Lamp panel positioning method and device, storage medium and program product

Abstract

The invention provides a lamp panel positioning method and device, a storage medium and a program product. Relates to the technical field of intelligent traffic. The method comprises the steps that lamp panels in multiple single-trip maps can be clustered, clustering centers are determined, a lamp panel set of each clustering center in a target single-trip map is acquired, and the target single-trip map is selected from the multiple single-trip maps based on the number of the lamp panels. Furthermore, according to the first center coordinate of the clustering center and the coordinate of each lamp panel in the lamp panel set, the target coordinate of each lamp panel in the lamp panel set can be determined. In the process, the target single-trip map with representativeness and stability can be selected from the multiple single-trip maps based on the number of the lamp panels, and the target coordinate of each lamp panel in the lamp panel set is accurately calculated according to the clustering center and the lamp panel set determined from the target single-trip map, so that the accuracy of lamp panel positioning is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method, device, storage medium and program product for locating a light panel. Background Art

[0002] In the development of intelligent driving, generating highly complete and fresh maps required for intelligent driving has become a key factor affecting the safety and efficiency of intelligent driving. Among them, the light panels of the traffic light group are a vital part of the map, and their accurate positioning in the map is particularly important. This accurate positioning can provide crucial prior information for autonomous driving vehicles, enabling vehicles to better understand and predict changes in traffic signals, thereby significantly improving the safety and reliability of intelligent driving.

[0003] In the prior art, a map is usually constructed based on the road data collected by vehicles, and cluster analysis is performed on the light boards in the generated map. The location of the cluster center is selected as the accurate location of the light board. However, the accuracy of the light board location obtained in this way is low. Summary of the invention

[0004] The present application provides a method, device, storage medium and program product for locating a light panel, which are used to improve the accuracy of the obtained light panel position.

[0005] In a first aspect, the present application provides a method for positioning a light panel, comprising:

[0006] Clustering the light boards in multiple single-trip maps to determine at least one cluster center;

[0007] For each cluster center, obtain a set of light boards of the cluster center in a target single-trip map, where the target single-trip map is selected from the multiple single-trip maps based on the number of light boards, where the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map;

[0008] According to the first center coordinates of the cluster center and the coordinates of each light board in the light board set, the target coordinates of each light board in the light board set are determined.

[0009] In a possible implementation manner, obtaining the light board set of the cluster center in the target single-trip map includes:

[0010] Determining the number of light panels within a preset range of the cluster center in each single-trip map;

[0011] Determine at least one single trip map to be selected from the plurality of single trip maps according to a reference number of light panels within a preset range of the cluster center in each single trip map;

[0012] Selecting a target single-trip map from the at least one single-trip map to be selected;

[0013] From the target single-trip map, light boards within a preset range of the cluster center are obtained to obtain a light board set.

[0014] In a possible implementation, clustering the light panels in the plurality of single-trip maps to determine at least one cluster center includes:

[0015] Clustering the light boards in the plurality of single-trip maps according to a preset clustering condition to determine the at least one cluster center;

[0016] The clustering condition is determined based on the projection overlap area and / or position relationship of the light panels that can be clustered in the same cluster in different trip maps in the driving direction.

[0017] In a possible implementation, the clustering condition includes at least one of the following conditions:

[0018] The projected overlapping area between the light panels in the driving direction is larger than the preset projected overlapping area;

[0019] The distance between the light panels in the driving direction is less than a first preset distance;

[0020] The distance between the light panels in the height direction is less than the second preset distance;

[0021] The distance between the light panels parallel to the ground and perpendicular to the driving direction is less than a third preset distance.

[0022] In a possible implementation, determining the target coordinates of each light board in the light board set according to the first center coordinates of the cluster center and the coordinates of each light board in the light board set includes:

[0023] Obtaining the second center coordinates of the common center of all light boards in the light board set;

[0024] Determining a coordinate correction value according to the first center coordinate and the second center coordinate;

[0025] According to the coordinate correction value, the coordinates of each light board in the light board set are corrected to obtain the target coordinates of each light board.

[0026] In a possible implementation manner, determining the coordinate correction value according to the first center coordinate and the second center coordinate includes:

[0027] The coordinate deviation between the first center coordinate and the second center coordinate is determined as the coordinate correction value.

[0028] In a possible implementation manner, selecting a target single-trip map from the at least one single-trip map to be selected includes:

[0029] Randomly selecting a single-trip map to be selected from the at least one single-trip map to be selected as the target single-trip map;

[0030] or,

[0031] The target single-trip map is selected from the at least one single-trip map to be selected according to the collection time of each single-trip map to be selected.

