CN113160351A

CN113160351A - Lane line segmentation method and device and electronic equipment

Info

Publication number: CN113160351A
Application number: CN202010075344.4A
Authority: CN
Inventors: 荆晓阳; 何云燕
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2020-01-22
Filing date: 2020-01-22
Publication date: 2021-07-23

Abstract

The embodiment of the invention provides a lane line segmentation method, a lane line segmentation device and electronic equipment. The method comprises the following steps: based on the manufacturing data of the lane line segments, organizing the head nodes and the tail nodes of the lane line segments belonging to the same lane line together to obtain the lane line data of the lane line consisting of the head nodes and the tail nodes; acquiring lane line matching results and node matching results of any two lane lines with the same driving direction based on lane line data of the lane lines; dividing the lane lines belonging to the same road surface into a group based on the lane line matching result of the lane lines; and determining a cross section for segmenting a road surface formed by the group of lane lines based on the node matching result of the lane lines in each group, wherein the part of the road surface between two adjacent cross sections forms a section of the road surface.

Description

Lane line segmentation method and device and electronic equipment

Technical Field

The present application relates to the field of electronic map technologies, and in particular, to a lane line segmentation method, apparatus, and electronic device.

Background

At present, an electronic map is evolving from a common electronic map with lower precision to a high-precision map, and the high-precision map can be understood as an electronic map with precision meeting the precision standard required by automatic driving or advanced assistant driving or other scenes. At present, the process of making high-precision maps still depends on manual work, for example, an operator completes the making of lane line type and attribute. With the gradual maturity of technologies required by application scenes based on high-precision maps, how to improve the manufacturing efficiency and quality of the high-precision maps becomes a core problem.

It should be noted that the above background description is only for the sake of clarity and complete description of the technical solutions of the present invention and for the understanding of those skilled in the art. Such solutions are not considered to be known to the person skilled in the art merely because they have been set forth in the background section of the invention.

Disclosure of Invention

In order to solve the above problems or similar problems, embodiments of the present invention provide a lane line segmentation method, a lane line segmentation device, and an electronic device, which can automatically segment a lane line, and improve the manufacturing efficiency and quality of a high-precision map.

According to a first aspect of embodiments of the present invention, there is provided a lane line segmentation method, including: based on the manufacturing data of the lane line segments, organizing the head nodes and the tail nodes of the lane line segments belonging to the same lane line together to obtain the lane line data of the lane line consisting of the head nodes and the tail nodes; acquiring lane line matching results and node matching results of any two lane lines with the same driving direction based on lane line data of the lane lines; dividing the lane lines belonging to the same road surface into a group based on the lane line matching result of the lane lines; and determining a cross section for segmenting a road surface formed by the group of lane lines based on the node matching result of the lane lines in each group, wherein the part of the road surface between two adjacent cross sections forms a section of the road surface.

According to a second aspect of embodiments of the present invention, there is provided a lane line segmenting device including: a lane line data acquisition unit that organizes a head node and a tail node of a lane line segment belonging to the same lane line together based on the production data of the lane line segment to obtain lane line data of the lane line composed of the head node and the tail node; a matching unit that obtains lane line matching results and node matching results for any two lane lines having the same traveling direction based on lane line data of the lane lines; a grouping unit that divides the lane lines belonging to the same lane surface into a group based on a lane line matching result of the lane lines; and the segmenting unit is used for determining a cross section for segmenting a road surface formed by the group of lane lines based on the node matching result of the lane lines in each group, wherein one section with the same number of lanes in the road surface is positioned between two adjacent cross sections.

According to a third aspect of embodiments of the present invention, there is provided an electronic device comprising the apparatus according to the second aspect described above.

The embodiment of the invention has the beneficial effects that the lane line can be automatically segmented, and the manufacturing efficiency and quality of the high-precision map are improved.

Specific embodiments of the present invention are disclosed in detail with reference to the following description and drawings, indicating the manner in which the principles of the invention may be employed. It should be understood that the embodiments of the invention are not so limited in scope. The embodiments of the invention include many variations, modifications and equivalents within the spirit and scope of the appended claims.

Features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments, in combination with or instead of the features of the other embodiments.

It should be emphasized that the term "comprises/comprising" when used herein, is taken to specify the presence of stated features, integers, steps or components but does not preclude the presence or addition of one or more other features, integers, steps or components.

