Data processing and map updating method, device, equipment and storage medium

Abstract

The present disclosure provides a data processing and map updating method, device and equipment and storage medium, relates to the technical field of artificial intelligence, in particular to the field of intelligent transportation and computer vision. The specific implementation scheme is: extracting first feature data of a road element from a road scene image; determining first change data of the road element according to the first feature data and second feature data of the road element recorded in an element entity library; updating the element entity library according to the first feature data and the first change data; and the element entity library is used for updating an electronic map. A solution for maintaining an element entity library is given, and the element entity library can be used for timely and accurate data updating of an electronic map.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the fields of intelligent transportation and computer vision, and is specifically used in map update scenarios. Background Technology

[0002] With the development of intelligent transportation technology, electronic maps are being used more and more widely. In order to ensure the timeliness of electronic maps, it is necessary to update the data of electronic maps in a timely manner when road elements in the real environment change. Summary of the Invention

[0003] This disclosure provides a data processing and map updating method, apparatus, device, and storage medium.

[0004] According to one aspect of this disclosure, a data processing method is provided, comprising:

[0005] Extracting the first feature data of road elements from road scene images;

[0006] Based on the first feature data and the second feature data of the road element recorded in the element entity database, the first change data of the road element is determined;

[0007] The feature entity database is updated based on the first feature data and the first change data; the feature entity database is used to update the electronic map.

[0008] According to another aspect of this disclosure, a map updating method is provided, comprising:

[0009] Based on the second change data of road elements in the updated element entity database and the base map data of the electronic map, the data to be updated is determined; wherein, the element entity database is updated based on the data processing device described in any embodiment of this disclosure;

[0010] Update the base map data of the electronic map based on the data to be updated.

[0011] According to another aspect of this disclosure, an electronic device is provided, the electronic device comprising:

[0012] At least one processor; and

[0013] A memory that is communicatively connected to at least one processor; wherein,

[0014] The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform the data processing method of any embodiment of the present disclosure and / or the map updating method of any embodiment of the present disclosure.

[0015] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to perform a data processing method of any embodiment of this disclosure, and / or a map updating method of any embodiment of this disclosure.

[0016] The present disclosure provides a solution for maintaining a feature entity database, which can be used to update electronic maps in a timely and accurate manner.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0018] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0019] Figure 1 This is a flowchart of a data processing method provided according to an embodiment of the present disclosure;

[0020] Figure 2A This is a flowchart of a data processing method provided according to an embodiment of the present disclosure;

[0021] Figure 2B This is a schematic diagram illustrating the update process of the element entity library according to embodiments of this disclosure;

[0022] Figure 3 This is a flowchart of a data processing method provided according to an embodiment of the present disclosure;

[0023] Figure 4 This is a flowchart of a map updating method provided according to an embodiment of the present disclosure;

[0024] Figure 5 This is a flowchart of a map updating method provided according to an embodiment of the present disclosure;

[0025] Figure 6 This is a schematic diagram of the structure of a data processing apparatus provided according to an embodiment of the present disclosure;

[0026] Figure 7 This is a schematic diagram of a map updating device provided according to an embodiment of the present disclosure;

[0027] Figure 8 This is a block diagram of an electronic device used to implement the data processing method and / or map updating method of the embodiments of this disclosure. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] Figure 1 This is a flowchart illustrating a data processing method according to an embodiment of this disclosure, applicable to updating a feature entity database. The method can be executed by a data processing device, which can be implemented in software and / or hardware. Specifically, it can be integrated into an electronic device with data processing capabilities. Figure 1 As shown, the data processing method provided in this embodiment may include:

[0030] S101, the first feature data for extracting road elements from a road scene image.

[0031] Road scene images refer to images captured of real-world road scenes. Specifically, road scene images can include images of the road surface itself, as well as images of areas beside the road containing signs. Road elements refer to informational elements that characterize the road environment, such as directional arrows, pedestrian crossings, or lane markings on the road surface, or roadside signs or traffic light indicators. Primary feature data refers to the characteristic data of road elements in the current real world across various dimensions. In the spatial dimension, this could be the location information of road elements; in the temporal dimension, it could be the time-related constraints of road elements and their respective lanes; in other dimensions, it could include information such as the traffic status, attributes, or types of road elements and their respective lanes.

