Data matching method, map updating method, device and electronic equipment

Abstract

This disclosure provides a method for matching data with roads, a map updating method, an apparatus, and an electronic device. The method includes: acquiring currently collected road data, a current collection trajectory, and existing road information; determining candidate roads that match the currently collected data from the existing road information based on the current collection trajectory; if there are associated roads parallel to the candidate roads in the existing road information, acquiring existing reference data associated with the candidate roads; determining similar features in the currently collected data and the existing reference data; and determining the matching relationship between the currently collected data and the candidate roads by the positions of the similar features in the currently collected data and the existing reference data. This technical solution can avoid mismatching the currently collected data to parallel roads of the actual matching roads, and can improve the matching accuracy of the currently collected data and roads, the accuracy of road attribute data production, and the production efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of geographic information technology, specifically to a method for matching data with roads, a map updating method, an apparatus, and an electronic device. Background Technology

[0002] In the process of producing road attribute data, parallel roads are usually close together and have similar vertical connectivity. Matching collected data with roads solely based on trajectory connectivity or similarity can easily lead to incorrect matching due to positioning deviations, potentially resulting in incorrect attribute creation for the generated road data. To address this issue, a manual review process is added. However, manual review is insufficient for determining correct matching with only a single data collection run. With multiple data collection runs, it's necessary to repeatedly compare data from each run to eliminate outliers and determine the matching relationship between the current data and parallel roads. This approach is either prone to errors or time-consuming.

[0003] Therefore, a solution is needed to quickly and accurately determine the matching relationship between collected data and roads. Summary of the Invention

[0004] This disclosure provides a method for matching data with roads, a map updating method, an apparatus, and an electronic device.

[0005] In a first aspect, this disclosure provides a method for matching data with roads, comprising:

[0006] Acquire current data, current data collection trajectory, and existing road information for the road;

[0007] Based on the current collected trajectory, candidate roads that match the current collected data are determined from the existing road information;

[0008] If there is an associated road parallel to the candidate road in the existing road information, then obtain the existing reference data associated with the candidate road;

[0009] Identify similar features in the currently collected data and the existing reference data;

[0010] The matching relationship between the current data and the candidate roads is determined by the positions of the similar features in the current data and in the existing reference data.

[0011] Furthermore, the method also includes:

[0012] Acquire multiple historical data sets, the historical data collection trajectories of the historical data sets, and existing road information;

[0013] Based on the historical data collection trajectory, at least one initial associated road of the historical data collection is determined from the existing road information;

[0014] When associating multiple historical data sets with the initial associated road, the one with the highest matching degree is selected from the multiple historical data sets as the existing reference data for the initial associated road; the candidate road is one of the initial associated roads.

[0015] Further, identifying similar features in the currently collected data and the existing reference data includes:

[0016] Utilize image features to identify target road elements of a specified type in the currently acquired data and the existing reference data;

[0017] The similar features are determined based on the similarity between the target road elements in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road elements.

[0018] Further, determining the similar features based on the similarity between the target road element in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road element, includes:

[0019] If the similarity of the image features of the target road element is greater than or equal to the first similarity threshold, then the similarity of the image features of the reference road element is determined.

[0020] When the similarity of the image features of the reference road element in the currently collected data and the existing reference data is greater than or equal to the second similarity threshold, the target road element is identified as the similar land feature.

[0021] Further, by determining the matching relationship between the current data and the candidate roads based on the positions of the similar features in the current data and in the existing reference data, the following steps are taken:

[0022] Based on the relative positional relationship between the similar feature and the reference road element within the second preset range of the similar feature, determine whether the position of the similar feature is consistent in the current data and the existing reference data;

[0023] If the similar feature is in the same position in the current data and the existing reference data, then determine the first relative position of the similar feature in the current data relative to the data collection road, and the second relative position of the similar feature in the existing reference data relative to the data collection road in the existing reference data;

[0024] Based on the first relative position and the second relative position, it is determined whether the currently collected data matches the candidate road.

[0025] Furthermore, the method also includes:

[0026] If there is no associated road parallel to the candidate road in the existing road information, then the currently collected data is determined to match the candidate road.

[0027] Secondly, embodiments of the present invention provide a map updating method, comprising:

[0028] Obtain the currently collected data;

[0029] Based on the method described in the first aspect, a target road matching the currently collected data is determined;

[0030] The map data corresponding to the target road is updated based on the currently collected data.

[0031] Thirdly, embodiments of the present invention provide a data-road matching device, comprising:

[0032] The first acquisition module is configured to acquire the current data collected on the road, the current acquisition trajectory, and existing road information;

[0033] The first determining module is configured to determine candidate roads that match the currently collected data from the existing road information based on the current collected trajectory.

[0034] The second acquisition module is configured to acquire existing reference data associated with the candidate road if there is an associated road parallel to the candidate road in the existing road information.

[0035] The second determining module is configured to determine similar features in the currently collected data and the existing reference data;

[0036] The third determining module is configured to determine the matching relationship between the current data and the candidate roads by using the positions of the similar features in the current data and the positions in the existing reference data.

[0037] The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above function.

[0038] In one possible design, the above-described device includes a memory and a processor. The memory stores one or more computer instructions that support the device in performing the corresponding methods described above, and the processor is configured to execute the computer instructions stored in the memory. The device may also include a communication interface for communicating with other devices or communication networks.

[0039] Fourthly, embodiments of this disclosure provide an electronic device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any of the above aspects.

[0040] Fifthly, embodiments of this disclosure provide a computer-readable storage medium for storing computer instructions used by any of the above-described devices, which, when executed by a processor, are used to implement the methods described in any of the above aspects.

[0041] In a sixth aspect, embodiments of this disclosure provide a computer program product comprising computer instructions which, when executed by a processor, are used to implement the methods described in any of the preceding aspects.

