that since the midpoint position may fall outside the first lane line L1 and L2, the midpoint positions located in the lane are mostly concentrated at the center line of the lane. Therefore, in this embodiment, the longitude and latitude coordinates of all midpoint positions are used as input, and the clustering feature of each midpoint position is obtained using a clustering algorithm. Then, it is determined whether the midpoint position is a cluster point based on the clustering feature of the midpoint position, thereby determining whether the midpoint position is an available midpoint position.

[0049] Optionally, the clustering algorithm described in this embodiment may be a K-means clustering algorithm, wherein the K-means clustering algorithm takes k sample points in the input data as the initial center in each calculation, calculates the distance between other input data and the k sample points, reselects k sample points to repeat the above process, and finally obtains a classification set based on the clustering characteristics of each sample point. The specific implementation method and principle of the K-means algorithm can be referred to the prior art, and this application does not limit this. Figure 4 For all the midpoint positions shown, the classification set S in the figure can be determined by the K-means clustering algorithm. The midpoint positions within the classification set S that meet the requirements of the classification set S are cluster points. The clustering features of the midpoint positions outside the classification set S do not meet the requirements of the classification set S and are not cluster points. Optionally, in this embodiment, the number of positioning points of the first lane line and the number of positioning points of the second lane line can be used as the value of the parameter k in the K-means clustering algorithm.

[0050] It can be understood that the above two different methods of determining whether the midpoint position is an available midpoint position, namely, by the target area and by the clustering algorithm, can be selected for determination separately or combined for determination in actual applications, and both are within the protection scope of this embodiment.

[0051] Furthermore, in S103 of the present embodiment, before the midpoint positions are connected in sequence, it also includes: determining the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line based on the position data of the first lane line and the second lane line; then, in S103, taking the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line as the starting point, the midpoint positions are connected in sequence.

[0052] For example, Figure 2 The first lane line and the second lane line shown in the figure are used as examples for explanation. In the map data, the positioning points of the first lane line are marked in a certain order, such as A, B, C, D and E, with the starting end being A and the ending end being B. Similarly, the positioning points of the second lane line are marked in a certain order, such as F, G, H, I and J, with the starting end being F and the ending end being J. In this embodiment, the midpoint of the connecting line AF between the starting end A of the first lane line and the starting segment F of the second lane line is taken as the starting point of the lane centerline.

[0053] Then, the midpoints of AF determined above are used as the starting point of the connecting line connecting the midpoints in S103, and all the midpoints determined in S102 are connected in sequence. In this embodiment, the midpoint position closest to the previous midpoint position is used as the next midpoint position, so that the midpoint positions are connected in sequence. For example, in Figure 2 In the example shown, midpoint ① is taken as the starting point, and the midpoint closest to midpoint ① is determined to be midpoint ②, and midpoint ① is connected to midpoint ②; then, the midpoint closest to midpoint ② is determined to be midpoint ③, and midpoint ② is connected to midpoint ③; then, midpoint ③ is connected to midpoint ④, and midpoint ④ is connected to midpoint ⑤ in sequence.

[0054] Finally, after processing steps S101-S103 of the above embodiment, the midpoint position of the connecting line of each positioning point between the first lane line and the second lane line can be determined according to the position data of the first lane line and the second lane line, and the lane center line between the first lane line and the second lane line can be obtained by connecting the midpoint positions in sequence. This improves the intelligence level when determining the lane center line, and further improves the work efficiency of determining the lane center line.

[0055] Furthermore, based on the above-mentioned embodiments, in the lane centerline determination method provided by the present application, the elevation data of the lane centerline can be further determined. Specifically, the position data of the lane provided by the map data also includes the elevation data of each positioning point of the lane. In this embodiment, after the midpoint position is determined in S102, for each of the midpoint positions, after the elevation data of the two lane positioning point positions closest to the midpoint position are determined, the elevation data of the midpoint position can be determined according to the average of the elevation data of the two lane positioning point positions closest to the midpoint position.

