Method and System for Synchronously Processing Multi-Scene High-Precision Map Images

Abstract

The present invention discloses a method and system for synchronously processing a multi-scenario high-precision map image, which preliminarily determines the ground object association relationship in the high-precision map image; classifies the roads in the high-precision map image according to a preset scenario road classification rule, and retrieves corresponding scenario processing modules to process the ground objects in the classified scenarios respectively; combines and stores the processed data of different scenarios in the form of a dictionary, and re-determines the ground object association relationship in the high-precision map image to update the ground object association relationship in the high-precision map image; thereby realizing the unified synchronous processing of multiple scenarios included in the high-precision map image, improving the processing efficiency of the high-precision map; and for a new scenario, only an independent scenario processing module needs to be added, which has universality.

Description

Technical Field

[0001] The present invention relates to high-precision map production technology, and particularly to a method and system for synchronously processing high-precision map images including multiple scenarios. Background Art

[0002] High-precision electronic maps mainly serve autonomous driving vehicles, providing lane-level planning within road segments and self-vehicle positioning assistance for autonomous driving vehicles. Different from traditional navigation electronic maps, high-precision electronic maps not only provide high-precision road and lane information, but also provide a large amount of ground object information, such as traffic signs, traffic lights, static obstacles, crosswalks, etc. These ground object information helps to assist autonomous driving decision-making and improve the autonomous driving experience. In the road classification of high-precision electronic maps, roads will be divided into multiple scenarios according to road categories, such as highways, urban expressways, general roads (urban roads), AVP (parking lot roads), ports, etc. Roads in these different scenarios will have their own processing and output standards, but at the boundaries of scenarios, it is relatively complex due to involving multiple scenarios, especially in areas where different scenarios interact, such as intersections, diverging and converging points, and interchanges. Traditional methods for processing different scenarios use different tools, and the multi-scenario edge connection can only be processed sequentially according to single scenarios, with low efficiency. Therefore, it is necessary to provide a method and system for synchronously processing high-precision map images including multiple scenarios. Summary of the Invention

[0003] The purpose of the present invention is to overcome the above technical deficiencies, and propose a method and system for synchronously processing high-precision map images including multiple scenarios, so as to solve the problem that the multi-scenario edge connection can only be processed sequentially according to single scenarios, with low efficiency.

[0004] To achieve the above technical purpose, the first aspect of the technical solution of the present invention provides a method for synchronously processing high-precision map images including multiple scenarios, which includes the following steps:

[0005] Preliminarily determine the ground object association relationship in the high-precision map image;

[0006] Based on the preset scenario road classification rules, classify the roads in the high-precision map image, and call the corresponding scenario processing modules to process the ground objects in the classified scenarios respectively;

[0007] Merge and store the processed data of different scenarios in the form of a dictionary, and re-determine the ground object association relationship in the high-precision map image to update the ground object association relationship in the high-precision map image.

[0008] The second aspect of the present invention provides a system for synchronously processing high-precision map images including multiple scenarios, which includes the following functional modules:

[0009] A preliminary judgment module for preliminarily determining the association relationship of ground objects in a high-precision map image;

[0010] A classification processing module for classifying roads in a high-precision map image based on preset scene road classification rules, and invoking corresponding scene processing modules to process the ground objects in the classified scenes respectively;

[0011] A merging and updating module for merging and storing the processed data of different scenes in the form of a dictionary, and re-determining the association relationship of ground objects in the high-precision map image to update the association relationship of ground objects in the high-precision map image.

[0012] A third aspect of the present invention provides a server, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above method for synchronously processing a high-precision map image including multiple scenes is implemented.

[0013] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above method for synchronously processing a high-precision map image including multiple scenes is implemented.

