Lane line data processing method and device and storage medium

Abstract

The invention discloses a lane line data processing method and device and a storage medium. The method comprises the steps of obtaining a plurality of lane line segments; taking the lane line segments as nodes, and searching father nodes corresponding to the nodes; the set membership among the nodes represents the connection condition among the nodes; and based on the set membership between the nodes, connecting the plurality of lane segments to obtain at least one lane line. According to the scheme, the lane line can be obtained through automatic connection, manual participation is reduced, and working efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a lane line data processing method, device and storage medium. Background Art

[0002] In the field of autonomous driving, lane lines need to be identified through neural network models, so large-scale lane line data is required as model training data. The scale of model training data is large, and the efficiency of manual labeling is low. How to improve the efficiency of obtaining lane lines has become an urgent problem to be solved. Summary of the invention

[0003] The present application at least provides a lane line data processing method, device and storage medium.

[0004] The present application provides a lane line data processing method, including: obtaining multiple lane line segments; using the lane line segments as nodes and searching for the parent nodes corresponding to each node; the parent-child relationship between the nodes represents the connection status between the nodes; based on the parent-child relationship between the nodes, connecting the multiple lane line segments to obtain at least one lane line.

[0005] The present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory, and when the program instructions are executed by the processor, any of the above methods is implemented.

[0006] The present application provides a computer-readable storage medium on which program instructions are stored. When the program instructions are executed by a processor, any of the above methods is implemented.

[0007] In the above scheme, lane segments are taken as nodes, and the parent nodes corresponding to each node are searched to characterize the connection between the nodes. Based on the parent-child relationship between the nodes, multiple lane segments are connected to obtain at least one lane line. This can identify the parent-child relationship between nodes and automatically connect them to obtain lane lines, thereby reducing manual participation and improving work efficiency.

[0008] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0010] Figure 1 This is a flow chart of an embodiment of a lane line data processing method of the present application;

[0011] Figure 2is a flowchart of another embodiment of step S120 of the present application;

[0012] Figure 3 is a schematic diagram of another embodiment of the lane line data processing method in the present application;

[0013] Figure 4 is a schematic diagram of another embodiment of the lane line data processing method in the present application;

[0014] Figure 5 is a schematic diagram of another embodiment of the lane line data processing method in the present application;

[0015] Figure 6 is a schematic diagram of another embodiment of the lane line data processing method in the present application;

[0016] Figure 7 is a schematic diagram of another embodiment of the lane line data processing method in the present application;

[0017] Figure 8 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application;

[0018] Fig. 9 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0019] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0020] In the following description, for the purpose of explanation rather than limitation, specific details such as specific subsystem structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0021] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0022] See also Figure 1 , Figure 1 1 is a flow chart of an embodiment of a lane line data processing method of the present application. Specifically, the method may include:

[0023] Step S110: Acquire multiple lane line segments.

[0024] It is understandable that the above lane line segments may be obtained through manual annotation. Each lane line segment has two endpoints, and the position information of the two endpoints is known.

[0025] Furthermore, a lane has a vehicle travel direction, and accordingly, a lane segment has a direction, which may be consistent with the vehicle travel direction of the corresponding lane. A lane segment has a first end and a second end, or may be respectively referred to as a head end and a tail end, and the direction of the lane segment may be from the second end to the first end.

[0026] Step S120: Take the lane line segment as a node and search for the parent node corresponding to each node.

[0027] It can be understood that each lane segment can be represented by a node.

[0028] Each node is regarded as a child node, and its corresponding parent node is determined. The parent-child relationship between nodes represents the connection between nodes.

[0029] In some embodiments, one end of the child node segment is connected to one end of the parent node segment, so that the parent-child relationship between nodes can indicate that the corresponding segments are connected. Of course, the above connection judgment conditions can be set according to actual application needs. For example, the connection condition can be used as a condition for judging whether it is connected. Specifically, the connection condition can include that the distance between the two endpoints is less than a preset distance threshold.

[0030] In some embodiments, a child node may be consistent with a parent node, which may indicate that one end of the node is not connected to other line segments.

[0031] In some embodiments, the connection mode between the parent node and the child node can be fixed, so that the parent-child relationship between the nodes can also characterize the connection order between the nodes. For example, the first end of the child node is connected to the second end of the parent node. Exemplarily, there are two ways to connect node A and node B. The first is that node A is the parent node and node B is the child node. The second is that node B is the parent node and node A is the child node. In the first connection mode, the first end of B is connected to the second end of A, and the direction of the lane line is from B to A. In the second connection mode, the first end of A is connected to the second end of B, and the direction of the lane line is from A to B.

