Multi-packet fusion method, device, medium and equipment based on hierarchical iterative matching

Abstract

The application discloses a multi-pack fusion method based on hierarchical iterative matching, and belongs to the field of map data processing. The method comprises the following steps: performing loop cutting on a plurality of low-precision map packs containing a loop in the same task to obtain low-precision single-pack maps; in each low-precision single-pack map, a corresponding fixed-range submap is generated with a randomly selected data element as a center point, wherein the plurality of submaps have overlapping areas; according to the relative accuracy of the low-precision single-pack maps, a first correlation threshold of a first level and a second correlation threshold of a second level are respectively set in proportion; data elements between two submaps corresponding to each center point in each of two adjacent low-precision single-pack maps are respectively iteratively matched at the first level and the second level at the same time to obtain the most confident matching of each object. The application guarantees the accuracy and efficiency of matching, saves the device cost, and does not depend on the uniqueness of map elements.

Description

Technical Field

[0001] This application relates to the field of map data processing, and in particular to a multi-package fusion method, apparatus, medium and device based on hierarchical iterative matching. Background Technology

[0002] In existing technologies, rule-based methods rely heavily on the uniqueness of map elements when processing map data. These methods first identify the most unique objects within a single map packet, then match these unique objects together, and so on, finding and matching less unique objects. Matching failures can occur if the single map packet lacks unique elements, or if unique elements are missing (e.g., in tunnel scenes or scenes without signs or poles); if unique elements are poorly positioned (e.g., improperly placed signs or poles); or if a large amount of map data is discarded during the matching process. Rule-based methods also rely on thresholds, requiring continuous adjustment for different scenarios, such as determining the range within which an object is considered unique.

[0003] This solution utilizes low-precision equipment to generate high-precision maps through learning and computation, thus solving the problems of high cost of high-precision equipment and reliance on the uniqueness of map elements in existing technologies. Summary of the Invention

[0004] To address the problems of excessive reliance on the uniqueness of map elements and high cost of obtaining high-precision maps in existing technologies, this application mainly provides a multi-package fusion method, apparatus, medium, and device based on hierarchical iterative matching.

[0005] One technical solution adopted in this application is: providing a multi-packet fusion method based on hierarchical iterative matching, which includes:

[0006] Multiple low-precision map packets containing backtracking paths in the same task are split into low-precision single-packet maps to ensure that each low-precision single-packet map does not contain overlapping data elements.

[0007] In each low-precision single-package map, a sub-map with a fixed range is generated with a randomly selected data element as the center point, and there are overlapping areas between multiple sub-maps.

[0008] Based on the relative accuracy of the low-precision single-package map, the first correlation threshold of the first level and the second correlation threshold of the second level are set proportionally, wherein the first correlation threshold is broader than the second correlation threshold.

[0009] In each of the two adjacent low-precision single-package maps, the data elements between the two sub-maps corresponding to each center point are simultaneously iteratively matched at the first and second levels to obtain the most certain match for each object.

[0010] Align the objects that are most confidently matched between any two adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0011] By merging and optimizing high-precision single-package maps, a high-precision map is obtained.

[0012] Another technical solution adopted in this application is: providing a multi-packet fusion device based on hierarchical iterative matching, which includes:

[0013] This module is used to perform loop-based segmentation on multiple low-precision map packets containing backtracking paths in the same task to obtain low-precision single-packet maps, so that each low-precision single-packet map does not contain overlapping data elements.

[0014] This module is used to generate a sub-map with a fixed range in each low-precision single-package map, with randomly selected data elements as the center point, where there are overlapping areas between multiple sub-maps.

[0015] A module for setting a first correlation threshold for the first level and a second correlation threshold for the second level according to the relative accuracy of the low-precision single-package map, wherein the first correlation threshold is broader than the second correlation threshold;

[0016] This module is used to iteratively match the data elements between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps at the first and second levels, respectively, to obtain the most certain match for each object.