Drawings

The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

fig. 1 is a schematic view of a lane line segmentation method according to embodiment 1 of the present invention.

Fig. 2 is a schematic view of a lane line and a lane segment according to embodiment 1 of the present invention.

Fig. 3 is a schematic diagram of an implementation manner of step 101 in embodiment 1 of the present invention.

Fig. 4 is a schematic diagram of an implementation manner of step 103 in embodiment 1 of the present invention.

Fig. 5 is a schematic diagram of an implementation manner of step 401 in embodiment 1 of the present invention.

Fig. 6 is a schematic diagram of an implementation manner of step 105 in embodiment 1 of the present invention.

Fig. 7 is a schematic diagram of an implementation manner of step 107 in embodiment 1 of the present invention.

Fig. 8 is a schematic diagram of an implementation manner of step 109 in embodiment 1 of the present invention.

Fig. 9 is a schematic diagram of an implementation manner of step 803 in embodiment 1 of the present invention.

Fig. 10 is a schematic view of a lane line segmenting device according to embodiment 2 of the present invention.

Fig. 11 is a schematic diagram of a lane line data acquisition unit according to embodiment 2 of the present invention.

Fig. 12 is a schematic diagram of a matching unit of embodiment 2 of the present invention.

Fig. 13 is a schematic diagram of a matching node pair obtaining unit according to embodiment 2 of the present invention.

Fig. 14 is a schematic diagram of a matching result determining unit of embodiment 2 of the present invention.

Fig. 15 is a schematic diagram of a grouping unit of embodiment 2 of the present invention.

Fig. 16 is a schematic diagram of a segmentation unit of embodiment 2 of the present invention.

Fig. 17 is a schematic view of an electronic device according to embodiment 3 of the present invention.

Detailed Description

The foregoing and other features of the invention will become apparent from the following description taken in conjunction with the accompanying drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the embodiments in which the principles of the invention may be employed, it being understood that the invention is not limited to the embodiments described, but, on the contrary, is intended to cover all modifications, variations, and equivalents falling within the scope of the appended claims.

Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.

In the embodiments of the present invention, the terms "first", "second", and the like are used for distinguishing different elements by name, but do not denote a spatial arrangement, a temporal order, or the like of the elements, and the elements should not be limited by the terms. The term "and/or" includes any and all combinations of one or more of the associated listed terms.

In embodiments of the invention, the singular forms "a", "an", and the like include the plural forms and are to be construed broadly as "a" or "an" and not limited to the meaning of "a" or "an"; furthermore, the term "comprising" should be understood to include both the singular and the plural, unless the context clearly dictates otherwise. Further, the term "according to" should be understood as "at least partially according to … …," and the term "based on" should be understood as "based at least partially on … …," unless the context clearly dictates otherwise.

It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present. Other words used to describe the relationship between elements (e.g., "between" versus "directly between", "adjacent" versus "directly adjacent to", etc.) should be interpreted in a similar manner.

It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.

Various embodiments of the present invention will be described below with reference to the drawings. These embodiments are merely exemplary and are not intended to limit embodiments of the present invention.

Example 1

This embodiment 1 provides a lane line segmentation method. Fig. 1 is a schematic view of the lane line segmentation method of the present embodiment.

As shown in fig. 1, the method includes:

step 101, based on the making data of the lane line segment, organizing a head node and a tail node of the lane line segment belonging to the same lane line together to obtain the lane line data of the lane line consisting of the head node and the tail node;

103, acquiring lane line matching results and node matching results of any two lane lines with the same driving direction based on lane line data of the lane lines;

105, dividing the lane lines belonging to the same road surface into a group based on the lane line matching result of the lane lines;

and step 107, determining a cross section for segmenting a road surface formed by the set of lane lines based on the node matching result of the lane lines in each set, wherein the part of the road surface between two adjacent cross sections forms a section of the road surface.

In the present embodiment, a lane segment is a segment of a lane line having a common attribute. The common attribute may include, for example, a common curvature range, a common number of lanes, etc. The production data of the lane segments is data for acquiring the lane segments, which can be generated by a worker performing rough manual interruption of the lane lines in the collected raw road data.

