Map data updating method, device and equipment

Abstract

The invention discloses a map data updating method, device and equipment, and the method comprises the steps: carrying out the clustering of a first semantic object in historical data and a second semantic object in new data, so as to obtain a plurality of clusters formed by the clustering of the first semantic object and / or the second semantic object; and carrying out fitting on clusters formed by clustering so as to update the semantic objects in the map data by judging the existence confidence and the type confidence of the semantic objects subjected to cluster fitting. According to the method, the defects that local sensing data in historical data is less, a semantic object cannot be clustered and fitted, and a high-precision map cannot be made are overcome; the defects that local sensing data in new data is less, and a high-precision map cannot be independently updated and made are overcome; and the defects that the change of the high-precision map is large and the mapping result is unstable due to the sensing data difference in multiple times of data are overcome. Historical data is utilized to standardize and constrain, and compared with a high-precision map manufactured at a time, the data range is more perfect, and the fault tolerance is high.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a method, device and equipment for updating map data. Background Art

[0002] High-precision maps can be used for autonomous driving, and the recognition and production of road signs are important components of generating high-precision maps. Road signs (semantic objects) are generally identified and extracted through road image information collected by cameras mounted on vehicles.

[0003] In the process of making high-precision maps, in order to solve the drawback of large resource investment in single-trip closed-loop collection (closed-loop single-trip collection) and optimize application scenarios, the inventor previously proposed a solution for making high-precision maps based on multi-source crowdsourcing data, that is, by using private cars as collection equipment, data collection is performed without interfering with the stable and fast driving of the vehicle. In the process of using private cars to collect data, since it is impossible to stipulate that a certain vehicle strictly follows a closed-loop trajectory, most vehicle trajectories are only one-way trajectories from the starting point to the destination, so multiple single-track data is used in the later production of high-precision maps, that is, multiple / multiple image collections are required for the same location, and then the road sign information in each collected image is extracted separately, and finally the same road sign collected in multiple trips is fused, and then a high-precision map is produced based on multi-source crowdsourcing data.

[0004] After the high-precision map is produced, it will also face the problem of map updating during use. There are two common ways. One is to overlay on historical data, which will inevitably cause the historical database to become infinitely large; the second is to update based on data differentials. Although the historical database is no longer infinitely large, due to the aggregation nature and fusion characteristics of semantic objects, direct differential updates are not suitable for scenarios with multi-source crowdsourcing data. Summary of the invention

[0005] In order to update the high-precision map produced based on multi-source crowdsourcing data, so as to fully consider the contribution of historical data to semantic objects, and thus enrich the technical routes and increase the selection space, a method, device and equipment for updating map data are provided in the embodiments of the present invention.

[0006] In a first aspect, an embodiment of the present invention provides a method for updating map data, which may include:

[0007] Clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters including the first semantic object and / or the second semantic object;

[0008] The clusters formed by clustering are fitted, so as to update the semantic objects in the map data by determining the existence confidence and type confidence of the semantic objects fitted by the clusters.

[0009] Optionally, after clustering to form the cluster, the method may further include: determining the source of the semantic objects in the cluster formed by clustering to divide the cluster; if the semantic objects include the first semantic object and the second semantic object, treating the cluster as a mixed cluster;

[0010] If the semantic object is the second semantic object, taking the cluster as a newly added cluster;

[0011] If the semantic object is the first semantic object, the cluster is taken as a historical cluster.

[0012] Optionally, fitting the mixed cluster may include:

[0013] Based on the number of newly added segment data in the group corresponding to the mixed cluster, increase the existence confidence of the semantic object fitted by the mixed cluster; and

[0014] Based on the type confidence of the first semantic object in the mixed cluster and the type confidence of the second semantic object, the type confidence of the semantic object after the mixed cluster is fitted is determined.

[0015] Optionally, determining the type confidence of the semantic object after the hybrid cluster is fitted based on the type confidence of the first semantic object in the hybrid cluster and the type confidence of the second semantic object may include:

[0016] sorting the second semantic objects in the mixed cluster based on the acquisition time of the new data;

[0017] A weighted accumulation is performed based on the type confidence of the first semantic object and the sorted type confidence of the second semantic object to determine the type confidence of the fitted semantic object based on the type confidence result obtained by the weighted accumulation and the type confidence of the second semantic object.

[0018] Optionally, fitting the newly added cluster may include:

[0019] sorting the second semantic objects in the newly added cluster based on the collection time of the new data corresponding to the newly added cluster;

[0020] Performing weighted accumulation based on the type confidences of the sorted semantic objects to determine the type confidence of the semantic object after the newly added cluster is fitted;

[0021] And, setting an initial value of the existence confidence of the semantic object after the newly added cluster is fitted.

