Map construction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a map construction method and apparatus, an electronic device and a storage medium, since constructed primary skeleton lines mainly comprise highways, expressways and other roads, the situation that the roads are not coherent does not exist, from secondary skeleton line data, after a skeleton line is constructed according to the skeleton line data of the highest level, the skeleton line can be constructed according to the skeleton line data of the highest level; the situation that the constructed skeleton lines are not coherent possibly exists, so that the skeleton line data of which the grade needs to be improved can be upgraded from the unprocessed skeleton line data, namely from all skeleton line data of which the skeleton lines are not constructed, according to the geometrical relationship between the skeleton line corresponding to each skeleton line data and the constructed skeleton line; after the skeleton lines are constructed according to the skeleton line data after the level adjustment, the coherence between the skeleton lines can be ensured, that is, the constructed map can be ensured to be coherent and available, and the accuracy of the map is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a map construction method, device, electronic device and storage medium. Background Art

[0002] In autonomous driving technology, accurate map construction is a prerequisite for ensuring the safe driving of autonomous vehicles. Specifically, high-precision maps can be constructed based on open source skeleton line data, where a skeleton line is a combination of roads in the road network, and a one-way road is a skeleton line.

[0003] Specifically, the open source skeleton line data can classify all skeleton lines into different levels, such as level 1, level 2, level 3, and level 4. When building a high-precision map, roads can be constructed in sequence according to the level of the skeleton lines. That is, the level 1 skeleton line can be constructed first, then the level 2 skeleton line can be constructed, and the level 2 skeleton line can be combined with the constructed level 1 skeleton line; then the level 3 skeleton line can be constructed, and the level 3 skeleton line can be combined with all the previously constructed skeleton lines; finally, the level 4 skeleton line can be constructed, and the level 4 skeleton line can be combined with all the previously constructed skeleton lines to complete the map construction.

[0004] However, when constructing a map based on the existing skeleton line data, after the secondary skeleton line is constructed and combined with the constructed primary skeleton line, there is a situation where the skeleton line is not coherent; after the third-level skeleton line is constructed and combined with other constructed skeleton lines, there is also a situation where the skeleton line is not coherent, and the same is true for the fourth-level skeleton line. In other words, the map constructed using the above method has a situation where the skeleton line is not coherent due to inaccurate skeleton line classification, which will make the constructed map unusable. Therefore, how to accurately classify the skeleton lines, thereby improving the accuracy of map construction and ensuring that the constructed map is coherent and usable, has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a map construction method, device, electronic device and storage medium to improve the accuracy of map construction. The specific technical solution is as follows.

[0006] In a first aspect, an embodiment of the present invention provides a map construction method, the method comprising:

[0007] Acquire skeleton line data; the skeleton line data includes skeleton line data of different levels;

[0008] Extracting primary skeleton line data from the skeleton line data, and constructing a primary skeleton line according to the primary skeleton line data;

[0009] Extracting the highest level of skeleton line data from the unprocessed skeleton line data as current skeleton line data, and constructing each current skeleton line according to each current skeleton line data;

[0010] In the unprocessed skeleton line data, according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line, the target skeleton line data meeting the conditions is identified, and the level of the target skeleton line data is upgraded to the same level as the current skeleton line data;

[0011] constructing a target skeleton line according to the target skeleton line data, and determining whether there is unprocessed skeleton line data;

[0012] When there is unprocessed skeleton line data, the process returns to the step of extracting the highest level skeleton line data from the unprocessed skeleton line data as current skeleton line data, and constructing the current skeleton line according to the current skeleton line data.

[0013] Optionally, the step of identifying target skeleton line data that meets the conditions in the unprocessed skeleton line data according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line includes:

[0014] Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold;

[0015] Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold; the second distance threshold is less than the first distance threshold;

[0016] The skeleton line data corresponding to the first skeleton line and the second skeleton line are both used as target skeleton line data.