[0032] In a second aspect, the present application provides a device for positioning a light panel, comprising:

[0033] A first processing module is used to cluster the light boards in multiple single-trip maps and determine at least one cluster center;

[0034] An acquisition module, for acquiring, for each cluster center, a set of light boards of the cluster center in a target single-trip map, wherein the target single-trip map is selected from the multiple single-trip maps based on the number of light boards, where the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map;

[0035] The second processing module is used to determine the target coordinates of each light board in the light board set according to the first center coordinates of the cluster center and the coordinates of each light board in the light board set.

[0036] In a third aspect, the present application provides an electronic device, including: a memory, a processor;

[0037] The memory stores computer-executable instructions;

[0038] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method for positioning the light panel as described in any one of the first aspects.

[0039] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method for positioning a light panel as described in any one of the first aspects.

[0040] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for positioning a light panel as described in any one of the first aspects.

[0041] The present application provides a method, device, storage medium and program product for locating light boards, including clustering light boards in multiple single-trip maps, and after determining the cluster center, further determining the light board set of each cluster center in the target single-trip map, wherein the target single-trip map is selected from multiple single-trip maps based on the number of light boards, and the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map. Furthermore, for each cluster center, the target coordinates of each light board in the light board set can be determined based on the first center coordinate of the cluster center and the coordinates of each light board in the light board set. In the above process, since the target single-trip map can be selected from multiple single-trip maps based on the number of light boards, and the target coordinates of each light board in the light board set can be accurately calculated based on the cluster center and the light board set determined from the target single-trip map, the accuracy of light board positioning is comprehensively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] Figure 1 A schematic diagram of the application scenario provided for this application;

[0044] Figure 2 A schematic diagram of a flow chart of a first embodiment of a method for positioning a light panel provided in the present application;

[0045] Figure 3 A schematic diagram of light board clustering provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of the structure of the light panel arrangement provided in the embodiment of the present application;

[0047] Figure 5 A schematic diagram of a flow chart of a second embodiment of a method for locating a light panel provided in the present application;

[0048] Figure 6 A schematic flow chart of an example of a method for locating a light panel provided in this application;

[0049] Figure 7 A schematic diagram of the structure of a device for positioning a light panel provided in an embodiment of the present application;

[0050] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0051] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0053] First, the terms involved in this application are explained:

[0054] Single-trip mapping: is a method of creating an environmental map using road data collected by an autonomous mobile device (such as a vehicle) during a single trip using Simultaneous Localization and Mapping (SLAM) technology.

[0055] Single-trip map: refers to an environmental map generated by processing road data collected by an autonomous mobile device during a single trip through single-trip mapping technology.

[0056] In related technologies, different data collected by multiple vehicles on the same road are usually mapped to generate multiple single-trip maps. Then, the light boards in these maps are clustered and the location of the cluster center is selected as the accurate location of the light board. However, in actual applications, multiple light boards in a light group may be close to each other, which makes it impossible to effectively distinguish adjacent light boards when directly clustering multiple single-trip maps. Therefore, relying solely on the cluster center to determine the location of the light board often reduces the accuracy of light board positioning.

[0057] In response to the above problems, the inventors propose that after obtaining the cluster center, the advantage of the high local accuracy of the single-trip map can be combined to improve the accuracy of light board positioning. Specifically, after obtaining the cluster center, for each cluster center, a set of light boards in the target single-trip map of the cluster center can be obtained. Among them, the target single-trip map is selected from multiple single-trip maps based on the number of light boards, and the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map. Then, the target coordinates of each light board in the light board set can be determined based on the first center coordinate of the cluster center and the coordinates of each light board in the light board set, thereby improving the accuracy of light board positioning. Based on this, the present application proposes a method for light board positioning to further improve the accuracy of light board positioning.

[0058] Figure 1 A schematic diagram of the application scenario provided for this application. Figure 1,The electronic device can perform cluster analysis on the light boards in multiple single trip maps, and select the cluster center as the accurate location of the light board in the map.

[0059] For example, there are two light boards on the actual road A, namely light board A and light board B. The single-trip map of road A generated Figure 1 The light board 1 and the light board 2 can be included in the generated single trip map of road A. Figure 2 The light board 3 and the light board 4 may be included to generate a single trip of the road A. Figure 3 The light board 5 and the light board 6 may be included.

[0060] The method provided in the embodiment of the present application can be used to perform cluster analysis on the six light boards in the three single-trip maps. It is assumed here that cluster center 1 and cluster center 2 are obtained, wherein cluster center 1 can be the center after light board 1, light board 3, and light board 5 are clustered; cluster center 2 can be the center after light board 2, light board 4, and light board 6 are clustered. In this case, cluster center 1 can be selected as the exact position of light board A of road A in the map, and cluster center 2 can be selected as the exact position of light board B of road A in the map.