[0042] The technical solutions provided in this disclosure may have the following beneficial effects:

[0043] In this embodiment, after acquiring the current data, in order to accurately match the matching value of the current data to the actual road, candidate roads can be initially matched from existing road information based on the acquisition trajectory of the current data. If the candidate road has parallel roads in the existing road information, the actual matching road for the current data may not be the candidate road, but a parallel road of the candidate road. Therefore, this embodiment further acquires existing reference data associated with the candidate road and identifies similar features in the existing reference data and the current data. By determining the position of the similar features in the existing reference data and the current data, it is determined whether the current data matches the candidate road associated with the existing reference data. Through the above method, when there are parallel roads to the candidate road that matches the current acquisition trajectory of the current data, it is possible to avoid mismatching the current data to a parallel road of the actual matching road, thereby improving the matching accuracy of the current data and the road, improving the accuracy and efficiency of road attribute data production, and reducing labor costs.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0045] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments, taken in conjunction with the accompanying drawings. In the drawings:

[0046] Figure 1 A flowchart illustrating a method for matching data with roads according to an embodiment of this disclosure is shown.

[0047] Figures 2(a) and 2(b) show schematic diagrams of the image effects of currently collected data and existing reference data according to an embodiment of the present disclosure.

[0048] Figures 3(a) and 3(b) show schematic diagrams illustrating the effect of identifying similar features using current collected data and existing reference data according to an embodiment of the present disclosure.

[0049] Figure 4 A structural block diagram of a data and road matching device according to an embodiment of the present disclosure is shown.

[0050] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing a data and road matching method and / or map updating method according to an embodiment of the present disclosure. Detailed Implementation

[0051] In the following, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings to enable those skilled in the art to readily implement them. Furthermore, for clarity, portions unrelated to the description of the exemplary embodiments have been omitted from the drawings.

[0052] In this disclosure, it should be understood that terms such as “comprising” or “having” are intended to indicate the presence of features, figures, steps, behaviors, components, parts or combinations thereof disclosed in this specification, and do not preclude the possibility of the presence or addition of one or more other features, figures, steps, behaviors, components, parts or combinations thereof.

[0053] It should also be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0054] The user information (including but not limited to user device information such as location information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0055] The details of the embodiments of this disclosure are described in detail below through specific examples.

[0056] Figure 1 A flowchart illustrating a method for matching data with roads according to an embodiment of this disclosure is shown. Figure 1 As shown, the method for matching this data with roads includes the following steps:

[0057] In step S101, the current collected data, current collected trajectory, and existing road information of the road are acquired;

[0058] In step S102, candidate roads matching the currently collected data are determined from the existing road information based on the current collected trajectory;

[0059] In step S103, if there is an associated road parallel to the candidate road in the existing road information, then the existing reference data associated with the candidate road is obtained.

[0060] In step S104, similar features in the currently collected data and the existing reference data are determined;

[0061] In step S105, the matching relationship between the current data and the candidate road is determined by the position of the similar land features in the current data and the position in the existing reference data.

[0062] In this embodiment, the data-road matching method can be executed on a server. During the road data creation process, in order to generate accurate and comprehensive attribute information for the corresponding road, such as road identification, road location coordinates, road type, and lane information, the road identification, location coordinates, or location coordinates of the area where the road is located are usually sent to the data collection vehicle. The data collection vehicle will travel to the corresponding road based on the received information and collect data on the road, forming collected data, and the collection trajectory is recorded in association with the collected data. The collected data may include, but is not limited to, image data of the road collected by the collection vehicle. The collection trajectory is the driving trajectory of the collection vehicle when collecting data.

[0063] The currently collected data can be understood as the data that needs to be matched with existing road information to find the data of the road that actually corresponds to the currently collected data. The current collection trajectory is the driving trajectory of the data collection vehicle when collecting the current data. Existing road information may include, but is not limited to, the location coordinates and labels of each road in the road network. It can be understood that the existing road information may include the known original attribute information of each road. In other words, matching the currently collected data with the roads in the existing road information is to update the attribute information of the corresponding roads based on the new currently collected data, so that the attribute information of the roads in the map data can maintain its freshness.

[0064] Understandably, since the current data collected from the data collection vehicle is associated with a corresponding current data collection trajectory, matching the current data collection trajectory with the location coordinates of existing roads can preliminarily determine candidate roads that match the current data collection. In some embodiments, existing roads whose location coordinates are completely or partially covered by the current data collection trajectory can be identified as matching candidate roads.

[0065] It is understandable that the location coordinates of an existing road can be a series of location coordinates of multiple preset shape points on the existing road. Whether the current acquisition trajectory covers the location coordinates of the existing road can be understood as whether the series of location coordinates of multiple preset shape points on the existing road coincides with the current acquisition trajectory within a threshold range. If the series of location coordinates of all preset shape points on the existing road coincides with the current acquisition trajectory within the threshold range, it can be considered that the current acquisition trajectory completely covers the location coordinates of the existing road. If the series of location coordinates of some preset shape points on the existing road coincides with the current acquisition trajectory within the threshold range, it can be understood as the current acquisition trajectory partially covers the location coordinates of the existing road. The coverage ratio can be understood as the ratio of the number of preset shape points that coincide within the threshold range to the total number of preset shape points. In some embodiments, coincidence within the threshold range can be understood as whether the shortest distance from the location coordinates of the preset shape point to the current acquisition trajectory is within the threshold range.

[0066] As mentioned above, there are many parallel roads in the real world, and these parallel roads are close to each other and have similar vertical connections. Matching the data collection trajectory with the road coordinates alone is prone to errors, that is, it is easy to match the collected data to related parallel roads.

[0067] Therefore, in this embodiment of the disclosure, it can be first determined whether there are parallel related roads among the candidate roads matched by the current acquisition trajectory. If there are parallel related roads among the candidate roads that match the current acquisition data, it is possible that the candidate road is not the actual matching road of the current acquisition data, but rather a related road that is parallel to the actual matching road.

[0068] In some embodiments, it can be determined whether there are parallel associated roads to the current candidate road by comparing the current candidate road with the surrounding roads. For example, lines can be drawn from each shape point on the current candidate road to the nearest point on the surrounding roads. If all the lines are parallel, the current candidate road can be considered to be parallel to the surrounding roads, that is, the surrounding roads are associated roads that are parallel to the current candidate road.

[0069] Therefore, when a candidate road has parallel associated roads, it can be further determined whether the candidate road is an actual matching road in the currently collected data. In this embodiment, the association between each road in the existing road information and existing reference data can be established in advance. The existing reference data can be historical data corresponding to the associated roads, and it has been determined that the existing reference data matches the associated roads. In some embodiments, the existing reference data can be the data with the highest matching degree among multiple historical reference data corresponding to the candidate road.