[0022] Optionally, fitting the historical cluster may include: reducing the existence confidence of the semantic object fitted by the historical cluster based on the number of newly added segment data in the group corresponding to the historical cluster.

[0023] Optionally, the method may further include: combining the second semantic objects that have not been successfully clustered into a new segment data for storage.

[0024] Optionally, before clustering the first semantic object in the historical data and the second semantic object in the new data, the following may also be included:

[0025] Acquire new data, wherein the new data includes at least one newly added single trip data;

[0026] Based on the association relationship between the lane and the semantic object in the newly added single trip data, calibrating the position relationship of the semantic object in the newly added single trip data;

[0027] Segmenting the calibrated newly added single trip data based on the position of the preset mark in the newly added single trip data to obtain a plurality of segment data after the newly added single trip data is segmented; wherein each segment data includes boundary information, vehicle lanes and semantic objects;

[0028] Determine the correspondence between each segment data in the newly added single-pass data and the group data composed of the segment data at the same position after the multi-pass data in the historical data are segmented, so as to cluster the second semantic object in each segment data in the newly added single-pass data with the first semantic object in the group data in the historical data corresponding to the segment data.

[0029] In a second aspect, an embodiment of the present invention provides a map data updating device, which may include:

[0030] A clustering module, used for clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters formed by clusters containing the first semantic object and / or the second semantic object;

[0031] The fitting module is used to fit the clusters formed by clustering;

[0032] The updating module is used to update the semantic objects in the map data by determining the existence confidence and type confidence of the semantic objects fitted by the cluster.

[0033] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for updating map data as described in the first aspect.

[0034] In a fourth aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for updating map data as described in the first aspect is implemented.

[0035] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0036] The embodiments of the present invention provide a method, device and equipment for updating map data. The updating method has the following beneficial effects: first, it solves the problem that there is little local perception data in historical data, which cannot be clustered and fitted into semantic objects and produce high-precision maps; second, it solves the problem that there is little local perception data in new data, which cannot be updated separately and produce high-precision maps; third, it solves the problem that the high-precision map changes are large and the mapping results are unstable due to the differences in perception data in multiple passes of data.

[0037] Furthermore, this updating method solves the technical problems of uncertain data collection scope, uncertain data collection quantity, and unstable data collection quality of multi-source crowdsourcing data, and uses historical data to regulate and constrain the final generated high-precision map. Compared with a single-production high-precision map, its data range is more complete, has a higher fault tolerance, and can reflect changes in single data, as well as reflect real road changes from cumulative changes.

[0038] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0039] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 A flowchart of a method for updating map data provided in an embodiment of the present invention;

[0042] Figure 2 A flow chart of dividing cluster types provided in an embodiment of the present invention;

[0043] Figure 3 A flowchart of preprocessing single-trip data provided in an embodiment of the present invention;

[0044] Figure 4One of the flowcharts of the detailed map data updating method provided in the embodiment of the present invention;

[0045] Figure 5 This is a second flowchart of a detailed map data updating method provided in an embodiment of the present invention;

[0046] Figure 6 A schematic diagram of segment data provided in an embodiment of the present invention;

[0047] Figure 7 A schematic diagram of line production provided in an embodiment of the present invention;

[0048] Figure 8 A schematic diagram of multiple data groupings provided in an embodiment of the present invention;

[0049] Fig. 9 It is a schematic diagram of the structure of a map data updating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0051] Existing differential extraction schemes are mainly aimed at the storage and use of data that has not been successfully clustered, as well as the differential extraction of two aggregation (fitting) results. When the inventors updated the high-precision map after actually making it based on multi-source crowdsourcing data, they found the following problems: (1) There are relatively few local perception data (semantic objects, etc.) in the historical data, and clustering and map output cannot be achieved. When making a high-precision map, new data needs to be accumulated, and then the perception data at that location can be clustered and mapped; (2) There are enough local perception data in the historical data to be clustered into a map, but there are relatively few new data, and the new data alone cannot be clustered into a map; (3) There are perception differences between the historical data and the new data, such as differences in data type, data shape, and data location, which leads to large changes in the clustering results and unstable clustering results. It should be noted that the above clustering into a map mainly refers to clustering into specific semantic objects (roadside signs), such as lane lines, straight arrows, turn arrows, sidewalks, etc.; (4) The deletion scenario of historical data is not judged, which causes the historical data to become infinitely large; (5) The existing update scheme focuses on how to use the data that has not been successfully clustered, and does not fully consider the weight of historical data during the clustering or update process. In view of the above problems, the present invention is proposed to provide a method, device and equipment for updating map data that overcomes the above problems or at least partially solves the above problems.

[0052] In an embodiment of the present invention, a method for updating map data is provided. The method is suitable for differentially updating high-precision map data produced based on multi-source crowdsourcing data. A new update scheme is proposed for updating multi-source data. Figure 1 As shown, the method may include the following steps:

[0053] Step S11 : clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters formed by clustering including the first semantic object and / or the second semantic object.