[0061] In the embodiments of the present application, the electronic device may be any one of a terminal device, an independent computer device, an independent server, a server cluster, an Internet of Vehicles device, etc. Technical personnel in this field may set it according to actual needs. The following article uses an independent server as an example of an electronic device for explanation.

[0062] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] Figure 2 This is a flow chart of the first embodiment of the method for locating a light panel provided in this application. Figure 2 , the method may include:

[0064] S201. Cluster the light boards in multiple single-trip maps to determine at least one cluster center.

[0065] The execution subject of the embodiment of the present application may be a server, or a device for positioning a light panel in the server. The device for positioning the light panel may be implemented by software, or by a combination of software and hardware. For ease of understanding, the following description will be made by taking the execution subject as a server as an example.

[0066] In this step, the server may obtain multiple single-trip maps, and cluster the light boards in the multiple single-trip maps to determine at least one cluster center.

[0067] The single-trip map in the embodiment of the present application can be a map obtained by mapping a trip of road data collected by the vehicle; wherein the road data may include but is not limited to speed and acceleration data collected by the vehicle's Inertial Measurement Unit (IMU), positioning data generated by the Global Positioning System (GPS), point cloud data collected by a lidar or radar, and at least one of image data collected by a camera; technicians in this field can also set the specific data format of other road data according to actual needs.

[0068] For multiple single-trip maps, the server can build maps for multiple road data separately. For example, the server can build maps for the received road data 1 to obtain single-trip maps. Figure 1 , the received road data 2 can be mapped to obtain a single trip map Figure 2 ; The received road data 3 can be mapped to obtain a single trip map Figure 3 Among them, road data 1 may be road data about road A collected by vehicle A in one trip, road data 2 may be road data about road A collected by vehicle B in one trip, and road data 3 may be road data about road A collected by vehicle C in one trip.

[0069] Optionally, a single-trip map may include the coordinate information of each light panel. Figure 1 The coordinates of the upper left corner (A1, B1, C1), the upper right corner (D1, E1, F1), the lower left corner (G1, H1, I1), and the lower right corner (J1, K1, L1) of the light board 1 can be included. The coordinate system of the coordinates of each light board is the geographic coordinate system. By taking the average value of the coordinate values ​​of the four vertices in different dimensions, the center coordinates (O1, P1, Q1) of the light board 1 can be determined.

[0070] The cluster center can be determined by the vector data composed of the coordinates of the four vertices of the light board. For example, if cluster center 1 is at the same position as light board 1, cluster center 1 can be determined by the vector data composed of the coordinates of the four vertices of light board 1. The vector data can be [A1, B1, C1, D1, E1, F1, G1, H1, I1, J1, K1, L1].

[0071] Figure 3 This is a schematic diagram of the light board clustering provided in the embodiment of this application. Figure 3For ease of understanding, only the clustering of the light panels of the same light group in the three single-trip maps is shown. Figure 1 The light board 1, light board 2 and light board 3 are included in the single trip. Figure 2 The light board 4, light board 5, and light board 6 are included in the single trip. Figure 3 The light board 7, light board 8, and light board 9 are included. After clustering the 9 light boards in the 3 single-trip maps, 3 cluster centers can be determined, namely cluster center 1, cluster center 2, and cluster center 3.

[0072] S202: For each cluster center, obtain a set of light boards of the cluster center in the target single-trip map.

[0073] In this step, for each cluster center obtained by clustering, the set of light boards of the cluster center in the target single-trip map can be obtained. The target single-trip map is selected from multiple single-trip maps based on the number of light boards, and the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map.

[0074] For ease of understanding, combined Figure 4 The arrangement of the light panels in a light group on an actual road is schematically illustrated.

[0075] Figure 4 This is a schematic diagram of the structure of the light board arrangement provided in the embodiment of the present application. Figure 4 In the actual road where the vehicle is traveling, a light pole can be installed on the right side of lane 2, and the light group arranged in the light pole can include light board 1, light board 2 and light board 3. Among them, light board 1 can be used to control the vehicle that is about to turn left in lane 1, light board 2 can be used in conjunction with light board 1 to display the waiting time of the vehicle that is about to turn left in lane 1, and light board 3 is used to control the vehicle that is traveling in lane 2 to keep going straight.

[0076] Optionally, the light board set refers to all light boards located within a preset range of the cluster center in the target single-trip map.

[0077] Optionally, the target single-trip map is selected from multiple single-trip maps based on the number of light boards, which can be determined based on a reference number of light boards within a preset range of the cluster center in each single-trip map. The reference number can be a mode, a median, or an integer with the smallest difference from the mean.