[0070] In this embodiment of the disclosure, existing reference data associated with candidate roads can be compared with the currently collected data to determine whether similar features exist in the currently collected data and the existing reference data. Features can be understood as distinguishable objects on both sides of the road or on the road surface, such as buildings, signs, traffic lights, overpasses, zebra crossings, etc.

[0071] Similar features in the current data and existing reference data can be understood as road elements that are relatively similar and coexist in both the current data and existing reference data. For example, if there are traffic signs that are similar in size and shape in both the current data and existing reference data, then the traffic sign can be considered a similar feature in both the current data and existing reference data.

[0072] In some embodiments, the location of similar features in the currently acquired data can be determined. This location can be a relative position of the similar feature in the currently acquired data, such as its position relative to the image location of the acquired road in the currently acquired data, like being on the left or right side of the acquired road. The location of similar features in existing reference data can also be determined. This location can be a relative position of the similar feature in the existing reference data, such as its position relative to the image location of the acquired road in the existing reference data, like being on the left or right side of the road. It is understood that the currently acquired data and the existing reference data are image acquisition data of roads, and the location of similar features in the currently acquired data and the existing reference data can be understood as their image location. It is also understood that the acquired road is the road on which the data acquisition vehicle travels during data acquisition.

[0073] Then, based on whether the positions of similar features in the current data and in the existing reference data match, it can be determined whether the current data and the existing reference data match. If the current data and the existing reference data match, it can be determined that the candidate roads associated with the current data and the existing reference data match.

[0074] In this embodiment, the relative positions of similar features in the data are used to determine whether the currently collected data matches the existing reference data. This is because, in scenarios with multiple parallel roads, matching based on the collection trajectory can easily lead to the current collected data being matched to a parallel associated road. However, by comparing similar features and matching their relative positions in the current collected data and the existing reference data, such as their positions relative to the collected roads, it is possible to accurately determine whether the current collected data matches the existing reference data. This allows us to determine whether the current collected data matches a candidate road associated with the existing reference data, thus avoiding the mistaken matching of the current collected data to a parallel associated road.

[0075] In this embodiment, after acquiring the current data, in order to accurately match the current data's matching value to the actual road, candidate roads can be initially matched from existing road information based on the acquisition trajectory of the current data. If the candidate road has parallel related roads in the existing road information, the actual matching road for the current data may not be the candidate road, but rather a parallel related road. Therefore, this embodiment further acquires existing reference data associated with the candidate road and identifies similar features in the existing reference data and the current data. By determining the position of similar features in the existing reference data and the current data, it is determined whether the current data matches the candidate road associated with the existing reference data. Through the above method, when there are parallel related roads for the candidate road that matches the current acquisition trajectory of the current data, it is possible to avoid mismatching the current data to a parallel related road of the actual matching road, thereby improving the matching accuracy of the current data and the road, improving the accuracy and efficiency of road attribute data production, and reducing labor costs.

[0076] Figures 2(a) and 2(b) show schematic diagrams illustrating the image effects of current collected data and existing reference data according to an embodiment of this disclosure. As shown in Figure 2(a), the existing reference data is collected by a data collection vehicle traveling on the main road, with the sign located on the right side of the main road. As shown in Figure 2(b), the current collected data is collected by a data collection vehicle traveling on an auxiliary road parallel to the main road, and the sign located on the right side of the main road is also captured in the current collected data. Through image recognition, it can be determined that the sign is a similar feature in both the current collected data and the existing reference data. However, in the existing reference data, the image position of the sign relative to the collected road (main road) is on the right side of the road, while in the current collected data, the image position relative to the collected road (auxiliary road) is on the left side of the road. It can be seen that the relative positions of similar features are different in the current collected data and the existing reference data. Therefore, the current collected data does not match the existing reference data, and consequently, the current collected data does not match the candidate road associated with the existing reference data. In fact, the road matched by the current collected data and the road associated with the existing reference data are not the same road, but rather parallel roads.

[0077] In an optional implementation of this embodiment, the method further includes the following steps:

[0078] Acquire multiple historical data sets, the historical data collection trajectories of the historical data sets, and existing road information;

[0079] Based on the historical data collection trajectory, at least one initial associated road of the historical data collection is determined from the existing road information;

[0080] When associating multiple historical data sets with the initial associated road, the one with the highest matching degree is selected from the multiple historical data sets as the existing reference data for the initial associated road; the candidate road is one of the initial associated roads.

[0081] In this optional implementation, existing reference data can be pre-associated with all or part of the existing road information. This existing reference data can be selected from historical data collection. Since road elements change in the real world, to adapt to these changes, data on the same road can be collected periodically or multiple times triggered by other events. Each collected data can be used to update road attribute information, and the collected data can also be stored as historical data in a database. In this embodiment, a data reference library can be established using the historical data stored in the database. This data reference library can include all or part of the existing road information and the existing reference data associated with those roads.

[0082] In some embodiments, at least one initial associated road in the existing road information can be initially matched based on the historical acquisition trajectory of the historical acquisition data. The process of initial matching can be referred to above regarding the process of determining the candidate road that matches the current acquisition data based on the current acquisition trajectory, and will not be repeated here.

[0083] When a single initial associated road is associated with multiple historical data sets, the one with the highest matching degree can be selected as the existing reference data for that initial associated road. It is understandable that if an initial associated road is associated with only one historical data set, and that historical data set meets the requirements for reference data in terms of quality and other attributes, then that historical data set can be used as the existing reference data for that initial associated road.

[0084] In some embodiments, multiple historical data sets that initially match the initially associated road can be sorted based on road attributes and trajectory matching degree with the initially associated road. The matching degree is determined according to the sorting result, and the data with the highest matching degree can be used as existing reference data for the initially associated road. In some embodiments, the road attribute information in the historical data set may include, but is not limited to, road identification, road type, road location coordinates, and number of lanes. The higher the similarity between the attribute information of the collected road in the historical data set and the attribute information of the initially associated road, the higher the ranking of the historical data set and the higher the matching degree. Conversely, the lower the similarity between the attribute information of the collected road in the historical data set and the attribute information of the initially associated road, the lower the ranking of the historical data set and the lower the matching degree.

