Low-confidence area map road network segmentation method, device, medium and equipment

Abstract

The application discloses a low-confidence area map road network segmentation method, device, medium and equipment, and belongs to the technical field of computers. The method mainly comprises the following steps: acquiring each low-confidence road segment and its adjacent high-confidence road segment in a map road network of a predetermined area, and acquiring a high-low-confidence road segment intersection of each low-confidence road segment and the corresponding adjacent high-confidence road segment; breaking at a predetermined length of the corresponding low-confidence road segment and the high-confidence road segment from the corresponding high-low-confidence road segment intersection, to obtain a low-confidence minimum indivisible unit including the corresponding high-low-confidence road segment intersection; and obtaining a map road network segmentation unit by using the low-confidence minimum indivisible unit. The positioning accuracy of the high-confidence road segment is higher than that of the low-confidence road segment. The application can improve the efficiency of high-precision map making, reduce merging errors, and improve the accuracy of low-confidence road segment area mapping.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, medium, device, and map production system for road network segmentation in low-confidence area maps. Background Technology

[0002] In many practical applications, it is necessary to merge map data from multiple regions based on road network information from existing maps. For example, when creating a high-precision map of a predetermined area, maps are created separately through multiple segment tasks, and then the map data from these multiple segment tasks are merged. However, if the endpoints of road network units happen to be in low-confidence areas, such as the lower-level sections of overpasses or inside tunnels where satellite signals are weak, the trajectory points collected in the field will be inaccurate due to the poor satellite signal in these areas. This will lead to data accuracy issues, increasing the difficulty of merging the corresponding map data. Summary of the Invention

[0003] To address the problems existing in the prior art, this application mainly provides a method, apparatus, medium, equipment, and map production system for road network segmentation in low-confidence areas. By dividing low-confidence road segments and adjacent high-confidence road segments into an indivisible unit, and further obtaining the corresponding road network segmentation unit, the low-confidence and high-confidence road segments are combined into a single mapping segmentation task during the high-precision map segmentation process. This avoids merging segmented high-precision map data at the intersection of low-confidence and high-confidence road segments, improving the efficiency of high-precision map production, reducing merging errors, and utilizing the more accurate satellite positioning information of high-confidence road segments to improve the accuracy of mapping adjacent low-confidence road segment areas.

[0004] In a first aspect, embodiments of this application provide a method for road network segmentation in a low-confidence area map, comprising:

[0005] Obtain each low-confidence road segment and its adjacent high-confidence road segment in the map road network of the predetermined area, and obtain the intersection point of the high and low confidence road segments of each low-confidence road segment and the corresponding adjacent high-confidence road segment; break the corresponding low-confidence road segment and the high-confidence road segment at a predetermined length from the intersection point of the corresponding high and low confidence road segment to obtain the smallest indivisible low-confidence unit including the intersection point of the corresponding high and low confidence road segment; use the smallest indivisible low-confidence unit to obtain the map road network segmentation unit; wherein, the positioning accuracy of the high-confidence road segment is higher than that of the low-confidence road segment.

[0006] Secondly, embodiments of this application provide a road network segmentation device for low-confidence area maps, comprising:

[0007] The high-confidence and low-confidence road segment intersection acquisition module is used to acquire each low-confidence road segment and its adjacent high-confidence road segment in the map road network of a predetermined area, and to acquire the high-low confidence road segment intersection point of each low-confidence road segment and its corresponding adjacent high-confidence road segment; the low-confidence minimum indivisible unit acquisition module is used to break the corresponding low-confidence road segment and high-confidence road segment at a predetermined length from the corresponding high-low confidence road segment intersection point to obtain the low-confidence minimum indivisible unit including the corresponding high-low confidence road segment intersection point; the merging module uses the low-confidence minimum indivisible unit to obtain map road network segmentation units; wherein, the positioning accuracy of the high-confidence road segment is higher than that of the low-confidence road segment.

