A robust multi-packet matching and fusion method and apparatus based on subgraph redundancy

Abstract

This application discloses a robust multi-packet matching and fusion method based on subgraph redundancy, belonging to the field of map data processing. The method includes generating a subgraph with a fixed range in each low-precision single-packet map, centered on randomly selected data elements, where multiple subgraphs overlap. For each pair of low-precision single-packet maps, the two subgraphs corresponding to each center point are automatically matched sequentially to obtain matching scores for different data elements between the two subgraphs. The objects corresponding to the most certain matching that conforms to geometric consistency are determined based on the matching scores. Based on the most certain matching, other objects corresponding to the most certain matching that conform to geometric consistency and are adjacent to the most certain matching are obtained. The objects corresponding to the most certain matching in multiple low-precision single-packet maps are aligned one-to-one to obtain a high-precision single-packet map. This application ensures the robustness of the matching through a large number of redundant subgraphs, saves equipment costs, and does not rely 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-packet robust matching and fusion method and apparatus based on subgraph redundancy. 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 problem 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-packet robust matching and fusion method and apparatus based on subgraph redundancy.

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

[0006] Multiple low-precision single-package maps obtained from the same task, none of which 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] In each of the two low-precision single-package maps, the two sub-maps corresponding to each center point are automatically matched in sequence to obtain the matching score of different data elements between the two sub-maps. The object corresponding to the most certain match that meets geometric consistency is determined by the matching score.

[0009] Based on the most certain match, obtain the objects corresponding to other most certain matches that are geometrically consistent and are adjacent to the most certain match;

[0010] Align the objects with the most certain matching from multiple 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 robust matching and fusion device based on subgraph redundancy, which includes:

[0013] A module for acquiring multiple low-precision single-package maps that do not contain overlapping data elements in the same task;

[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] The two sub-maps corresponding to each center point in each of the two low-precision single-package maps are automatically matched sequentially to obtain the matching score corresponding to different data elements between the two sub-maps. The module corresponding to the most certain matching object that meets the geometric consistency is determined by the matching score.

[0016] A module for obtaining objects that are geometrically consistent and adjacent to the most certain match, based on the most certain match;

[0017] This module is used to align the objects that are most confidently matched among multiple 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 robust matching and fusion method based on subgraph redundancy 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 robust matching fusion method based on subgraph redundancy in Scheme 1.

[0021] The beneficial effects of the technical solution in this application are as follows: This application designs a multi-packet robust matching and fusion method and apparatus based on subgraph redundancy. This application generates a large number of redundant subgraphs to ensure the robustness of the matching for subsequent redundant matching (redundancy mechanism); low-precision single-packet maps save equipment costs, and most certain matching saves computing power, without relying 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 robust matching and fusion method based on subgraph redundancy according to this application;

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

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

[0026] The accompanying drawings illustrate 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 particular 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 robust matching and fusion method based on subgraph redundancy, as proposed in this application. Figure 1 In the specific implementation shown, the multi-packet robust matching and fusion method based on subgraph redundancy includes:

[0031] Step S101: Obtain multiple low-precision single-package maps that do not contain overlapping data elements in the same task.

[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 robust matching and fusion method based on subgraph redundancy 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, 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. This includes: distributing data elements at predetermined distance intervals in each low-precision single-package map, generating a corresponding sub-map with a fixed range with each data element as the center point, wherein the fixed range is the product of a preset length and a preset width, and both the preset length and the preset width are greater than the predetermined distance interval, so that there are overlapping areas between multiple fixed-range sub-maps.

[0039] In this embodiment, the number of subgraphs is variable, determined by the number of data elements in the low-precision single-package map. The number of subgraphs can be equal to or less than the number of data elements. There are significant overlaps between the multiple subgraphs, ensuring robust 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 robust matching and fusion method based on subgraph redundancy further includes:

[0042] In step S103, the two sub-maps corresponding to each center point in each of the two low-precision single-package maps are automatically matched in sequence to obtain the matching scores corresponding to different data elements between the two sub-maps. The objects corresponding to the most certain matching that meet the geometric consistency are determined by the matching scores.

[0043] In this implementation, when matching two low-precision single-package maps, multiple pairs of sub-maps are matched simultaneously, obtaining matching scores for different types of data elements. Geometric consistency is then checked based on these matching scores to determine the object with the highest certainty of a match. This method does not rely on the uniqueness of map elements, does not discard map data, and eliminates the need for constantly adjusting rule thresholds, thus reducing unnecessary complexity.

[0044] In one specific embodiment of this application, the two sub-graphs corresponding to each center point in every two low-precision single-package maps are automatically matched sequentially to obtain matching scores for different data elements between the two sub-graphs. This includes: simultaneously extracting features from the different data elements corresponding to the two sub-graphs to obtain feature information for the two sub-graphs; and inputting the feature information for the two sub-graphs into an attention map neural network for automatic matching to obtain matching scores.