[0054] A single semantic object in historical data is fitted by objects in multiple passes of data, and can represent multiple geometric bodies. In order to facilitate the distinction and explanation of semantic objects in historical data and new data, in an embodiment of the present invention, the semantic object in historical data is referred to as the first semantic object, and the semantic object in new data is referred to as the second semantic object. The above-mentioned first semantic object and second semantic object have different attributes (historical data attributes and new data attributes). Those skilled in the art can understand that there are several semantic objects in historical data and several semantic objects in new data, and it is not limited to one semantic object data.

[0055] The embodiment of the present invention can cluster the semantic objects in a segment of data. Each segment of data corresponding to each pass can have multiple semantic objects. If the segment of data is historical data, the semantic objects in the segment of data are all first semantic objects; if the segment of data is new data, the semantic objects in the segment of data are all second semantic objects. Due to the difference in signal quality during acquisition, etc., the semantic objects in a single pass of data are missing. Therefore, in the clustering process, the cluster initially clustered at the same position may only contain the first semantic object, or only contain the second semantic object, or of course, may contain the first semantic object and the second semantic object.

[0056] Step S12: Fit the clusters formed by clustering. In this step, a cluster is finally fitted into a semantic object, and the semantic object will be retained or deleted according to the subsequent steps.

[0057] Step S13: updating the semantic objects in the map data by judging the existence confidence and type confidence of the semantic objects fitted by the cluster.

[0058] This step updates the semantic objects in the map data by judging the confidence of the semantic objects fitted by the clusters. During the update, historical data with low confidence is deleted and the types of semantic objects are adjusted.

[0059] The updating method provided by the embodiment of the present invention uses historical data to standardize the effect and scope of the final map output, solving the problems of uncertain scope, quantity, and quality of multi-source crowdsourcing data; the type confidence can be used to compare the single-production output, and the data range is more complete, with a high fault tolerance rate, and can reflect the changes in single data. At the same time, the cumulative changes can ultimately reflect the actual road surface changes. Furthermore, the existence confidence of the semantic object fitted by the cluster can be used to judge the deletion scenario of the historical data, reducing the storage of historical data.

[0060] In an optional embodiment, after clustering is performed in step S11, the cluster types may be divided to update the semantic objects formed by subsequent cluster data fitting. Figure 2 As shown, the following steps may be specifically included:

[0061] Step S21, determine the source of the semantic objects in the clusters formed by clustering to divide the clusters; if the semantic object includes the first semantic object and the second semantic object, execute step S22; if the semantic object is the second semantic object, execute step S23; if the semantic object is the first semantic object, execute step S24.

[0062] Step S22: The cluster is used as a hybrid cluster. The hybrid cluster may be called a first type cluster, and the hybrid cluster inherits the ID of the original cluster in the historical data, and updates the high-precision map based on the ID in the map data.

[0063] Step S23, the cluster is used as a newly added cluster. The newly added cluster can be called a second type cluster, which can generate an ID for the newly added cluster according to the ID generation rule in the group data or segment data to facilitate subsequent map data updates. Of course, if the newly added cluster has a second semantic object of new data for clustering after clustering during the next update, the type of the newly added cluster will also be changed to a mixed cluster.

[0064] Step S24: use the cluster as a historical cluster. The historical cluster can be called a third type of cluster, and the historical cluster also inherits the ID of the original cluster to which it belongs. The semantic object after fitting will not change. In the embodiment of the present invention, the confidence of the existence of the historical data will be judged to determine whether the historical data needs to be deleted.

[0065] The embodiment of the present invention determines the data sources contained in different clusters, and there will be different clustering results after clustering. There will be different differential update methods for fitting the clusters into semantic objects after clustering. In this way, the semantic objects after cluster fitting from different data sources will be fully considered for differentiated updates, avoiding the use of the same update method that leads to the inability to effectively distinguish the differences between data from different sources.

[0066] In another optional embodiment, fitting the mixed cluster in the above step S12 may include: on the one hand, increasing the existence confidence of the semantic object fitted by the mixed cluster based on the number of newly added segment data in the group corresponding to the mixed cluster; on the other hand, determining the type confidence of the semantic object after the mixed cluster is fitted based on the type confidence of the first semantic object in the mixed cluster and the type confidence of the second semantic object.

[0067] In the embodiment of the present invention, since the semantic objects of new data are added to the mixed cluster, that is, the number of semantic objects corresponding to the position is further increased, the confidence of the existence of the mixed cluster is better, and the confidence of the existence of the semantic objects after the cluster fitting needs to be increased to improve the accuracy of the existence of the updated map elements. The semantic objects corresponding to the single-trip data in the historical data and the new data have their own type attributes. During the cluster fitting process, the type confidence will be updated, which can not only reflect the change process of the single-trip data of the semantic object, but also reflect the changes in the real-world road surface from the final result of the cumulative changes.