[0078] Specifically, for the mode, it refers to the number with the highest frequency; for the median, it refers to the number in the middle after the number of light panels is sorted. If the size of the data set consisting of the number of light panels is an odd number, the median is the number in the middle of the sorted data set; if it is an even number, the median is the average of the two numbers in the middle of the sorted data set; for the integer with the smallest difference from the mean, it refers to finding an integer in the data set consisting of the number of light panels so that the difference between the integer and the mean is the smallest. For ease of understanding, the reference number is taken as the mode as an example for explanation.

[0079] For example, within the preset range of cluster center 1, the number of light boards in a single trip map can be as shown in Table 1:

[0080] Table 1

[0081]

[0082] For cluster center 1, the light board set of cluster center 1 in the target single-trip map can be obtained. Figure 1 , Single trip Figure 2 , and single trip Figure 3 , further, from a single trip Figure 1 , Single trip Figure 2 , and single trip Figure 3 Select the target single-trip map. Figure 1 , Single trip Figure 2 , and single trip Figure 3 In the random selection, a single trip Figure 2 , as the target single-trip map.

[0083] Furthermore, for cluster center 1, we can obtain the cluster center 1 in a single trip. Figure 2 The light board set includes light board 4, light board 5, and light board 6.

[0084] S203: Determine the target coordinates of each light board in the light board set according to the first center coordinates of the cluster center and the coordinates of each light board in the light board set.

[0085] In this step, the target coordinates of each light board in the light board set can be determined based on the first center coordinates of the cluster center and the coordinates of each light board in the light board set. In a specific implementation, the second center coordinates of the common center of all light boards in the light board set can be obtained, and the coordinate correction value can be determined based on the first center coordinates and the second center coordinates. Based on the coordinate correction value, the coordinates of each light board in the light board set are corrected to obtain the target coordinates of each light board.

[0086] The first center coordinate refers to the center coordinate of the light board represented by the cluster center; the second center coordinate refers to the common center coordinate of all light boards in the light board set.

[0087] The first center coordinate may be determined by the average value of the coordinate values ​​of the four vertices of the cluster center in different dimensions.

[0088] For example, through the four vertex coordinates of cluster center 1, the first center coordinates determined may be as shown in Table 2:

[0089] Table 2

[0090]

[0091] Among them, the coordinates of the upper left corner vertex of cluster center 1 are (A, B, C); the coordinates of the upper right corner vertex are (D, E, F); the coordinates of the upper right corner vertex are (G, H, I); the coordinates of the lower right corner vertex are (J, K, L); the first center coordinates (O1, P1, Q1) can be determined by calculating the average value of each dimension.

[0092] The second center coordinate may be determined by the average value of the coordinate values ​​of the four vertices of all the light boards in the light board set in different dimensions.

[0093] For example, the light board set includes light board 4, light board 5, and light board 6, and the determined second center coordinates may be as shown in Table 3:

[0094] Table 3

[0095]

[0096] The second center coordinates (O2, P2, Q2) can be determined by calculating the average value of each dimension.

[0097] For example, the second center coordinates of the common center of light board 4, light board 5, and light board 6 in the light board set can be obtained, and the coordinate correction value can be determined based on the first center coordinates and the second center coordinates of cluster center 1. Based on the coordinate correction value, the four vertex coordinates of light board 4, light board 5, and light board 6 in the light board set are corrected to obtain the target coordinates of light board 4, light board 5, and light board 6.

[0098] In an embodiment of the present application, the server can cluster the light boards in multiple single-trip maps to determine at least one cluster center, and for each cluster center, obtain its light board set in the target single-trip map. According to the first center coordinate of the cluster center and the coordinates of each light board in the light board set, the target coordinates of each light board in the light board set are determined. In the above process, the target single-trip map can be selected from multiple single-trip maps based on the number of light boards to obtain a more representative and stable result, thereby improving the accuracy of light board positioning.

[0099] Furthermore, the method for locating light boards provided in the present embodiment can, after determining the light board set by the number of light boards, utilize the high local accuracy of single-pass mapping, combined with the first center coordinates of the cluster center, to correct the coordinates of each light board in the light board set to determine its target coordinates, thereby improving the accuracy of light board positioning.

[0100] exist Figure 2 Based on the embodiment shown below, combined with Figure 5 , the method of positioning the above-mentioned light panel is further described in detail.

[0101] Figure 5 This is a flow chart of the second embodiment of the method for locating a light panel provided in this application. Figure 5 , the method may include:

[0102] S501. Cluster the light boards in a plurality of single-trip maps according to a preset clustering condition, and determine at least one cluster center.