Fig. 2 is a schematic diagram of the lane line and the lane line segment of the present embodiment. As shown in fig. 2, each lane line 201 may be divided into at least two

lane segments

201a, 201 b. The lane line segment 201a is a straight line segment, namely the curvature is zero, and the number of lanes in the lane line segment 201a is kept unchanged by 3 lanes; the lane segment 201b is a curved segment with a curvature within a certain range, and the number of lanes in the lane segment 201b is kept constant at 3.

In addition, in the present embodiment, each lane line segment has a leading node constituting a start point of the lane line and a trailing node constituting an end point of the lane line. For example, as shown in fig. 2, in the leftmost lane line 201, the lane line segment 201a has the head node a1 and the tail node a2, and the lane line segment 201B has the head node B1 and the tail node B2, and then the head node and the tail node of the lane line segments 201a and 201B belonging to the same lane line are organized, specifically, the head node B1 of the following lane line segment 201B and the tail node a2 of the preceding lane line segment 201a are overlapped in the traveling direction of the lane, and the head node and the tail node of the lane line segment can be organized as described above with respect to the other lane lines on the right side, whereby lane line data composed of the head node and the tail node can be obtained.

By the method, the lane line can be automatically segmented based on the existing lane line manufacturing data, so that the manufacturing requirement on the lane line manufacturing data can be reduced, and the manufacturing efficiency and quality of the high-precision map are improved.

Fig. 3 is a schematic diagram of an implementation manner of step 101 of this embodiment. As shown in fig. 3, the step 101 may include:

301, acquiring topologically communicated lane segments based on the making data of the lane segments;

and 303, organizing a head node and a tail node of the lane line segment belonging to the same lane line in the topologically communicated lane line segments together to obtain lane line data of the lane line consisting of the head node and the tail node.

In step 301, a lane line graph in graph theory may be constructed based on the data for making lane line segments, and topologically connected lane line segments may be obtained based on the lane line graph. The lane line segment map is a directed map. Wherein, constructing the lane line segment diagram may include: and obtaining nodes in the lane line segment graph and connectivity and communication directions among the nodes based on the making data of the lane line segment, and generating edges in the lane line segment graph according to the connectivity and communication directions among the nodes. This enables a directional lane segment map to be constructed. Two nodes that spatially satisfy a certain condition may be considered to be the same node, e.g., two virtual nodes whose spatial distance is less than a prescribed threshold may be considered to be the same pseudo-node.

Fig. 4 is a schematic diagram of an implementation manner of step 103 of the present embodiment. As shown in fig. 4, the step 103 may include:

step 401, obtaining matching node pairs between any two lane lines with the same driving direction based on nodes included in lane line data of the lane lines;

step 403, determining lane line matching results and node matching results of the two lane lines with the same driving direction based on the matching node pairs between the two lane lines with the same driving direction.

Here, any two lane lines having the same traveling direction means two lane lines having the same traveling direction, which are arbitrarily selected from all the lane lines. By acquiring the matching node pairs between the lane lines with the same driving direction, the node matching between the lane lines with different driving directions is avoided, and the lane lines with different driving directions are prevented from being divided into the same group.

Fig. 5 is a schematic diagram of an implementation manner of step 401 of the present embodiment. As shown in fig. 5, the step 401 may include:

step 501, projecting any first node included in the lane line data of any one lane line of any two lane lines with the same driving direction to the other lane line to obtain a projection point;

step 503, determining the distance between the projection point and each second node included in the lane line data of the other lane line;

step 505, the arbitrary first node and the second node that minimizes the distance are determined as a matching node pair.

After the steps 501-505 are performed on any two lane lines with the same driving direction in all lane lines, the step 401 may further include: if any second node is included in the at least two matching node pairs, keeping the matching node pair with the minimum distance in the at least two matching node pairs according to the distance corresponding to the at least two matching node pairs respectively, and deleting the remaining matching node pairs in the at least two matching node pairs. Therefore, only one pairing between the nodes is reserved, and the situation of one pairing and more nodes is avoided.

Fig. 6 is a schematic diagram of an implementation manner of step 105 of the present embodiment. As shown in fig. 6, the step 105 may include:

601, obtaining lane line matching results of any two lane lines with the same driving direction based on lane line data of the lane lines;

step 603, obtaining node matching results of any two lane lines with the same driving direction based on lane line data of the lane lines.

The obtaining of the lane line matching result of any two lane lines with the same driving direction based on the lane line data of the lane lines may include:

acquiring the number of matching node pairs between any two lane lines with the same driving direction;

and if the number of the matching node pairs is more than 1, determining any two lane lines with the same driving direction as a mutual matching.