[0032] Optionally, there are many ways to extract the first feature data of road elements from a road scene image. For example, one possible implementation is to extract the first feature data of road elements from the road scene image using common image processing algorithms. Another possible implementation is to input the road scene image into a pre-trained neural network model and use a neural network algorithm to output the first feature data of the road elements. Other methods can also be used to extract the first feature data of road elements from the road scene image, which are not limited in this embodiment.

[0033] Optionally, the road scene image can be preprocessed before extracting the first feature data of road elements from the road scene image. For example, an image enhancement algorithm can be used to preprocess the road scene image to improve image clarity; a denoising algorithm can be used to preprocess the road scene image to remove noise interference; or an image segmentation algorithm can be used to preprocess the road scene image to segment the road area and signage area, etc., of the scene image.

[0034] S102, based on the first feature data and the second feature data of the road elements recorded in the feature entity library, determine the first change data of the road elements.

[0035] The element entity database is used to update the electronic map. It is a database that records the characteristic information of road elements in the real world. Specifically, it records feature data of road elements in various dimensions, as well as change data of these features. The second feature data is information stored in the element entity database about the multi-dimensional features of road elements. This second feature data includes at least the first feature data, and may also include more comprehensive information about the road elements, such as creation time, change time, and image acquisition time. The first change data refers to information about changes in the first feature data compared to the second feature data. This first change data may include the feature data showing changes to the first feature data, as well as information about the corresponding changes.

[0036] Optionally, the first feature data and the second feature data can be differentially processed to compare the changes in the first feature data compared to the second feature data, thus obtaining the first change data of the road elements.

[0037] Specifically, forward differencing and / or backward differencing can be used to process the first and second feature data to determine the changed features, thus obtaining the first changed data. Forward differencing refers to determining the difference between the second and first feature data based on the first feature data, while backward differencing refers to determining the difference between the first and second feature data based on the second feature data. Forward differencing can identify the new features added to the first feature data compared to the second feature data. Backward differencing can identify the features removed from the first feature data compared to the second feature data.

[0038] For example, if the first feature data contains feature data that the second feature data does not contain, it indicates that the first feature data has added feature data compared to the second feature data. In this case, the first change data of the determined road element may include the added feature data and the creation time of the corresponding road element. If the second feature data contains feature data that the first feature data does not contain, it indicates that the first feature data has deleted the corresponding feature data. In this case, the first change data of the determined road element may include the deleted feature data and the corresponding deletion time. If the first feature data contains feature data that has changed compared to the corresponding feature data of the second feature data, it indicates that the first feature data has been updated. In this case, the first change data of the determined road element may include the feature data that needs to be updated and the corresponding update time.

[0039] Optionally, the first feature data, the second feature data, and the first change data can be stored in the feature entity database in tabular form, or in other forms such as text. This disclosure does not impose any restrictions on this.

[0040] S103, Update the element entity database based on the first feature data and the first change data.

[0041] Optionally, after extracting the first feature data and determining the first changed data, there are many ways to update the element entity database based on the first feature data and the first changed data. For example, one possible implementation is to update the element entity database serially based on the arrangement of data in the first changed data, according to each changed data and its corresponding first feature data. Another possible implementation is to update the element entity database in parallel each time based on the storage time of data in the first changed data, according to the changed data and the first feature data for multiple specified time periods. Alternatively, the element entity database can be updated based on its dependencies on the first feature data and the first changed data. This embodiment does not limit this approach.

[0042] The solution of this disclosure extracts first feature data of road elements from a road scene image, then determines first change data of the road elements based on the first feature data and second feature data of the road elements recorded in the element entity database, and finally updates the element entity database based on the first feature data and the first change data. This disclosure provides a solution for updating an element entity database, which can correlate the information in the element entity database with changes in the real world, enabling the element entity database to record constantly changing information in the real world, ensuring the accuracy, effectiveness, and real-time nature of the element entity database. The updated element entity database can also be better applied to updating electronic maps, improving the efficiency and accuracy of electronic map updates.

[0043] Optionally, in this embodiment, after extracting the first feature data and determining the first change data, another possible implementation of updating the element entity library based on the first feature data and the first change data is as follows: update the second feature data and the second change data in the element entity library respectively. Accordingly, after extracting the first feature data, the second feature data of the road element in the element entity library can be updated based on the first feature data; after determining the first change data, the second change data of the road element in the element entity library can be updated based on the first change data.

[0044] The second change data refers to the information data stored in the feature entity database used to record changes in feature data.