[0103] In this step, the server can obtain multiple single-trip maps, cluster the light panels in the multiple single-trip maps according to preset clustering conditions, and determine at least one cluster center. The clustering conditions are determined according to the overlapping projection areas and / or positional relationships of the light panels that can be clustered in the same cluster in different trip maps in the driving direction.

[0104] In a specific embodiment, the clustering conditions include at least one of the following conditions: the projected overlapping area between the light boards in the driving direction is greater than a preset projected overlapping area; the distance between the light boards in the driving direction is less than a first preset distance; the distance between the light boards in the height direction is less than a second preset distance; the distance between the light boards parallel to the ground and perpendicular to the driving direction is less than a third preset distance.

[0105] Optionally, the projection overlap area can be calculated based on the projection of the geometric shape determined by the four vertex coordinates of the light board in the direction of travel. Specifically, the geometric shape of the light board can be determined based on the four vertex coordinates of the light board, the projection of each light board in the direction of travel can be determined, the projection areas of the light boards can be compared, and the area of ​​the overlapping part can be calculated.

[0106] Since the accuracy of a single-trip map in the direction of travel is lower than that in the lateral direction parallel to the ground and perpendicular to the direction of travel, and the accuracy in the height direction is also relatively low, the first preset distance, the second preset threshold, and the third preset threshold in different dimensions can be set with different thresholds based on historical experience.

[0107] For example, if the preset projection overlap area is X1, the first preset distance is X2, the second preset distance is X3, and the third preset distance is X4. Figure 3 As shown, the light boards 1, 4 and 7 can be clustered to obtain the cluster center 1 based on the fact that the projected overlapping area Y1 between the light board 1 and the light board 4, and between the light board 4 and the light board 7 in the driving direction is greater than the preset projected overlapping area X1, the distance Y2 in the driving direction is less than the first preset distance X2, and the distance Y3 in the height direction is less than the second preset distance X3; and the distance Y4 parallel to the ground and perpendicular to the driving direction is less than the third preset distance X4.

[0108] S502: For each cluster center, determine the number of light panels within a preset range of the cluster center in each single-trip map.

[0109] In this step, after at least one cluster center is determined, for each cluster center, the number of light panels within a preset range of the cluster center in each single-trip map can be determined.

[0110] In an optional embodiment, the preset range includes a preset distance in the driving direction, a preset distance in the height direction, and a preset distance parallel to the ground and perpendicular to the driving direction. The preset distance in the driving direction can be set according to the minimum distance that needs to be maintained between two traffic light boards along the driving direction of the road, the preset distance in the height direction can be preset according to the minimum installation height of the light board, and the preset distance parallel to the ground and perpendicular to the driving direction can be preset according to the minimum width of the lane.

[0111] For example, if the minimum distance between two traffic light boards along the driving direction of the road is 10m, the preset distance in the driving direction can be 5m; if the minimum installation height of the light board is 4m, the preset distance in the height direction can be 2m; if the minimum width of the lane is 3m, the preset distance parallel to the ground and perpendicular to the driving direction can be 1.5m.

[0112] For example, after cluster center 1 is determined, the number of light boards within a preset range of cluster center 1 in each single-trip map may be determined, and the specific number may be as shown in Table 1.

[0113] It should be noted that for each cluster center, when determining the number of light boards within the preset range of the cluster center in each single-trip map, the selection can be made by any one of the four vertex coordinates of the cluster center and the first center coordinate of the cluster center. For example, the selection can be made by the upper left corner vertex coordinate of cluster center 1. If there is another light board whose upper left corner coordinate falls within the preset range, then the light board is considered to be within the preset range of cluster center 1.

[0114] S503: Determine at least one single trip map to be selected from a plurality of single trip maps according to a reference number of light panels within a preset range of a cluster center in each single trip map.

[0115] In this step, after searching the number of light boards within the preset range of the cluster center in each single-trip map according to the preset range, at least one single-trip map to be selected can be determined from the multiple single-trip maps according to the reference number of light boards within the preset range of the cluster center. The reference number can be the mode, the median, or the integer with the smallest difference from the mean.

[0116] For example, for cluster center 1, as shown in Table 1, if the reference quantity is the majority, then after searching a single trip according to the preset range, Figure 1 , Single trip Figure 2 , Single trip Figure 3 , Single trip Figure 4 , and single trip Figure 5 Then, according to the mode 3 of the number of light panels within the preset range of the cluster center 1, 3 single-trip maps to be selected can be determined from the 5 single-trip maps, which are single-trip maps Figure 1 , Single trip Figure 2 , and single trip Figure 3 .