[0032] Step S130: Based on the parent-child relationship between nodes, multiple lane line segments are connected to obtain at least one lane line.

[0033] The parent-child relationship between nodes can represent the connection status between the nodes. Based on this, it can be determined which line segments are connected and how they are connected among all the line segments, so that at least one lane line can be obtained by connecting multiple lane line segments.

[0034] In the above steps, each node can determine its parent node.

[0035] In the above scheme, lane segments are taken as nodes, and the parent nodes corresponding to each node are found to characterize the connection between the nodes. Based on the parent-child relationship between the nodes, multiple lane segments are connected to obtain at least one lane line. This can identify the parent-child relationship between nodes and automatically connect them to obtain a complete lane line, reducing manual participation and improving work efficiency.

[0036] See also Figure 2 , Figure 2 1 is a flow chart of another embodiment of step S120 of the present application. Specifically, step S120 may include:

[0037] Step S221: Select a node to be checked corresponding to the first current node from other nodes except the first current node.

[0038] Among them, each node can be used as the first current node in turn.

[0039] In some embodiments, after a node is determined as the first current node, other nodes after the node can be selected as nodes to be checked corresponding to the first current node. It is understandable that the method of selecting the nodes to be checked can be set according to actual application needs.

[0040] Step S222: Based on the position information of both ends of the first current node and the node to be checked, determine whether there is an association relationship between the first current node and the node to be checked.

[0041] The association relationship includes a connection relationship, which may indicate that the line segments corresponding to two nodes are sequentially connected, that is, the first end of a node line segment is connected to the second end of another node line segment.

[0042] It is understandable that each lane segment can be manually marked on the point cloud map or obtained by other means. The position information of the two endpoints of each lane segment and the direction information of the lane segment are known information. Whether the lane segments are connected can be determined based on the position information of the endpoints.

[0043] In some embodiments, based on the position information of the first end of the first current node and the second end of the node to be checked, and / or the position information of the second end of the first current node and the first end of the node to be checked, it can be determined whether there is a connection relationship between the first current node and the node to be checked. The above correspond to two connection modes respectively.

[0044] In some implementation scenarios, whether the two endpoints are connected can be determined based on whether the two endpoints meet a connection condition. If the connection condition is met, it is determined that there is a connection relationship between the two nodes, and if the connection condition is not met, it is determined that there is no connection relationship between the two nodes. The connection condition may include that the distance between the two endpoints is less than a preset distance threshold.

[0045] In a specific application scenario, when a first end of one of the first current node and the node to be checked and a second end of the other satisfy a connection condition, it is determined that there is a connection relationship between the node to be checked and the first current node.

[0046] Step S223: Determine the parent node of each node based on the association relationship between the nodes.

[0047] The parent node of each node is determined, that is, the parent-child relationship between all nodes is determined. When a node is a child node, its parent node can be itself or another node.

[0048] It should be noted that the above method of selecting the node to be checked and the method of determining the connection relationship may be related.

[0049] In some implementation scenarios, if two connection modes are determined for the first current node and each node to be checked respectively, all nodes can be sorted in sequence. After a node is determined to be the first current node, other nodes after the node can be selected as the nodes to be checked corresponding to the first current node.

[0050] In a specific application scenario, there are n nodes in total. The i-th node is selected as the first current node, and the i+1-th node to the n-th node are sequentially selected as the corresponding nodes to be checked. It is determined whether the first end of the first current node and the second end of each node to be checked meet the connection condition, and it is determined whether the second end of the first current node and the first end of each node to be checked meet the connection condition. In this way, the possibility of sequential connection of all nodes can be traversed.

[0051] In some implementation scenarios, if a connection method is determined between the first current node and each node to be checked, all nodes can be sorted in sequence. After a node is determined as the first current node, all nodes other than this node can be used as nodes to be checked corresponding to the first current node.

[0052] In a specific application scenario, there are n nodes in total, the i-th node is selected as the first current node, and the n-1 nodes except the i-th node are sequentially used as corresponding nodes to be checked. Determine whether the first end of the first current node and the second end of each node to be checked meet the connection condition, or determine whether the second end of the first current node and the first end of each node to be checked meet the connection condition. It should be noted that for node A and node B, there are two connection methods, one is from A to B, and the other is from B to A. One is to determine whether such a connection exists when A is the first current node and B is the node to be checked, and the other is to determine whether such a connection exists when B is the first current node and A is the node to be checked.