[0045] 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.

[0046] In one specific embodiment of this application, there is at least one method for feature extraction of the same type of data element in the same subgraph, and different methods for feature extraction of different types of data elements.

[0047] In this embodiment, different extraction methods are selected based on the different characteristics of the same type of data element, and different extraction methods are selected for different types of data elements with different characteristics.

[0048] In one specific embodiment of this application, feature extraction is performed simultaneously on different types of data elements corresponding to two sub-graphs to obtain feature information corresponding to the two sub-graphs. This includes: in the same sub-graph, when the data element is of the first category, a trained semantic map element processing network is used to enhance the features of the surrounding element information to obtain semantic feature information, and a trained multilayer perceptron is used to encode the features of its own attribute information to obtain perceptual feature information. The semantic feature information and perceptual feature information are superimposed to obtain the overall feature information corresponding to the same type of data element; when the data element is of the second category, a sub-layer layer-level neural network is used to encode the features of its own attribute information to obtain attribute feature information, thereby obtaining the feature information corresponding to the two sub-graphs respectively.

[0049] In this embodiment, various networks are used to encode and extract features from data elements, resulting in feature information that makes matching data elements easier and more convenient. Feature extraction can be performed simultaneously on each sub-map within multiple low-precision single-package maps, improving efficiency.

[0050] In a specific example of this application, the data elements in the subgraph are divided into two types because signs and poles are clearly different from lane lines, so a single method cannot be used to resolve the two categories. Signs and poles are composed of lines, which can only be viewed as mirror images, while lane lines are composed of a series of points, whose displacement is three-dimensional. Therefore, the matching of points and lines is different.

[0051] exist Figure 2 In a specific example of the multi-packet robust matching fusion method based on subgraph redundancy shown in this application, in Figure 2 In this model, data elements in the subgraph are divided into two types: Landmarks, which consist of points, such as signs and traffic lights; and Lines, which consist of lines, such as lane lines. Landmarks are used for feature extraction based on information from surrounding elements (types, positions (direction, depth)) and their own attributes (x, y, type). Lines are composed of a series of sampled points, and their features are extracted based on their own attributes (x, y, type). Landmarks currently include features such as (category, x, y, smbert); future features will include size, orientation, and height above ground. In experiments, the Semantic Map Element Processing Network (SMBert) does indeed improve landmark matching, but its drawback is its high time consumption. Multilayer Perceptron (MLP), a feedforward artificial neural network, can handle non-linear separable problems and is used to encode data elements at points. SubgraphLayer, derived from VectorNet, can encode a series of points. Graph Attention Networks are used for graph matching to obtain matching scores between different data elements in two subgraphs.

[0052] In one specific embodiment of this application, determining the object corresponding to the most certain match that meets geometric consistency by matching score includes: when the matching score is consistent with a benchmark threshold, the data element corresponding to the matching score meets geometric consistency; and when the proportion of the number of matching scores that are consistent with the benchmark threshold in the matching score is greater than a preset threshold, the data element corresponding to the matching score is the object corresponding to the most certain match.

[0053] In this embodiment, multiple matching results can be filtered out using a benchmark threshold. All multiple matching results meet the geometric consistency requirement. When the proportion of the benchmark threshold's number to the total number of matching scores reaches a preset threshold, it is considered the most certain match. This ensures the accuracy of the matching.

[0054] In one specific embodiment of this application, in multiple sub-graphs, based on the feature information of different types of extracted data elements, multiple corresponding semantic map element processing networks, multilayer perceptual networks, and sub-layer level neural networks are trained respectively.

[0055] In this embodiment, the semantic map element processing network, multilayer perceptron, and sublayer-level neural network are pre-trained, making subsequent feature extraction and matching more convenient and faster. Using feature information from different types of data elements can improve matching efficiency.

[0056] In a specific instance of this application, due to the lack of complete ground truth data, it is necessary to construct pseudo-single-packet data with complete ground truth. The attention graph neural network is pre-trained using this pseudo-single-packet data. The pre-trained attention graph neural network is then retrained using incomplete ground truth from the production line. Through these two training steps, pre-training and retraining, the attention graph neural network can be used for matching between subgraphs. The pseudo-single-packets are newly generated and used for the first training of the attention graph neural network, compensating for the lack of ground truth data. The second training of the attention graph neural network uses actual ground truth from the production line. Complete ground truth refers to all elements in the low-precision single-packet map having a ground truth match. Ground truth is generated on the production line using the rolebase method, and these ground truths are missing.