[0008] Thirdly, embodiments of this application provide a map production system, which includes the aforementioned low-confidence area map road network segmentation device.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions that are operated to perform the low-confidence area map road network segmentation method described above.

[0010] Fifthly, embodiments of this application provide a computer device including a processor and a memory, the memory storing computer instructions that are operated to execute the low-confidence area map road network segmentation method in the above-described scheme.

[0011] The beneficial effects of the technical solution of this application are: providing a method, apparatus, medium, equipment, and map production system for road network segmentation in low-confidence areas. This application divides low-confidence road segments and adjacent high-confidence road segments into an indivisible unit, and further obtains corresponding road network segmentation units. This allows low-confidence and high-confidence road segments to be segmented within a single mapping task during the high-precision map segmentation process, avoiding the merging of segmented high-precision map data at the intersection of low-confidence and high-confidence road segments. This improves the efficiency of high-precision map production, reduces merging errors, and utilizes the more accurate satellite positioning information of high-confidence road segments to improve the accuracy of mapping adjacent low-confidence road segment areas. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description exemplarily illustrate some embodiments of this application.

[0013] Figure 1 This is a schematic diagram of a specific implementation of a road network segmentation method for low-confidence area maps according to this application;

[0014] Figure 2This is a schematic diagram of a low-confidence road segment in a specific embodiment of a low-confidence area map road network segmentation method of this application;

[0015] Figure 3 This is a schematic diagram of a specific embodiment of a road network segmentation device for low-confidence area maps according to this application;

[0016] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0017] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0018] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0019] In many practical applications, it is necessary to merge map data from multiple regions based on existing road network information. For example, when creating a high-precision map of a predetermined area, maps are created separately through multiple segment tasks, and then the map data from these multiple segment tasks are merged. However, if the endpoints of road network units happen to be located in low-confidence areas, such as under overpasses, low-level road sections, or inside tunnels, the satellite signal is relatively poor in these areas, resulting in inaccurate positioning of trajectory points collected in the field. This leads to data accuracy issues. Therefore, if high-precision map segment tasks are merged in low-confidence areas, the challenge of correctly matching two inaccurate data sets becomes apparent, increasing the difficulty of merging the corresponding map data.

[0020] This application divides low-confidence road segments and adjacent high-confidence road segments into an indivisible unit, and further obtains corresponding road network segmentation units. This allows low-confidence and high-confidence road segments to be constructed in a single mapping segmentation task during the high-precision map segmentation process. This avoids merging segmented high-precision map data at the intersection of low-confidence and high-confidence road segments, improving the efficiency of high-precision map production, reducing merging errors, and utilizing the more accurate satellite positioning information of high-confidence road segments to improve the accuracy of mapping adjacent low-confidence road segment areas.

[0021] The technical solutions of this application will now be described in detail with reference to specific embodiments and accompanying drawings. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0022] Figure 1 This paper illustrates a specific implementation of a road network segmentation method for low-confidence area maps according to this application.

[0023] exist Figure 1 The specific implementation of the low-confidence area map road network segmentation method of this application shown includes the following steps: Step S101: Obtain each low-confidence road segment and its adjacent high-confidence road segment in the map road network of a predetermined area, and obtain the intersection point of high and low confidence road segments for each low-confidence road segment and its corresponding adjacent high-confidence road segment; Step S102: Break the corresponding low-confidence road segment and the high-confidence road segment at a predetermined length from the intersection point of the corresponding high and low confidence road segment to obtain the smallest indivisible low-confidence unit including the intersection point of the corresponding high and low confidence road segment; Step S103: Obtain map road network segmentation units using the smallest indivisible low-confidence unit; wherein, the low-confidence area is a road segment area with relatively poor satellite signal, such as under overpasses or low-level road segments, inside tunnels, etc., and the high-confidence road segment is a road segment area with relatively good satellite signal.