[0085] In an optional implementation of this embodiment, before the step of selecting the one with the highest matching degree from the multiple historical data sets as the existing reference data for the initial associated road when associating the road with multiple historical data sets, the method further includes the following steps:

[0086] Based on the quality of the historical data and / or the degree of matching between the historical data collection trajectory and the geographical location of the initial associated road, the historical data associated with the initial associated road is filtered.

[0087] In this optional implementation, before sorting the historical data, historical data that clearly does not meet the requirements of the reference materials can be filtered out based on the quality of the historical data and the matching degree between the collection trajectory of the historical data and the geographical location of the initially associated road. For example, if the clarity of the historical data is insufficient, or if the collection direction of the historical data is not facing the road ahead (e.g., facing upwards, left, or right), resulting in low quality of the historical data, then the historical data clearly does not meet the requirements of the reference materials and can be filtered out. Furthermore, if the historical collection trajectory of the historical data only covers a small portion of the preset shape points of the initially associated road, and the proportion of the covered preset shape points among all preset shape points of the initially associated road is less than a threshold, then the historical data can also be considered to clearly not meet the requirements of the reference materials and should be filtered out.

[0088] In some embodiments, a preliminary one-to-many or one-to-one association relationship can be established between the initial associated roads and the remaining historical data.

[0089] In an optional implementation of this embodiment, step S104, namely the step of determining similar features in the currently collected data and the existing reference data, further includes the following steps:

[0090] Utilize image features to identify target road elements of a specified type in the currently acquired data and the existing reference data;

[0091] The similar features are determined based on the similarity between the target road elements in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road elements.

[0092] In this optional implementation, as described above, the currently collected data and existing reference data are image data collected by a data collection vehicle traveling on the road. To compare whether the currently collected data and existing reference data are image data of the same road, similar features can be identified from the currently collected data and existing data through image recognition. Similar features can be target road elements of a set type, such as road signs like traffic signs. In some embodiments, the main type of road elements used to create road attribute information can be set as a set type, such as traffic signs, zebra crossings, traffic lights, etc. After identifying target road elements of the set type from the currently collected data and existing reference data through image recognition, the size, color, and other image features of target road elements of the same set type can be compared. If the similarity of the image features is higher than a set threshold, it can be further identified whether reference road elements within a first preset range of the target road element are similar. It is understood that reference road elements can be target road elements of the set type, or they can be target road elements of a different type; for example, reference road elements can be buildings, roadside store signs, etc. By comparing the similarity between reference road elements in the currently collected data and existing reference data, such as the similarity of image features like size, color, and shape, it is determined whether the target road element of this specified type is a similar feature between the currently collected data and existing reference data. In some embodiments, the first preset range can be preset based on the needs of actual application, and no specific limitations are imposed here.

[0093] In some embodiments, if the target road element of a certain type in the currently acquired data and the existing reference data are similar, and the reference road elements within the first preset range of the target road element of that type are also similar, for example, there are reference road elements with similar image features within the first preset range of the target road element of that type, then the target road element of that type can be determined as a similar land feature in the currently acquired data and the existing acquired data.

[0094] In an optional implementation of this embodiment, the step of determining the similar features based on the similarity between the target road element in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road element, further includes the following steps:

[0095] If the similarity of the image features of the target road element is greater than or equal to the first similarity threshold, then the similarity of the image features of the reference road element is determined.

[0096] When the similarity of the image features of the reference road element in the currently collected data and the existing reference data is greater than or equal to the second similarity threshold, the target road element is identified as the similar land feature.

[0097] In this optional implementation, image features can be used to identify whether a target road element of a specified type exists in the currently acquired data and existing reference data. If a target road element of a specified type exists, the similarity between the target road elements of that type in the currently acquired data and existing reference data can be compared one by one. If the similarity is greater than or equal to a first similarity threshold, the similarity between the current target road element of that specified type and the reference road elements within a first preset range can be further determined. It is understood that the similarity between target road elements of a specified type and the similarity between reference road elements are both determined based on the similarity of image features.

[0098] When the similarity between all or part of the reference road elements within the first preset range of the target road element of this setting type is greater than or equal to the second similarity threshold, the target road element of this setting type can be considered as a similar land feature between the currently collected data and the existing collected data. The first similarity threshold and the second similarity threshold can be equal or unequal, and can be set according to actual needs, without specific restrictions here.

[0099] In an optional implementation of this embodiment, step S105, which is the step of determining the matching relationship between the current data and the candidate road based on the location of the similar land features in the current data and their location in the existing reference data, further includes the following steps:

[0100] Based on the relative positional relationship between the similar feature and the reference road element within the second preset range of the similar feature, determine whether the position of the similar feature is consistent in the current data and the existing reference data;

[0101] If the similar feature is in the same position in the current data and the existing reference data, then determine the first relative position of the similar feature in the current data relative to the data collection road, and the second relative position of the similar feature in the existing reference data relative to the data collection road in the existing reference data;

[0102] Based on the first relative position and the second relative position, it is determined whether the currently collected data matches the candidate road.

[0103] In this optional implementation, after identifying similar features, the relative positional relationship between the similar feature and reference road elements within a second preset range can be used to determine whether the position of the similar feature is consistent in the currently collected data and existing reference data. For example, if there are one or more reference road elements surrounding the similar feature, and the relative positional relationship of the similar feature with respect to all or most of these reference road elements is consistent in the currently collected data and existing data (e.g., the similar feature is to the left of the surrounding reference road elements, while the reference road elements are to the right of the similar feature), then it can be determined that the position of the similar feature is consistent in the currently collected data and existing reference data. In some embodiments, the second preset range can be pre-set based on the needs of actual application, and no specific restrictions are imposed here.

[0104] After confirming the consistent locations of similar features, the relative positions of the similar features with respect to the data collection road (i.e., the road the data collection vehicle travels) can be used to determine whether the candidate roads associated with the current data collection and existing reference data match. A match can be determined when the first relative position of the similar feature in the current data collection relative to the data collection road and the second relative position of the similar feature in the existing reference data are consistent. For example, if both the first and second relative positions involve the similar feature being located to the upper right of the data collection road, then the first and second relative positions can be considered consistent.