[0057] exist Figure 1 In the specific implementation shown, the multi-packet robust matching and fusion method based on subgraph redundancy further includes:

[0058] Step S104: Based on the most certain match, obtain the objects corresponding to other most certain matches that are geometrically consistent and adjacent to the most certain match.

[0059] In this implementation, if a pair of matches represents the same object, it meets the geometric consistency requirement. Near the most certain match, the matching results of uncertain objects are checked to ensure that no object is missed in the low-precision single-package map, guaranteeing the completeness of the matching.

[0060] exist Figure 1 In the specific implementation shown, the multi-packet robust matching and fusion method based on subgraph redundancy further includes:

[0061] Step S105: Align the objects that are most certain to match in the multiple low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0062] 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.

[0063] exist Figure 1 In the specific implementation shown, the multi-packet robust matching and fusion method based on subgraph redundancy further includes:

[0064] Step S106: Merge and optimize the high-precision single-package maps to obtain a high-precision map.

[0065] In this embodiment, the map accuracy is improved through fusion optimization.

[0066] This application uses low-precision acquisition equipment to collect map data and establish low-precision single-package maps. To improve matching accuracy, the low-precision single-package maps with backtracking paths are segmented to ensure that each low-precision single-package map does not contain duplicate map data elements. Each low-precision single-package map has a center point distribution with a certain interval. Multiple center points are randomly selected to generate multiple corresponding sub-maps with fixed ranges. Each low-precision single-package map has a variable length, while each sub-map has a fixed length. The multiple sub-maps with fixed lengths contain a large amount of redundancy, which facilitates subsequent matching between data elements. The data elements in each sub-map are extracted according to their categories, and the information of the elements to be matched is extracted to form the basis for subsequent matching. The data elements between the two sub-maps corresponding to the same center point in two low-precision single-package maps are matched to obtain a matching score. The most confidently matched object is determined by the matching score and a benchmark threshold. The results of other uncertainly matched objects are checked in the vicinity of the first batch of most confidently matched objects. This scheme can save equipment costs, does not rely on the uniqueness of map elements, and can also ensure matching accuracy.

[0067] Figure 3 This paper illustrates a specific implementation of a multi-packet robust matching and fusion device based on subgraph redundancy according to this application. Figure 3 In the specific implementation shown, the multi-packet robust matching and fusion device based on subgraph redundancy mainly includes:

[0068] Module 301 is used to acquire multiple low-precision single-package maps that do not contain overlapping data elements in the same task;

[0069] 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, wherein there are overlapping areas between multiple sub-maps.

[0070] Module 303 is used to automatically match the two sub-maps corresponding to each center point in every two low-precision single-package maps in turn, obtain the matching score corresponding to different data elements between the two sub-maps, and determine the object corresponding to the most certain match that meets geometric consistency through the matching score.

[0071] Module 304 is used to obtain, based on the most certain match, other objects that meet geometric consistency and are adjacent to the most certain match.

[0072] Module 305 is used to align the objects that are most confidently matched among multiple low-precision single-packet maps one by one to obtain a high-precision single-packet map.

[0073] Module 306 is used to merge and optimize high-precision single-package maps to obtain high-precision maps.

[0074] In this embodiment, by performing loop-based segmentation on the low-precision single-packet map containing backtracking paths, an object has only one corresponding data element in a low-precision single-packet map, which facilitates subsequent matching and saves equipment costs for low-precision devices. By splitting the low-precision single-packet map into multiple sub-maps for matching, it is more efficient and accurate. The most certain matching method makes this solution independent of the uniqueness of map elements and saves more computing power.

[0075] In one specific embodiment of this application, 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. This includes: distributing data elements at predetermined distance intervals in each low-precision single-package map, generating a corresponding sub-map with a fixed range with each data element as the center point, wherein the fixed range is the product of a preset length and a preset width, and both the preset length and the preset width are greater than the predetermined distance interval, so that there are overlapping areas between multiple fixed-range sub-maps.

[0076] In this embodiment, the number of subgraphs is variable, determined by the number of data elements in the low-precision single-package map. The number of subgraphs can be equal to or less than the number of data elements. There are significant overlaps between the multiple subgraphs, ensuring robust matching.

[0077] The multi-packet robust matching and fusion apparatus based on subgraph redundancy provided in this application can be used to execute the multi-packet robust matching and fusion method based on subgraph redundancy described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0078] In one specific embodiment of this application, the functional modules of the multi-packet robust matching and fusion device based on subgraph redundancy can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0079] 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.

[0080] 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.

[0081] In another specific embodiment of this application, a computer-readable storage medium stores computer instructions that are operated to perform the multi-packet robust matching fusion method based on subgraph redundancy in any embodiment.

[0082] 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 robust matching fusion method based on subgraph redundancy in any embodiment.

[0083] 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.

[0084] 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.