[0056] For example: Figure 2 Taking the first lane line and the second lane line shown as an example, after the midpoint ① of the connecting line AF is determined through the aforementioned steps, the two lane positioning points closest to the midpoint ① can be further determined as A and F, and the average of the elevation data of the positioning points A and B is used as the elevation data of the midpoint ①. Subsequently, after the elevation data of all midpoint positions are determined in the same way, after the lane centerline is determined through S103, the elevation data of the lane centerline can be obtained according to each midpoint position. Finally, the lane centerline with elevation data obtained can be referred to Figure 5 , Figure 5 A schematic diagram of lane elevation data in the method for determining lane centerline provided by the present invention is drawn in a three-dimensional coordinate system, wherein the XY axes are longitude and latitude coordinates and the Z axis is the coordinate of the elevation data.

[0057] Furthermore, based on the above embodiments of the present invention, the present invention also provides a method for determining a road connection curve at a road bend using a lane centerline, and the obtained connection curve can be used to connect the two lane centerlines at a road bend, thereby providing a reference for the driving trajectory of the vehicle at the road bend. The method provided in this embodiment includes:

[0058] S201: Acquire centerline data of a first lane and centerline data of a second lane at a road turn in map data, wherein the first lane and the second lane are lanes connected to the same target road turn in the map data.

[0059] Specifically, the road centerline data obtained in S201 can be obtained by the present invention as follows: Figure 1 The lane centerline data of the first lane and the second lane centerline data obtained in the embodiment shown, the first lane and the second lane are the turning point of the target road. Alternatively, it can also be other methods such as manually marked lane centerline data. The lane centerline data includes the longitude and latitude coordinates of each midpoint position constituting the lane centerline and the coordinates of the elevation data.

[0060] S202: Determine a first endpoint in the centerline data of the first lane that is closest to the target road turning point, and a second endpoint in the centerline data of the second lane that is closest to the target road turning point.

[0061] S203: According to the first endpoint of the first lane and the second endpoint of the second lane determined in S202, a connection curve between the first endpoint and the second endpoint is obtained by using a Hermite curve equation.

[0062] The Hermite curve equation used in this embodiment is used to determine the curve connecting the two curves in a three-dimensional coordinate system when the two endpoints of the two curves and the tangent lines at the endpoints are known. Its matrix is ​​represented by Q(t)=T*M h *G h ; Among them, M h is a Hermite matrix composed of constants, G h is the Hermite set vector, Gh = [P0P1R0R1] T .

[0063] For example, Figure 6 A schematic diagram of a lane connection curve embodiment 1 in the method for determining the lane centerline provided by the present invention. Figure 6 In the example shown, P0 is the starting point of the connection curve to be determined, that is, the end point of the centerline data Q1 of the first lane; P1 is the end point of the connection curve to be determined, that is, the start point of the centerline data Q2 of the second lane, R0 is the tangent vector corresponding to the starting point P0, and R1 is the tangent vector corresponding to the end point P1. h After obtaining the Hermite set vector, substitute it into the Hermite curve equation to obtain Figure 6 The curve Q shown in FIG. The curve Q can be expressed by the formula Q(t), which also carries elevation data. Finally, the obtained connection curve can be referred to Figure 7 , Figure 7 A schematic diagram of the second embodiment of lane elevation data in the method for determining the lane centerline provided by the present invention is drawn in a three-dimensional coordinate system, where a position schematic diagram of a connecting curve Q obtained by the centerline data Q1 of the first lane and the centerline data Q2 of the second lane is drawn, wherein the XY axes are longitude and latitude coordinates, and the Z axis is the coordinate of the elevation data.