[0105] Figures 3(a) and 3(b) illustrate the effect of identifying similar features using current data and existing reference data according to an embodiment of this disclosure. As shown in Figures 3(a) and 3(b), both the current data and the existing reference data identify prohibition signs with similar image features such as size and color, shown in solid boxes in the figures. Further, reference road elements are identified around the prohibition sign, such as traffic signs (shown in black dashed boxes) and storefront signs (shown in gray dashed boxes). Since the traffic signs (shown in black dashed boxes) and storefront signs (shown in gray dashed boxes) in the current data and existing reference data are also similar in size, color, and other image features to similar features, it can be determined that similar reference road elements have been identified near the prohibition sign. Therefore, the prohibition sign can be identified as a similar feature between the current data and the existing reference data.

[0106] By comparing similar features in the current data and existing reference data—that is, the relative positions of prohibition signs (shown by light-colored solid lines) in the data—we can determine whether the positions of similar features are consistent in the current data and existing reference data. For example, we can compare the relative positional relationship between similar features and reference road elements to determine whether the positions of similar features are consistent in the current data and existing reference data, as shown in the figure, where the solid lines are relative to the two dashed lines. We can also compare the relative positional relationship between the road where the data collection vehicle was located and the similar features to determine whether the location of the data collection vehicle in the current data and the location of the data collection vehicle in the existing reference data are on the same road. If the positions of similar features are consistent in the current data and existing reference data, and the location of the data collection vehicle is on the same road, then the current data and existing reference data are matched. Furthermore, the roads associated with the current data and existing reference data are matched. Otherwise, the roads associated with the current data and existing reference data are not matched.

[0107] In an optional implementation of this embodiment, the method further includes the following steps:

[0108] If there is no associated road parallel to the candidate road in the existing road information, then the currently collected data is determined to match the candidate road.

[0109] In this optional implementation method, as mentioned above, there are many parallel roads in the real world, and these parallel roads are close to each other and have similar vertical connectivity. Matching the data collection trajectory with the road's location coordinates alone is prone to errors, that is, it is easy to match the collected data to parallel roads.

[0110] If no parallel roads exist for the candidate road, the matching of the current data with the candidate road can be determined directly based on the coordinates of the parallel roads and the data acquisition trajectory, without further processing. In other words, if no parallel roads exist, the candidate road matching the data acquisition trajectory can be identified as the matching road.

[0111] According to one embodiment of this disclosure, a map updating method is also proposed, comprising:

[0112] Obtain the currently collected data;

[0113] Based on the above data and road matching method, the target road that matches the currently collected data is determined;

[0114] The map data corresponding to the target road is updated based on the currently collected data.

[0115] In this embodiment, the roads in the real world and the road elements on those roads are constantly being updated. To ensure timely synchronization of map data, this embodiment dispatches data collection tasks to the data collection vehicle to collect data on various roads within a region. Considering that the data collected by the vehicle in a batch may include data from various parallel roads, and that the collection trajectories of parallel roads may be similar, matching the collected data with roads using only the collection trajectories could easily lead to errors.

[0116] Therefore, this embodiment of the disclosure utilizes the above-described data-road matching method to determine the target road that should actually be matched with the currently collected data. Then, it uses the currently collected data to generate attribute information for the target road and updates the map data of the target road based on the generated attribute information. Specific details regarding data-road matching can be found in the above description of the data-road matching method, and will not be repeated here.

[0117] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein.

[0118] Figure 4 This diagram illustrates a structural block diagram of a data and road matching device according to an embodiment of the present disclosure. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. Figure 4 As shown, the data-road matching device includes:

[0119] The first acquisition module 401 is configured to acquire the current collected data, current collected trajectory, and existing road information of the road.

[0120] The first determining module 402 is configured to determine candidate roads that match the currently collected data from the existing road information based on the current collected trajectory.

[0121] The second acquisition module 403 is configured to acquire existing reference data associated with the candidate road if there is an associated road parallel to the candidate road in the existing road information.

[0122] The second determining module 404 is configured to determine similar features in the currently collected data and the existing reference data;

[0123] The third determining module 405 is configured to determine the matching relationship between the current collected data and the candidate road by using the position of the similar land feature in the current collected data and the position in the existing reference data.

[0124] In this embodiment, the data and road matching device can be executed on a server. During the road data creation process, in order to generate accurate and comprehensive attribute information for the corresponding road, such as road identification, road location coordinates, road type, and lane information, the identification, location coordinates, or location coordinates of the area where the road is located are usually sent to the data collection vehicle. The data collection vehicle will travel to the corresponding road based on the received information and collect data on the road, forming collected data, and the collection trajectory is recorded in association with the collected data. The collected data may include, but is not limited to, image data of the road collected by the collection vehicle. The collection trajectory is the driving trajectory of the collection vehicle when collecting data.

[0125] The currently collected data can be understood as the data that needs to be matched with existing road information to find the data of the road that actually corresponds to the currently collected data. The current collection trajectory is the driving trajectory of the data collection vehicle when collecting the current data. Existing road information may include, but is not limited to, the location coordinates and labels of each road in the road network. It can be understood that the existing road information may include the known original attribute information of each road. In other words, matching the currently collected data with the roads in the existing road information is to update the attribute information of the corresponding roads based on the new currently collected data, so that the attribute information of the roads in the map data can maintain its freshness.

[0126] Understandably, since the current data collected from the data collection vehicle is associated with a corresponding current data collection trajectory, matching the current data collection trajectory with the location coordinates of existing roads can preliminarily determine candidate roads that match the current data collection. In some embodiments, existing roads whose location coordinates are completely or partially covered by the current data collection trajectory can be identified as matching candidate roads.

[0127] It is understandable that the location coordinates of an existing road can be a series of location coordinates of multiple preset shape points on the existing road. Whether the current acquisition trajectory covers the location coordinates of the existing road can be understood as whether the series of location coordinates of multiple preset shape points on the existing road coincides with the current acquisition trajectory within a threshold range. If the series of location coordinates of all preset shape points on the existing road coincides with the current acquisition trajectory within the threshold range, it can be considered that the current acquisition trajectory completely covers the location coordinates of the existing road. If the series of location coordinates of some preset shape points on the existing road coincides with the current acquisition trajectory within the threshold range, it can be understood as the current acquisition trajectory partially covers the location coordinates of the existing road. The coverage ratio can be understood as the ratio of the number of preset shape points that coincide within the threshold range to the total number of preset shape points. In some embodiments, coincidence within the threshold range can be understood as whether the shortest distance from the location coordinates of the preset shape point to the current acquisition trajectory is within the threshold range.