[0068] In another optional embodiment, the specific process of determining the type confidence of the semantic object after the mixed cluster is fitted may include the following steps: first, sorting the second semantic objects in the mixed cluster based on the acquisition time of the new data; then, weighted accumulation is performed based on the type confidence of the first semantic object and the type confidence of the sorted second semantic object, so as to determine the type confidence of the fitted semantic object based on the type confidence result obtained by the weighted accumulation and the type confidence of the second semantic object.

[0069] In the embodiment of the present invention, when the second semantic objects are sorted based on the collection time of the new data, they are sorted from old to new, which can reflect the credibility of the latest collected data on the one hand, and on the other hand, can also reflect the process of single data type change. For example, in the mixed cluster, the original data type is a straight arrow type, and the second semantic object of the new data has a straight arrow and a right turn arrow. The type of the semantic object fitted by the mixed cluster will be judged, and the final type of the semantic object will be determined by accumulation.

[0070] In another optional embodiment, fitting the newly added cluster in the above step S12 may include the following steps: first, sorting the second semantic objects in the newly added cluster based on the acquisition time of the new data corresponding to the newly added cluster; then, performing weighted accumulation based on the type confidence of the sorted semantic objects to determine the type confidence of the semantic objects after fitting the new cluster; finally, setting the initial value of the existence confidence of the semantic objects after fitting the new cluster.

[0071] In the embodiment of the present invention, the fitting method of the newly added cluster is the same as the method in which the newly added second semantic object in the mixed cluster participates in the fitting. The above-mentioned introduction to the mixed cluster can be referred to, and the embodiment of the present invention will not be repeated here. It should be noted here that since the newly added cluster only includes the second semantic object of the new data, the semantic object fitted into the newly added cluster needs to set an initial value of existence confidence. The initial value should be set reasonably, neither too low nor too high, to avoid being directly deleted when compared with the existence confidence threshold when it is too low (the newly added semantic object cannot be reflected), and to avoid being too high, resulting in the overall existence confidence threshold needing to be set higher, which is likely to cause the weight of the historical data to become relatively low, and the reduced effect of the historical data cluster fitting will affect the inability to form a map when the data is insufficient.

[0072] In another optional embodiment, fitting the historical cluster in the above step S12 may include: based on the number of newly added segment data in the group corresponding to the historical cluster, reducing the existence confidence of the semantic object fitted by the historical cluster. In this embodiment, since the historical cluster only has historical data, the semantic object after fitting the historical cluster will not change. However, if the semantic object does not exist in multiple subsequent collections, it is necessary to judge whether the actual road corresponding to the semantic object will change, that is, the semantic object may need to be deleted.

[0073] In another optional embodiment, also refer to Figure 1 As shown, the above method may also include: step S14, combining the second semantic objects that have not been successfully clustered into a new segment data for storage. The second semantic object that has not been successfully clustered does not mean that the semantic object does not exist in the actual road. It may be due to the accuracy of the collected signal or the latest added road surface signs (semantic objects), etc., which causes some data to fail to be clustered successfully, but it is impossible to determine whether these data really exist. Therefore, the semantic objects that have not been successfully clustered will be combined into a new segment data for storage. It should be noted here that the semantic objects that have not been successfully clustered will not be output again, so that this type of semantic object will not be displayed in the map data. If clustering can be successfully performed when there is new data updated later, the semantic objects formed by the cluster fitting after successful clustering will be output at this time. In this embodiment, the data that has not been successfully clustered is retained for backup, which improves the accuracy of the later updated map data.

[0074] In another optional embodiment, before clustering, the following steps need to be performed, that is, pre-processing the single-pass data included in the new data, referring to Figure 3 As shown, the following steps may be included:

[0075] Step S31: Acquire new data, where the new data includes at least one newly added single trip data.

[0076] Step S32: based on the association relationship between the lanes and the semantic objects in the newly added single trip data, calibrate the position relationship of the semantic objects in the newly added single trip data.

[0077] Step S33, segmenting the calibrated newly added single trip data based on the position of the preset mark in the newly added single trip data to obtain a plurality of segment data after segmenting the newly added single trip data; wherein each segment data includes boundary information, vehicle lanes and semantic objects.

[0078] Step S34, determine the correspondence between each segment data in the newly added single-pass data and the group data composed of the segment data at the same position after the multi-pass data in the historical data are segmented, so as to cluster the second semantic object in each segment data in the newly added single-pass data with the first semantic object in the group data in the historical data corresponding to the segment data.