[0045] Optionally, for each feature data in the first feature data, the second feature data in the element entity library can be replaced with the corresponding first feature data in a one-to-one correspondence, that is, the second feature data of the road elements in the element entity library can be updated. Alternatively, based on the first feature data, forward differencing and / or backward differencing can be used to perform differential processing on the first feature data and the second feature data stored in the element entity library to determine the changed features, and then the second feature data can be updated based on the changed features.

[0046] Optionally, there are many ways to update the second change data of road elements in the element entity library based on the first change data. For example, one possible implementation is to replace the second change data in the element entity library with the corresponding first change data for each change data item in the first change data, thus updating the second change data of road elements in the element entity library. Another possible implementation is to perform differential processing on the first change data and the second change data stored in the element entity library using forward differential and / or reverse differential methods to determine the characteristics of the change, and further update the second change data of road elements in the element entity library based on the characteristics of the change.

[0047] The advantage of this setup is that by updating the element entity database in a more granular way, specifically updating the second feature data and the second change data, the efficiency of updating the element entity database is improved, and the update results are more accurate.

[0048] Figure 2A This is a flowchart of a data processing method provided according to an embodiment of the present disclosure. Figure 2B This is a schematic diagram of the update process of the element entity library provided in the embodiments of this disclosure. Based on the above embodiments, this disclosure further explains in detail how to update the second feature data of road elements in the element entity library according to the first feature data, such as... Figure 2A As shown, the data processing method provided in this embodiment may include:

[0049] S201, the first feature data for extracting road elements from a road scene image.

[0050] S202, Based on the first feature data and the second feature data of the road elements recorded in the feature entity library, determine the first change data of the road elements.

[0051] S203, based on the location characteristics of the road elements in the first feature data, update the basic feature data of the road elements in the second feature data of the feature entity library.

[0052] Location features refer to characteristic information related to the location of road elements. Basic feature data refers to the basic characteristic information of road elements, such as element ID (Identity Document, unique code), element type, coordinate information, element status, creation time, and update time. Coordinate information refers to the location information of road elements in the real world. For example, for directional arrow road elements, if the directional arrow is placed as an overhead sign or is located on an elevated road, the coordinate information also includes the elevation coordinates of the directional arrow.

[0053] Specifically, the process first checks if the road element in the first feature data has a corresponding element ID in the basic feature data of the second feature data in the element entity library. If so, the location feature corresponding to that road element is replaced with the location feature in the basic feature data corresponding to that element ID, and the update time is modified. If not, an element ID is assigned to the road element in the basic feature data, and the element type, location feature, and creation time are added under that element ID. If the element ID in the basic feature data of the second feature data does not have a corresponding road element in the first feature data, the relevant data corresponding to that element ID in the basic feature data is deleted. This completes the update of the basic feature data of the road element in the second feature data of the element entity library.

[0054] Optionally, in this embodiment, when replacing the location feature in the basic feature data corresponding to the element ID with the location feature corresponding to the road element, the location feature corresponding to the road element and the location feature in the basic feature data corresponding to the element ID can be differentially processed to determine the changed part, and then only the changed location feature in the basic feature data can be replaced to improve the replacement efficiency.

[0055] It should be noted that there can only be one road element of the same type located at the same position on the road. For example, if there are three different directional arrows at an intersection, but these three directional arrows correspond to one directional arrow road element, that is, the element IDs corresponding to these three different directional arrows are the same.

[0056] S204. Based on the attribute characteristics of the entities corresponding to the road elements in the first feature data and the attribute characteristics of the lanes to which the entities belong, update the detailed feature data in the second feature data of the road elements in the feature entity database.

[0057] In this context, an entity refers to a road element entity that represents the road environment at a smaller dimension. A road element can include multiple entities; for example, a road can contain multiple lanes, and each lane can contain a directional arrow entity. That is, a road contains one directional arrow road element, but multiple directional arrow entities pointing to the same or different directions. Entity attributes can include entity ID, orientation angle, content information, entity status, etc. The attribute characteristics of the lane to which an entity belongs can include time information, vehicle type, and lane status, etc. Detailed feature data records the detailed attribute information corresponding to each entity, as well as the attribute information of the lane to which each entity belongs. Specifically, detailed feature data can also include the creation time and update time of each road element entity in the element entity library.