[0085] 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 robust multi-packet matching and fusion method based on subgraph redundancy, characterized in that, include: Multiple low-precision single-package maps that do not contain overlapping data elements in the same task are obtained, wherein the same task includes one low-precision single-package map for each path segment; 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. There are overlapping areas between multiple sub-maps, and the sub-maps with the fixed range are sub-maps of the same size and shape. The two sub-maps corresponding to each center point in each of the two low-precision single-package maps are automatically matched sequentially to obtain the matching score corresponding to different data elements between the two sub-maps. The object corresponding to the most certain match that meets geometric consistency is determined by the matching score. Based on the most certain match, obtain the objects corresponding to other most certain matches that are adjacent to the most certain match and conform to the geometric consistency. Align the objects corresponding to the most certain matches in the multiple 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 robust matching and fusion method based on subgraph redundancy as described in claim 1, characterized in that, In each of the low-precision single-package maps, a sub-map with a fixed range is generated, centered on a randomly selected data element. Multiple sub-maps overlap, including: In each of the low-precision single-package maps, data elements are distributed at predetermined distance intervals. A sub-map with a fixed range is generated with each data element as the center point. The fixed range is the product of a preset length and a preset width. Both the preset length and the preset width are greater than the predetermined distance interval, so that there are overlapping areas between the sub-maps of multiple fixed ranges.

3. The multi-packet robust matching and fusion method based on subgraph redundancy as described in claim 1, characterized in that, The two sub-maps corresponding to each center point in every two low-precision single-package maps are automatically matched sequentially to obtain matching scores for different data elements between the two sub-maps, including: Simultaneously, feature extraction is performed on the different types of data elements corresponding to the two subgraphs to obtain the feature information corresponding to the two subgraphs respectively; The feature information corresponding to the two subgraphs is input into the attention map neural network for automatic matching to obtain a matching score.

4. The robust multi-packet matching and fusion method based on subgraph redundancy as described in claim 3, characterized in that, There is at least one way to extract features from the same type of data element in the same subgraph, and different ways to extract features from different types of data elements.

5. The robust multi-packet matching and fusion method based on subgraph redundancy as described in claim 3, characterized in that, The simultaneous extraction of features from different types of data elements corresponding to the two subgraphs yields feature information for each of the two subgraphs, including: In the same sub-graph, when the data element is of the first category, the features of the surrounding element information are enhanced by the trained semantic map element processing network to obtain semantic feature information, and the features of its own attribute information are encoded by the trained multilayer perceptron to obtain perceptual feature information. The semantic feature information and the perceptual feature information are superimposed to obtain the overall feature information corresponding to the same type of data element. When the data element is of the second category, the features of its own attribute information are encoded using a sub-layer-level neural network to obtain attribute feature information, and then the feature information corresponding to the two sub-graphs are obtained respectively.

6. The multi-packet robust matching and fusion method based on subgraph redundancy as described in claim 1, characterized in that, The step of determining the object corresponding to the most certain match that meets geometric consistency through the matching score includes: When the matching score is consistent with the benchmark threshold, the data element corresponding to the matching score meets the geometric consistency. Furthermore, when the proportion of the number of matching scores that are consistent with the benchmark threshold is greater than the preset threshold, the data element corresponding to the matching score is the object that is most confidently matched.

7. The multi-packet robust matching and fusion method based on subgraph redundancy as described in claim 5, characterized in that, In the multiple sub-graphs, based on the feature information of different types of extracted data elements, the multiple corresponding semantic map element processing networks, the multilayer perceptual networks, and the sub-layer level neural networks are trained respectively.

8. A robust multi-packet matching and fusion device based on subgraph redundancy, characterized in that, include: Multiple low-precision single-package maps used to acquire data elements that do not overlap in the same task, wherein the same task includes a module of the low-precision single-package map for each path segment; This module is used to generate 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 multiple sub-maps, and the fixed-range sub-maps are sub-maps of the same size and shape. The module is used to automatically match the two sub-maps corresponding to each center point in each of the two low-precision single-package maps in turn, to obtain the matching score corresponding to different data elements between the two sub-maps, and to determine the module corresponding to the object that meets the most certain matching of geometric consistency through the matching score. A module for obtaining, based on the most certain match, other objects that conform to the geometric consistency and are adjacent to the most certain match; A module for aligning the objects corresponding to the most certain matches in multiple low-precision single-package maps one by one to obtain a high-precision single-package map; This module is used to fuse and optimize the high-precision single-package maps to obtain a high-precision map.

9. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are operated to perform the multi-packet robust matching and fusion method based on subgraph redundancy as described in any one of claims 1-7.

10. A computer device comprising a processor and a memory storing computer instructions, wherein the processor operates the computer instructions to perform the multi-packet robust matching fusion method based on subgraph redundancy as described in any one of claims 1-7.

Images