[0024] This application divides low-confidence road segments and adjacent high-confidence road segments into an indivisible unit, and further obtains corresponding road network segmentation units. This allows low-confidence and high-confidence road segments to be constructed in a single mapping segmentation task during the high-precision map segmentation process. This avoids merging segmented high-precision map data at the intersection of low-confidence and high-confidence road segments, improving the efficiency of high-precision map production, reducing merging errors, and utilizing the more accurate satellite positioning information of high-confidence road segments to improve the accuracy of mapping adjacent low-confidence road segment areas.

[0025] Process S101 represents the process of obtaining each low-confidence road segment and its adjacent high-confidence road segment in the map road network of the predetermined area, and obtaining the intersection point of high and low confidence road segments of each low-confidence road segment and its corresponding adjacent high-confidence road segment. This process can facilitate the obtaining of the smallest indivisible low-confidence unit based on the intersection point of high and low confidence road segments.

[0026] Specifically, the road network of the aforementioned predetermined area can be a traditional road network of a city.

[0027] In one specific embodiment of this application, the traditional map road network of the aforementioned predetermined area is the traditional map road network in an open-source map database. The road network segmentation method of this application further includes obtaining the traditional map road network of the aforementioned predetermined area from the open-source map database. Directly obtaining the traditional map road network from the open-source map database can improve work efficiency by utilizing existing resources.

[0028] In one specific embodiment of this application, low-confidence road segments and their adjacent high-confidence road segments in a predetermined area are obtained based on the road segment label information inherent in a traditional map road network.

[0029] In one specific embodiment of this application, low-confidence road segments and their adjacent high-confidence road segments in the map road network of a predetermined area are obtained based on the annotation information during field data collection.

[0030] In one specific embodiment of this application, the aforementioned low-confidence area includes interchange sections and / or tunnel sections.

[0031] Specifically, for interchange sections, the hierarchical relationship of interchange roads can be obtained based on the built-in labels and / or annotation information labels of traditional map road networks. The upper layers are high-confidence areas with better satellite signals, such as... Figure 2 The road segment CD shown is located in the lower layer, which represents a low-confidence area with relatively poor satellite signal. Figure 2 The road segment BC is shown. Points B and C are the intersection of the high-confidence and low-confidence road segments.

[0032] Process S102 represents the process of breaking the corresponding low-confidence road segment and the high-confidence road segment at a predetermined length from the intersection of the corresponding high- and low-confidence road segments to obtain the lowest low-confidence indivisible unit including the intersection of the corresponding high- and low-confidence road segments. This can help obtain the corresponding map road network segmentation unit by using the lowest low-confidence indivisible unit, making the production of high-precision maps based on the corresponding map road network segmentation unit more accurate and efficient.

[0033] Specifically, low-confidence road segments and a high-confidence road segment are mapped in a single mapping task. This avoids merging map data at the intersection of high- and low-confidence road segments and allows the use of more accurate trajectory information from the high-confidence area to correct the trajectory information of adjacent low-confidence areas.

[0034] Specifically, the aforementioned predetermined length can be 50m, which ensures that the merging of map data can be carried out on the 50m high-confidence road segment connecting the intersection of high and low confidence road segments. This avoids the increased algorithmic difficulty caused by merging at the intersection of high and low confidence road segments with poor satellite signals. At the same time, the relatively accurate trajectory information of 50m on each side is used to correct the low-confidence area.

[0035] In a specific instance of this application, such as Figure 2 As shown, at point A, which is 50m away from the intersection of high and low confidence levels B, the high-confidence road segment connected to it is broken, and at point B', which is 50m away from point B, the low-confidence road segment connected to it is broken, resulting in the smallest undivisible low-confidence unit including road segment AB'; at point D, which is 50m away from the intersection of high and low confidence levels C, the high-confidence road segment connected to it is broken, and at point C', which is 50m away from point C, the low-confidence road segment connected to it is broken, resulting in the smallest undivisible low-confidence unit including road segment C'D.