[0058] Specifically, orientation angle refers to the direction of action of each entity contained in the road feature, such as the turning information of directional arrows, i.e., left, straight, right, or U-turn indications. Shape profile refers to the outline information of each entity contained in the extracted road feature. Lane type refers to the type of lane in which each entity in the road feature is located, such as bus lane, reversible lane, reversible lane, HOV (High-Occupancy Vehicle Lane), and turning lane, etc. Time information can be the time-related constraint information of the lane in which each entity in the road feature is located, such as whether the lane is open to traffic at different times, or whether the entity in the lane is valid at different times. Vehicle type object refers to the constraint information of the lane in which each entity in the road feature is located on the types of vehicles that can travel, such as the types of vehicles that are allowed to travel in the lane at different times.

[0059] For example, the attribute characteristics of each directional arrow entity may include: coordinate information, orientation angle, shape outline, and arrow text information. The attribute characteristics of the lane to which the entity belongs may include lane type, time information, vehicle type, lane markings on both sides of the arrow, and lane traffic status. Specifically, the lane markings on both sides of the arrow refer to the type of lane markings on the road surface to the left and right of the directional arrow, used to indicate whether lane changing is permitted in the lane where the directional arrow is located. For example, if the lane marking is a solid line, lane changing is not allowed; if the lane marking is a dashed line, lane changing is permitted. Arrow text information refers to information explaining the arrow's indication through ground or aerial signs, such as indicating the destination or road the arrow points to. Lane traffic status refers to the status information regarding whether traffic is permitted in the lane where the directional arrow is located, such as information indicating that traffic is prohibited due to lane construction.

[0060] Specifically, based on the attribute features of entities and the attribute features of the lanes to which the entities belong in the first feature data, the method for updating the detailed feature data in the second feature data is as follows: First, determine whether there is a corresponding element ID in the detailed feature data of the second feature data in the element entity library for the road element in the first feature data. If there is, replace the attribute features of the detailed feature data corresponding to the element ID with the attribute features of the road element and its lane. If not, assign an element ID to the road element in the detailed feature data and add relevant attribute features and creation time, etc., under the element ID. If there is no corresponding road element in the first feature data for the element ID in the detailed feature data of the second feature data, delete the relevant data corresponding to the element ID in the detailed feature data.

[0061] Optionally, in this embodiment, when replacing the attribute features of the detailed feature data corresponding to the feature ID with the attribute features of the road feature and its lane, the attribute features of the road feature and its lane can be differentially processed with the attribute features of the detailed feature data corresponding to the feature ID to determine the changed attribute features. Then, only the changed attribute features in the detailed feature data are replaced to improve the replacement efficiency.

[0062] S205, based on the first change data, update the second change data of the road elements in the element entity library.

[0063] The solution of this embodiment extracts first feature data of road elements from a road scene image and determines first change data. Then, it further updates the basic feature data in the second feature data of the element entity database based on the location features in the first feature data. Finally, it updates the detailed feature data in the second feature data of the element entity database based on the attribute features of the entity and the attribute features of the lane to which the entity belongs in the first feature data. Finally, it updates the second change data based on the first change data. By updating the basic feature data and detailed feature data in the second feature data in a more refined manner, the update of the second feature data can be completed, reducing data redundancy and improving the search efficiency of the element entity database.

[0064] Optionally, based on the first feature data, the additional feature data in the second feature data can also be updated to update the feature entity library. Specifically, the additional feature data in the second feature data of the road elements in the feature entity library can be updated based on the additional attribute features of the road elements in the first feature data.

[0065] Additional attribute features refer to the characteristics of unstructured attribute information of road elements. Additional feature data refers to the feature data in the element entity database that represents the unstructured information of elements or entities. Specifically, additional feature data can include image acquisition information, trajectory acquisition information, and signage information of entities within road elements.

[0066] For example, the image acquisition information in this embodiment can be acquired by a camera installed on the road or by a vehicle dashcam. The trajectory acquisition information can include the position and speed information of the vehicle carrying the dashcam when it acquires road features. Signage information refers to the content recorded on signs installed along the roadside; for example, a sign stating "continuous tunnels" indicates that the road ahead is a group of continuous tunnels.

[0067] Specifically, based on the additional attribute features of road elements in the first feature data, the method for updating the additional feature data of road elements in the second feature data of the element entity library is as follows: First, determine whether there is a corresponding element ID in the additional attribute features of the road elements in the first feature data and the second feature data in the element entity library. If there is, replace the additional attribute feature in the additional feature data corresponding to the element ID with the additional attribute feature corresponding to the road element. If not, assign an element ID to the road element in the additional feature data and add the additional attribute feature and creation time, etc., under the element ID. If there is no corresponding road element in the first feature data for the element ID in the additional feature data of the second feature data, delete the relevant data corresponding to the element ID in the additional feature data.