[0117] For another example, for cluster center 1, as shown in Table 1, if the reference quantity is the median, then after searching a single trip according to the preset range, Figure 1 , Single trip Figure 2 , Single trip Figure 3 , Single trip Figure 4 , and single trip Figure 5 Then, the single trip map can be determined from the five single trip maps according to the median 3 of the number of light panels within the preset range of the cluster center 1. Figure 2 As the single-trip map to be selected. Among them, the order of the 5 single-trip maps after sorting according to the number of light panels can be: single-trip map Figure 4 , Single trip Figure 1 , Single trip Figure 2 , Single trip Figure 3 , Single trip Figure 5 .

[0118] For another example, for cluster center 1, as shown in Table 1, if the reference number is an integer with the smallest difference from the average, then three single-trip maps to be selected can be determined from the five single-trip maps, namely, single-trip maps Figure 1 , Single trip Figure 2 , and single trip Figure 3 .

[0119] S504: Select a target single-trip map from at least one single-trip map to be selected.

[0120] In this step, a single-trip map to be selected can be randomly selected from at least one single-trip map to be selected as the target single-trip map; or, the target single-trip map can be selected from at least one single-trip map to be selected based on the collection time of each single-trip map to be selected.

[0121] In an optional implementation, a single-trip map obtained by mapping the road data with the latest collection time may be selected from at least one single-trip map to be selected as the target single-trip map.

[0122] For example, a single trip Figure 2 If the collection time of the corresponding road data is the latest, you can select a single trip. Figure 2 As a single-trip map.

[0123] S505: Obtain the light boards within a preset range of the cluster center from the target single-trip map to obtain a light board set.

[0124] For example, you can Figure 2 In the process, light boards within a preset range of cluster center 1 are obtained to obtain a light board set, which includes light board 4, light board 5, and light board 6.

[0125] S506: Obtain the second center coordinates of the common center of all the light boards in the light board set.

[0126] In this step, after the light board set is determined, the second center coordinates of the common center of all the light boards in the light board set can be determined according to the four vertex coordinates of each light board in the light board set.

[0127] S507: Determine a coordinate correction value according to the first center coordinate and the second center coordinate.

[0128] In this step, the coordinate correction value can be determined according to the first center coordinate and the second center coordinate. In a specific implementation, the coordinate deviation between the first center coordinate and the second center coordinate can be determined as the coordinate correction value.

[0129] S508. Correct the coordinates of each light board in the light board set according to the coordinate correction value to obtain the target coordinates of each light board.

[0130] In this step, after the coordinate correction is calculated, the vertex coordinates of each light board in the light board set can be corrected according to the coordinate correction value to obtain the target coordinates of each light board. The target coordinates of each light board may include the four vertex coordinates after the four vertex coordinates are corrected.

[0131] In an optional implementation, a coordinate correction value may be added to each vertex coordinate of each light board in the light board set to obtain the target vertex coordinate of each light board.

[0132] In an embodiment of the present application, the server can cluster the light boards in multiple single-trip maps according to preset clustering conditions, determine at least one cluster center, and calculate the number of light boards within the preset range of the cluster center in each single-trip map. By selecting a reference number in the number of light boards, the single-trip map to be selected is determined, and the target single-trip map is selected therefrom. Then, a set of light boards within the range of the cluster center is obtained from the target single-trip map, and the second center coordinates of their common center are calculated. Based on the first and second center coordinates, a coordinate correction value is calculated and applied to each light board in the light board set to obtain its target coordinates. In the above process, by selecting the reference number in the number of light boards as a standard, it can be ensured that the selected target single-trip map is more representative, thereby improving the accuracy of light board positioning. In addition, by calculating the correction value between the first and second center coordinates, the error in the light board coordinates in the single-trip map can be effectively corrected, further improving the positioning accuracy.

[0133] Figure 6 This is a flow chart of an example of a method for locating a light panel provided in this application. Figure 6 , the method may include:

[0134] S601. Obtain multiple single-trip maps.

[0135] Optionally, different vehicles can transmit collected road data about the target road back to the server. After receiving the road data about the target road transmitted back by different vehicles, the server can perform single-trip mapping for each road data to obtain a single-trip map.

[0136] For example, the server can obtain a single trip map of target road A. Figure 1 , Single trip Figure 2 , ..., and a single trip map N. The N single trip maps may be obtained by the server mapping the road data about the target road A collected by different vehicles.

[0137] S602: Calculate the coordinates of the center point of each light board in each single-trip map, cluster the light boards in multiple single-trip maps according to preset clustering conditions, and determine at least one cluster center.