[0036] This approach avoids merging the relatively accurate AB and CD segment map data with the inaccurate BB' and CC' segment map data at points B and C where satellite signals are weak, which would cause merging errors. At the same time, the relatively accurate AB and CD segments are used to correct the inaccurate BC segment trajectory information.

[0037] Process S103 represents the process of obtaining map road network segmentation units using the smallest undivisible unit with low confidence. This process can help obtain map road network segmentation units with the required length and size as needed, in order to carry out high-precision map segmentation tasks.

[0038] In one optional embodiment of this application, the length of multiple map road network segmentation units does not exceed the range of length values ​​predetermined based on available computer resources and corresponding task time limits, so as to maximize the saving of available computer resources and improve mapping efficiency.

[0039] Specifically, the number of concurrent mapping tasks can be determined based on available computer resources, as well as the size of the data processed by each concurrent task, in order to save computer resources as much as possible and reduce task time. Accordingly, the number of concurrent mapping tasks can be determined based on the size of the data processed by each concurrent task.

[0040] Specifically, each of the above-mentioned traditional map segmentation units can be a road network unit with a length value not much different from 3km.

[0041] In one specific embodiment of this application, the low-confidence area map road network segmentation method of this application further includes dividing the traditional map network of the predetermined area, except for the low-confidence minimum indivisible unit, into multiple other minimum indivisible units whose lengths differ from the sum of the lengths of all road segments in the low-confidence minimum indivisible unit by no more than a preset length threshold.

[0042] This embodiment facilitates the subsequent merging of low-confidence minimum indivisible units and other minimum indivisible units to obtain multiple traditional road network segmentation units with similar lengths. This enables the use of multiple map road network segmentation units of uniform length to achieve high concurrency in the map production process, thereby achieving low resource consumption and low time consumption, thus improving the efficiency of producing high-precision maps and reducing resource consumption.

[0043] In one specific embodiment of this application, the process of dividing the traditional map network of the predetermined area, excluding the low-confidence minimum indivisible unit, according to a predetermined rule to obtain a plurality of other minimum indivisible units whose difference from the sum of the lengths of all road segments in the low-confidence minimum indivisible unit does not exceed a preset length threshold includes uniformly dividing the traditional map network of the predetermined area, excluding the low-confidence minimum indivisible unit, to obtain a plurality of other minimum indivisible units whose difference from the sum of the lengths of all road segments in each low-confidence minimum indivisible unit does not exceed a first preset length threshold.

[0044] This embodiment applies to areas where there are no other sensitive points besides low-confidence areas that would easily lead to merging difficulties when merging map data. Specifically, the aforementioned other smallest indivisible unit can be a road network unit with a length of 300m.

[0045] Specifically, the traditional map network of the predetermined area, except for the smallest indivisible unit with low confidence, is divided into subdivision units that are not much different from the sum of the lengths of all road segments in each smallest indivisible unit with low confidence. This is beneficial for subsequent merging to obtain multiple map road network subdivision units with the smallest length differences.

[0046] In one specific embodiment of this application, the process of obtaining map road network segmentation units using low-confidence minimum indivisible units includes merging each low-confidence minimum indivisible unit with at least one other adjacent minimum indivisible unit to obtain multiple map road network segmentation units with lengths conforming to a preset length range.

[0047] This embodiment can benefit from merging multiple map road network segmentation units with the smallest difference in length and size, enabling multiple mapping tasks to be performed concurrently, achieving low resource consumption and low time consumption, thereby improving the production efficiency of high-precision maps, reducing resource consumption, and reducing merging errors.

[0048] Figure 3 This application illustrates a specific embodiment of a road network segmentation device for low-confidence area maps.