[0068] Optionally, in this embodiment, when replacing the additional attribute features in the additional attribute data corresponding to the feature ID with the additional attribute features corresponding to the road feature, the additional attribute features corresponding to the road feature and the additional attribute features in the additional attribute data corresponding to the feature ID can be differentially processed to determine the additional attribute features that have changed. Then, only the additional attribute features that have changed in the additional attribute data are replaced to improve the replacement efficiency.

[0069] The advantage of this setup is that by updating the basic feature data and detailed feature data in the second feature data separately, and then further refining the update of the additional feature data in the second feature data, the update of the second feature data is completed, thereby further improving the comprehensiveness of the road feature data maintained in the feature entity database.

[0070] For example, participate Figure 2BBasic feature data can include feature ID, feature type, coordinate information, feature status, creation time, and update time. Detailed feature data can include feature ID, entity ID, orientation angle, content information, entity status, time information, vehicle type, creation time, and update time. Additional feature data can include information primary key, feature ID, image address, trajectory information, lane number, lane status, and update time. Secondary change data can include change ID, entity ID, orientation angle, projected coordinates, road line ID, base map feature ID, update information, time information, vehicle type, confidence level, image address, trajectory information, creation time, and update time. After extracting the first feature data of road elements from real-world road scene images and determining the first change data, the basic feature data, detailed feature data, and additional feature data in the secondary feature data are further updated based on the first feature data. The secondary change data is then updated based on the first change data, thereby completing an effective and accurate update of the feature entity database.

[0071] Figure 3 This is a flowchart of a data processing method provided according to an embodiment of the present disclosure. Based on the above embodiments, this disclosure further explains in detail the steps preceding the extraction of the first feature data of road elements from a road scene image, such as... Figure 3 As shown, the data processing method provided in this embodiment may include:

[0072] S301, if the trajectory acquisition information of the target road segment meets the road element change conditions, then acquire the road scene image of the target road segment.

[0073] The target road segment refers to any segment of a road in the real world. The trajectory data collected can include the vehicle's position and speed information when the dashcam collects road features. The road feature change conditions can be conditions under which changes in the position or speed of road features meet certain requirements.

[0074] Specifically, there are many ways to determine whether trajectory-collected information meets the road element change conditions. For example, one possible approach is to analyze vehicle speeds in the trajectory-collected information of the target road segment. If the changes in vehicle speeds in the target road segment collected over a period of time all meet the speed limit threshold corresponding to that target road segment, then the road element change conditions are considered met. Another possible approach is to analyze vehicle positions in the trajectory-collected information of the target road segment. If vehicle position information previously corresponded to the target road segment but has not been collected recently; or if a vehicle position was previously uncollectible but has recently become collectible, then the road element change conditions are considered met. When the trajectory-collected information meets the road element change conditions, a road scene image of the target road segment can be obtained.

[0075] It should be noted that this embodiment can also trigger the acquisition of road scene images of the target road segment in other ways. For example, the road scene images of the target road segment can be acquired once every preset time interval, or the road scene images of the target road segment can be acquired when the number of stored road scene images accumulates to a certain threshold, or the road scene images of the target road segment can be acquired when a road element change notification is received. This embodiment does not limit this.

[0076] Optionally, road scene images of the target road section can be directly acquired, or the acquired road scene images can be filtered to delete those that do not meet preset conditions, and only high-quality road scene images that meet the preset conditions can be acquired. For example, road scene images whose image clarity does not reach the preset clarity threshold can be deleted, and road scene images whose image brightness does not reach the preset brightness threshold can also be deleted.

[0077] S302, First feature data of road elements extracted from road scene images.

[0078] S303, Based on the first feature data and the second feature data of the road elements recorded in the feature entity library, determine the first change data of the road elements.

[0079] S304, Update the element entity database based on the first feature data and the first change data.

[0080] The solution of this embodiment of the disclosure, when the trajectory acquisition information of the target road segment meets the road element change conditions, acquires the road scene image of the target road segment, further extracts the first feature data from the road scene image that meets the road element change conditions, determines the first change data, and thus updates the element entity library. In this way, it can ensure that as many road scene images as possible corresponding to road segments where road elements have changed are acquired to update the element entity library and avoid repeatedly judging road change data.