[0128] As mentioned above, there are many parallel roads in the real world, and these parallel roads are close to each other and have similar vertical connections. Matching the data collection trajectory with the road coordinates alone is prone to errors, that is, it is easy to match the collected data to related parallel roads.

[0129] Therefore, in this embodiment of the disclosure, it can be first determined whether there are parallel related roads among the candidate roads matched by the current acquisition trajectory. If there are parallel related roads among the candidate roads that match the current acquisition data, it is possible that the candidate road is not the actual matching road of the current acquisition data, but rather a related road that is parallel to the actual matching road.

[0130] In some embodiments, it can be determined whether there are parallel associated roads to the current candidate road by comparing the current candidate road with the surrounding roads. For example, lines can be drawn from each shape point on the current candidate road to the nearest point on the surrounding roads. If all the lines are parallel, the current candidate road can be considered to be parallel to the surrounding roads, that is, the surrounding roads are associated roads that are parallel to the current candidate road.

[0131] Therefore, when a candidate road has parallel associated roads, it can be further determined whether the candidate road is an actual matching road in the currently collected data. In this embodiment, the association between each road in the existing road information and existing reference data can be established in advance. The existing reference data can be historical data corresponding to the associated roads, and it has been determined that the existing reference data matches the associated roads. In some embodiments, the existing reference data can be the data with the highest matching degree among multiple historical reference data corresponding to the candidate road.

[0132] In this embodiment of the disclosure, existing reference data associated with candidate roads can be compared with the currently collected data to determine whether similar features exist in the currently collected data and the existing reference data. Features can be understood as distinguishable objects on both sides of the road or on the road surface, such as buildings, signs, traffic lights, overpasses, zebra crossings, etc.

[0133] Similar features in the current data and existing reference data can be understood as road elements that are relatively similar and coexist in both the current data and existing reference data. For example, if there are traffic signs that are similar in size and shape in both the current data and existing reference data, then the traffic sign can be considered a similar feature in both the current data and existing reference data.

[0134] In some embodiments, the location of similar features in the currently acquired data can be determined. This location can be a relative position of the similar feature in the currently acquired data, such as its position relative to the image location of the acquired road in the currently acquired data, like being on the left or right side of the acquired road. The location of similar features in existing reference data can also be determined. This location can be a relative position of the similar feature in the existing reference data, such as its position relative to the image location of the acquired road in the existing reference data, like being on the left or right side of the road. It is understood that the currently acquired data and the existing reference data are image acquisition data of roads, and the location of similar features in the currently acquired data and the existing reference data can be understood as their image location. It is also understood that the acquired road is the road on which the data acquisition vehicle travels during data acquisition.

[0135] Then, based on whether the positions of similar features in the current data and in the existing reference data match, it can be determined whether the current data and the existing reference data match. If the current data and the existing reference data match, it can be determined that the candidate roads associated with the current data and the existing reference data match.

[0136] In this embodiment, the relative positions of similar features in the data are used to determine whether the currently collected data matches the existing reference data. This is because, in scenarios with multiple parallel roads, matching based on the collection trajectory can easily lead to the current collected data being matched to a parallel associated road. However, by comparing similar features and matching their relative positions in the current collected data and the existing reference data, such as their positions relative to the collected roads, it is possible to accurately determine whether the current collected data matches the existing reference data. This allows us to determine whether the current collected data matches a candidate road associated with the existing reference data, thus avoiding the mistaken matching of the current collected data to a parallel associated road.

[0137] In this embodiment, after acquiring the current data, in order to accurately match the current data's matching value to the actual road, candidate roads can be initially matched from existing road information based on the acquisition trajectory of the current data. If the candidate road has parallel related roads in the existing road information, the actual matching road for the current data may not be the candidate road, but rather a parallel related road. Therefore, this embodiment further acquires existing reference data associated with the candidate road and identifies similar features in the existing reference data and the current data. By determining the position of similar features in the existing reference data and the current data, it is determined whether the current data matches the candidate road associated with the existing reference data. Through the above method, when there are parallel related roads for the candidate road that matches the current acquisition trajectory of the current data, it is possible to avoid mismatching the current data to a parallel related road of the actual matching road, thereby improving the matching accuracy of the current data and the road, improving the accuracy and efficiency of road attribute data production, and reducing labor costs.

[0138] In an optional implementation of this embodiment, the apparatus further includes:

[0139] The third acquisition module is configured to acquire multiple historical data, historical acquisition trajectories, and existing road information.

[0140] The association module is configured to initially associate the historical data with at least one initial associated road in the existing road information based on the historical data acquisition trajectory.

[0141] The filtering module is configured to, when the initial associated road is initially associated with multiple historical data, select the one with the highest matching degree from the multiple historical data as the existing reference data associated with the initial associated road; the candidate road is one of the initial associated roads.

[0142] In this optional implementation, existing reference data can be pre-associated with all or part of the existing road information. This existing reference data can be selected from historical data collection. Since road elements change in the real world, to adapt to these changes, data on the same road can be collected periodically or multiple times triggered by other events. Each collected data can be used to update road attribute information, and the collected data can also be stored as historical data in a database. In this embodiment, a data reference library can be established using the historical data stored in the database. This data reference library can include all or part of the existing road information and the existing reference data associated with those roads.

[0143] In some embodiments, at least one initial associated road in the existing road information can be initially matched based on the historical acquisition trajectory of the historical acquisition data. The process of initial matching can be referred to above regarding the process of determining the candidate road that matches the current acquisition data based on the current acquisition trajectory, and will not be repeated here.

[0144] When a single initial associated road is associated with multiple historical data sets, the one with the highest matching degree can be selected as the existing reference data for that initial associated road. It is understandable that if an initial associated road is associated with only one historical data set, and that historical data set meets the requirements for reference data in terms of quality and other attributes, then that historical data set can be used as the existing reference data for that initial associated road.