[0049] exist Figure 3 The specific implementation of the low-confidence area map road network segmentation device of this application shown includes,

[0050] The high-confidence and low-confidence road segment intersection acquisition module 301 is used to acquire each low-confidence road segment and its adjacent high-confidence road segment in the map road network of a predetermined area, and to acquire the high-confidence and low-confidence road segment intersection point of each low-confidence road segment and its corresponding adjacent high-confidence road segment; the low-confidence minimum indivisible unit acquisition module 302 is used to break the corresponding low-confidence road segment and the high-confidence road segment at a predetermined length from the corresponding high-confidence and low-confidence road segment intersection point to obtain the low-confidence minimum indivisible unit including the corresponding high-confidence and low-confidence road segment intersection point; the map road network segmentation unit acquisition module 303 is used to obtain map road network segmentation units using the low-confidence minimum indivisible unit; wherein, the low-confidence area is the road segment area with relatively poor satellite signal, such as under the overpass or low-level road segment, inside the tunnel, etc., and the high-confidence road segment is the road segment area with relatively good satellite signal.

[0051] This application divides low-confidence road segments and adjacent high-confidence road segments into an indivisible unit, and further obtains corresponding road network segmentation units. This allows low-confidence and high-confidence road segments to be constructed in a single mapping segmentation task during the high-precision map segmentation process. This avoids merging segmented high-precision map data at the intersection of low-confidence and high-confidence road segments, improving the efficiency of high-precision map production, reducing merging errors, and utilizing the more accurate satellite positioning information of high-confidence road segments to improve the accuracy of mapping adjacent low-confidence road segment areas.

[0052] The high-low confidence intersection point acquisition module 301, which is used to obtain each low-confidence road segment and its adjacent high-confidence road segment in the map road network of a predetermined area, and to obtain the high-low confidence intersection point of each low-confidence road segment and its corresponding adjacent high-confidence road segment, can facilitate the acquisition of the smallest indivisible low-confidence unit based on the obtained high-low confidence intersection point.

[0053] Specifically, the traditional road network of the aforementioned predetermined area can be the traditional road network of a city.

[0054] In one specific embodiment of this application, the traditional map road network of the aforementioned predetermined area is the traditional map road network in an open-source map database. The road network segmentation method of this application further includes a traditional map road network acquisition module for obtaining the traditional map road network of the aforementioned predetermined area from the open-source map database. Obtaining the traditional map road network directly from the open-source map database can improve work efficiency by utilizing existing resources.

[0055] In one specific embodiment of this application, the aforementioned label information includes the built-in label information of traditional map road networks and / or label information obtained from the annotation information during field data collection.

[0056] In one specific embodiment of this application, the aforementioned low-confidence area includes interchange sections and / or tunnel sections.

[0057] Specifically, for interchange sections, the hierarchical relationship of interchange roads can be obtained based on the built-in labels and / or annotation information labels of traditional map road networks. The upper layers are high-confidence areas with better satellite signals, such as... Figure 2 The road segment CD shown is located in the lower layer, which represents a low-confidence area with relatively poor satellite signal. Figure 2 The road segment BC is shown. Points B and C are the intersection of the high-confidence and low-confidence road segments.

[0058] The module 302 is used to break the road segment at a predetermined length from the intersection of the corresponding low-confidence road segment and the high-confidence road segment, and to obtain the lowest confidence minimum indivisible unit including the intersection of the corresponding high-confidence road segment. This module can be used to obtain the corresponding map road network segmentation unit, making the production of high-precision maps based on the corresponding map road network segmentation unit more accurate and efficient.

[0059] Specifically, low-confidence road segments and a high-confidence road segment are mapped in a single mapping task. This avoids merging map data at the intersection of high- and low-confidence road segments and allows the use of more accurate trajectory information from the high-confidence area to correct the trajectory information of adjacent low-confidence areas.