[0017] Optionally, the step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold comprises:

[0018] Among the skeleton lines corresponding to the unprocessed skeleton line data, any skeleton line is used as the skeleton line to be processed;

[0019] Determine whether the skeleton line to be processed is parallel to any skeleton line that has been constructed;

[0020] When the skeleton line to be processed is parallel to any constructed skeleton line, a connected skeleton line connecting the skeleton line to be processed and any constructed skeleton line within a first distance threshold is identified among the skeleton lines corresponding to the unprocessed skeleton line data, and both the skeleton line to be processed and the connected skeleton line are used as the first skeleton line.

[0021] Optionally, the step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold, and taking both the skeleton line to be processed and the connected skeleton line as the first skeleton line comprises:

[0022] Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold;

[0023] Among the skeleton lines to be processed and the continuous skeleton lines, identifying parallel skeleton line segments that are parallel to the constructed skeleton lines, and counting the lengths of the parallel skeleton line segments;

[0024] When the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, the skeleton line to be processed and the continuous skeleton line are both used as the first skeleton line.

[0025] Optionally, the step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold comprises:

[0026] A deep search algorithm is used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

[0027] In a second aspect, an embodiment of the present invention provides a map construction device, the device comprising:

[0028] A data acquisition module, used to acquire skeleton line data; the skeleton line data includes skeleton line data of different levels;

[0029] A data extraction module, used to extract primary skeleton line data from the skeleton line data, and construct a primary skeleton line according to the primary skeleton line data;

[0030] A data processing module, used to extract the highest level skeleton line data from the unprocessed skeleton line data as the current skeleton line data, and construct each current skeleton line according to each current skeleton line data;

[0031] A data identification module is used to identify target skeleton line data that meets the conditions in the unprocessed skeleton line data according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line, and upgrade the level of the target skeleton line data to the same level as the current skeleton line data;

[0032] The data judgment module is used to construct a target skeleton line according to the target skeleton line data and judge whether there is unprocessed skeleton line data; when there is unprocessed skeleton line data, the data processing module is triggered.

[0033] Optionally, the data identification module includes:

[0034] A first identification submodule is used to identify, among the skeleton lines corresponding to the unprocessed skeleton line data, a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold;

[0035] A second identification submodule is used to identify, from the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold; the second distance threshold is less than the first distance threshold;

[0036] The data determination submodule is used to use the skeleton line data corresponding to the first skeleton line and the second skeleton line as target skeleton line data.

[0037] Optionally, the first identification submodule is specifically used to:

[0038] Among the skeleton lines corresponding to the unprocessed skeleton line data, any skeleton line is used as the skeleton line to be processed;

[0039] Determine whether the skeleton line to be processed is parallel to any skeleton line that has been constructed;

[0040] When the skeleton line to be processed is parallel to any constructed skeleton line, a connected skeleton line connecting the skeleton line to be processed and any constructed skeleton line within a first distance threshold is identified among the skeleton lines corresponding to the unprocessed skeleton line data, and both the skeleton line to be processed and the connected skeleton line are used as the first skeleton line.

[0041] Optionally, the first identification submodule is specifically used to:

[0042] Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold;

[0043] Among the skeleton lines to be processed and the continuous skeleton lines, identifying parallel skeleton line segments that are parallel to the constructed skeleton lines, and counting the lengths of the parallel skeleton line segments;

[0044] When the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, the skeleton line to be processed and the continuous skeleton line are both used as the first skeleton line.

[0045] Optionally, the second identification submodule is specifically used to:

[0046] A deep search algorithm is used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

[0047] In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, wherein the memory and the processor are coupled;

[0048] The memory is used to store one or more computer instructions;

[0049] The processor is used to execute the one or more computer instructions to implement the map construction method as described in the first aspect above.

[0050] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having one or more computer instructions stored thereon, which are executed by a processor to implement the map construction method as described in the first aspect above.

[0051] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the map construction method described in the first aspect is implemented.

[0052] From the above content, it can be known that the map construction method, device, electronic device and storage medium provided by the embodiment of the present invention, since the first-level skeleton lines constructed mainly include highways, expressways and other roads, there will be no road discontinuity. Therefore, it can start from the second-level skeleton line data. When the skeleton lines are constructed according to the highest-level skeleton line data, there may be discontinuity in the constructed skeleton lines. Therefore, the skeleton line data that need to be upgraded can be upgraded from the unprocessed skeleton line data, that is, from all the skeleton line data that have not yet constructed the skeleton lines, according to the geometric relationship between the skeleton lines corresponding to each skeleton line data and the constructed skeleton lines. After the skeleton lines are constructed according to the skeleton line data after the adjustment of the level, the continuity between the skeleton lines can be guaranteed, that is, the constructed map can be guaranteed to be coherent and available, thereby improving the accuracy of the map. Of course, it is not necessary to achieve all the advantages described above at the same time to implement any product or method of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work.