[0064] In summary, in the lane connection curve determination method provided in this embodiment, the center lines of the lanes to be connected can be connected through the connection curve through the Hermite curve equation, so as to connect the center lines of the lanes at the turns in the map data, and can provide a reference for the driving trajectory for the vehicle in scenarios such as navigation and automatic driving. Compared with the prior art that requires manual curve connection of the center lines of the lanes, the work efficiency of determining the connection curve between the center lines of the lanes is also improved.

[0065] Figure 8 This is a schematic diagram of the structure of the first embodiment of the lane centerline determination device provided by the present invention, as shown in FIG. Figure 8As shown, the lane centerline determination device provided in this embodiment includes: an acquisition module 801, a determination module 802 and a processing module 803. Among them, the acquisition module 801 is used to obtain the position data of the first lane line and the second lane line located on both sides of the target lane in the map data, and the position data includes the position of at least one positioning point; the determination module 802 is used to sequentially determine the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line; the processing module 803 is used to determine the lane centerline data of the target lane according to the midpoint position.

[0066] The lane centerline determination device provided in this embodiment can be used to perform the following steps: Figure 1 The method for determining the lane centerline shown is implemented in the same manner and principle and will not be described in detail.

[0067] Optionally, in the above embodiment, the processing module 803 is specifically used to determine an available midpoint position from all midpoint positions; and connect the available midpoint positions in sequence to obtain lane centerline data of the target lane.

[0068] Optionally, in the above embodiment, the processing module 803 is specifically used to determine, based on the position data of the first lane line and the position data of the second lane line, a target area surrounded by connecting lines between the endpoints of the first lane line and the second lane line in the same direction; and determine the midpoint position within the target area as an available midpoint position.

[0069] Optionally, in the above embodiment, the processing module 803 is specifically used to perform clustering operations on all midpoint positions by using a clustering algorithm to obtain cluster points; and determine the cluster points as available midpoint positions.

[0070] Optionally, the determination module 802 is also used to determine the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line based on the position data of the first lane line and the second lane line; the processing module 803 is specifically used to connect the available midpoint positions in sequence with the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line as the starting point.

[0071] Optionally, the processing module 803 is specifically used to take the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line as the starting point, and sequentially use the midpoint position closest to the previous midpoint position as the next midpoint position, thereby connecting the available midpoint positions in sequence.

[0072] Optionally, the determination module 802 is further configured to, for each midpoint position, determine the elevation data of the two lane positioning points closest to the midpoint position; and determine the elevation data of the midpoint position according to the average of the elevation data of the two lane positioning points closest to the midpoint position.

[0073] Fig. 9 This is a schematic diagram of the structure of Embodiment 2 of the lane centerline determination device provided by the present invention. Fig. 9 The lane centerline determination device shown in FIG. Figure 8 On the basis of the illustrated embodiment, it also includes: a curve determination module 901; wherein the acquisition module 801 is also used to acquire the centerline data of the first lane and the centerline data of the second lane, the first lane and the second lane being lanes connected to the same target road turning point in the map data; the curve determination module 901 is used to determine the first endpoint in the centerline data of the first lane that is closest to the target road turning point, and the second endpoint in the centerline data of the second lane that is closest to the target road turning point; the curve determination module 901 is also used to obtain a connection curve with the first endpoint and the second endpoint through the Hermite curve equation based on the first endpoint and the second endpoint, and the connection curve is used to connect the centerline data of the first lane and the centerline data of the second lane.

[0074] The lane centerline determination device provided in this embodiment can be used to execute the lane centerline determination method shown in the above-mentioned embodiment. Its implementation method and principle are the same and will not be repeated here.

[0075] The present invention also provides an electronic device, comprising: a processor, a memory and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor, and the computer program includes instructions for executing the method described in any of the aforementioned embodiments.

[0076] The present invention also provides a storage medium storing a computer program. When the computer program is executed on a computer, the computer executes the method described in any one of the above embodiments.