[0060] Specifically, the aforementioned predetermined length can be 50m, which ensures that when merging map data, it can be done on a 50m high-confidence road segment connecting the intersection of high and low confidence road segments. This avoids increasing the algorithm difficulty when merging at the intersection of high and low confidence road segments with poor satellite signals. At the same time, the relatively accurate trajectory information of 50m on each side is used to correct the low-confidence area.

[0061] The map road network segmentation unit acquisition module 303, which is used to obtain map road network segmentation units by utilizing the smallest indivisible unit with low confidence, can facilitate obtaining road network segmentation units of the required length and size as needed for high-precision map segmentation tasks.

[0062] In one optional embodiment of this application, the length of multiple map road network segmentation units does not exceed the range of length values ​​predetermined based on available computer resources and corresponding task time limits, so as to maximize the saving of available computer resources and improve mapping efficiency.

[0063] Specifically, the number of concurrent mapping tasks and the size of the data processed by each concurrent task can be determined based on available computer resources. This allows for the conservation of computer resources and reduction of task time as much as possible. Correspondingly, the above-mentioned...

[0064] Specifically, each of the above traditional map segmentation units can be a road network unit with a length value not much different from 3km.

[0065] In one specific embodiment of this application, the low-confidence area map road network segmentation device of this application further includes a module for obtaining other minimum indivisible units, which is used to divide the traditional map network of a predetermined area except for the minimum indivisible unit with low confidence according to a predetermined rule, and obtain multiple other minimum indivisible units whose difference from the sum of the lengths of all road segments in the minimum indivisible unit with low confidence does not exceed a preset length threshold.

[0066] This embodiment facilitates the subsequent merging of low-confidence minimum indivisible units and other minimum indivisible units to obtain multiple traditional road network segmentation units with similar lengths. This enables the use of multiple map road network segmentation units of uniform length to achieve high concurrency in the map production process, thereby achieving low resource consumption and low time consumption, thus improving the efficiency of producing high-precision maps and reducing resource consumption.

[0067] In one specific embodiment of this application, the module for obtaining other smallest indivisible units, which is used to divide the traditional map network of the predetermined area except for the low-confidence smallest indivisible unit according to a predetermined rule, and obtain multiple other smallest indivisible units whose difference from the sum of the lengths of all road segments in the low-confidence smallest indivisible unit does not exceed a preset length threshold, includes further being used to uniformly divide the traditional map network of the predetermined area except for the low-confidence smallest indivisible unit, and obtain multiple other smallest indivisible units whose difference from the sum of the lengths of all road segments in each low-confidence smallest indivisible unit does not exceed a first preset length threshold.

[0068] This embodiment applies to areas where there are no other sensitive points besides low-confidence areas that would easily lead to merging difficulties when merging map data. Specifically, the aforementioned other smallest indivisible unit can be a road network unit with a length of 300m.

[0069] Specifically, the traditional map network of the predetermined area, except for the smallest indivisible unit with low confidence, is divided into subdivision units that are not much different from the sum of the lengths of all road segments in each smallest indivisible unit with low confidence. This is beneficial for subsequent merging to obtain multiple map road network subdivision units with the smallest length differences.

[0070] In one specific embodiment of this application, the map road network segmentation unit acquisition module 303, which is used to obtain map road network segmentation units using low-confidence minimum indivisible units, can be used to merge each low-confidence minimum indivisible unit with at least one other adjacent minimum indivisible unit to obtain multiple map road network segmentation units with lengths conforming to a preset length range.

[0071] This embodiment can benefit from merging multiple map road network segmentation units with the smallest difference in length and size, enabling multiple mapping tasks to be performed concurrently, achieving low resource consumption and low time consumption, thereby improving the production efficiency of high-precision maps, reducing resource consumption, and reducing merging errors.

[0072] In one specific embodiment of this application, the functional modules in the low-confidence area map road network segmentation device of this application can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0073] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0074] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0075] In another specific embodiment of this application, a map production system is provided, wherein the driving system includes a map matching device, and optionally, the image sensing and display device includes a processor and a memory, which are coupled together; the map matching device is used to execute the map road network segmentation method in any of the above schemes.