[0053] In some embodiments, based on the association relationship between nodes, determining the parent node of each node may include: when there is a connection relationship between two nodes, two node segments are connected in sequence, and the first end of one node is connected to the second end of the other node. The node participating in the connection at the first end is determined as a child node, and the node participating in the connection at the second end is determined as the corresponding parent node. In this way, the parent node of a node is determined.

[0054] In some embodiments, before determining the parent node of each node based on the association relationship between nodes, the parent nodes of all nodes may be initialized. Initialization may be to use each node as its own parent node, so that all node segments are independent of each other. Then, adjustments are made based on the initial value according to the association relationship between nodes.

[0055] See also Figure 3 , Figure 3 It is a schematic diagram of another embodiment of the lane line data processing method in the present application.

[0056] To simplify the problem, Figure 3 In the default, the line segments are in the same direction. Each lane line segment is a node. Take node 0 and node 1 as an example. The first end of node 0 is connected to the second end of node 1. There is a connection relationship between node 0 and node 1, between node 2 and node 3, and between node 3 and node 4. The same applies to other nodes.

[0057] Specifically, the parent node of node 0 is node 1, the parent node of node 2 is node 3, and the parent node of node 3 is node 4.

[0058] In some embodiments, the association relationship may also include a confluence relationship, which may indicate that the line segments corresponding to two nodes converge at the same end. Specifically, the first ends of the two node line segments may be connected, or the second ends of the two node line segments may be connected.

[0059] Furthermore, it may also be determined whether there is a convergence relationship between the first current node and the node to be checked.

[0060] In some embodiments, whether two nodes have a confluence relationship can be determined based on the position information of the same end of the two node segments. In some cases, whether two nodes have a confluence relationship can also be determined by whether they have the same parent node or the same child node.

[0061] In some embodiments, the merging relationship can be further divided into two types. The first type of merging relationship is merging at the second end, and the second type of merging relationship is merging at the first end.

[0062] See also Figure 4 , Figure 4 It is a schematic diagram of another embodiment of the lane line data processing method in the present application.

[0063] like Figure 4 As shown, Figure 4 5 lane line segments are shown, which are denoted as 173, 132, 138, 98, and 103. Among them, 132 and 138 merge at their second ends. Figure 4 The shown type of confluence relationship is a first type of confluence relationship. It is understandable that multiple line segments may converge at one point, and any two of them may be judged to have a confluence relationship.

[0064] See also Figure 5 , Figure 5 It is a schematic diagram of another embodiment of the lane line data processing method in the present application.

[0065] like Figure 5 As shown, Figure 5 4 lane line segments are shown, which are denoted as 166, 95, 125, and 90. Among them, 95 and 125 merge at their first ends. Figure 5 The type of confluence relationship shown is a second type of confluence relationship.

[0066] In some embodiments, it is possible to determine whether the first current node and the node to be checked satisfy a connection condition based on the location information of the same end between the two nodes. If the connection condition is satisfied, it can be considered that there is a convergence relationship between the two nodes.

[0067] In a specific application scenario, when the second end of the first current node and the second end of the node to be checked meet a connection condition, it can be determined that a first type of convergence relationship exists between the first current node and the node to be checked.

[0068] In a specific application scenario, when the first end of the first current node and the first end of the node to be checked meet the connection condition, it can be determined that a second type of convergence relationship exists between the first current node and the node to be checked.

[0069] like Figure 4 As shown, according to the connection relationship, node 132 and node 138 are both parent nodes of node 173. Figure 5 As shown, according to the connection relationship, node 95 and node 125 are both child nodes of node 90.

[0070] In some embodiments, the parent-child relationship can be set to be one-to-one, that is, a child node can only have one parent node, and a parent node can only have one child node. Figure 4 For the first type of confluence relationship shown, two nodes with the first type of confluence relationship cannot be the parent nodes of other nodes. Take these two nodes as the first target nodes. If there is a first end of a second target node that meets the connection condition with the second end of any first target node, since the first target node cannot be the parent node, the second target node can be its own parent node.