[0138] For example, the coordinates of the center points of each light board in each single-trip map can be calculated, and the light boards in N single-trip maps are clustered to determine M cluster centers (M≥1) based on the following conditions: the projection overlap area between the light boards in the driving direction is greater than the preset projection overlap area; the distance between the light boards in the driving direction is less than the first preset distance; the distance between the light boards in the height direction is less than the second preset distance; the distance between the light boards parallel to the ground and perpendicular to the driving direction is less than the third preset distance.

[0139] S603: For any cluster center, determine the first center coordinate of the cluster center, and search for light boards adjacent to the cluster center in a single-pass mapping according to a preset range.

[0140] Optionally, for ease of understanding, a cluster center is selected to introduce the solution of this step.

[0141] For example, for cluster center A, the first center coordinate of cluster center A can be determined, and the light panels adjacent to cluster center A in a single-pass mapping are searched according to the preset distance of cluster center A in the driving direction, the preset distance in the height direction, and the preset distance parallel to the ground and perpendicular to the driving direction. Cluster center A is one of the M cluster centers.

[0142] Specifically, it can be determined by the average value of the coordinate values ​​of the four vertices of the cluster center A in different dimensions.

[0143] S604: For each cluster center, obtain a set of light boards of the cluster center in a target single-trip map, where the target single-trip map is selected from multiple single-trip maps based on the majority of the number of light boards.

[0144] Similarly, a cluster center is selected to introduce the solution of this example.

[0145] For example, the set of light boards of cluster center A in the target single-trip map may be obtained, and the target single-trip map is selected from N single-trip maps based on the majority of the number of light boards.

[0146] S605: Calculate the second center coordinates of the common centers of all the light boards in the light board set.

[0147] For example, the second center coordinates of the common centers of all the light boards in the light board set determined in step S604 may be calculated.

[0148] S606: Determine a coordinate correction value according to the first center coordinate and the second center coordinate.

[0149] For example, the coordinate correction value may be determined according to the first center coordinate of the cluster center A and the second center coordinate of the common center of all the light boards in the light board set.

[0150] S607: Correct the vertex coordinates of each light board in the light board set according to the coordinate correction value to obtain the target coordinates of each light board.

[0151] For example, if the light board set includes light board 4, light board 5, and light board 6, the coordinate correction values ​​can be added to the four vertex coordinates of light board 4, light board 5, and light board 6 respectively to obtain the four target vertex coordinates of light board 4, light board 5, and light board 6.

[0152] Furthermore, the exact positions of the three light boards in the map can be determined based on the vector data composed of the coordinates of the four target vertices of light board 4, light board 5, and light board 6.

[0153] The method example of light panel positioning provided in the present application, the implementation process of which can refer to the process shown in the above method embodiment, the implementation principle and beneficial effects are similar, and will not be repeated here.

[0154] Figure 7 This is a schematic diagram of the structure of the device for positioning the light panel provided in the embodiment of the present application. Figure 7 , the light panel positioning device 10 comprises:

[0155] The first processing module 11 is used to cluster the light boards in multiple single-trip maps and determine at least one cluster center;

[0156] An acquisition module 12 is used to acquire, for each cluster center, a set of light boards of the cluster center in a target single-trip map, wherein the target single-trip map is selected from the multiple single-trip maps based on the number of light boards, and the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map;

[0157] The second processing module 13 is used to determine the target coordinates of each light board in the light board set according to the first center coordinates of the cluster center and the coordinates of each light board in the light board set.

[0158] The device for positioning the light panel provided in the embodiment of the present application can implement the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0159] In a possible implementation manner, the acquisition module 12 is specifically configured to:

[0160] Determining the number of light panels within a preset range of the cluster center in each single-trip map;

[0161] Determine at least one single trip map to be selected from the plurality of single trip maps according to a reference number of light panels within a preset range of the cluster center in each single trip map;

[0162] Selecting a target single-trip map from the at least one single-trip map to be selected;

[0163] From the target single-trip map, light boards within a preset range of the cluster center are obtained to obtain a light board set.

[0164] In a possible implementation manner, the first processing module 11 is specifically configured to:

[0165] Clustering the light boards in the plurality of single-trip maps according to a preset clustering condition to determine the at least one cluster center;

[0166] The clustering condition is determined based on the projection overlap area and / or position relationship of the light panels that can be clustered in the same cluster in different trip maps in the driving direction.

[0167] In a possible implementation, the clustering condition includes at least one of the following conditions:

[0168] The projected overlapping area between the light panels in the driving direction is larger than the preset projected overlapping area;

[0169] The distance between the light panels in the driving direction is less than a first preset distance;

[0170] The distance between the light panels in the height direction is less than the second preset distance;

[0171] The distance between the light panels parallel to the ground and perpendicular to the driving direction is less than a third preset distance.