[0076] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that are operated to perform the low-confidence area map road network segmentation method in any of the above schemes.

[0077] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions that are operated to perform the low-confidence area map road network segmentation method in any of the above schemes.

[0078] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0079] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0080] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A method for road network segmentation in low-confidence area maps, characterized in that, include: Obtain each low-confidence road segment and its adjacent high-confidence road segment in the map road network of the predetermined area, and obtain the intersection point of the high and low confidence road segments of each low-confidence road segment and the corresponding adjacent high-confidence road segment; The road segment with low confidence and the road segment with high confidence are interrupted at a predetermined length from the intersection of the high and low confidence road segments to obtain the smallest indivisible low confidence unit including the intersection of the high and low confidence road segments. Map road network segmentation units are obtained using the low-confidence minimum indivisible unit; The positioning accuracy of the high-confidence road segment is higher than that of the low-confidence road segment.

2. The low-confidence area map road network segmentation method according to claim 1, characterized in that, The map road network is a traditional map road network. The low-confidence road segments and their adjacent high-confidence road segments in the map road network of the predetermined area are obtained based on the road segment label information provided by the traditional map road network.

3. The low-confidence area map road network segmentation method according to claim 1, characterized in that, Based on the annotation information during field data collection, obtain the low-confidence road segments and their adjacent high-confidence road segments in the map road network of the predetermined area.

4. The low-confidence area map road network segmentation method according to claim 1, characterized in that, The low-confidence road sections include overpass sections and / or tunnel sections.

5. The method for road network segmentation in low-confidence area maps according to claim 1, characterized in that, It also includes, The map road network of the predetermined area, excluding the minimum indivisible unit with low confidence, is divided according to predetermined rules to obtain multiple other minimum indivisible units whose lengths differ from the sum of the lengths of all road segments in the minimum indivisible unit with low confidence by no more than a preset length threshold.

6. The low-confidence area map road network segmentation method according to claim 5, characterized in that, The process of obtaining map road network segmentation units using the low-confidence minimum undividerable unit includes: Each of the low-confidence minimum indivisible units is merged with at least one of the adjacent other minimum indivisible units to obtain multiple map road network segmentation units with lengths conforming to a preset length range.

7. A road network segmentation device for low-confidence area maps, characterized in that, include, The high- and low-confidence road segment intersection acquisition module is used to acquire each low-confidence road segment and its adjacent high-confidence road segment in the map road network of a predetermined area, and to acquire the high- and low-confidence road segment intersection point of each low-confidence road segment and the corresponding adjacent high-confidence road segment. The low-confidence minimum indivisible unit acquisition module is used to interrupt the corresponding low-confidence road segment and the high-confidence road segment at a predetermined length from the intersection of the corresponding high and low confidence road segments, so as to obtain the low-confidence minimum indivisible unit including the intersection of the corresponding high and low confidence road segments. The merging module uses the low-confidence minimum indivisible unit to obtain map road network segmentation units; The positioning accuracy of the high-confidence road segment is higher than that of the low-confidence road segment.

8. The low-confidence area map road network segmentation device according to claim 7, characterized in that, It also includes, The other smallest indivisible unit acquisition module is used to divide the map road network of the predetermined area, excluding the low-confidence smallest indivisible unit, according to a predetermined rule to obtain a number of other smallest indivisible units whose lengths differ from the sum of the lengths of all road segments in the low-confidence smallest indivisible unit by no more than a preset length threshold.

9. A driving system, characterized in that, The driving system includes the low-confidence area map road network segmentation device as described in claim 7.

10. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the low-confidence area map road network segmentation method as described in any one of claims 1-6.

11. A computer device comprising a processor and a memory, the memory storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the low-confidence area map road network segmentation method as described in any one of claims 1-6.

Images