[0054] Figure 1 A schematic diagram of a flow chart of a map construction method provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of the structure of a map construction device provided by an embodiment of the present invention;

[0056] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] It should be noted that the terms "including" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0059] The embodiment of the present invention discloses a map construction method, device, electronic device and storage medium, which can improve the accuracy of map construction. The embodiment of the present invention is described in detail below.

[0060] Figure 1 A flowchart of a map construction method provided in an embodiment of the present invention is provided. The method is applied to an electronic device. The method specifically includes the following steps.

[0061] S110: Obtain skeleton line data; the skeleton line data includes skeleton line data of different levels.

[0062] For example, the electronic device can obtain skeleton line data from an open source database. The skeleton line data may include different levels, such as level 1, level 2, level 3, and level 4. In other words, the electronic device can obtain all skeleton line data included in the range of the map to be constructed to construct a complete map.

[0063] It is understandable that as the complexity of the road changes or other factors change, the level of the skeleton line data may also change accordingly, such as being reduced to only level 1, level 2, and level 3, or being increased to level 1, level 2, level 3, level 4, and level 5. In the embodiment of the present invention, the electronic device obtains all the skeleton line data within the scope of the map to be constructed, and the specific number of levels of the skeleton line data is not limited.

[0064] S120: extracting primary skeleton line data from the skeleton line data, and constructing a primary skeleton line based on the primary skeleton line data.

[0065] In the field of autonomous driving, the construction of high-precision maps can be carried out in sequence according to the level of skeleton lines. Therefore, in an embodiment of the present invention, the first-level skeleton line data can be first extracted from the skeleton line data, and the first-level skeleton line can be constructed. Among them, the constructed first-level skeleton line can include highways, expressways, etc., for example, it can include city ring highways, etc.

[0066] S130: extracting the highest level skeleton line data from the unprocessed skeleton line data as current skeleton line data, and constructing each current skeleton line according to each current skeleton line data.

[0067] After constructing the first-level skeleton line according to the first-level skeleton line data, the electronic device can construct skeleton lines of other levels in sequence. For example, taking the skeleton line data including the first level, second level, third level and fourth level as an example, after constructing the first-level skeleton line, the currently unprocessed skeleton line data, that is, the skeleton line data that has not yet constructed the skeleton line, is the second-level, third-level and fourth-level skeleton line data, among which the highest level of skeleton line data is the second-level skeleton line data. The electronic device can use the second-level skeleton line data as the current skeleton line data, and construct each current skeleton line, that is, the second-level skeleton line. Among them, the constructed second-level skeleton line can include main roads in the city, etc.

[0068] S140: In the unprocessed skeleton line data, according to the geometric relationship between the skeleton lines corresponding to each skeleton line data and the constructed skeleton lines, the target skeleton line data that meets the conditions is identified, and the level of the target skeleton line data is upgraded to the same level as the current skeleton line data.

[0069] For example, after constructing the primary skeleton line and the secondary skeleton line, some of the skeleton lines may be incoherent. Therefore, in the embodiment of the present invention, target skeleton line data that meets the conditions can be identified in the unprocessed skeleton line data, that is, the lower-level skeleton line data, that is, the third-level and fourth-level skeleton line data, and upgraded to the second-level skeleton line data.

[0070] When the primary skeleton line is a highway and the secondary skeleton line is a main urban road, the skeleton line that can connect the primary skeleton line and the secondary skeleton line may include two situations: the auxiliary road of the highway and the ramp of the highway exit or entrance.