[0014] Compared with the prior art, the method and system for synchronously processing a high-precision map image including multiple scenes according to the present invention preliminarily determine the association relationship of ground objects in the high-precision map image; classify the roads in the high-precision map image based on preset scene road classification rules, and invoke corresponding scene processing modules to process the ground objects in the classified scenes respectively; merge and store the processed data of different scenes in the form of a dictionary, and re-determine the association relationship of ground objects in the high-precision map image to update the association relationship of ground objects in the high-precision map image; thereby realizing unified synchronous processing of multiple scenes included in the high-precision map image, improving the processing efficiency of the high-precision map; and only need to add a processing module for an independent scene for a new scene, which has universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flowchart of the method for synchronously processing a high-precision map image including multiple scenes according to an embodiment of the present invention;

[0016] Figure 2 is a schematic diagram of a self-intersecting road being interrupted;

[0017] Figure 3 is a block diagram of the modules of the system for synchronously processing a high-precision map image including multiple scenes according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0019] As Figure 1 shown, an embodiment of the present invention provides a method for synchronously processing a multi-scenario high-precision map image, which includes the following steps:

[0020] S1. Initially determine the object association relationship in the high-precision map image.

[0021] Display the two-dimensional map corresponding to the high-precision map through the interface. The user circles the required data range, required route range or required administrative division range on the two-dimensional map according to the requirements to form a high-precision map image.

[0022] Retrieve whether there is a self-intersecting road in the high-precision map image. If so, interrupt the self-intersecting road. If not, directly initially determine the object association relationship in the high-precision map image.

[0023] Specifically, when there is a self-intersecting road, retrieve the self-intersecting start point and self-intersecting end point of the self-intersecting road, select the midpoint of the road between the self-intersecting start point and the self-intersecting end point to interrupt the self-intersecting road, and form two non-self-intersecting roads at both ends. After all self-intersecting roads in the high-precision map image are interrupted, judge the association relationship between the ground object and the road network by calculating whether there is an overlap between the road section surface and the object, and comprehensively initially determine the object association relationship in the high-precision map image.

[0024] As Figure 2 shown, for the self-intersecting road L (non-spatially intersecting but intersecting in the plane projection), find A and B before and after the first intersection point along the road passing direction. If L is composed of [pt1, pt2,... ptn], traverse the shape points. When it is found that [pt1,... ptx] is self-intersecting, then A = pt(x - 1), B = ptx; then obtain its reverse line L_tmp according to the self-intersecting road L, and L_tmp is composed of [ptx,.., pt2, pt1]. Traverse along the passing direction. When it is found that [ptx,..pty] is self-intersecting, then C = pt(y - 1), D = pty; then the intersection point must be in the plane formed by A, B, C, D, and the break point is taken as pt = pt((x + y - 1) / 2), that is, the midpoint of A / D.

[0025] L is broken into L1 and L2, L1=[pt0, pt1, ... pt((x+y-1) / 2)], L2=[pt((x+y-1) / 2), ptn]; continue to traverse L2. If L2 has self-intersection, continue processing according to the above steps until traversing to ptn.

[0026] S2. Based on the preset scene road classification rules, the roads in the high-precision map image are classified, and the corresponding scene processing modules are called to process the objects in the classified scenes respectively.

[0027] That is, multiple scene processing modules are integrated into one image processing tool, and based on the preset scene road classification rules, the roads in the high-precision map image are classified, and then the corresponding scene processing modules are called to process the objects in the classified scene respectively.

[0028] In the process of scene classification of roads in high-precision map images based on preset scene road classification rules, if there is a feature that is associated with roads in multiple scenes at the same time, the reference information of the feature is retained in multiple scenes. For example, a guide strip A is associated with both the expressway rv1 and the ordinary road rv2. Guide strip A will be processed in both scenes, but there is actually only one guide strip A, but there are two references in the two scenes.

[0029] S3. The processed data of different scenes are merged and stored in the form of a dictionary, and the association relationship between the objects in the high-precision map image is re-determined, and the association relationship between the objects in the high-precision map image is updated.

[0030] First, the road network data of each scene are merged and stored in the form of a dictionary; for example, highway {rv1: rv1_info} and ordinary road {rv2: rv2_info} are merged into {rv1: rv1_info, rv2: rv2_info}.

[0031] The feature data of each scene are merged and stored in the form of a dictionary, and duplicate feature reference information is removed; for example, the highway feature is {obj1: obj1_info, obj2: obj2_info}, the general road feature is {obj2: obj2_info, obj3: obj3_info}, and obj2 is a feature shared by two scenes. After merging, it becomes {obj1: obj1_info, obj2: obj2_info, obj3: obj3_info}.