[0079] Since there are a large number of semantic objects in a single trip of data, and the starting and ending points of the routes of multi-source data are different, it would be very difficult to directly update the entire single trip of data. Therefore, in this embodiment, the single trip data needs to be divided into segments, and the segment data at the same position are used to form a group of data, and the semantic objects in a group of data are updated.

[0080] In a detailed embodiment, referring to Figure 4 and Figure 5 As shown, the above map data updating method may include the following steps:

[0081] Step S401: Acquire new data, where the new data includes at least one newly added single trip data.

[0082] Reference Figure 6 As shown, a single trip of data is composed of several connected segments, each of which contains an identification semantic object and a lane semantic object. Multiple trips of segment data at the same position can be combined into a group of data. When the embodiment of the present invention updates the above map data, a group of data is used as an update processing unit, that is, the semantic objects in the segment data included in the group data are first clustered and fitted, and finally multiple trips of collected data at the same position are fitted into a semantic object for output.

[0083] Step S402: based on the association relationship between the lanes and the semantic objects in the newly added single trip data, calibrate the position relationship of the semantic objects in the newly added single trip data.

[0084] In this step, only the newly added single-trip data is processed, and the single-trip data processing process in the historical data is the same. Only when the processing mechanism is the same can it be divided into the same group of data. The single-trip data processing process is as follows: Based on the line information, that is, the vehicle lane semantic object information, a position relationship is established in the horizontal and vertical directions. In the specific implementation, the vertical vehicle lane semantic object is made into a line (that is, the vertical relationship), and other semantic objects in the single-trip data (identification semantic objects, vehicle lane semantic objects, such as arrows, zebra crossings, etc.) are mounted on the line. Refer to Figure 7 As shown, the vertical thin line is the produced line. In the same frame of data, the absolute relationship between the above-mentioned car line and the semantic object is known, so the position relationship of the semantic object in a single trip of data can be calibrated.

[0085] Step S403, segmenting the calibrated new single trip data based on the position of the preset mark in the new single trip data to obtain a plurality of segment data after segmenting the new single trip data; wherein each segment data includes boundary information, vehicle lanes and semantic objects.

[0086] After the calibration is completed, due to the large amount of data and the different starting and ending points between the single-trip routes, it is not possible to use the entire route for update. At this time, the single-trip data needs to be segmented. In the specific implementation, the single-trip data is divided into several segments according to the locations of preset signs such as intersections, zebra crossings, stop lines, etc.

[0087] Step S404, determine the correspondence between each segment data in the newly added single-pass data and the group data composed of the segment data at the same position after the multi-pass data in the historical data are segmented, so as to cluster the second semantic object in each segment data in the newly added single-pass data with the first semantic object in the group data in the historical data corresponding to the segment data.

[0088] This step is to group the multi-trip data after segmentation, that is, to establish a group relationship for the multi-trip data, to divide multiple single-trip data representing the same section of road into one group, to establish a topological relationship between adjacent groups, and to write an ID to each group based on the longitudinal extension characteristics of the line. Figure 8 As shown in the figure, the segments at the same position will form a group data. The endpoints of the group data are crosses. The cross represents the location point of the end of the bunch. Through the relationship of the cross, we can determine which bunch it belongs to, and also determine the relationship between adjacent bunches. Figure 8 As shown, after grouping, the same semantic objects in the group need to be matched and aligned before updating. The purpose of matching is to adjust the geometric position of the semantic objects, and the purpose of alignment is to increase the weight of historical data when clustering after moving the semantic objects.

[0089] Step S405, clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a number of clusters formed by clusters containing the first semantic object and / or the second semantic object. This step can be implemented with reference to the above-mentioned step S11. During the specific implementation, the individual semantic object (first semantic object) in the historical data can be copied into multiple copies, and the number of copies can be determined based on whether the semantic object is formed by clustering and fitting in several segment data. The purpose of copying the first semantic object into multiple copies is to increase the weight of the historical data, so as to increase the density during clustering, and thus fully consider the role of the historical data. It should be noted that after the historical data is fitted with a semantic object, in order to reduce data storage and save resources, only the last fitted semantic object is retained, and the semantic objects in the multiple passes of data before the fitting are no longer retained. Therefore, the multiple copies are the semantic objects fitted by the copied historical data.

[0090] Step S406: Determine the sources of the semantic objects in the clusters formed by clustering to divide the clusters.

[0091] Step S407: If the semantic object includes the first semantic object and the second semantic object, the cluster is regarded as a mixed cluster.

[0092] Step S408: If the semantic object is the second semantic object, the cluster is used as a newly added cluster.

[0093] Step S409: If the semantic object is the first semantic object, the cluster is used as a historical cluster.

[0094] The detailed description of different types of clusters in steps S407 to S409 can be referred to the above embodiments, which will not be described in detail here.

[0095] Step S410: based on the number of newly added segment data in the group corresponding to the mixed cluster, increase the existence confidence of the semantic object fitted by the mixed cluster.