[0081] Figure 4 This is a flowchart of a map updating method according to an embodiment of this disclosure. This disclosure is applicable to updating electronic maps. The method can be executed by a map updating device, which can be implemented in software and / or hardware. Specifically, it can be integrated into an electronic device that has an electronic map. Figure 4 As shown, the map update method provided in this embodiment may include:

[0082] S401, Based on the second change data of road elements in the updated element entity database and the base map data of the electronic map, determine the data to be updated.

[0083] The element entity database can be updated based on the data processing method of any of the embodiments described above. An electronic map refers to a map configured in an electronic device and stored and accessed digitally using computer technology. Base map data refers to the feature data of road elements and corresponding entities recorded in the electronic map, specifically including road elements and their feature data. Data to be updated refers to the data in the determined base map data that needs to be updated.

[0084] Specifically, forward and / or reverse differencing methods can be used to perform differential processing between the second change data of road elements in the element entity library and the base map data to determine the changed features, and then directly use the changed features as the data to be updated; or the changed features can be further processed to obtain the data to be updated.

[0085] S402, Update the base map data of the electronic map based on the data to be updated.

[0086] Specifically, after determining the data to be updated, a matching algorithm can be used to perform corresponding update operations on the base map data of the electronic map for each piece of data to be updated, that is, to update the base map data of the electronic map.

[0087] The solution of this embodiment first determines the second change data based on the updated feature entity database, further combines it with the base map data of the electronic map to determine the data to be updated, and finally updates the base map data of the electronic map based on the data to be updated, thereby completing the update of the electronic map. In this way, the updated feature entity database can be directly used to determine the data that needs to be updated, improving the efficiency of electronic map updates, while the updated content is more detailed, ensuring the accuracy of electronic map updates.

[0088] Figure 5 This is a flowchart of a map updating method provided according to an embodiment of the present disclosure. Based on the above embodiments, this disclosure further explains in detail how to determine the data to be updated based on the second change data of road elements in the updated element entity database and the base map data of the electronic map. Figure 5 As shown, the map update method provided in this embodiment may include:

[0089] S501, Determine the target change data based on the second change data of the road elements in the updated element entity library.

[0090] Among them, target change data refers to the updated target data that needs to be displayed on the electronic map.

[0091] Specifically, there are many ways to determine the target change data based on the second change data. For example, one possible implementation is to filter the second change data of road elements in the updated element entity library according to preset rules, and determine the change data that meets the filtering requirements as the target change data. Another possible implementation is to input the second change data of road elements in the updated element entity library into a pre-trained neural network model, and output the target change data, thus determining the target change data.

[0092] S502, based on the target change data and the base map data of the electronic map, determine the data to be updated.

[0093] Specifically, after determining the target change data, forward differencing and / or reverse differencing can be used to perform differential processing on the target change data and the base map data of the electronic map to determine the characteristics of the change, and further determine the data to be updated based on the characteristics of the change.

[0094] S503, Update the base map data of the electronic map based on the data to be updated.

[0095] The solution of this embodiment first identifies the target change data in the second change data, then compares the target change data with the base map data of the electronic map to determine the data to be updated, and finally updates the base map data of the electronic map based on the data to be updated. This solution first filters the second change data, removing feature data in the electronic map that does not need to be updated, and then updates the electronic map based on the remaining change data. This improves the efficiency of electronic map updates while ensuring the accuracy of the updates.

[0096] Figure 6 This is a schematic diagram of a data processing apparatus according to an embodiment of the present disclosure, which is applicable to updating a feature entity database. The apparatus can be implemented using software and / or hardware, and can implement the data processing methods of any embodiment of the present disclosure. Figure 6 As shown, the data processing device 600 includes:

[0097] Extraction module 601 is used to extract first feature data of road elements from road scene images;

[0098] The determining module 602 is used to determine the first change data of the road element based on the first feature data and the second feature data of the road element recorded in the element entity library;

[0099] The update module 603 is used to update the element entity database based on the first feature data and the first change data; the element entity database is used to update the electronic map.

[0100] The solution of this disclosure extracts first feature data of road elements from a road scene image, then determines first change data of the road elements based on the first feature data and second feature data of the road elements recorded in the element entity database, and finally updates the element entity database based on the first feature data and the first change data. This disclosure provides a solution for updating an element entity database, which can update the element entity database based on the first feature data extracted from the road scene image and the second feature data obtained from the element entity database records, ensuring the accuracy and real-time performance of the element entity database. Furthermore, the updated element entity database can be better applied to updating electronic maps, thereby improving the update efficiency and accuracy of electronic maps.