[0145] In some embodiments, multiple historical data sets that initially match the initially associated road can be sorted based on road attributes and trajectory matching degree with the initially associated road. The matching degree is determined according to the sorting result, and the data with the highest matching degree can be used as existing reference data for the initially associated road. In some embodiments, the road attribute information in the historical data set may include, but is not limited to, road identification, road type, road location coordinates, and number of lanes. The higher the similarity between the attribute information of the collected road in the historical data set and the attribute information of the initially associated road, the higher the ranking of the historical data set and the higher the matching degree. Conversely, the lower the similarity between the attribute information of the collected road in the historical data set and the attribute information of the initially associated road, the lower the ranking of the historical data set and the lower the matching degree.

[0146] In an optional implementation of this embodiment, the device further includes the following before the filtering module:

[0147] The filtering module is configured to filter the historical data associated with the initial associated road based on the quality of the historical data and / or the degree of matching between the historical data acquisition trajectory and the geographical location of the initial associated road.

[0148] In this optional implementation, before sorting the historical data, historical data that clearly does not meet the requirements of the reference materials can be filtered out based on the quality of the historical data and the matching degree between the collection trajectory of the historical data and the geographical location of the initially associated road. For example, if the clarity of the historical data is insufficient, or if the collection direction of the historical data is not facing the road ahead (e.g., facing upwards, left, or right), resulting in low quality of the historical data, then the historical data clearly does not meet the requirements of the reference materials and can be filtered out. Furthermore, if the historical collection trajectory of the historical data only covers a small portion of the preset shape points of the initially associated road, and the proportion of the covered preset shape points among all preset shape points of the initially associated road is less than a threshold, then the historical data can also be considered to clearly not meet the requirements of the reference materials and should be filtered out.

[0149] In some embodiments, a preliminary one-to-many or one-to-one association relationship can be established between the initial associated roads and the remaining historical data.

[0150] In an optional implementation of this embodiment, the second determining module includes:

[0151] The identification submodule is configured to use image features to identify target road elements of a specified type in the currently acquired data and the existing reference data;

[0152] The first determining submodule is configured to determine the similar features based on the similarity between the target road element in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road element.

[0153] In this optional implementation, as described above, the currently collected data and existing reference data are image data collected by a data collection vehicle traveling on the road. To compare whether the currently collected data and existing reference data are image data of the same road, similar features can be identified from the currently collected data and existing data through image recognition. Similar features can be target road elements of a set type, such as road signs like traffic signs. In some embodiments, the main type of road elements used to create road attribute information can be set as a set type, such as traffic signs, zebra crossings, traffic lights, etc. After identifying target road elements of the set type from the currently collected data and existing reference data through image recognition, the size, color, and other image features of the same set type of target road elements can be compared. If the similarity of the image features is higher than a set threshold, it can be further identified whether reference road elements within a first preset range of the road element are similar. It is understood that reference road elements can be target road elements of the set type, or they can be target road elements of a different type; for example, reference road elements can be buildings, roadside store signs, etc. By comparing the similarity between reference road elements in the currently collected data and existing reference data, such as the similarity of image features like size, color, and shape, it is determined whether the target road element of this set type is a similar feature between the currently collected data and existing reference data.

[0154] In some embodiments, if the target road element of a certain type in the currently acquired data and the existing reference data are similar, and the reference road elements within a first preset range of the target road element of that type are also similar, for example, there are reference road elements with similar image features within a certain range of the target road element of that type, then the target road element of that type can be determined as a similar land feature in the currently acquired data and the existing acquired data.

[0155] In an optional implementation of this embodiment, the first determining submodule includes:

[0156] The second determining submodule is configured to determine the similarity of the image features of the reference road element if the similarity of the image features of the target road element is greater than or equal to a first similarity threshold.

[0157] The third determination submodule is configured to determine the target road element as the similar land feature when the similarity of the image features of the reference road element in the currently collected data and the existing reference data is greater than or equal to a second similarity threshold.

[0158] In this optional implementation, image features can be used to identify whether a target road element of a specified type exists in the currently acquired data and existing reference data. If a target road element of a specified type exists, the similarity between the target road elements of that type in the currently acquired data and existing reference data can be compared one by one. If the similarity is greater than or equal to a first similarity threshold, the similarity between the current target road element of that specified type and the reference road elements within a first preset range can be further determined. It is understood that the similarity between target road elements of a specified type and the similarity between reference road elements are both determined based on the similarity of image features.

[0159] When the similarity between all or part of the reference road elements within the first preset range of the target road element of this setting type is greater than or equal to the second similarity threshold, the target road element of this setting type can be considered as a similar land feature between the currently collected data and the existing collected data. The first similarity threshold and the second similarity threshold can be equal or unequal, and can be set according to actual needs, without specific restrictions here.

[0160] In an optional implementation of this embodiment, the third determining module includes:

[0161] The fourth determination submodule is configured to determine whether the position of the similar land feature is consistent in the current data and the existing reference data based on the relative positional relationship between the similar land feature and the reference road element within the second preset range of the similar land feature;

[0162] The fifth determination submodule is configured to determine, if the similar feature is in the same position in the current data and the existing reference data, a first relative position of the similar feature relative to the acquisition road in the current data and a second relative position of the similar feature relative to the acquisition road in the existing reference data.

[0163] The sixth determining submodule is configured to determine whether the currently collected data matches the candidate road based on the first relative position and the second relative position.

[0164] In this optional implementation, after identifying similar features, the relative positional relationship between the similar feature and reference road elements within a second preset range can be used to determine whether the position of the similar feature is consistent in the currently collected data and existing reference data. For example, if there are one or more reference road elements surrounding the similar feature, and the relative positional relationship of the similar feature with respect to all or most of these reference road elements is consistent in the currently collected data and existing data (e.g., the similar feature is to the left of the surrounding reference road elements, while the reference road elements are to the right of the similar feature), then it can be determined that the position of the similar feature is consistent in the currently collected data and existing reference data.

[0165] After confirming the consistent locations of similar features, the relative positions of the similar features with respect to the data collection road (i.e., the road the data collection vehicle travels) can be used to determine whether the candidate roads associated with the current data collection and existing reference data match. A match can be determined when the first relative position of the similar feature in the current data collection relative to the data collection road and the second relative position of the similar feature in the existing reference data are consistent. For example, if both the first and second relative positions involve the similar feature being located to the upper right of the data collection road, then the first and second relative positions can be considered consistent.

[0166] In an optional implementation of this embodiment, the apparatus further includes:

[0167] The fourth determining module is configured to determine that the currently collected data matches the candidate road if there is no associated road parallel to the candidate road in the existing road information.