[0071] In one implementation, when the electronic device identifies target skeleton line data that meets the conditions based on the geometric relationship between the skeleton lines corresponding to each skeleton line data and the constructed skeleton lines, it can identify a first skeleton line that is parallel to any constructed skeleton line and is coherent within a first distance threshold among the skeleton lines corresponding to the unprocessed skeleton line data; and identify a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold among the skeleton lines corresponding to the unprocessed skeleton line data; the second distance threshold is less than the first distance threshold; finally, the skeleton line data corresponding to the first skeleton line and the second skeleton line can be used as target skeleton line data.

[0072] That is to say, the situation of the auxiliary road can be identified first, and then the situation of the ramp can be identified. Generally, the auxiliary road of the expressway is parallel to the expressway. Therefore, when identifying the auxiliary road, any skeleton line in the skeleton line corresponding to the unprocessed skeleton line data can be used as the skeleton line to be processed; determine whether the skeleton line to be processed is parallel to any of the constructed skeleton lines; when the skeleton line to be processed is parallel to any of the constructed skeleton lines, identify the skeleton line to be processed and any of the above-mentioned skeleton lines in parallel relationship within the first distance threshold among the skeleton lines corresponding to the unprocessed skeleton line data, and use both the skeleton line to be processed and the connected skeleton line as the first skeleton line.

[0073] Among them, a deep search algorithm can be used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a continuous skeleton line that connects the skeleton line to be processed and any of the above-mentioned skeleton lines in parallel relationship within the first distance threshold. For example, the search can be conducted from both ends of the skeleton line to be processed to the distance in sequence. When both ends can be connected with any of the above-mentioned skeleton lines in parallel relationship, and the total length of the continuous skeleton lines passing through the middle is within the first distance threshold, the skeleton line to be processed and the continuous skeleton line can be used as the first skeleton line.

[0074] In one implementation, in order to improve the accuracy and rationality of map construction and avoid the length of the continuous skeleton line being too long and inconsistent with the actual driving trajectory, when determining the first skeleton line, the electronic device can identify, among the skeleton lines corresponding to the unprocessed skeleton line data, a continuous skeleton line that connects the skeleton line to be processed and any constructed skeleton line within a first distance threshold; then, among the skeleton lines to be processed and the continuous skeleton lines, identify parallel skeleton line segments that are parallel to the constructed skeleton lines, and count the lengths of the parallel skeleton line segments; then, when the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, both the skeleton line to be processed and the continuous skeleton line are used as the first skeleton line.

[0075] The preset ratio range may be determined according to actual conditions, such as the size of the map to be constructed, the accuracy of the map to be constructed, etc. For example, it may include: 50%-100%, 60%-100%, etc. The embodiment of the present invention does not limit its specific value.

[0076] When identifying ramp conditions, the electronic device may use a deep search algorithm to search for the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

[0077] For example, for each skeleton line corresponding to the unprocessed skeleton line data, the search can be conducted from both ends of the skeleton line to the distance in sequence. When both ends can be connected with any constructed skeleton line and the total length of the connected skeleton line in the middle is within the second distance threshold, the skeleton line and the connected skeleton line can be used as the second skeleton line.

[0078] It is understandable that the distance required to connect the auxiliary road with the highway is greater than the distance required to connect the ramp with the highway. Therefore, in order to ensure the accuracy of the skeleton line upgrade, the first distance threshold can be set to be greater than the second distance threshold, so as to avoid upgrading the skeleton line that does not meet the actual situation, improve the accuracy of the skeleton line level determination, and thus improve the accuracy of the map construction.

[0079] S150: construct the target skeleton line according to the target skeleton line data, and determine whether there is unprocessed skeleton line data; if there is unprocessed skeleton line data, return to step S130. If there is no unprocessed skeleton line data, the process ends and the map construction is completed.

[0080] After adjusting the level of the target skeleton line data, the target skeleton line can be constructed according to the target skeleton line data. As in the above example, after the skeleton line data that meets the conditions in the third-level and fourth-level skeleton line data are upgraded to the second-level skeleton line data, the second-level skeleton line can be reconstructed according to the upgraded second-level skeleton line data, and the second-level skeleton line constructed in the above step S130 is used as the second-level skeleton line. All the constructed second-level skeleton lines can be guaranteed to be coherent and usable with the first-level skeleton lines.