[0077] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a lane centerline, characterized in that: include: Acquire position data of a first lane line and a second lane line located on both sides of a target lane in the map data, wherein the position data includes a position of at least one positioning point; Determine in sequence the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line; Determining an available midpoint position from all midpoint positions; the available midpoint position is determined based on a target area enclosed by a connecting line between end points of the first lane line and the second lane line in the same direction, or determined by a clustering algorithm; Determining lane centerline data of the target lane according to the available midpoint position; Acquire centerline data of a first lane and centerline data of a second lane, wherein the first lane and the second lane are lanes connected to a turning point of the same target road in the map data; Determine a first endpoint in the centerline data of the first lane that is closest to the turning point of the target road, and a second endpoint in the centerline data of the second lane that is closest to the turning point of the target road; According to the first endpoint and the second endpoint, a connection curve with endpoints being the first endpoint and the second endpoint is obtained by using a Hermite curve equation, and the connection curve is used to connect the centerline data of the first lane and the centerline data of the second lane.

2. The method according to claim 1, characterized in that Determining lane centerline data of the target lane according to the available midpoint position includes: The available midpoint positions are connected in sequence to obtain lane centerline data of the target lane.

3. The method according to claim 2, characterized in that The step of determining the available midpoint position from all midpoint positions comprises: Determine a target area surrounded by a connecting line between end points of the first lane line and the second lane line in the same direction according to the position data of the first lane line and the position data of the second lane line; A midpoint position within the target area is determined as the available midpoint position.

4. The method according to claim 2, characterized in that: The step of determining the available midpoint position from all midpoint positions comprises: Perform clustering operations on all midpoint positions through a clustering algorithm to obtain cluster points; The cluster point is determined to be the available midpoint position.

5. The method according to claim 2, characterized in that: Before connecting the available midpoint positions in sequence, the method further includes: Determine the midpoint of a connecting line between starting points of the first lane line and the second lane line according to the position data of the first lane line and the second lane line; The step of sequentially connecting the available midpoint positions comprises: The available midpoint positions are connected in sequence, taking the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line as the starting point.

6. The method according to claim 5, characterized in that Starting from the midpoint of the connecting line between the starting points of the first lane line and the second lane line, the available midpoints are sequentially connected, including: Taking the midpoint position of the connecting line between the starting ends of the first lane line and the second lane line as the starting point, the midpoint position closest to the previous midpoint position is sequentially used as the next midpoint position, so as to sequentially connect the available midpoint positions.

7. The method according to claim 1, characterized in that After sequentially determining the midpoint position of the connecting line between each positioning point of the first lane line and all positioning points of the second lane line, the method further includes: For each of the midpoint positions, determining the elevation data of the two lane positioning point positions closest to the midpoint position; The elevation data of the midpoint position is determined according to the average of the elevation data of the two lane positioning point positions that are closest to each other.

8. A device for determining a lane centerline, characterized in that: include: An acquisition module, used for acquiring position data of a first lane line and a second lane located on both sides of a target lane in map data, wherein the position data includes at least one positioning point position; A determination module, used to sequentially determine the midpoint position of the connection line between each positioning point of the first lane line and all positioning points of the second lane line; determine an available midpoint position from all midpoint positions; the available midpoint position is determined based on a target area surrounded by the connection lines between the first lane line and the end points of the second lane line in the same direction, or is determined by a clustering algorithm; A processing module, configured to determine lane centerline data of the target lane according to the available midpoint position; The acquisition module is further used to acquire centerline data of a first lane and centerline data of a second lane, wherein the first lane and the second lane are lanes connected to a turn of the same target road in the map data; a curve determination module, configured to determine a first endpoint in the centerline data of the first lane that is closest to the turning point of the target road, and a second endpoint in the centerline data of the second lane that is closest to the turning point of the target road; The curve determination module is also used to obtain, according to the first endpoint and the second endpoint, a connection curve with endpoints being the first endpoint and the second endpoint through a Hermite curve equation, wherein the connection curve is used to connect the centerline data of the first lane and the centerline data of the second lane.

Images