[0017] This module is used to align the objects that are most confidently matched between any two adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0018] This module is used to merge and optimize high-precision single-package maps to obtain high-precision maps.

[0019] Another technical solution adopted in this application is to provide a computer-readable storage medium storing computer instructions that are operated to execute the multi-packet fusion method based on hierarchical iterative matching in Scheme 1.

[0020] Another technical solution adopted in this application is: providing a computer device, which includes a processor and a memory, the memory storing computer instructions, which are operated to execute the multi-packet fusion method based on hierarchical iterative matching in Scheme 1.

[0021] The beneficial effects of the technical solution of this application are as follows: This application designs a multi-package fusion method, apparatus, medium, and device based on hierarchical iterative matching. This application ensures the accuracy and efficiency of matching through hierarchical iterative matching, obtains high-precision maps through low-precision single-package map matching and fusion, saves equipment costs, and does not rely on the uniqueness of map elements. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of a specific implementation of a multi-packet fusion method based on hierarchical iterative matching according to this application;

[0024] Figure 2 This is a schematic diagram of a specific example of a multi-packet fusion method based on hierarchical iterative matching proposed in this application;

[0025] Figure 3 This is a schematic diagram of a specific implementation of a multi-packet fusion device based on hierarchical iterative matching according to this application.

[0026] The accompanying drawings have illustrated specific embodiments of this application, 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 concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0027] 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.

[0028] 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.

[0029] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. 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. The embodiments of this application will now be described with reference to the accompanying drawings.

[0030] Figure 1 This paper illustrates a specific implementation of a multi-packet fusion method based on hierarchical iterative matching according to this application. Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching includes:

[0031] Step S101: Perform loop-based segmentation on multiple low-precision map packets containing backtracking paths in the same task to obtain low-precision single-packet maps, so that each low-precision single-packet map does not contain overlapping data elements.

[0032] In this implementation, a task can create multiple low-precision single-package maps. However, in order to prevent the same path from being created twice, the low-precision single-package map containing backtracking needs to be split at the backtracking point to create two low-precision single-package maps that do not contain backtracking, which facilitates subsequent matching.

[0033] It should be noted that a low-precision single-package map refers to a vector map that collects spatial and semantic information about traffic elements such as traffic signs and lane lines by a vehicle traveling along a section of road.

[0034] In a specific example of this application, a low-precision device can collect data in one pass to build a low-precision single-package map. All data collected in one pass belongs to the information within this low-precision single-package map. The low-precision single-package maps built from multiple passes are then matched, fused, and optimized. Because low-precision data collection devices, such as GPS, have low accuracy and limited computing power, the perception results are unreliable. This method uses a pairwise pairing approach; the same object is paired with only one type of data element in the low-precision single-package map. If a low-precision single-package map has a backtracking mechanism, it's equivalent to traversing the same location twice, building maps twice, and having two data elements. The same object will correspond to two data elements represented in the low-precision single-package map.

[0035] exist Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching further includes:

[0036] Step S102: In each low-precision single-package map, a sub-map with a fixed range is generated with a randomly selected data element as the center point, wherein there are overlapping areas between multiple sub-maps.

[0037] In this embodiment, a low-precision single-packet map contains many sub-maps. The low-precision single-packet map is of variable size, while the sub-maps are of fixed size. The purpose of the sub-maps is to facilitate matching. There is a large amount of overlap between multiple sub-maps, which is for subsequent redundant matching (redundancy mechanism) to ensure the robustness of the matching.

[0038] In one specific embodiment of this application, each low-precision single-package map is covered by data elements at a preset distance, and the fixed range is much larger than the preset distance.

[0039] In this embodiment, the fixed range is much larger than the preset distance, which allows multiple sub-maps in each low-precision single-package map to have a large number of overlapping areas, ensuring the robustness of the matching.