[0081] After the secondary skeleton line is constructed, it can be determined whether there is unprocessed skeleton line data, that is, whether there is skeleton line data for which the skeleton line is not constructed. Generally, only part of the skeleton line data in the third and fourth level skeleton line data is upgraded to the second level skeleton line data. Therefore, the electronic device can determine that there is unprocessed skeleton line data. In this case, it can return to step S130, that is, the third level skeleton line data can be extracted and the third level skeleton line can be constructed.

[0082] Similarly, there may be skeleton lines in the fourth-level skeleton lines that connect the third-level skeleton lines with the first-level and second-level skeleton lines that have been constructed before. In this case, the fourth-level skeleton lines need to be upgraded to third-level skeleton lines. The method in step S140 is used to identify the fourth-level skeleton line data that needs to be upgraded, upgrade it to third-level skeleton line data, and execute step S150 to complete the construction of the third-level skeleton line, and determine that there is still unprocessed skeleton line data, that is, fourth-level skeleton line data.

[0083] When the method in step S140 is used to identify the fourth-level skeleton line data that needs to be upgraded to the third-level skeleton line data, there may be no parallel relationship. This is mainly based on the second situation, that is, among the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is connected to any constructed skeleton line within a second distance threshold is identified, and the skeleton line data corresponding to the identified skeleton line is upgraded to a third-level skeleton line.

[0084] When it is determined that there is unprocessed skeleton line data, the process can return to step S130, that is, the fourth-level skeleton line data can be extracted and the fourth-level skeleton line can be constructed. At this time, there is no unprocessed skeleton line data, so there is no need to execute steps S140 and S150, and all skeleton lines are constructed, that is, the map is constructed.

[0085] From the above content, it can be seen that since the constructed first-level skeleton lines mainly include highways, expressways and other roads, there will be no road discontinuity. Therefore, we can start from the second-level skeleton line data. When the skeleton lines are constructed according to the highest-level skeleton line data, there may be discontinuity in the constructed skeleton lines. Therefore, we can use the unprocessed skeleton line data, that is, from all the skeleton line data for which the skeleton lines have not yet been constructed, according to the geometric relationship between the skeleton lines corresponding to each skeleton line data and the constructed skeleton lines, the skeleton line data that need to be upgraded can be upgraded. After the skeleton lines are constructed according to the skeleton line data after the level is adjusted, the continuity between the skeleton lines can be guaranteed, that is, the constructed map can be guaranteed to be consistent and available, thereby improving the accuracy of the map.

[0086] like Figure 2 As shown, it shows a schematic diagram of the structure of a map construction device provided by an embodiment of the present invention, the device comprising:

[0087] The data acquisition module 210 is used to acquire skeleton line data; the skeleton line data includes skeleton line data of different levels;

[0088] A data extraction module 220, used to extract primary skeleton line data from the skeleton line data, and construct a primary skeleton line according to the primary skeleton line data;

[0089] The data processing module 230 is used to extract the highest level skeleton line data from the unprocessed skeleton line data as the current skeleton line data, and construct each current skeleton line according to each current skeleton line data;

[0090] The data identification module 240 is used to identify target skeleton line data that meets the conditions in the unprocessed skeleton line data according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line, and upgrade the level of the target skeleton line data to the same level as the current skeleton line data;

[0091] The data judgment module 250 is used to construct a target skeleton line according to the target skeleton line data and judge whether there is unprocessed skeleton line data; when there is unprocessed skeleton line data, the data processing module 230 is triggered.

[0092] Optionally, the data identification module 240 includes:

[0093] A first identification submodule is used to identify, among the skeleton lines corresponding to the unprocessed skeleton line data, a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold;

[0094] A second identification submodule is used to identify, from the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold; the second distance threshold is less than the first distance threshold;

[0095] The data determination submodule is used to use the skeleton line data corresponding to the first skeleton line and the second skeleton line as target skeleton line data.