[0071] For example Figure 5 For the second type of confluence relationship shown, the two nodes with the second type of confluence relationship cannot be child nodes of other nodes. These two nodes are used as the third target nodes. If the second end of a fourth target node and the first end of any third target node can meet the connection conditions, the third target node can be its own parent node.

[0072] The above confluence relationship can be treated as a special case. That is, on the basis that the above special case does not exist, if there is a connection relationship between two nodes, the parent-child relationship can be determined for the two nodes according to the connection relationship.

[0073] In some implementation scenarios, when there is a connection relationship between two nodes, and the nodes participating in the connection at the second end of the two nodes do not have a first-type confluence relationship, and the nodes participating in the connection at the first end do not have a second-type confluence relationship, the node participating in the connection at the second end serves as the parent node, and the node participating in the connection at the first end serves as the corresponding child node.

[0074] The first type of confluence relationship that the second end participates in connecting the node may be a confluence relationship existing with other nodes. The second type of confluence relationship that the first end participates in connecting the node is similar.

[0075] In some embodiments, if a node is not searched for its subsequent connected nodes, such as Figure 4 Node 98 and node 103 in , their parent node can be itself, indicating that their first end is not connected to another line segment, and the first end of this line segment can be used as an endpoint of a lane line. Figure 5Node 90 in.

[0076] like Figure 4 In the application scenario shown, the parent node of node 173 is node 173 , the parent node of node 132 is node 98 , the parent node of node 138 is node 103 , the parent node of node 98 is node 98 , and the parent node of node 103 is node 103 .

[0077] like Figure 5 In the application scenario shown, the parent node of node 90 is node 90 , the parent node of node 95 is node 95 , the parent node of node 125 is node 125 , and the parent node of node 166 is node 125 .

[0078] It should be noted that the multiple lane segments obtained may include lane segments in different directions. However, since the lane segments in different directions are a certain distance apart in actual scenarios, they are usually not considered to be associated when confirming the association relationship. Therefore, this part is simplified in the drawings provided in the embodiments of the present application, and only the segments in the same direction are used as examples.

[0079] In a specific application scenario, each node can be traversed through a for loop. Specifically, the association relationship between each node and all other nodes can be determined through two layers of for loops.

[0080] In a specific application scenario, each node is traversed, and for each node, the parent node and child node of the node are searched in the corresponding node to be checked, and it is determined whether there is a confluence relationship between the node and other nodes. If a new confluence relationship is found, the parent node of the adjacent node can be adjusted according to the node disposal method corresponding to the confluence relationship. Specifically, two nodes with a first type of confluence relationship are used as the first target node; when the first end of the second target node and the second end of any first target node meet the connection condition, the second target node is used as its own parent node; two nodes with a second type of confluence relationship are used as the third target node, and when the second end of the fourth target node and the first end of any third target node meet the connection condition, the third target node is used as its own parent node. And a mark bit can be set to indicate the existing confluence relationship. Determine whether the parent-child relationship is determined for the two nodes with a connection relationship based on the determined connection relationship and the existing confluence relationship.

[0081] In a specific application scenario, each node is traversed, and for each node, the parent node of the node is searched in other nodes. The number of nodes connected to the node can be recorded. If the node is connected to multiple nodes at the same time, these multiple nodes cannot be used as parent nodes. After the traversal is completed, it is determined whether there are multiple nodes corresponding to the same parent node. In this case, these multiple nodes cannot be used as child nodes, and the parent nodes of these multiple nodes need to be adjusted to themselves.

[0082] In some embodiments, based on the parent-child relationship between nodes, connecting multiple lane line segments to obtain at least one lane line may include: finding the root node corresponding to each node, selecting all nodes corresponding to the same root node, and connecting the corresponding lane line segments in sequence according to the parent-child relationship between the nodes to obtain a lane line.

[0083] The root node of a node can be found by searching for the parent node from the node until the parent node is found to be a node of the node itself. The lane line segments corresponding to all nodes belonging to the same root node can be connected together to form a lane line.

[0084] In some embodiments, each node is used as the fifth target node, and the fifth target node is used as the second current node to find the parent node of the second current node. If the parent node of the second current node is the same as the second current node, then the second current node is directly used as the root node of the fifth target node. Figure 4 When the node 98 in is the second current node, its parent node is itself, so it can be determined to be the root node of node 98. Figure 5 When node 90 in is used as the second current node, its parent node is itself, so it can be determined to be the root node of node 90.