[0101] Furthermore, the update module 603 includes:

[0102] The feature data update unit is used to update the second feature data of the road element in the feature entity library according to the first feature data;

[0103] The change data update unit is used to update the second change data of the road element in the element entity library according to the first change data.

[0104] Furthermore, the feature data update unit includes:

[0105] The basic data update subunit is used to update the basic feature data in the second feature data of the road element in the element entity library according to the location features of the road element in the first feature data;

[0106] The detailed data update subunit is used to update the detailed feature data in the second feature data of the road element in the feature entity library according to the attribute features of the entity corresponding to the road element in the first feature data and the attribute features of the lane to which the entity belongs.

[0107] Furthermore, the update module 603 is also specifically used for:

[0108] Based on the additional attribute features of the road elements in the first feature data, update the additional feature data in the second feature data of the road elements in the feature entity library.

[0109] Furthermore, the data processing device further includes:

[0110] The acquisition module is used to acquire a road scene image of the target road segment if the trajectory acquisition information of the target road segment meets the road element change conditions.

[0111] Figure 7This is a schematic diagram of a map updating device according to an embodiment of the present disclosure. This embodiment is applicable to updating electronic maps. The device can be implemented using software and / or hardware, and can implement the map updating method of any embodiment of the present disclosure. Figure 7 As shown, the map updating device 700 includes:

[0112] The data determination module 701 is used to determine the data to be updated based on the second change data of road elements in the updated element entity library and the base map data of the electronic map; wherein, the element entity library is updated based on the data processing method described in any embodiment of this disclosure;

[0113] The data update module 702 is used to update the base map data of the electronic map according to the data to be updated.

[0114] The solution of this embodiment first determines the second change data based on the updated feature entity database, further combines it with the base map data of the electronic map to determine the data to be updated, and finally updates the base map data of the electronic map based on the data to be updated, thereby completing the update of the electronic map. In this way, the updated feature entity database can be directly used to determine the data that needs to be updated, improving the efficiency of electronic map updates, while the updated content is more detailed, ensuring the accuracy of electronic map updates.

[0115] Furthermore, the data determination module is specifically used for:

[0116] Based on the second change data of the road elements in the updated element entity library, determine the target change data;

[0117] Based on the target change data and the base map data of the electronic map, the data to be updated is determined.

[0118] The above-described products can perform the methods provided in any embodiment of this disclosure, and have the corresponding functional modules and beneficial effects for performing the methods.

[0119] The acquisition, storage, and application of road scene images, feature data, change data, and base map data involved in the technical solution disclosed herein all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0120] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0121] Figure 8 This is a block diagram of an electronic device used to implement the data processing method and / or map updating method of the embodiments of this disclosure.

[0122] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0123] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0124] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0125] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as data processing methods and / or map updating methods. For example, in some embodiments, the data processing methods and / or map updating methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the data processing methods and / or map updating methods described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform data processing methods and / or map update methods by any other suitable means (e.g., by means of firmware).

[0126] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0128] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0130] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0131] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem that addresses the management difficulties and weak business scalability inherent in traditional physical hosting and VPS services. Servers can also be servers for distributed systems or servers integrated with blockchain technology.

[0132] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0133] Cloud computing refers to a technology system that enables access to a shared pool of physical or virtual resources via a network. These resources can include servers, operating systems, networks, software, applications, and storage devices, and can be deployed and managed on demand and in a self-service manner. Cloud computing technology can provide efficient and powerful data processing capabilities for applications such as artificial intelligence and blockchain, as well as for model training.