Thus, the result of determining whether any two lane lines with the same driving direction are matched with each other is the lane line matching result.

In addition, obtaining the node matching result of any two lane lines with the same driving direction based on the lane line data of the lane lines may include:

and taking the matching node pair between any two lane lines with the same driving direction as the node matching result of any two lane lines with the same driving direction.

Fig. 7 is a schematic diagram of an implementation of step 107 of this embodiment. As shown in fig. 7, the step 107 may include:

step 701, determining whether any two lane lines with the same driving direction belong to the same road surface based on whether any two lane lines with the same driving direction are matched with each other;

and 703, dividing all the lane lines which belong to the same road surface and have the same driving direction into a group based on whether any two lane lines which have the same driving direction belong to the same road surface.

In step 701, when the two arbitrary lane lines in the same driving direction are matched with each other, it is determined that the two arbitrary lane lines in the same driving direction belong to the same lane surface, and when the two arbitrary lane lines in the same driving direction are not matched with each other, it is determined that the two arbitrary lane lines in the same driving direction do not belong to the same lane surface.

In this embodiment, the step 703 may include:

determining all lane lines belonging to the same road surface and having the same driving direction according to the following rules: if the first lane line and the second lane line which are the same in the driving direction belong to the same road surface, and the second lane line and the third lane line which are the same in the driving direction belong to the same road surface, the first lane line, the second lane line and the third lane line belong to the same road surface;

all lane lines belonging to the same road surface and having the same driving direction are divided into a group.

By the above rule, the coplanar relationship between any two lane lines can be converted into the coplanar relationship between a plurality of lane lines, whereby all the lane lines belonging to the same road surface and having the same traveling direction can be divided into the same group.

Fig. 8 is a schematic diagram of an implementation manner of step 109 of the present embodiment. As shown in fig. 8, the step 109 may include:

step 801, determining a potential cross section based on the node matching result of the lane lines in each group;

and 803, determining the cross section with the optimal linear fitting in the potential cross sections as an optimal cross section, and performing loss deduction based on the optimal cross section so as to determine the cross section for segmenting the road surface formed by the group of lane lines from the potential cross sections.

In this embodiment, the step 801 may include:

determining a potential cross section containing the matching node pairs for each matching node pair of the lane lines in each group;

the potential cross sections are integrated according to the following rules: and if the first matching node pair and the second matching node pair contain a common node, merging the potential cross section corresponding to the first matching node pair and the potential cross section corresponding to the second matching node pair into the same potential cross section.

In this embodiment, the potential cross section is a plane that includes the matching node pair and is perpendicular to the road surface where the lane line group corresponding to the matching node pair is located.

Through the rules, the overlapping relation between the potential cross sections corresponding to the multiple matching nodes can be obtained based on the concurrent relation between any two matching node pairs, and therefore the overlapping potential cross sections can be merged.

Fig. 9 is a schematic diagram of an implementation manner of step 803 of the present embodiment. As shown in fig. 8, the step 109 may include:

in this embodiment, the step 803 may include:

step 901, configuring all the potential cross sections determined in step 801 into an unretraversed state;

step 903, determining the cross section with the optimal linear fitting in the potential cross sections which are not traversed as the optimal cross section;

step 905, performing loss deduction based on the optimal cross section until a termination condition of the loss deduction is met (i.e. a condition that the loss deduction cannot be continued), thereby obtaining at least one selected cross section, wherein the loss deduction traverses at least a part of the potential cross sections, and configures the at least part of the potential cross sections as traversed;

step 907, determining whether a potential cross section which is not traversed exists; if the potential cross section which is not traversed exists, returning to the step 903, otherwise, executing the step 909;

all selected cross sections obtained are determined to be cross sections for segmenting the road surface made up of the set of lane lines, step 909.

In this way, it is finally possible to traverse all potential cross sections and obtain all cross sections within each lane line group for segmenting the road surface constituted by the set of lane lines.

In the

above step

803 or 903, for example, a cross section with the best linear fit among the potential cross sections, that is, a potential cross section with the smallest error among the potential cross sections, may be obtained based on a linear fit formula and a corresponding error formula.

Specifically, the linear fitting formula may be, for example:

f(x，y，z)＝a+b(x，z，y) (1)

the error formula may be, for example:

where a, b are linear fitting coefficients, m is the number of sample points for each potential cross-section, f (x, y, z) is the fitted result, and Q (a, b) is the calculated error.

