A crowdsourcing lane line fusion and update method and system

Abstract

The present invention provides a crowdsourcing lane line fusion and update method and system. The method includes: splitting the lane line data collected by crowdsourcing at a predetermined time interval; respectively merging the initial map and the lane line data of the time slices to obtain a lane line data set, and distributively performing lane line fusion optimization on each lane line data set, and using the fused lane line data as the update data of the initial map; when there is no initial map, distributively performing lane line fusion optimization on the lane line data of each time slice, and generating an initial map according to the lane line data after fusion optimization. Thus, distributed fusion processing can be realized, the performance requirements for a single computer are reduced, the fusion and update efficiency is improved, and the failure of the fusion and update process caused by single-task processing is avoided.

Description

Technical Field

[0001] The present invention belongs to the field of high-precision map making, and particularly relates to a crowdsourcing lane line fusion and update method and system. Background Art

[0002] In the process of high-precision map making, lane line point data on the road surface is usually required to draw lane maps and update existing lane maps. Generally, the cost of crowdsourcing collection and drawing is relatively low, and it is usually widely deployed to collect high-freshness data to improve the update frequency of high-precision maps.

[0003] However, the data volume collected by crowdsourcing is usually very large, and there will be a problem that the single-computer memory is not enough when processing lane line data and updating maps. Even if the hardware configuration is improved on a single computer, this problem cannot be effectively solved significantly, and there may be a failure due to insufficient memory of a single computer, resulting in the failure of the entire fusion and update processing process. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a crowdsourcing lane line fusion and update method and system for solving the problem of insufficient memory in the existing crowdsourcing lane line fusion processing.

[0005] In the first aspect of the embodiments of the present invention, a crowdsourcing lane line fusion and update method is provided, including:

[0006] Segmenting the lane line data collected by crowdsourcing at a predetermined time interval;

[0007] Respectively merging the initial map with the lane line data of the time slice to obtain a lane line data set, and performing distributed lane line fusion optimization on each lane line data set, and using the fused lane line data as the update data of the initial map;

[0008] When there is no initial map, perform distributed lane line fusion optimization on the lane line data of each time slice, and generate an initial map according to the lane line data after fusion optimization.

[0009] In the second aspect of the embodiments of the present invention, a crowdsourcing lane line fusion and update system is provided, including:

[0010] A time segmentation module for segmenting the lane line data collected by crowdsourcing at a predetermined time interval;

[0011] A fusion and update module for respectively merging the initial map with the lane line data of the time slice to obtain a lane line data set, performing distributed lane line fusion optimization on each lane line data set, and using the fused lane line data as the update data of the initial map;

[0012] A fusion generation module, which is used to perform lane line fusion optimization on the lane line data of each time slice in a distributed manner when there is no initial map, and generate an initial map according to the lane line data after fusion optimization.

[0013] In a third aspect of the embodiments of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect of the embodiments of the present invention are implemented.

[0014] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect of the embodiments of the present invention are implemented.

[0015] In the embodiments of the present invention, by reasonably dividing the crowdsourced lane line data at time intervals, the data is decentralized, and distributed data fusion is performed through time slice data, so that each fusion task processes a controllable small amount of data, avoiding insufficient memory of a single computer and avoiding a single task from performing all data processing. Thus, multi-computer distributed processing can be achieved, improving the processing efficiency, reducing the performance requirements for a single computer, and avoiding the failure of the fusion update process caused by single-task processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic flowchart of a crowdsourced lane line fusion update method provided by an embodiment of the present invention;

[0018] Figure 2 It is another schematic flowchart of a crowdsourced lane line fusion update method provided by an embodiment of the present invention;

[0019] Figure 3 It is a schematic structural diagram of a crowdsourced lane line fusion update system provided by an embodiment of the present invention;

[0020] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, features, and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

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

[0023] Please refer to Figure 1 , a flowchart of a crowdsourcing lane line fusion and update method provided by an embodiment of the present invention, including:

[0024] S101. Split the lane line data collected by crowdsourcing at a predetermined time interval;

[0025] The lane line data generally includes the point cloud data collected by an on-vehicle lidar, and the lane line data collected by crowdsourcing vehicles is split at a certain time interval.

[0026] Specifically, the collected lane line data is sorted in chronological order, and the data is equally divided according to a certain time interval threshold to obtain all time slice data, and the start and end times of each slice data are recorded.

[0027] Optionally, check the number of lane lines in the lane line data of each time slice. If the number of lane lines in the slice exceeds a certain threshold, according to the multiple relationship between the number of lane lines and the threshold, perform data splitting at a smaller time interval or equal division according to the number of lane lines, and record the start and end times of the split data.

[0028] S102. Respectively merge the initial map with the lane line data of the time slice to obtain a lane line data set, and distributively perform lane line fusion optimization on each lane line data set, and use the fused lane line data as the update data of the initial map;

[0029] Respectively merge the corresponding lane line data in the initial map with the lane line data of the time slice. In the merged data set, fuse and optimize the existing lane line data with the newly collected lane line slice data, and use the fused lane line as the map update.