[0040] In a specific instance of this application, all low-precision single-package maps in a task are covered by center points spaced 10–20 meters apart; each center point can generate a submap with a fixed range of 100 meters by 100 meters; where 100 is much larger than 10, there is a large amount of overlap between any two adjacent submaps. A single center point may exist in more than a dozen submaps.

[0041] exist Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching further includes:

[0042] Step S103: Based on the relative accuracy of the low-precision single-package map, set the first correlation threshold of the first level and the second correlation threshold of the second level proportionally, wherein the first correlation threshold is broader than the second correlation threshold.

[0043] In this embodiment, the first correlation threshold of the first level is set more leniently based on the relative accuracy of the low-precision single-package map, in order to find a definite match; the second correlation threshold of the second level is set more strictly, in order to increase the most definite match.

[0044] In one specific embodiment of this application, based on the relative accuracy of the low-precision single-package map, a first correlation threshold for the first level and a second correlation threshold for the second level are set proportionally, including: setting a first center distance range, a first displacement deviation, and a first proportion in the first correlation threshold of the first level according to the relative accuracy; and setting a second center distance range, a second displacement deviation, and a second proportion in the second correlation threshold of the second level according to a certain proportion of the relative accuracy.

[0045] In this embodiment, the first correlation threshold of the first level and the second correlation threshold of the second level are set proportionally according to the relative accuracy of the low-precision single-package map, so that the matching is more accurate and complete.

[0046] exist Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching further includes:

[0047] In step S104, the data elements between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-packet maps are simultaneously iteratively matched at the first and second levels to obtain the most certain match for each object.

[0048] In this embodiment, the matching results from the first level are added to the second level for more stringent matching, resulting in more accurate matching.

[0049] In a specific instance of this application, such as Figure 2 As shown, the upward-sloping lines to the right and left represent the translation between map elements corresponding to the same object from one submap to another. Each pair of matches will give a corresponding vertical line. Translation refers to the displacement of the object constructed from one submap to another. Each vertical line represents an object and a displacement. If the length of the vertical line is close to the baseline threshold, it means that the geometric objects are consistent, that is, the objects are the same, and they are added to the most certain group. The length of each vertical line of the most certain group is similar to the system bias. This bias is used to check the results of other remaining most certain objects that were not selected in the first batch.

[0050] In one specific embodiment of this application, the data elements between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps are simultaneously iteratively matched at the first level and the second level to obtain the most certain match for each object. This includes: automatically matching each type of data element between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps to obtain the most certain match for the object corresponding to each type of data element; within the first center range of the first correlation threshold and the second center range of the second correlation threshold, other non-certain match objects whose displacement deviations are within the first displacement deviation of the first correlation threshold and the second displacement deviation of the second correlation threshold, and whose number of other non-certain match objects is within the first proportion of the first correlation threshold and the second proportion of the second correlation threshold, are included in the most certain match.

[0051] In this embodiment, the first level and the second level exist simultaneously. Within the area around the most certain matching object, i.e. the first center range and the second center range, objects with small deviations from the most certain matching object are found based on displacement deviation and included in the most certain matching category.

[0052] In a specific example of this application, for an uncertain object, vertical lines within a 50-meter radius are searched, and each line is compared to it. If a large proportion of the comparisons are consistent, the object is considered consistent; the proportion within 50 meters is approximately 50% or more. Consistency is used when the mapping is well-constructed.

[0053] In one specific embodiment of this application, within the first center range of the first correlation threshold and the second center range of the second correlation threshold, other non-confident matching objects whose displacement deviations are within the first displacement deviation of the first correlation threshold and the second displacement deviation of the second correlation threshold, and whose number is within the first proportion of the first correlation threshold and the second proportion of the second correlation threshold, are included in the row of most certain matches. The method further includes: through multiple iterative matching, outputting the row of most certain matches determined by the second correlation threshold in the second level as the result of most certain matching.

[0054] In this embodiment, in the row and column of the most certain match found in each iteration, other matching results are searched according to the first correlation threshold of the first level and the second correlation threshold of the second level to ensure that every object can be matched.