[0032] Merge and store the association relationships of each scene in dictionary form, and accumulate the association relationships of the same ground objects; for example, the highway ground object association relationship {rel1: <obj1, rv1>} and the general road {rel2: <obj2, rv2>} are merged into {rel1: <obj1, rv1>, rel2: <obj2, rv2>}.

[0033] Then, determine the overpass relationship according to whether the road surfaces cover each other, and generate an interchange point at the center of the covered area;

[0034] Recalculate whether there is coverage between the road section surface and the ground objects, and re-determine the ground object association relationship in the high-precision map image;

[0035] Delete and filter the ground objects that are not associated with the road section;

[0036] By retrieving whether there is a physical isolation facility in the middle of adjacent roads, establish the adjacency relationship of the corresponding road sections. The absence of a physical isolation facility indicates that vehicles can drive into adjacent roads in case of emergency.

[0037] The present invention preliminarily determines the ground object association relationship in the high-precision map image; classifies the roads in the high-precision map image based on the preset scene road classification rules, and invokes the corresponding scene processing modules to process the ground objects in the classified scenes respectively; merges and stores the data of different processed scenes in dictionary form, and re-determines the ground object association relationship in the high-precision map image to update the ground object association relationship in the high-precision map image; thereby realizing the unified synchronization processing of multiple scenes included in the high-precision map image, improving the processing efficiency of the high-precision map; and for new scenes, only need to add the processing module of the independent scene, which has universality.

[0038] As Figure 3 shown, the embodiment of the present invention also discloses a system for synchronously processing a high-precision map image containing multiple scenes, which includes the following functional modules:

[0039] The preliminary judgment module 10 is used to preliminarily determine the ground object association relationship in the high-precision map image;

[0040] The classification processing module 20 is used to classify the roads in the high-precision map image based on the preset scene road classification rules, and invoke the corresponding scene processing modules to process the ground objects in the classified scenes respectively;

[0041] The merging and updating module 30 is used to merge and store the data of different processed scenes in dictionary form, and re-determine the ground object association relationship in the high-precision map image to update the ground object association relationship in the high-precision map image.

[0042] The execution manner of the system for synchronously processing multi-scenario high-precision map images in this embodiment is basically the same as the method for synchronously processing multi-scenario high-precision map images described above, so it will not be elaborated in detail.

[0043] The server in this embodiment is a device that provides computing services, usually referring to a computer with relatively high computing power and provided to multiple consumers through a network. The server of this embodiment includes: a memory, a processor, and a system bus. The memory includes a runnable program stored thereon. Those skilled in the art can understand that the structure of the terminal device in this embodiment does not constitute a limitation on the terminal device, and it may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0044] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing of the terminal by running the software programs and modules stored in the memory. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the terminal (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0045] A runnable program for a method of synchronously processing multi-scenario high-precision map images is included in the memory. The runnable program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the process of information acquisition and implementation. The one or more modules / units can be a series of computer program instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program in the server. For example, the computer program can be divided into a preliminary judgment module 10, a classification processing module 20, and a merging and updating module 30.

[0046] The processor is the control center of the server, connecting various parts of the entire terminal device through various interfaces and lines. By running or executing software programs and / or modules stored in the memory, and by calling the data stored in the memory, it executes various functions of the terminal and processes data, thereby monitoring the terminal as a whole. Optionally, the processor may include one or more processing units; preferably, the processor may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor either.

[0047] The system bus is used to connect the internal functional components of a computer and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, VESA bus, etc. The instructions of the processor are transmitted to the memory through the bus, and the memory feeds back data to the processor. The system bus is responsible for the data and instruction interaction between the processor and the memory. Of course, the system bus can also be connected to other devices, such as network interfaces, display devices, etc.

[0048] The server should at least include a CPU, a chipset, memory, a disk system, etc. Other components will not be elaborated here.

[0049] In the embodiment of the present invention, the executable program executed by the processor included in the terminal is specifically: a method for synchronously processing multi-scenario high-precision map images, which includes the following steps:

[0050] Preliminarily determine the ground object association relationship in the high-precision map image;

[0051] Based on the preset scene road classification rules, classify the roads in the high-precision map image by scene, and call the corresponding scene processing modules to process the ground objects in the classified scenes respectively;

[0052] Merge and store the processed data of different scenes in the form of a dictionary, and re-determine the ground object association relationship in the high-precision map image to update the ground object association relationship in the high-precision map image.