[0030] Exemplarily, if there is already a first map, the lane line data in the first map is denoted as L0, and all time slice data is denoted as L1, L2, L3... L n ;

[0031] L0 is respectively merged with L1, L2, L3... L n to obtain new lane line data sets L′1, L′2, L′3... L′ n , and for each lane line ID in each merged data set, starting from 0, it is incremented by 1 in sequence to re - assign an ID number;

[0032] For each of the data sets L′1, L′2, L′3... L′ n perform a lane line fusion optimization once (for the fusion optimization method, refer to "A Fast Fusion Optimization Method for Multi - Road Segment Data of Crowdsourced Lane Line Data"), to obtain the fused lane line data L"1, L"2, L"3... L" n , and the new fused lane lines are the updates of the first map for multiple time slices.

[0033] Through a multi - task parallel execution framework such as a distributed program or multi - process processing, the distributed execution of lane line fusion optimization is realized.

[0034] Among them, set the weight values of the lane line data of the initial map and the time slices to control whether the map update focuses on the original data of the initial map or the newly collected crowdsourced data.

[0035] When merging data, different weights can be given to the two different data for merging to control whether the result of updating the first map favors the old data or the new data.

[0036] S103. When there is no initial map, the lane line data of each time slice is distributedly subjected to lane line fusion optimization, and an initial map is generated according to the fused lane line data.

[0037] When there is no initial map in a certain area, it is necessary to perform fusion optimization on the lane line data collected by crowdsourcing to obtain the corresponding lane lines.

[0038] Exemplarily, perform a lane line fusion optimization once on each of the data sets L1, L2, L3... L n to obtain the fused lane line data L"1, L"2, L"3... L" n , and the new fused lane lines are the fusion optimization results of the time slices for generating the first map.

[0039] In one embodiment, the lane line data after fusion optimization is merged, and an ID is reassigned to each lane line in the merged lane line dataset; the merged lane line dataset is further subjected to lane line fusion optimization to obtain a new lane line dataset as the initial map lane line.

[0040] Exemplarily, the obtained data L"1, L"2, L"3... L" n are merged to obtain a merged lane line dataset D. The ID of each lane line in each merged dataset is sequentially incremented by 1 starting from 0, and a new ID number is assigned; the dataset D is subjected to a lane line fusion optimization once to obtain a fused new lane line dataset D′, and D′ is the result of the time-slice-based lane line fusion update.

[0041] Among them, the above-mentioned lane line fusion optimization specifically is: fitting and optimizing the local shape points of the lane line to obtain a local lane line, combining the local lane line segments into an entire lane line, and processing the broken and incorrect connection parts of the lane line to obtain a lane line set.

[0042] In this embodiment, by reasonably dividing the time, the lane line data is dispersed. In each time slice, through sub-time fusion and re-fusion of the fusion results, each fusion process deals with a controllable small amount of data, so as to avoid insufficient memory of a single computer. When a single task executes all the data, it will cause insufficient memory and the task cannot be executed, improving the processing efficiency. And by setting the merging weight, the bias of the result can be controlled, which is convenient for adjusting the result.

[0043] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0044] Figure 3 FIG. 18 is a schematic structural diagram of a crowdsourcing lane line fusion update system provided by an embodiment of the present invention. The system includes:

[0045] A time slicing module 310, configured to slice the lane line data collected by crowdsourcing at a predetermined time interval;

[0046] Optionally, check the number of lane lines in the lane line data of each time slice. If the number of lane lines in the slice exceeds a certain threshold, perform data slicing at a smaller time interval or equal division according to the multiple relationship between the number of lane lines and the threshold, and record the start and end times of the sliced data.

[0047] The fusion and update module 320 is used to separately merge the initial map and the lane line data of the time slice to obtain a lane line data set, and distributively perform lane line fusion optimization on each lane line data set, and use the fused lane line data as the update data of the initial map;

[0048] Among them, the weight values of the initial map and the lane line data of the time slice are set to control whether the map update emphasizes the original data of the initial map or the newly collected crowdsourcing data.

[0049] The fusion generation module 330 is used to, when there is no initial map, distributively perform lane line fusion optimization on the lane line data of each time slice, and generate an initial map according to the fused and optimized lane line data.

[0050] Preferably, the fused and optimized lane line data is merged, and an ID is re-assigned to each lane line in the merged lane line data set; the merged lane line data set is further subjected to lane line fusion optimization to obtain a new lane line data set as the lane lines of the initial map.

[0051] Specifically, the lane line fusion optimization is specifically as follows:

[0052] The local shape points of the lane line are fitted and optimized to obtain local lane lines, the local lane line segments are combined into an entire lane line, and the broken and incorrect connection parts of the lane line are processed to obtain a lane line set.

[0053] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described system and modules can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0054] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device is used for crowdsourcing lane line fusion and update. As Figure 4 shown, the electronic device 4 of this embodiment includes: a memory 410, a processor 420, and a system bus 430. The memory 410 includes a runnable program 4101 stored thereon. Those skilled in the art can understand that Figure 4 the shown structural diagram of the electronic device does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0055] Next, Figure 4 specific introductions will be made to the respective components of the electronic device:

[0056] The memory 410 can be used to store software programs and modules. The processor 420 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 410. The memory 410 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 electronic device (such as cached data, etc.). In addition, the memory 410 can include high-speed random access memory, and can 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.