[0096] This step increases the existence confidence (N\A confidence) of the semantic object successfully fitted by the mixed cluster. The specific method is as follows: count the number of segments of the new data on the bunch. For example, if there are n new segments on the bunch, and the fitting result also inherits the ID of the historical data, then use the N\A confidence of the historical data to perform n times N=N+(100-N)*10% on the fitting result (semantic object), thereby increasing the existence confidence of the semantic object fitted by the mixed cluster.

[0097] Step S411: Determine the type confidence of the semantic object after the mixed cluster is fitted based on the type confidence of the first semantic object and the type confidence of the second semantic object in the mixed cluster.

[0098] Specifically, the second semantic objects in the mixed cluster are first sorted based on the acquisition time of the new data; then, a weighted accumulation is performed based on the type confidence of the first semantic object and the type confidence of the sorted second semantic object, so as to determine the type confidence of the fitted semantic object based on the type confidence result obtained by the weighted accumulation and the type confidence of the second semantic object.

[0099] In a specific example, the type confidence is calculated in a weighted accumulation manner, combining the type confidence of the perceived data (semantic object) itself to determine the type confidence of the final fitted semantic object. For example, there are four data in a cluster. First, the four data are sorted according to time (from old to new), and then weighted accumulation is performed. In the specific implementation, a uniformization parameter k is set, assuming k = 20.

[0100] The first data is a straight arrow, and its type confidence is 70. Its type confidence P(A1) is:

[0101] P(A1)=70 / 20=3.5

[0102] The second data is a straight arrow, and its type confidence is 80. Its type confidence P(A2) is:

[0103] P(A2)=3.5+80 / 20=7.5

[0104] The third data is a straight arrow, and its type confidence is 60. Its type confidence P(A3) is:

[0105] P(A3)=7.5+60 / 20=10.5

[0106] The fourth data is a right-turn arrow, and its type confidence is 60. Its type confidence P(A4) is:

[0107] P(A4)=10.5+(-60) / 20=7.5

[0108] At this time, the right-turn arrow of the fourth data is new data. In the previous historical data, the cumulative confidence of the straight arrow type is 10.5, and the confidence of the right-turn arrow of the new data is 60 / 20=3. The type confidence of the historical data is higher than the type confidence of the new data. The type of the historical data is kept, that is, the straight arrow is kept unchanged. After the new data subtracts the type confidence of the original historical data, after obtaining the right-turn arrow of the fourth data, the type confidence of the semantic object is 7.5. Finally, the type of the fitting result of the cluster is a straight arrow, and the type confidence is 7.5.

[0109] Continue to obtain data. If two data are added to the new cluster, and the fifth data is a right-turn arrow with a type confidence of 80, then its type confidence P(A5) is:

[0110] P(A5)=7.5+(-80) / 20=3.5

[0111] The sixth data is a right-turn arrow, and its type confidence is 80. Its type confidence P(A6) is:

[0112] P(A6)=3.5+(-80) / 20=-0.5

[0113] At this time, the fifth and sixth right-turn arrows are new data, which reduces the type confidence of the original historical data. The cumulative confidence of the straight arrow type is 3.5, and the confidence of the new data right-turn arrow is 80 / 20=4. The type confidence of the historical data is lower than the type confidence of the new data. The type of the historical data is modified, that is, the type is changed to a right-turn arrow. At this time, P(A6) changes the type to a right-turn arrow, and the type confidence is 0.5. Finally, the type of the fitting result of the cluster is a right-turn arrow, and the type confidence is 0.5.

[0114] Step S412: Sort the second semantic objects in the newly added cluster based on the collection time of the new data corresponding to the newly added cluster.

[0115] Step S413: performing weighted accumulation based on the type confidences of the sorted semantic objects to determine the type confidence of the semantic object after the newly added cluster is fitted.

[0116] In step S412 and step S413 of the embodiment of the present invention, the fitting method of the newly added cluster is the same as the method in which the second semantic object newly added in the mixed cluster participates in the fitting. Please refer to the introduction of the mixed cluster part above, and the embodiment of the present invention will not be repeated here.

[0117] Step S414: setting an initial value of the existence confidence of the semantic object after the newly added cluster fitting. In the embodiment of the present invention, the initial value of the existence confidence can be set to 50.

[0118] Step S415: based on the number of newly added segment data in the group corresponding to the historical cluster, reduce the existence confidence of the semantic object fitted by the historical cluster.

[0119] In the specific implementation of this step, the existence confidence of the semantic object fitted by the historical cluster is reduced by counting the number of new data segments on the bunch. For example, if there are n new segments on the bunch, the current existence confidence of the historical cluster (N\A confidence) N needs to be reduced n times N=N-(100-N)*10%. The purpose of this reduction is to combine the number of existence confidence with new data, ensuring the consistency of the results of multiple one-time calculations and multiple multiple calculations.