[0096] Optionally, the first identification submodule is specifically used to:

[0097] Among the skeleton lines corresponding to the unprocessed skeleton line data, any skeleton line is used as the skeleton line to be processed;

[0098] Determine whether the skeleton line to be processed is parallel to any skeleton line that has been constructed;

[0099] When the skeleton line to be processed is parallel to any constructed skeleton line, a connected skeleton line connecting the skeleton line to be processed and any constructed skeleton line within a first distance threshold is identified among the skeleton lines corresponding to the unprocessed skeleton line data, and both the skeleton line to be processed and the connected skeleton line are used as the first skeleton line.

[0100] Optionally, the first identification submodule is specifically used to:

[0101] Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold;

[0102] Among the skeleton lines to be processed and the continuous skeleton lines, identifying parallel skeleton line segments that are parallel to the constructed skeleton lines, and counting the lengths of the parallel skeleton line segments;

[0103] When the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, the skeleton line to be processed and the continuous skeleton line are both used as the first skeleton line.

[0104] Optionally, the second identification submodule is specifically used to:

[0105] A deep search algorithm is used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

[0106] From the above content, it can be seen that the map construction device provided by the embodiment of the present invention, since the first-level skeleton lines constructed mainly include roads such as highways and expressways, there will be no road discontinuity. Therefore, it can start from the second-level skeleton line data. When the skeleton lines are constructed according to the highest-level skeleton line data, there may be a situation where the constructed skeleton lines are discontinuous. Therefore, the skeleton line data that need to be upgraded can be upgraded according to the geometric relationship between the skeleton lines corresponding to each skeleton line data and the constructed skeleton lines from the unprocessed skeleton line data, that is, from all the skeleton line data for which the skeleton lines have not been constructed. After the skeleton lines are constructed according to the skeleton line data after the level is adjusted, the continuity between the skeleton lines can be guaranteed, that is, the constructed map can be guaranteed to be consistent and available, thereby improving the accuracy of the map.

[0107] The above device embodiment corresponds to the method embodiment and has the same technical effect as the method embodiment. For specific description, please refer to the method embodiment. The device embodiment is obtained based on the method embodiment. For specific description, please refer to the method embodiment part, which will not be repeated here.

[0108] Next, an electronic device provided by an embodiment of the present application is introduced. Figure 3 , Figure 3 A schematic diagram of a structure of a server provided in an embodiment of the present application, the server comprising:

[0109] one or more processors 40;

[0110] The processor 40 is coupled to a storage device 41, and the storage device 41 is used to store one or more programs.

[0111] When the one or more programs are executed by the one or more processors 40, the electronic device implements the following Figure 1 A technical solution for the map construction method.

[0112] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the following is achieved: Figure 1 The map construction method described.

[0113] The present application provides a computer program product, the computer program product comprising a computer program, the computer program when executed by a processor to achieve the following Figure 1 The map construction method described.

[0114] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0115] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A map construction method, characterized in that: The method comprises: Acquire skeleton line data; the skeleton line data includes skeleton line data of different levels; Extracting primary skeleton line data from the skeleton line data, and constructing a primary skeleton line according to the primary skeleton line data; Extracting the highest level of skeleton line data from the unprocessed skeleton line data as current skeleton line data, and constructing each current skeleton line according to each current skeleton line data; In the unprocessed skeleton line data, according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line, the target skeleton line data meeting the conditions is identified, and the level of the target skeleton line data is upgraded to the same level as the current skeleton line data; constructing a target skeleton line according to the target skeleton line data, and determining whether there is unprocessed skeleton line data; When there is unprocessed skeleton line data, the process returns to the step of extracting the highest level skeleton line data from the unprocessed skeleton line data as current skeleton line data, and constructing the current skeleton line according to the current skeleton line data.

2. The method according to claim 1, characterized in that The step of identifying target skeleton line data that meets the conditions in the unprocessed skeleton line data according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line comprises: Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold; Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold; the second distance threshold is less than the first distance threshold; The skeleton line data corresponding to the first skeleton line and the second skeleton line are both used as target skeleton line data.

3. The method according to claim 2, characterized in that The step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold comprises: Among the skeleton lines corresponding to the unprocessed skeleton line data, any skeleton line is used as the skeleton line to be processed; Determine whether the skeleton line to be processed is parallel to any skeleton line that has been constructed; When the skeleton line to be processed is parallel to any constructed skeleton line, a connected skeleton line connecting the skeleton line to be processed and any constructed skeleton line within a first distance threshold is identified among the skeleton lines corresponding to the unprocessed skeleton line data, and both the skeleton line to be processed and the connected skeleton line are used as the first skeleton line.