[0057] A runnable program 4101 including a signboard extraction method is included in the memory 410. The runnable program 4101 can be divided into one or more modules / units. The one or more modules / units are stored in the memory 410 and executed by the processor 420 to implement distributed processing of lane line data fusion, etc. 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 4101 in the electronic device 4. For example, the computer program 4101 can be divided into a time slice module, a fusion update module, and a fusion generation module.

[0058] The processor 420 is the control center of the electronic device. It uses various interfaces and lines to connect all parts of the entire electronic device. By running or executing the software programs and / or modules stored in the memory 410, and by calling the data stored in the memory 410, it executes various functions of the electronic device and processes data, thereby monitoring the overall state of the electronic device. Optionally, the processor 420 can include one or more processing units; preferably, the processor 420 can integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 420 either.

[0059] The system bus 430 is used to connect various functional components inside the computer and can transmit data information, address information, and control information. Its types can be, for example, PCI bus, ISA bus, VESA bus, etc. The instructions of the processor 420 are transmitted to the memory 410 through the bus, and the memory 410 feeds back data to the processor 420. The system bus 430 is responsible for the data and instruction interaction between the processor 420 and the memory 410. Of course, the system bus 430 can also be connected to other devices, such as a network interface, a display device, etc.

[0060] In the embodiments of the present invention, the executable program executed by the processor 420 included in the electronic device includes:

[0061] Segmenting the lane line data collected through crowdsourcing at a predetermined time interval;

[0062] Respectively merging the initial map and the lane line data of the time slices to obtain a lane line data set, and distributively performing lane line fusion optimization on each lane line data set, and using the fused lane line data as the update data of the initial map;

[0063] When there is no initial map, distributively perform lane line fusion optimization on the lane line data of each time slice, and generate an initial map according to the lane line data after fusion optimization.

[0064] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0065] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0066] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A crowdsourcing lane line fusion and update method, characterized in that Including: Segmenting the lane line data collected by crowdsourcing at a predetermined time interval; Among them, check the number of lane lines in the lane line data of each time slice. If the number of lane lines in the slice exceeds a certain threshold, according to the multiple relationship between the number of lane lines and the threshold, perform data segmentation at a smaller time interval or equal division according to the number of lane lines, and record the start and end times of the segmented data; Respectively merge the initial map with the lane line data of the time slice to obtain a lane line data set, and distributively perform lane line fusion optimization on each lane line data set, and use the fused lane line data as the update data of the initial map; When there is no initial map, distributively perform lane line fusion optimization on the lane line data of each time slice, and generate an initial map according to the lane line data after fusion optimization.

2. The method according to claim 1, wherein The step of respectively merging the initial map with the lane line data of the time slice to obtain a lane line data set, and distributively performing lane line fusion optimization on each lane line data set includes: Setting the weight values of the initial map and the lane line data of the time slice to control whether the map update focuses on the original data of the initial map or the newly collected crowdsourcing data.

3. The method according to claim 1, characterized in that, The step of distributively performing lane line fusion optimization on the lane line data of each time slice and generating an initial map according to the lane line data after fusion optimization includes: Merging the lane line data after fusion optimization, and reassigning an ID to each lane line in the merged lane line data set; Performing lane line fusion optimization on the merged lane line data set again to obtain a new lane line data set as the lane lines of the initial map.

4. The method according to claim 1, characterized in that The lane line fusion optimization specifically is: Performing fitting optimization on the local shape points of the lane line to obtain local lane lines, combining the local lane line segments into the whole lane line, and processing the broken and incorrect connection parts of the lane line to obtain a lane line set.

5. A crowdsourcing lane line fusion and update system, characterized in that, Including: A time segmentation module, which is used to segment the lane line data collected by crowdsourcing at a predetermined time interval; Among them, check the number of lane lines in the lane line data of each time slice. If the number of lane lines in the slice exceeds a certain threshold, according to the multiple relationship between the number of lane lines and the threshold, perform data segmentation at a smaller time interval or equal division according to the number of lane lines, and record the start and end times of the segmented data; A fusion update module, which is used to respectively merge the initial map with the lane line data of the time slice to obtain a lane line data set, distributively perform lane line fusion optimization on each lane line data set, and use the fused lane line data as the update data of the initial map; A fusion generation module, which is used to, when there is no initial map, distributively perform lane line fusion optimization on the lane line data of each time slice, and generate an initial map according to the lane line data after fusion optimization.

6. The system according to claim 5, wherein The step of respectively merging the initial map with the lane line data of the time slice to obtain a lane line data set, and distributively performing lane line fusion optimization on each lane line data set includes: Setting the weight values of the initial map and the lane line data of the time slice to control whether the map update focuses on the original data of the initial map or the newly collected crowdsourcing data.

7. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein, When the processor executes the computer program, it implements the steps of a crowdsourcing lane line fusion update method according to any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of a crowdsourcing lane line fusion and update method according to any one of claims 1 to 4.

Images