[0085] If the parent node of the second current node is different from the second current node, the parent node of the second current node is used as the second current node again until the parent node of the second current node is found to be the same as the second current node, and the second current node at this time is used as the root node corresponding to the fifth target node. Figure 4 Node 132 in the example, when it is used as the second current node, its parent node is node 98. Node 98 is used as the second current node again, and its parent node is itself. Therefore, it can be determined that the second current node at this time, that is, node 98, can be used as the root node corresponding to the fifth target node, that is, node 132.

[0086] like Figure 3In the application scenario shown, node 1 and node 0 both correspond to root node 1, and node 2, node 3, and node 4 all correspond to root node 4. All nodes corresponding to the same root node are connected in sequence according to the parent-child relationship to obtain a complete lane line. The above nodes constitute two lane lines, lane line 1 is line segment 0 and line segment 1, and lane line 2 is line segment 2, line segment 3, and line segment 4.

[0087] In some specific application scenarios, all child nodes corresponding to the same root node can be saved together to indicate that they constitute the same lane line. And the order of saving can be determined according to the parent-child relationship to indicate the order of connection of each line segment.

[0088] See also Figure 6 , Figure 6 It is a schematic diagram of another embodiment of the lane line data processing method in the present application.

[0089] like Figure 6 As shown, Figure 6 There are 4 lane segments, labeled 5-8. The direction of the segments is shown in the figure. In the process of finding the root node corresponding to each node, there is a Figure 6 In the special case shown, after the second current node is redetermined at least once, the fifth target node is found as the parent node of the second current node, which means that the parent nodes are searched forward from the fifth target node in sequence, and then returned to the fifth target node, forming a loop.

[0090] In this case, all the historical second current nodes corresponding to the fifth target node at this time can be used to combine them in sequence according to the parent-child relationship between the nodes to form a lane line loop.

[0091] like Figure 6 As shown, the parent node corresponding to node 5 is node 6, the parent node corresponding to node 6 is node 7, the parent node corresponding to node 7 is node 8, and the parent node corresponding to node 8 is node 5. Nodes 5-8 are used to form a lane line loop.

[0092] See also Figure 7 , Figure 7 It is a schematic diagram of another embodiment of the lane line data processing method in the present application.

[0093] like Figure 7 As shown, the device can display a two-dimensional image and a corresponding point cloud map to the user, so that the user can mark lane segments on the point cloud map. The multiple lane segments marked by the user can be used to implement the lane line data processing method in this application, so as to combine the lane line segments marked by the user into a complete lane line.

[0094] In some implementation scenarios, in the field of autonomous driving, lane lines need to be identified through neural networks, so large-scale lane line data is required as training data. The lane line data processing method provided in the embodiment of the present application can merge manually marked segmented lines into one line. Thereby providing instance-level training data for subsequent neural networks. (Instance level, that is, a line should not be divided into many segments).

[0095] In some implementation scenarios, the device can provide the user with a segmented two-dimensional image and a corresponding point cloud map. For example, a 50-meter-long road segment two-dimensional image and a point cloud map are provided for the user to mark. The user can manually mark both bidirectional lanes of this section of the road. All lane line segments in the marking results of multiple road segments are used as the multiple lane line segments mentioned in the above embodiment.

[0096] In some embodiments, laser radar point cloud and inertial measurement (IMU) data can be obtained, and the laser radar point cloud and inertial measurement data can be processed using a laser SLAM (Simultaneous Localization and Mapping) algorithm to obtain a point cloud map. The point cloud map and the corresponding two-dimensional image are provided to the user for viewing so that the user can mark the line segments.

[0097] See also Figure 8 , Figure 8 It is a schematic diagram of the framework of an embodiment of the electronic device of the present application.

[0098] The electronic device 80 includes a memory 81 and a processor 82. The processor 82 is used to execute program instructions stored in the memory 81 to implement the steps in any of the above lane line data processing method embodiments. In a specific implementation scenario, the electronic device 80 may include, but is not limited to: computer equipment, power equipment, microcomputers, desktop computers, servers, and in addition, the electronic device 80 may also include mobile devices such as laptops and tablet computers, which are not limited here.

[0099] Specifically, the processor 82 is used to control itself and the memory 81 to implement the steps in any of the above-mentioned lane line data processing method embodiments. The processor 82 can also be called a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip with signal processing capabilities. The processor 82 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 82 can be implemented by an integrated circuit chip.