[0172] In a possible implementation manner, the second processing module 13 is specifically configured to:

[0173] Obtaining the second center coordinates of the common center of all light boards in the light board set;

[0174] Determining a coordinate correction value according to the first center coordinate and the second center coordinate;

[0175] According to the coordinate correction value, the coordinates of each light board in the light board set are corrected to obtain the target coordinates of each light board.

[0176] In a possible implementation manner, the second processing module 13 is specifically configured to:

[0177] The coordinate deviation between the first center coordinate and the second center coordinate is determined as the coordinate correction value.

[0178] In a possible implementation manner, the acquisition module 12 is specifically configured to:

[0179] Randomly selecting a single-trip map to be selected from the at least one single-trip map to be selected as the target single-trip map;

[0180] or,

[0181] The target single-trip map is selected from the at least one single-trip map to be selected according to the collection time of each single-trip map to be selected.

[0182] The device for positioning the light panel provided in the embodiment of the present application can implement the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0183] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 The electronic device 20 includes: at least one processor 21 and a memory 22. Optionally, the electronic device 20 also includes a communication component 23. The processor 21, the memory 22 and the communication component 23 are connected via a bus 24.

[0184] In a specific implementation process, at least one processor 21 executes the computer-executable instructions stored in the memory 22, so that at least one processor 21 executes the above-mentioned method for positioning the light panel.

[0185] The specific implementation process of the processor 21 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0186] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0187] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0188] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0189] The present application also provides a computer program product, including a computer program, which implements the above-mentioned method for positioning the light panel when executed by a processor.

[0190] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above-mentioned method for positioning the light panel is implemented.

[0191] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0192] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0193] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0196] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0197] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0198] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for positioning a light panel, characterized in that: include: Clustering the light boards in multiple single-trip maps to determine at least one cluster center; For each cluster center, obtain a set of light boards of the cluster center in a target single-trip map, where the target single-trip map is selected from the multiple single-trip maps based on the number of light boards, where the number of light boards is the number of light boards within a preset range of the cluster center in the single-trip map; According to the first center coordinates of the cluster center and the coordinates of each light board in the light board set, the target coordinates of each light board in the light board set are determined.

2. The method according to claim 1, characterized in that The step of obtaining a light board set of the cluster center in a target single-trip map includes: Determining the number of light panels within a preset range of the cluster center in each single-trip map; Determine at least one single trip map to be selected from the plurality of single trip maps according to a reference number of light panels within a preset range of the cluster center in each single trip map; Selecting a target single-trip map from the at least one single-trip map to be selected; From the target single-trip map, light boards within a preset range of the cluster center are obtained to obtain a light board set.

3. The method according to claim 1 or 2, characterized in that: The clustering of the light panels in the plurality of single-trip maps to determine at least one cluster center includes: Clustering the light boards in the plurality of single-trip maps according to a preset clustering condition to determine the at least one cluster center; The clustering condition is determined based on the projection overlap area and / or position relationship of the light panels that can be clustered in the same cluster in different trip maps in the driving direction.

4. The method according to claim 3, characterized in that The clustering condition includes at least one of the following conditions: The projected overlapping area between the light panels in the driving direction is larger than the preset projected overlapping area; The distance between the light panels in the driving direction is less than a first preset distance; The distance between the light panels in the height direction is less than the second preset distance; The distance between the light panels parallel to the ground and perpendicular to the driving direction is less than a third preset distance.

5. The method according to claim 1 or 2, characterized in that: The determining the target coordinates of each light board in the light board set according to the first center coordinates of the cluster center and the coordinates of each light board in the light board set includes: Obtaining the second center coordinates of the common center of all light boards in the light board set; Determining a coordinate correction value according to the first center coordinate and the second center coordinate; According to the coordinate correction value, the coordinates of each light board in the light board set are corrected to obtain the target coordinates of each light board.

6. The method according to claim 5, characterized in that The step of determining a coordinate correction value according to the first center coordinate and the second center coordinate includes: The coordinate deviation between the first center coordinate and the second center coordinate is determined as the coordinate correction value.

7. The method according to claim 2, characterized in that The step of selecting a target single-trip map from the at least one single-trip map to be selected includes: Randomly selecting a single-trip map to be selected from the at least one single-trip map to be selected as the target single-trip map; or, The target single-trip map is selected from the at least one single-trip map to be selected according to the collection time of each single-trip map to be selected.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method for positioning the light panel according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method for positioning a light panel as described in any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for positioning a light panel as claimed in any one of claims 1 to 7.

Images