[0055] In a specific example of this application, two levels are used: a lenient first level (within 50 meters, deviation of 2 meters, and a proportion of over 50%) and a strict second level (within 50 meters, deviation of 1 meter, and a proportion of over 50%). Matches meeting the first level are retained but not used as the final output. The stricter second level is not used directly because it might not find the most certain match. If the strict second level were used, the first batch of most certain matches would be found, the second batch would search for certain objects near the first batch's most certain matches, but the second batch would find fewer objects, and the third batch would find none, with no new objects to add to the most certain match list. The lenient first level is set to allow more matching results to be added to the most certain match list, continuing the iterative matching process, and finally selecting the first batch of strict second-level matches as the final output. Adding unfavorable matches to favorable ones, and specifying which level to add them to, ensures that the most certain match list is not limited to a single batch but is continuously added iteratively. A deviation of 2 meters refers to a length difference of 2 meters from the most certain match. For example, if the most certain displacement is 0.5 meters, and the displacement of the object to be judged is 2.5 meters, then the requirement is met. Each judgment checks all surrounding objects. As more and more objects are added, accuracy decreases, so a proportion is needed to control the accuracy. Added objects may be removed, but may be added again in the next iteration. Each iteration requires a re-comparison for each object.

[0056] In one specific embodiment of this application, automatic matching is performed between each data element in the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-packet maps to obtain the most certain match of the object corresponding to each data element. The method further includes: simultaneously extracting features from each data element in the two sub-maps to obtain feature information corresponding to the two sub-maps; simultaneously inputting the feature information corresponding to the two sub-maps into an attention map neural network for automatic matching to obtain a matching score; and determining the object corresponding to the most certain match that meets the geometric consistency through the matching score.

[0057] In this embodiment, the information of the data elements to be matched is extracted to lay the foundation for subsequent matching; different data elements in each sub-graph can be extracted simultaneously. When matching, the feature information of the data elements in the corresponding sub-graphs of the same center point in two low-precision single-package maps is matched simultaneously, which is efficient and convenient.

[0058] In one specific embodiment of this application, the feature information includes, but is not limited to, the category, location coordinates, orientation, size, and / or height of the data element.

[0059] In this embodiment, the semantic feature information in the feature information includes, but is not limited to, the type, size, relative depth, and orientation of other elements surrounding the data element; the perceptual feature information and attribute feature information in the feature information include the position coordinates of the data element.

[0060] In a specific example of this application, the relative accuracy of a low-precision single-package map is 2%, equivalent to a deviation of 2 meters per 100 meters, or a deviation of 1 meter per 50 meters. If there are two low-precision single-package maps, the deviation will be even greater, possibly 2 meters per 50 meters. The center distance range can be set to approximately 40 to 60 meters, with the threshold set based on the relative accuracy standard of the low-precision single-package map. The strict second level is the relative accuracy itself, while the lenient first level is twice the relative accuracy.

[0061] exist Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching further includes:

[0062] Step S105: Align the objects that are most certain to match between any two adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0063] In this embodiment, through multiple iterations of pose graph optimization, matching objects from every two low-precision single-packet maps are combined to obtain high-precision single-packet maps. This improves the accuracy of the maps.

[0064] exist Figure 1 In the specific implementation shown, the multi-packet fusion method based on hierarchical iterative matching further includes:

[0065] Step S106: Merge and optimize the high-precision single-package maps to obtain a high-precision map.

[0066] In this embodiment, the map accuracy is improved through fusion optimization.

[0067] The relative accuracy of the low-precision single-package map in this application is acceptable, but it cannot be ruled out that there may still be missing objects in the low-precision single-package map. This application mainly utilizes the relative positional relationship between different map elements for iterative matching. For each object, there may be multiple sub-maps, resulting in multiple matching results. The most confident match of the network is prioritized as the most robust match. Based on these robust matches, other matches that conform to geometric consistency are iteratively selected.