In addition, in the embodiment, the specific implementation manner of the churn deduction may refer to the prior art.

By the lane line segmentation method, the lane line can be automatically segmented, and the manufacturing efficiency and quality of the high-precision map are improved.

Example 2

This embodiment 2 provides a lane line grouping device. The same contents of this embodiment as those of embodiment 1 are not repeated, and the following description explains the differences of this embodiment from embodiment 1.

Fig. 10 is a schematic view of the lane line segmenting device of the present embodiment. As shown in fig. 10, the lane line segmenting device 1000 includes a lane line data acquiring unit 1001, a matching unit 1002, a grouping unit 1003, and a segmenting unit 1004.

The lane line data acquisition unit 1001 organizes the head node and the tail node of a lane line segment belonging to the same lane line together based on the production data of the lane line segment to obtain lane line data of the lane line composed of the head node and the tail node; the matching unit 1002 obtains lane line matching results and node matching results of any two lane lines having the same driving direction based on lane line data of the lane lines; the grouping unit 1003 divides the lane lines belonging to the same lane surface into a group based on the lane line matching result of the lane lines; the segmenting unit 1004 determines a cross section for segmenting a road surface constituted by the set of lane lines, a portion of the road surface between two adjacent cross sections constituting a segment of the road surface, based on the node matching result of the lane lines in each set.

Fig. 11 is a schematic diagram of the lane line data acquisition unit of the present embodiment. As shown in fig. 11, the lane line data acquisition unit 1001 may include a lane line segment acquisition unit 1101 and an organization unit 1102. The system comprises a lane line segment acquisition unit, a topology communication unit and a topology communication unit, wherein the lane line segment acquisition unit is used for acquiring a topology communication lane line segment based on the manufacturing data of the lane line segment; the organizing unit 1102 organizes the head node and the tail node of the lane line segment belonging to the same lane line in the topologically connected lane line segments together to obtain the lane line data of the lane line composed of the head node and the tail node.

Fig. 12 is a schematic diagram of the matching unit of the present embodiment. As shown in fig. 12, the matching unit 1002 may include a matching node pair obtaining unit 1201 and a matching result determining unit 1202. The matching node pair obtaining unit obtains matching node pairs between any two lane lines in the same driving direction based on nodes included in lane line data of the lane lines; the matching result determination unit 1202 determines the lane line matching result and the node matching result of the two lane lines having the same traveling direction based on the matching node pair between the two lane lines having the same traveling direction.

Fig. 13 is a schematic diagram of the matching node pair obtaining unit according to the present embodiment. As shown in fig. 13, the matching node pair obtaining unit 1201 may include a projection unit 1301, a distance determining unit 1302, and a matching node pair determining unit 1303. The projection unit 1301 projects any first node included in the lane line data of any one of the two lane lines with the same driving direction to the other lane line to obtain a projection point; the distance determining unit 1302 determines the distance between the projection point and each second node included in the lane line data of the other lane line; the matching-node-pair determining unit 1303 determines the arbitrary first node and the second node that minimizes the distance as a matching node pair.

In this embodiment, the matching node pair obtaining unit 1201 further retains, when any second node is included in the at least two matching node pairs, the matching node pair with the smallest distance in the at least two matching node pairs according to the distances corresponding to the at least two matching node pairs, and deletes the remaining matching node pairs in the at least two matching node pairs.

Fig. 14 is a schematic diagram of the matching result determination unit of the present embodiment. As shown in fig. 14, the matching result determination unit 1202 may include a lane line matching result determination unit 1401 and a node matching result determination unit 1402. The lane line matching result determining unit 1401 determines the lane line matching result of any two lane lines having the same driving direction, and the node matching result determining unit 1402 determines the lane line matching result of any two lane lines having the same driving direction.

In this embodiment, the lane line matching result determining unit 1401 may acquire the number of matching node pairs between any two lane lines having the same driving direction; when the number of the matching node pairs is greater than 1, the two lane lines having the same traveling direction are determined to match each other. The node matching unit determination unit 1402 may take a matching node pair between the arbitrary two lane lines whose traveling directions are the same as a node matching result of the arbitrary two lane lines whose traveling directions are the same.