[0134] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0135] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data processing method, comprising: Extracting the first feature data of road elements from road scene images; Based on the first feature data and the second feature data of the road element recorded in the element entity database, the first change data of the road element is determined; The element entity database is updated based on the first feature data and the first change data. The element entity database is a database that records feature data of road elements in different dimensions in the real world, as well as change data of road element features. The second change data in the element entity database is used to perform differential processing with the base map data to determine the data to be updated for updating the base map data of the electronic map. The base map data is feature data that records road elements and corresponding entities in the electronic map. The second change data is information data stored in the element entity database to record changes in feature data. Updating the element entity database based on the first feature data and the first change data includes: Based on the first feature data, update the second feature data of the road element in the element entity library, including: Based on the location features of the road elements in the first feature data, update the basic feature data in the second feature data of the road elements in the feature entity library; wherein, the location features refer to feature information related to the location of the road elements; Based on the attribute features of the road element corresponding to the entity in the first feature data and the attribute features of the lane to which the entity belongs, update the detailed feature data in the second feature data of the road element in the feature entity library; wherein, the entity is a road element entity used to characterize the road environment; the attribute features of the entity include entity ID, orientation angle, content information, and entity status; the attribute features of the lane to which the entity belongs include time information, vehicle type, and lane status; The step of updating the element entity database based on the first feature data and the first change data includes: Based on the first change data, update the second change data of the road element in the element entity library.

2. The method according to claim 1, wherein, The step of updating the second feature data of the road element in the element entity database based on the first feature data further includes: Based on the additional attribute features of the road elements in the first feature data, update the additional feature data in the second feature data of the road elements in the feature entity library.

3. The method according to claim 1, further comprising: If the trajectory acquisition information of the target road segment meets the road element change conditions, then the road scene image of the target road segment is acquired.

4. A map updating method, comprising: Based on the second change data of road elements in the updated element entity database and the base map data of the electronic map, the data to be updated is determined; wherein, the element entity database is updated based on the method described in any one of claims 1-3; Update the base map data of the electronic map based on the data to be updated.

5. The method according to claim 4, wherein, The step of determining the data to be updated based on the second change data of the road elements in the updated element entity database and the base map data of the electronic map includes: Based on the second change data of the road features in the updated feature entity library, determine the target change data: Based on the target change data and the base map data of the electronic map, the data to be updated is determined.

6. A data processing apparatus, comprising: The extraction module is used to extract the first feature data of road elements from road scene images; The determining module is used to determine the first change data of the road element based on the first feature data and the second feature data of the road element recorded in the element entity library; The update module is used to update the element entity library based on the first feature data and the first change data. The element entity library is a database that records the feature data of road elements in different dimensions in the real world and the change data of road element features. The second change data in the element entity library is used to perform differential processing with the base map data to determine the data to be updated for updating the base map data of the electronic map. The base map data is the feature data of road elements and corresponding entities recorded in the electronic map. The second change data refers to the information data stored in the feature entity database used to record changes in feature data; The update module includes: The feature data update unit is used to update the second feature data of the road element in the feature entity library according to the first feature data; The feature data update unit includes: The basic data update subunit is used to update the basic feature data in the second feature data of the road element in the feature entity library according to the location features of the road element in the first feature data; wherein, the location features refer to feature information related to the location of the road element; The detailed data update subunit is used to update the detailed feature data in the second feature data of the road element in the feature entity library according to the attribute features of the entity corresponding to the road element in the first feature data and the attribute features of the lane to which the entity belongs; wherein, the entity is a road element entity used to represent the road environment; the attribute features of the entity include entity ID, orientation angle, content information and entity status; the attribute features of the lane to which the entity belongs include time information, vehicle type object and lane status; The update module includes: The change data update unit is used to update the second change data of the road element in the element entity library according to the first change data.

7. The data processing apparatus according to claim 6, wherein, The update module is also specifically used for: Based on the additional attribute features of the road elements in the first feature data, update the additional feature data in the second feature data of the road elements in the feature entity library.

8. The data processing apparatus according to claim 6, further comprising: The acquisition module is used to acquire a road scene image of the target road segment if the trajectory acquisition information of the target road segment meets the road element change conditions.

9. A map updating device, comprising: The data determination module is used to determine the data to be updated based on the second change data of road elements in the updated element entity database and the base map data of the electronic map; wherein the element entity database is updated based on the data processing device according to any one of claims 6-8; The data update module is used to update the base map data of the electronic map based on the data to be updated.

10. The map updating apparatus according to claim 9, wherein the data determining module is specifically used for: Based on the second change data of the road elements in the updated element entity library, determine the target change data; Based on the target change data and the base map data of the electronic map, the data to be updated is determined.

11. An electronic device, comprising: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the data processing method of any one of claims 1-3 and / or the map updating method of any one of claims 4-5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the data processing method of any one of claims 1-3, and / or the map updating method of any one of claims 4-5.

13. A computer program product comprising a computer program that, when executed by a processor, implements the data processing method of any one of claims 1-3, and / or the map updating method of any one of claims 4-5.

Images