[0068] Figure 3 This paper illustrates a specific implementation of a multi-packet fusion device based on hierarchical iterative matching according to this application. Figure 3 In the specific implementation shown, the multi-packet fusion device based on hierarchical iterative matching mainly includes:

[0069] Module 301 is used to perform loop-based segmentation on multiple low-precision map packets containing backtracking paths in the same task to obtain low-precision single-packet maps, so that each low-precision single-packet map does not contain overlapping data elements.

[0070] Module 302 is used to generate a sub-map with a fixed range in each low-precision single-package map, with randomly selected data elements as the center point, where there are overlapping areas between multiple sub-maps;

[0071] Module 303 is used to set a first correlation threshold for the first level and a second correlation threshold for the second level according to the relative accuracy of the low-precision single-package map, wherein the first correlation threshold is broader than the second correlation threshold.

[0072] Module 304 is used to iteratively match the data elements between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-packet maps at the first and second levels, respectively, to obtain the most certain match for each object.

[0073] Module 305 is used to align the objects that are most confidently matched between each pair of adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0074] Module 306 is used to merge and optimize high-precision single-package maps to obtain high-precision maps.

[0075] In this embodiment, the uniqueness of map elements is not dependent on the hierarchical iterative matching method, thus saving equipment costs.

[0076] The multi-packet fusion apparatus based on hierarchical iterative matching provided in this application can be used to execute the multi-packet fusion method based on hierarchical iterative matching described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0077] In one specific embodiment of this application, the functional modules in the multi-packet fusion device based on hierarchical iterative matching can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0078] 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.

[0079] 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.

[0080] In another specific embodiment of this application, a computer-readable storage medium stores computer instructions that are operated to perform the multi-packet fusion method based on hierarchical iterative matching in any embodiment.

[0081] 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 multi-packet fusion method based on hierarchical iterative matching in any embodiment.

[0082] 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.

[0083] 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.

[0084] The above description is merely an embodiment of this application and does not limit the patent scope of this 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 patent protection scope of this application.

Claims

1. A multi-packet fusion method based on hierarchical iterative matching, characterized in that, include: Multiple low-precision map packets containing backtracking paths in the same task are subjected to loop-based segmentation to obtain low-precision single-packet maps, so that each low-precision single-packet map does not contain overlapping data elements. In each of the low-precision single-package maps, a sub-map with a fixed range is generated with a randomly selected data element as the center point, wherein there are overlapping areas between multiple sub-maps; Based on the relative accuracy of the low-precision single-package map, a first-level first correlation threshold and a second-level second correlation threshold are set proportionally, wherein the first correlation threshold is broader than the second correlation threshold, the second level is the relative accuracy itself, and the first level is twice the relative accuracy. The process of setting the first-level first correlation threshold and the second-level second correlation threshold proportionally based on the relative accuracy of the low-precision single-package map includes: Based on the relative accuracy, a first center distance range, a first displacement deviation, and a first proportion are set in the first relevant threshold of the first level; Based on a certain proportion of the relative accuracy, the second center distance range, the second displacement deviation, and the second proportion in the second relevant threshold of the second level are set; The data elements between the two subgraphs corresponding to each center point in each of the two adjacent low-precision single-package maps are subjected to hierarchical iterative matching to obtain the most certain match for each object. The hierarchical iterative matching of the data elements between the two subgraphs corresponding to each center point in each of the two adjacent low-precision single-package maps includes: adding the matching result of the data elements between the two subgraphs matched at the first level to the second level for matching. Align the objects corresponding to the most certain match in each pair of adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map; The high-precision single-package maps are merged and optimized to obtain a high-precision map.