[0053] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0054] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0055] Those of ordinary skill in the art can realize that the modules, units, and / or method steps of the embodiments described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0056] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for synchronously processing multi-scenario high-precision map images, characterized in that, It includes the following steps: Preliminarily determine the object association relationship in the high-precision map image; Based on the preset scene road classification rules, classify the roads in the high-precision map image by scene, and call the corresponding scene processing modules to process the objects in the classified scenes respectively; Merge and store the data of different processed scenes in the form of a dictionary, and re-determine the object association relationship in the high-precision map image to update the object association relationship in the high-precision map image; The merging and storing the data of different processed scenes in the form of a dictionary includes: Merge and store the road network data of each scene in the form of a dictionary; Merge and store the object data of each scene in the form of a dictionary, and eliminate duplicate object reference information; Merge and store the association relationships of each scene in the form of a dictionary, and accumulate the same object association relationships.

2. The method for synchronously processing multi-scenario high-precision map images according to claim 1, characterized in that, The preliminarily determining the object association relationship in the high-precision map image includes: Retrieve whether there are self-intersecting roads in the high-precision map image. If so, break the self-intersecting roads, and then preliminarily determine the object association relationship in the high-precision map image based on the road information after breaking; if not, directly preliminarily determine the object association relationship in the high-precision map image.

3. The method for synchronously processing multi-scenario high-precision map images according to claim 2, characterized in that, The breaking the self-intersecting roads and then preliminarily determining the object association relationship in the high-precision map image based on the road information after breaking includes: Retrieve the self-intersecting starting point and the self-intersecting ending point of the self-intersecting road, select the midpoint of the road between the self-intersecting starting point and the self-intersecting ending point to break the self-intersecting road, and form two non-self-intersecting roads at both ends; Judge the association relationship between the ground object and the road network by calculating whether there is an overlap between the road section plane and the object, and comprehensively preliminarily determine the object association relationship in the high-precision map image.

4. The method for synchronously processing multi-scenario high-precision map images according to claim 1, characterized in that, Before classifying the roads in the high-precision map image by scene based on the preset scene road classification rules, integrate multiple scene processing modules into an image processing tool.

5. The method for synchronously processing multi-scenario high-precision map images according to claim 1, characterized in that, During the process of classifying the roads in the high-precision map image by scene based on the preset scene road classification rules, if there is an object that is simultaneously associated with the roads in multiple scenes, retain the reference information of this object in multiple scenes.

6. The method for synchronously processing multi-scenario high-precision map images according to claim 1, characterized in that, The re-determining the object association relationship in the high-precision map image includes: Determine the interchange relationship according to whether the road surfaces overlap each other, and generate an interchange point at the center of the overlapping area; Recalculate whether there is an overlap between the road section plane and the object, and re-determine the object association relationship in the high-precision map image; Delete and filter the objects that are not associated with the road section; Establish the adjacency relationship of the corresponding road section by retrieving whether there is a physical isolation facility in the middle of adjacent roads.

7. A system for synchronously processing multi-scenario high-precision map images, characterized in that, It includes the following functional modules: A preliminary judgment module, which is used to preliminarily determine the object association relationship in the high-precision map image; A classification processing module, which is used to classify the roads in the high-precision map image by scene based on the preset scene road classification rules, and call the corresponding scene processing modules to process the objects in the classified scenes respectively; A merging and updating module, which is used to merge and store the processed data of different scenarios in the form of a dictionary, re-determine the object association relationships in the high-precision map image, and update the object association relationships in the high-precision map image; The merging and storing the processed data of different scenarios in the form of a dictionary includes: Merging and storing the road network data of each scenario in the form of a dictionary; Merging and storing the object data of each scenario in the form of a dictionary, and eliminating duplicate object reference information; Merging and storing the association relationships of each scenario in the form of a dictionary, and accumulating the same object association relationships.

8. A server, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for synchronously processing a high-precision map image including multiple scenarios as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for synchronously processing a high-precision map image including multiple scenarios as described in any one of claims 1 to 6.

Images