Fig. 15 is a schematic diagram of the grouping unit of the present embodiment. As shown in fig. 15, the grouping unit 1003 may include a determination unit 1501 and a division unit 1502. The determination unit 1501 determines whether any two lane lines having the same driving direction belong to the same lane surface based on whether any two lane lines having the same driving direction match with each other; the dividing unit 1502 divides all the lane lines belonging to the same road surface and having the same driving direction into one group based on whether any two lane lines having the same driving direction belong to the same road surface.

In the present embodiment, the determination unit 1501 may determine all the lane lines belonging to the same road surface and having the same traveling direction according to the following rule: if the first lane line and the second lane line which are the same in the driving direction belong to the same road surface, and the second lane line and the third lane line which are the same in the driving direction belong to the same road surface, the first lane line, the second lane line and the third lane line belong to the same road surface; and, all lane lines belonging to the same road surface and having the same driving direction are divided into one group.

Fig. 16 is a schematic diagram of the segmentation unit of the present embodiment. As shown in fig. 16, the segmentation unit 1004 may include a potential cross-plane determination unit 1601 and a segmentation cross-plane determination unit 1602. The potential cross section determining unit 1601 determines a potential cross section based on a node matching result of the lane lines in each group; the segmentation transverse plane determining unit 1602 determines the transverse plane with the best linear fit among the potential transverse planes as the optimal transverse plane, and performs loss deduction based on the optimal transverse plane, thereby determining the transverse plane for segmenting the road plane formed by the set of lane lines from the potential transverse planes.

In this embodiment, the potential cross section determining unit 1601 may determine, for each matching node pair of the lane lines in each group, a potential cross section containing the matching node pair; and, integrating the potential cross-sections according to the following rules: and if the first matching node pair and the second matching node pair contain a common node, merging the potential cross section corresponding to the first matching node pair and the potential cross section corresponding to the second matching node pair into the same potential cross section.

In this embodiment, the segmentation cross section determination unit 1602 may perform the following steps: configuring the determined potential cross sections into an unrotated state; determining the cross section with the optimal linear fitting in the potential cross sections which are not traversed as the optimal cross section; performing a churn deduction based on the optimal cross section until a termination condition of the churn deduction is satisfied (i.e., a condition that the churn deduction cannot be continued), thereby obtaining at least one selected cross section, the churn deduction traversing at least a portion of the potential cross sections and configuring the at least a portion of the potential cross sections as traversed; and judging whether the potential cross section which is not traversed exists, if so, returning to the step, determining the cross section which is the optimal cross section in the potential cross sections which are not traversed and is subjected to linear fitting as the optimal cross section, and continuing to execute the step, otherwise, determining all the obtained selected cross sections as the cross sections which are used for segmenting the road surface formed by the group of lane lines.

Through the lane line grouping device of this embodiment, can carry out the segmentation to the lane line automatically, promote the preparation efficiency and the quality of high-accuracy map.

Example 3

Embodiment 3 provides an electronic apparatus. The same contents of this embodiment as those of embodiment 1 or embodiment 2 are not repeated, and the following description explains the differences between this embodiment and embodiments 1 and 2.

Fig. 17 is a schematic diagram of the electronic apparatus of the present embodiment. As shown in fig. 17, an electronic device 1700 may include: a processor 1701 and a memory 1702, the memory 1702 coupled to the processor 1701.

Among them, the memory 1702 may store a program for realizing a certain function, for example, a program for realizing the lane line segmentation method of embodiment 1, and the program is executed under the control of the processor 1701; in addition, the memory 1702 may also store various data such as making data of lane line segments, lane line data, lane line matching results and node matching results, lane line grouping results and segmentation results, and the like.

In one embodiment, the functions in the lane line segmentation apparatus of example 2 may be integrated into the processor 1701 for execution.

In this embodiment, the processor 1701 may be configured to:

based on the manufacturing data of the lane line segments, organizing the head nodes and the tail nodes of the lane line segments belonging to the same lane line together to obtain the lane line data of the lane line consisting of the head nodes and the tail nodes;

acquiring lane line matching results and node matching results of any two lane lines with the same driving direction based on lane line data of the lane lines;

dividing the lane lines belonging to the same road surface into a group based on the lane line matching result of the lane lines;

and determining a cross section for segmenting a road surface formed by the group of lane lines based on the node matching result of the lane lines in each group, wherein the part of the road surface between two adjacent cross sections forms a section of the road surface.