2. The multi-packet fusion method based on hierarchical iterative matching as described in claim 1, characterized in that, The data elements between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps are subjected to hierarchical iterative matching to obtain the most certain match for each object, including: For each data element between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps, automatic matching is performed to obtain the most certain match of the object corresponding to each data element; Within the first central range of the first correlation threshold and the second central range of the second correlation threshold, other non-certain matching objects whose displacement deviation is within the first displacement deviation of the first correlation threshold and the second displacement deviation of the second correlation threshold, and whose number is within the first proportion of the first correlation threshold and the second proportion of the second correlation threshold, are included in the most certain match.

3. The multi-packet fusion method based on hierarchical iterative matching as described in claim 2, characterized in that, The step of including, within the first central range of the first correlation threshold and the second central range of the second correlation threshold, other non-certain matching objects whose displacement deviation is within the first displacement deviation of the first correlation threshold and the second displacement deviation of the second correlation threshold, and whose number is within the first proportion of the first correlation threshold and the second proportion of the second correlation threshold, in the column of most certain matches, further includes: Through multiple iterative matching, the row and column of the most certain match determined by the second correlation threshold in the second level are output as the result of the most certain match.

4. The multi-packet fusion method based on hierarchical iterative matching as described in claim 2, characterized in that, The step of automatically matching each data element between the two sub-maps corresponding to each center point in each of the two adjacent low-precision single-package maps to obtain the most certain match of the object corresponding to each data element further includes: Simultaneously, feature extraction is performed on each data element corresponding to the two subgraphs to obtain the feature information corresponding to the two subgraphs. Simultaneously, the feature information corresponding to the two sub-graphs is input into the attention graph neural network for automatic matching to obtain a matching score; The most certain match corresponding to the geometrically consistent object is determined based on the matching score.

5. The multi-packet fusion method based on hierarchical iterative matching as described in claim 4, characterized in that, The feature information includes the category, location coordinates, orientation, size, and / or height of the data element.

6. The multi-packet fusion method based on hierarchical iterative matching as described in claim 1, characterized in that, Each of the low-precision single-package maps is covered by data elements at a preset distance, and the fixed range is greater than the preset distance.

7. A multi-packet fusion device based on hierarchical iterative matching, characterized in that, include: A module for performing loop-based segmentation on multiple low-precision map packets containing backtracking paths in the same task to obtain low-precision single-packet maps, so that each low-precision single-packet map does not contain overlapping data elements. A module for generating a corresponding fixed-range sub-map in each of the low-precision single-package maps, with randomly selected data elements as the center point, wherein there are overlapping areas between the multiple sub-maps; A module for setting a first correlation threshold for a first level and a second correlation threshold for a second level proportionally based on the relative accuracy of the low-precision single-package map, wherein the first correlation threshold is broader than the second correlation threshold, the second level is the relative accuracy itself, and the first level is twice the relative accuracy. The step of setting the first correlation threshold for the first level and the second correlation threshold for the second level proportionally based on the relative accuracy of the low-precision single-package map includes: setting a first center distance range, a first displacement deviation, and a first proportion in the first correlation threshold of the first level based on the relative accuracy; and setting a second center distance range, a second displacement deviation, and a second proportion in the second correlation threshold of the second level based on a certain proportion of the relative accuracy. The module is used to perform hierarchical iterative matching of data elements between the two subgraphs corresponding to each center point in each of the two adjacent low-precision single-package maps to obtain the most certain match for each object. The hierarchical iterative matching of data elements between the two subgraphs corresponding to each center point in each of the two adjacent low-precision single-package maps includes: adding the matching result of the data elements between the two subgraphs matched at the first level to the second level for matching. A module for aligning the objects corresponding to the most certain match in each of two adjacent low-precision single-packet maps one by one to obtain a high-precision single-packet map; This module is used to fuse and optimize the high-precision single-package maps to obtain a high-precision map.

8. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are operated to perform the multi-packet fusion method based on hierarchical iterative matching as described in any one of claims 1-6.

9. A computer device comprising a processor and a memory storing computer instructions, wherein the processor operates the computer instructions to perform the multi-packet fusion method based on hierarchical iterative matching as described in any one of claims 1-6.

Images