4. The method according to claim 3, characterized in that: The step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold, and taking both the skeleton line to be processed and the connected skeleton line as the first skeleton line comprises: Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold; Among the skeleton lines to be processed and the continuous skeleton lines, identifying parallel skeleton line segments that are parallel to the constructed skeleton lines, and counting the lengths of the parallel skeleton line segments; When the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, the skeleton line to be processed and the continuous skeleton line are both used as the first skeleton line.

5. The method according to claim 2, characterized in that: The step of identifying, among the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold comprises: A deep search algorithm is used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

6. A map construction device, characterized in that: The device comprises: A data acquisition module, used to acquire skeleton line data; the skeleton line data includes skeleton line data of different levels; A data extraction module, used to extract primary skeleton line data from the skeleton line data, and construct a primary skeleton line according to the primary skeleton line data; A data processing module, used to extract the highest level skeleton line data from the unprocessed skeleton line data as the current skeleton line data, and construct each current skeleton line according to each current skeleton line data; A data identification module is used to identify target skeleton line data that meets the conditions in the unprocessed skeleton line data according to the geometric relationship between the skeleton line corresponding to each skeleton line data and each constructed skeleton line, and upgrade the level of the target skeleton line data to the same level as the current skeleton line data; The data judgment module is used to construct a target skeleton line according to the target skeleton line data and judge whether there is unprocessed skeleton line data; when there is unprocessed skeleton line data, the data processing module is triggered.

7. The device according to claim 6, characterized in that The data identification module comprises: A first identification submodule is used to identify, among the skeleton lines corresponding to the unprocessed skeleton line data, a first skeleton line that is parallel to any of the constructed skeleton lines and is coherent within a first distance threshold; A second identification submodule is used to identify, from the skeleton lines corresponding to the unprocessed skeleton line data, a second skeleton line that is coherent with any of the constructed skeleton lines within a second distance threshold; the second distance threshold is less than the first distance threshold; The data determination submodule is used to use the skeleton line data corresponding to the first skeleton line and the second skeleton line as target skeleton line data.

8. The device according to claim 7, characterized in that The first identification submodule is specifically used for: Among the skeleton lines corresponding to the unprocessed skeleton line data, any skeleton line is used as the skeleton line to be processed; Determine whether the skeleton line to be processed is parallel to any skeleton line that has been constructed; When the skeleton line to be processed is parallel to any constructed skeleton line, a connected skeleton line connecting the skeleton line to be processed and any constructed skeleton line within a first distance threshold is identified among the skeleton lines corresponding to the unprocessed skeleton line data, and both the skeleton line to be processed and the connected skeleton line are used as the first skeleton line.

9. The device according to claim 8, characterized in that The first identification submodule is specifically used for: Among the skeleton lines corresponding to the unprocessed skeleton line data, identifying a connected skeleton line that connects the skeleton line to be processed and any of the constructed skeleton lines within a first distance threshold; Among the skeleton lines to be processed and the continuous skeleton lines, identifying parallel skeleton line segments that are parallel to the constructed skeleton lines, and counting the lengths of the parallel skeleton line segments; When the ratio of the length of the parallel skeleton line segment to the total length of the skeleton line to be processed and the continuous skeleton line is within a preset ratio range, the skeleton line to be processed and the continuous skeleton line are both used as the first skeleton line.

10. The device according to claim 7, characterized in that The second identification submodule is specifically used for: A deep search algorithm is used to search the skeleton line corresponding to each unprocessed skeleton line data to obtain a second skeleton line that is coherent with any constructed skeleton line within a second distance threshold.

11. An electronic device, characterized in that: include: A memory and a processor, wherein the memory and the processor are coupled; The memory is used to store one or more computer instructions; The processor is used to execute the one or more computer instructions to implement the map construction method according to any one of claims 1 to 5.

12. A computer-readable storage medium having one or more computer instructions stored thereon, characterized in that: The instruction is executed by a processor to implement the map construction method as described in any one of claims 1 to 5.

Images