In this embodiment, the processor 1701 may be configured to:

obtaining topologically communicated lane segments based on the making data of the lane segments;

and organizing the head nodes and the tail nodes of the lane line segments belonging to the same lane line in the topologically communicated lane line segments together to obtain the lane line data of the lane line consisting of the head nodes and the tail nodes.

In this embodiment, the processor 1701 may be configured to:

acquiring a matching node pair between any two lane lines with the same driving direction based on nodes included in lane line data of the lane lines;

and determining lane line matching results and node matching results of any two lane lines with the same driving direction based on the matching node pairs between any two lane lines with the same driving direction.

In this embodiment, the processor 1701 may be configured to:

projecting any first node included in the lane line data of any one of the two lane lines with the same driving direction to the other lane line to obtain a projection point;

determining a distance between the projection point and each second node included in the lane line data of the other lane line;

determining the arbitrary first node and the second node that minimizes the distance as a matching node pair.

In this embodiment, the processor 1701 may be configured to:

if any second node is included in the at least two matching node pairs, according to the distances respectively corresponding to the at least two matching node pairs, keeping the matching node pair with the minimum distance in the at least two matching node pairs, and deleting the remaining matching node pairs in the at least two matching node pairs.

In this embodiment, the processor 1701 may be configured to:

determining whether any two lane lines with the same driving direction belong to the same road surface based on whether any two lane lines with the same driving direction are matched with each other;

and dividing all the lane lines which belong to the same road surface and have the same driving direction into a group based on whether any two lane lines which have the same driving direction belong to the same road surface.

In this embodiment, the processor 1701 may be configured to:

determining all lane lines belonging to the same road surface and having the same driving direction according to the following rules: if a first lane line and a second lane line which are the same in driving direction belong to the same road surface, and a second lane line and a third lane line which are the same in driving direction belong to the same road surface, the first lane line, the second lane line and the third lane line belong to the same road surface;

In this embodiment, the processor 1701 may be configured to:

determining a potential cross section based on the node matching result of the lane lines in each group;

and determining the cross section with the optimal linear fitting in the potential cross sections as the optimal cross section, and performing loss deduction based on the optimal cross section, thereby determining the cross section for segmenting the road surface formed by the group of lane lines from the potential cross sections.

In this embodiment, the processor 1701 may be configured to:

integrating the potential cross sections according to the following rules: and if the first matching node pair and the second matching node pair contain a common node, merging the potential cross section corresponding to the first matching node pair and the potential cross section corresponding to the second matching node pair into the same potential cross section.

In this embodiment, the processor 1701 may be configured to:

configuring the determined potential cross sections into an unrotated state; determining the cross section with the optimal linear fitting in the potential cross sections which are not traversed as the optimal cross section; performing a churn deduction based on the optimal cross section until a termination condition of the churn deduction is satisfied (i.e., a condition that the churn deduction cannot be continued), thereby obtaining at least one selected cross section, the churn deduction traversing at least a portion of the potential cross sections and configuring the at least a portion of the potential cross sections as traversed; and judging whether the potential cross section which is not traversed exists, if so, returning to the step, determining the cross section which is the optimal cross section in the potential cross sections which are not traversed and is subjected to linear fitting as the optimal cross section, and continuing to execute the step, otherwise, determining all the obtained selected cross sections as the cross sections which are used for segmenting the road surface formed by the group of lane lines.

In this embodiment, the electronic device 1700 may be a user device, such as a personal computer or the like. Furthermore, the electronic device 1700 may also be a network device, such as a single network server, a server group of multiple network servers, or a Cloud Computing (Cloud Computing) -based Cloud of numerous computers or network servers, wherein Cloud Computing is one type of distributed Computing, a super virtual computer consisting of a collection of loosely coupled computers. The computer equipment can run independently to realize the application, and can also be accessed to the network to realize the application through the interactive operation with other computer equipment in the network. The network where the computer is located includes the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

It should be noted that the user equipment, the network device, the network and the like are only examples, and other existing or future computer devices or networks may also be included in the scope of the present application if applicable.

Through the electronic equipment of this embodiment, can carry out the segmentation to the lane line automatically, promote the preparation efficiency and the quality of high-accuracy map.

The embodiment of the invention also provides a program readable by a processor, and the program enables the processor to execute the method in the embodiment of the invention.