[0168] In this optional implementation method, as mentioned above, there are many parallel roads in the real world, and these parallel roads are close to each other and have similar vertical connectivity. Matching the data collection trajectory with the road's location coordinates alone is prone to errors, that is, it is easy to match the collected data to parallel roads.

[0169] If no parallel roads exist for the candidate road, the matching of the current data with the candidate road can be determined directly based on the coordinates of the parallel roads and the data acquisition trajectory, without further processing. In other words, if no parallel roads exist, the candidate road matching the data acquisition trajectory can be identified as the matching road.

[0170] According to one embodiment of this disclosure, a map updating apparatus is also provided, comprising:

[0171] The data acquisition module is configured to acquire the currently collected data;

[0172] The road determination module is configured to determine the target road that matches the currently collected data based on the above data and road matching method;

[0173] The update module is configured to update the map data corresponding to the target road based on the currently collected data.

[0174] In this embodiment, the roads in the real world and the road elements on those roads are constantly being updated. To ensure timely synchronization of map data, this embodiment dispatches data collection tasks to the data collection vehicle to collect data on various roads within a region. Considering that the data collected by the vehicle in a batch may include data from various parallel roads, and that the collection trajectories of parallel roads may be similar, matching the collected data with roads using only the collection trajectories could easily lead to errors.

[0175] Therefore, this embodiment utilizes the aforementioned data-road matching device to determine the target road that should actually be matched with the currently collected data. Then, it uses the currently collected data to generate attribute information for the target road and updates the map data of the target road based on the generated attribute information. Specific details regarding the data-road matching process can be found in the above description of the data-road matching device, and will not be repeated here.

[0176] Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing a data and road matching method and / or map updating method according to an embodiment of the present disclosure.

[0177] like Figure 5 As shown, the electronic device 500 includes a processing unit 501, which can be implemented as a CPU, GPU, FPGA, NPU, or other processing unit. The processing unit 501 can execute various processes according to any of the methods described above in this disclosure, based on a program stored in the read-only memory (ROM) 502 or a program loaded from the storage portion 508 into the random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0178] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0179] In particular, according to embodiments of this disclosure, any of the methods described above in the embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program containing program code for performing any of the methods in the embodiments of this disclosure. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511.

[0180] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0181] The units or modules described in the embodiments of this disclosure can be implemented in software or hardware. The described units or modules can also be located in a processor, and the names of these units or modules do not necessarily constitute a limitation on the unit or module itself.

[0182] In another aspect, this disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the apparatus described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into a device. The computer-readable storage medium stores one or more programs that are used by one or more processors to perform the methods described in this disclosure.

[0183] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A method for matching data with roads, wherein, include: Acquire current data, current data collection trajectory, and existing road information for the road; Based on the current collected trajectory, candidate roads that match the current collected data are determined from the existing road information; If there is an associated road parallel to the candidate road in the existing road information, then the existing reference data associated with the candidate road is obtained. The existing reference data is the historical data collected corresponding to the associated road, and it has been determined that the existing reference data matches the associated road. Identify similar features in the currently collected data and the existing reference data; Based on the relative positional relationship between the similar feature and the reference road element within the second preset range of the similar feature, determine whether the position of the similar feature is consistent in the current data and the existing reference data; If the similar feature is in the same position in the current data and the existing reference data, then determine the first relative position of the similar feature in the current data relative to the data collection road, and the second relative position of the similar feature in the existing reference data relative to the data collection road in the existing reference data; Based on the first relative position and the second relative position, it is determined whether the currently collected data matches the candidate road.

2. The method according to claim 1, wherein, The method further includes: Acquire multiple historical data sets, the historical data collection trajectories of the historical data sets, and existing road information; Based on the historical data collection trajectory, at least one initial associated road of the historical data collection is determined from the existing road information; When associating multiple historical data sets with the initial associated road, the one with the highest matching degree is selected from the multiple historical data sets as the existing reference data for the initial associated road; the candidate road is one of the initial associated roads.

3. The method according to any one of claims 1-2, wherein, Identifying similar features in the currently collected data and the existing reference data includes: Utilize image features to identify target road elements of a specified type in the currently acquired data and the existing reference data; The similar features are determined based on the similarity between the target road elements in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road elements.

4. The method according to claim 3, wherein, Determining similar features based on the similarity between the target road element in the currently collected data and the existing reference data, and the similarity between reference road elements within a first preset range of the target road element, includes: If the similarity of the image features of the target road element is greater than or equal to the first similarity threshold, then the similarity of the image features of the reference road element is determined. When the similarity of the image features of the reference road element in the currently collected data and the existing reference data is greater than or equal to the second similarity threshold, the target road element is identified as the similar land feature.

5. The method according to any one of claims 1-2 and 4, wherein, The method further includes: If there is no associated road parallel to the candidate road in the existing road information, then the currently collected data is determined to match the candidate road.

6. A map update method, wherein, include: Obtain the currently collected data; Based on the method described in any one of claims 1-5, a target road matching the currently collected data is determined; The map data corresponding to the target road is updated based on the currently collected data.

7. A data-road matching device, wherein, include: The first acquisition module is configured to acquire the current data collected on the road, the current acquisition trajectory, and existing road information; The first determining module is configured to determine candidate roads that match the currently collected data from the existing road information based on the current collected trajectory. The second acquisition module is configured to acquire existing reference data associated with the candidate road if there is an associated road parallel to the candidate road in the existing road information. The existing reference data is historical data corresponding to the associated road, and it has been determined that the existing reference data matches the associated road. The second determining module is configured to determine similar features in the currently collected data and the existing reference data; The third determining module is configured to determine whether the position of the similar feature in the current data and the existing reference data is consistent based on the relative positional relationship between the similar feature and the reference road element within a second preset range of the similar feature; if the position of the similar feature is consistent in the current data and the existing reference data, then determine the first relative position of the similar feature relative to the collected road in the current data and the second relative position of the similar feature relative to the collected road in the existing reference data; based on the first relative position and the second relative position, determine whether the current data matches the candidate road.

8. An electronic device, wherein, The method includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of any one of claims 1-6.

9. A computer-readable storage medium having computer instructions stored thereon, wherein, When executed by a processor, the computer instructions implement the method described in any one of claims 1-6.

Images