[0120] Step S416: updating the semantic objects in the map data by determining the existence confidence and type confidence of the semantic objects fitted by the cluster.

[0121] This step compares the fitting results with historical data, updates historical data, checks the existence confidence of historical data (N\A confidence), and deletes historical data with too low confidence values ​​(by setting confidence thresholds); for example, after clustering, there are only historical data in the cluster, and the N\A confidence of the historical data will be reduced. After fitting, before differential update, check all historical data and delete historical data with N\A confidence less than 0. For mixed clusters, when updating, increase the existence confidence of the fitted semantic objects and update their type confidence. For newly added clusters, update directly and add the semantic objects fitted by the newly added clusters to the map data.

[0122] Step S417: Combine the unclustered second semantic objects into a new segment data for storage. This step can refer to the above step S14 and will not be described in detail here. It should be noted that the updated semantic objects also need to be stored, which is not specifically described in this embodiment.

[0123] The above-mentioned detailed map data updating method provided in the embodiment of the present invention has the following beneficial effects: first, it solves the problem that there is little local perception data in historical data, which cannot be clustered and fitted into semantic objects and produce high-precision maps; second, it solves the problem that there is little local perception data in new data, which cannot be updated separately and produce high-precision maps; third, it solves the problem that the high-precision map changes are large and the mapping results are unstable due to the differences in perception data in multiple trips of data; fourth, the updating method solves the technical problems of uncertain data collection range, uncertain data collection quantity, and unstable data collection quality of multi-source crowdsourcing data, and uses historical data to standardize and constrain the high-precision map finally generated; fifth, compared with the high-precision map produced once, its data range is more complete and has a high fault tolerance, and it can reflect the changes in single data, as well as the real road surface changes from the cumulative changes.

[0124] Based on the same inventive concept, an embodiment of the present invention further provides a map data updating device, referring to Fig. 9 As shown, the device may include: a clustering module 91, a fitting module 92 and an updating module 93, and its working principle is as follows:

[0125] The clustering module 91 is used to cluster the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters formed by clusters containing the first semantic object and / or the second semantic object;

[0126] The fitting module 92 is used to fit the clusters formed by clustering;

[0127] The updating module 93 is used to fit the clusters formed by clustering, so as to update the semantic objects in the map data by judging the existence confidence and type confidence of the semantic objects fitted by the clusters.

[0128] In an alternative embodiment, referring to Fig. 9 As shown, the device may also include: a division module 93, a division module 94 used to: determine the source of the semantic objects in the clusters formed by clustering to divide the clusters; if the semantic object contains the first semantic object and the second semantic object, then the cluster is treated as a mixed cluster; if the semantic object is the second semantic object, then the cluster is treated as a newly added cluster; if the semantic object is the first semantic object, then the cluster is treated as a historical cluster.

[0129] In another optional embodiment, the fitting module 92 is specifically used to: increase the existence confidence of the semantic object fitted by the mixed cluster based on the number of newly added segment data in the group corresponding to the mixed cluster; and

[0130] Based on the type confidence of the first semantic object in the mixed cluster and the type confidence of the second semantic object, the type confidence of the semantic object after the mixed cluster is fitted is determined.

[0131] In another optional embodiment, the fitting module 92 is further configured to: sort the second semantic objects in the mixed cluster based on the acquisition time of the new data;

[0132] A weighted accumulation is performed based on the type confidence of the first semantic object and the sorted type confidence of the second semantic object to determine the type confidence of the fitted semantic object based on the type confidence result obtained by the weighted accumulation and the type confidence of the second semantic object.

[0133] In another optional embodiment, the fitting module 92 is further configured to:

[0134] sorting the second semantic objects in the newly added cluster based on the collection time of the new data corresponding to the newly added cluster;

[0135] Performing weighted accumulation based on the type confidences of the sorted semantic objects to determine the type confidence of the semantic object after the newly added cluster is fitted;

[0136] And, setting an initial value of the existence confidence of the semantic object after the newly added cluster is fitted.

[0137] In another optional embodiment, the fitting module 92 is further specifically configured to reduce the existence confidence of the semantic object fitted by the historical cluster based on the number of newly added segment data in the group corresponding to the historical cluster.

[0138] In another alternative embodiment, referring to Fig. 9 As shown, the device may further include: a storage module 95, which is used to combine the unclustered second semantic objects into a new segment data for storage. It should be noted that the semantic objects updated by the update module 93 also need to be stored, which is not specifically described in this embodiment.