The embodiment of the invention also provides a storage medium stored with a program readable by a processor, wherein the program enables the processor to execute the method in the embodiment of the invention.

The above methods/apparatuses of the present invention may be implemented by hardware, or may be implemented by hardware in combination with software. The present invention relates to a computer-readable program which, when executed by a logic section, enables the logic section to realize the above-described apparatus or constituent section, or to realize the above-described various methods or steps. Logic components such as field programmable logic components, microprocessors, processors used in computers, and the like. The present invention also relates to a storage medium such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, or the like, for storing the above program.

The methods/apparatus described in connection with the embodiments of the invention may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. For example, one or more of the functional block diagrams and/or one or more combinations of the functional block diagrams illustrated in fig. 10 may correspond to individual software modules of a computer program flow or may correspond to individual hardware modules. These software modules may correspond to the various steps shown in fig. 1, respectively. These hardware modules may be implemented, for example, by solidifying these software modules using a Field Programmable Gate Array (FPGA).

A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium; or the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The software module may be stored in the memory of the device or in a memory card that is insertable into the device. For example, if the apparatus employs a relatively large capacity MEGA-SIM card or a large capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large capacity flash memory device.

One or more of the functional blocks and/or one or more combinations of the functional blocks described in the figures can be implemented as 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 device, discrete gate or transistor logic, discrete hardware components, or any suitable combination thereof designed to perform the functions described herein. One or more of the functional blocks and/or one or more combinations of the functional blocks described in connection with the figures may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP communication, or any other such configuration.

The present application has been described in conjunction with specific embodiments, but it should be understood by those skilled in the art that these descriptions are intended to be illustrative, and not limiting. Various modifications and adaptations of the present application may occur to those skilled in the art based on the teachings herein and are within the scope of the present application.

Claims

1. A method of segmenting a lane line, comprising:

2. The method of claim 1, wherein organizing a head node and a tail node of a lane segment belonging to the same lane line together based on production data of the lane segment to obtain lane line data of the lane line composed of the head node and the tail node comprises:

3. The method according to claim 1, wherein obtaining lane line matching results and node matching results for any two lane lines having the same driving direction based on lane line data of the lane lines comprises:

4. The method according to claim 3, wherein obtaining a matching node pair between any two lane lines in the same driving direction based on nodes included in lane line data of the lane lines comprises:

5. The method according to claim 4, wherein obtaining a matching node pair between any two lane lines in the same traveling direction based on nodes included in lane line data of the lane lines further comprises:

6. The method according to any one of claims 3 to 5, wherein determining lane line matching results of any two lane lines having the same driving direction based on pairs of matching nodes between the any two lane lines having the same driving direction comprises:

7. The method according to any one of claims 3 to 5, wherein determining the node matching result of any two lane lines with the same driving direction based on the matching node pair between any two lane lines with the same driving direction comprises:

8. The method of claim 6, wherein dividing lane lines belonging to the same road surface into a group based on a lane line matching result of the lane lines comprises:

9. The method of claim 8, wherein dividing all lane lines belonging to the same road surface and having the same driving direction into a group based on whether any two lane lines having the same driving direction belong to the same road surface comprises:

10. The method of claim 1, wherein determining a cross-section for segmenting a road surface formed by the set of lane lines based on the node matching results for the lane lines in each set comprises:

11. The method of claim 10, wherein obtaining the node matching result of any two lane lines having the same driving direction based on the lane line data of the lane lines comprises:

taking the matching node pair between any two lane lines with the same driving direction as the node matching result of any two lane lines with the same driving direction,

determining a potential cross section based on the node matching results of the lane lines in each group, including:

12. A lane line segmenting device, wherein the device comprises:

a lane line data acquisition unit that organizes a head node and a tail node of a lane line segment belonging to the same lane line together based on the production data of the lane line segment to obtain lane line data of the lane line composed of the head node and the tail node;

a matching unit that obtains lane line matching results and node matching results for any two lane lines having the same traveling direction based on lane line data of the lane lines;

a grouping unit that divides the lane lines belonging to the same lane surface into a group based on a lane line matching result of the lane lines;

and the segmenting unit is used for determining a cross section for segmenting a road surface formed by the set of lane lines on the basis of the node matching result of the lane lines in each set, wherein the part of the road surface between two adjacent cross sections forms one section of the road surface.

13. An electronic device comprising the apparatus of claim 12.