[0100] See also Fig. 9 , Fig. 9 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application.

[0101] The computer-readable storage medium 90 provided in this embodiment stores program instructions 91 that can be executed by a processor. When the program instructions 91 are executed by the processor, they are used to implement the steps in any of the above lane line data processing method embodiments.

[0102] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as units or components can be combined or integrated into another subsystem, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0104] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A lane line data processing method, characterized in that: The method comprises: Get multiple lane segments; The lane line segments are taken as nodes, and the parent nodes corresponding to the nodes are searched; the parent-child relationship between the nodes represents the connection between the nodes; Based on the parent-child relationship between the nodes, the multiple lane line segments are connected to obtain at least one lane line.

2. The method according to claim 1, characterized in that The lane segment has a first end and a second end; the direction of the lane segment is from the second end to the first end; The searching for the parent node corresponding to each of the nodes comprises: Taking each of the nodes as a first current node, and selecting a node to be checked corresponding to the first current node from other nodes except the first current node; Based on the location information of both ends of the first current node and the node to be checked, determining whether there is an association relationship between the first current node and the node to be checked, wherein the association relationship includes a connection relationship; Based on the association relationship between the nodes, the parent node of each node is determined.

3. The method according to claim 2, characterized in that The determining whether there is an association relationship between the first current node and the node to be checked based on the location information of both ends of the first current node and the node to be checked includes: When the first end of one of the first current node and the node to be checked and the second end of the other meet the connection condition, it is determined that the connection relationship exists between the node to be checked and the first current node; wherein the connection condition includes that the distance between the two endpoints is less than a preset distance threshold.

4. The method according to claim 2, characterized in that: The association relationship further includes a confluence relationship; and the determining whether there is an association relationship between the first current node and the node to be checked based on the position information of both ends of the first current node and the node to be checked further includes: When the second end of the first current node and the second end of the node to be checked meet a connection condition, determining that the first current node and the node to be checked have a first type of confluence relationship, wherein the first type of confluence relationship indicates confluence at the second end; When the first end of the first current node and the first end of the node to be checked meet a connection condition, it is determined that the first current node and the node to be checked have a second type of merging relationship, and the second type of merging relationship indicates merging at the first end.

5. The method according to claim 2, characterized in that: The association relationship also includes a confluence relationship; the confluence relationship includes a first type of confluence relationship and a second type of confluence relationship, the first type of confluence relationship indicates confluence at the second end, and the second type of confluence relationship indicates confluence at the first end; The determining the parent node of each node based on the association relationship between the nodes includes: In the case where the connection relationship exists between the two nodes, and the nodes that the second end participates in the connection do not have a first type of convergence relationship, and the nodes that the first end participates in the connection do not have a second type of convergence relationship, determining that the node that the second end participates in the connection is a parent node, and the node that the first end participates in the connection is a corresponding child node; The two nodes having the first type of confluence relationship are taken as first target nodes; when the first end of the second target node and the second end of any one of the first target nodes meet the connection condition, the second target node is taken as its own parent node; The two nodes having the second type of confluence relationship are taken as third target nodes, and when the second end of the fourth target node meets a connection condition with the first end of any of the third target nodes, the third target node is taken as its own parent node.

6. The method according to claim 1, characterized in that The step of connecting the plurality of lane line segments to obtain at least one lane line based on the parent-child relationship between the nodes comprises: Find the root node corresponding to each of the nodes; All the nodes corresponding to the same root node are selected, and the corresponding lane line segments are sequentially connected according to the parent-child relationship between the nodes to obtain one lane line.

7. The method according to claim 6, characterized in that The step of searching for the root node corresponding to each of the nodes comprises: Taking each of the nodes as a fifth target node, taking the fifth target node as a second current node, and searching for a parent node of the second current node; If the parent node of the second current node is the same as the second current node, taking the second current node as the root node of the fifth target node; If the parent node of the second current node is different from the second current node, the parent node of the second current node is re-used as the second current node until the parent node of the second current node is found to be the same as the second current node, and the second current node at this time is used as the root node corresponding to the fifth target node.

8. The method according to claim 7, characterized in that The method further comprises: After the second current node is re-determined, when the fifth target node is found as the parent node of the second current node, all the second current nodes in history are combined in sequence according to the parent-child relationship between the nodes to form a lane line loop.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores program instructions, and when the program instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images