[0139] In another alternative embodiment, referring to Fig. 9 As shown, the device may further include: an acquisition module 96, a calibration module 97, a segmentation module 98 and a determination module 99, and its working principle is as follows:

[0140] The acquisition module 96 is used to acquire new data, wherein the new data includes at least one newly added single trip data;

[0141] The calibration module 97 is used to calibrate the position relationship of the semantic objects in the newly added single trip data based on the association relationship between the lanes and the semantic objects in the newly added single trip data;

[0142] The segmentation module 98 is used to segment the calibrated newly added single trip data based on the position of the preset mark in the newly added single trip data to obtain a plurality of segment data after the newly added single trip data is segmented; wherein each segment data includes boundary information, vehicle lanes and semantic objects;

[0143] Correspondingly, the determination module 99 determines the correspondence between each segment data in the newly added single-pass data and the group data composed of the segment data at the same position after the multi-pass data in the historical data are segmented, and the clustering module 91 clusters the second semantic object in each segment data in the newly added single-pass data with the first semantic object in the group data in the historical data corresponding to the segment data.

[0144] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for updating map data is implemented.

[0145] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for updating map data when executing the program.

[0146] The principles of the problems solved by the above-mentioned devices, media, and related equipment in the embodiments of the present invention are similar to those of the above-mentioned methods, so their implementation can refer to the implementation of the above-mentioned methods, and the repeated parts will not be repeated.

[0147] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0148] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for updating map data, characterized in that: include: Clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters including the first semantic object and / or the second semantic object; The clusters formed by clustering are fitted, so as to update the semantic objects in the map data by determining the existence confidence and type confidence of the semantic objects fitted by the clusters.

2. The method according to claim 1, characterized in that: After the cluster is formed by clustering, the method further includes: determining the source of the semantic objects in the cluster formed by clustering to divide the cluster; if the semantic objects include the first semantic object and the second semantic object, treating the cluster as a mixed cluster; If the semantic object is the second semantic object, taking the cluster as a newly added cluster; If the semantic object is the first semantic object, the cluster is taken as a historical cluster.

3. The method according to claim 2, characterized in that Fitting the mixed cluster includes: Based on the number of newly added segment data in the group corresponding to the mixed cluster, increase the existence confidence of the semantic object fitted by the mixed cluster; and Based on the type confidence of the first semantic object in the mixed cluster and the type confidence of the second semantic object, the type confidence of the semantic object after the mixed cluster is fitted is determined.

4. The method according to claim 3, characterized in that: The determining, based on the type confidence of the first semantic object in the mixed cluster and the type confidence of the second semantic object, the type confidence of the semantic object after the mixed cluster is fitted includes: sorting the second semantic objects in the mixed cluster based on the acquisition time of the new data; A weighted accumulation is performed based on the type confidence of the first semantic object and the sorted type confidence of the second semantic object to determine the type confidence of the fitted semantic object based on the type confidence result obtained by the weighted accumulation and the type confidence of the second semantic object.

5. The method according to claim 2, characterized in that: Fitting the newly added clusters includes: sorting the second semantic objects in the newly added cluster based on the collection time of the new data corresponding to the newly added cluster; Performing weighted accumulation based on the type confidences of the sorted semantic objects to determine the type confidence of the semantic object after the newly added cluster is fitted; And, setting an initial value of the existence confidence of the semantic object after the newly added cluster is fitted.

6. The method according to claim 2, characterized in that Fitting the historical cluster includes: reducing the existence confidence of the semantic object fitted by the historical cluster based on the number of newly added segment data in the group corresponding to the historical cluster.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: The second semantic objects that are not successfully clustered are combined into a new segment data for storage.

8. The method according to any one of claims 1 to 6, characterized in that: Before clustering the first semantic object in the historical data and the second semantic object in the new data, the method further includes: Acquire new data, wherein the new data includes at least one newly added single trip data; Based on the association relationship between the lane and the semantic object in the newly added single trip data, calibrating the position relationship of the semantic object in the newly added single trip data; Segmenting the calibrated newly added single trip data based on the position of the preset mark in the newly added single trip data to obtain a plurality of segment data after the newly added single trip data is segmented; wherein each segment data includes boundary information, vehicle lanes and semantic objects; Determine the correspondence between each segment data in the newly added single-pass data and the group data composed of the segment data at the same position after the multi-pass data in the historical data are segmented, so as to cluster the second semantic object in each segment data in the newly added single-pass data with the first semantic object in the group data in the historical data corresponding to the segment data.

9. A map data updating device, characterized in that: include: A clustering module, used for clustering the first semantic object in the historical data and the second semantic object in the new data to obtain a plurality of clusters formed by clusters containing the first semantic object and / or the second semantic object; The fitting module is used to fit the clusters formed by clustering; The updating module is used to update the semantic objects in the map data by determining the existence confidence and type confidence of the semantic objects fitted by the cluster.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the map data updating method according to any one of claims 1 to 8 is realized.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the map data updating method according to any one of claims 1 to 8 is implemented.

Images