A method, apparatus and electronic device for generating a road network

Abstract

The application provides a method, device and electronic equipment for generating a road network to avoid the problem of low route and road network precision caused by directly clustering due to long mapping trajectories in the prior art. The method comprises: obtaining at least two mapping trajectories, and orientation information and position information of trajectory points on the mapping trajectories; wherein the orientation information comprises an included angle between the orientation of the trajectory points on the mapping trajectories and a preset coordinate axis of a preset coordinate system, and the position information comprises the coordinates of the trajectory points in the preset coordinate system; dividing the mapping trajectories by a preset size of a grid unit to obtain grid trajectories; the grid unit comprises at least one first trajectory segment; based on the orientation information and the position information, in adjacent two grid units, clustering any two first trajectory segments with a similarity less than a similarity threshold value into a same trajectory segment to obtain a target route; and generating a road network based on the target route.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and electronic device for generating road networks. Background Technology

[0002] Road networks in electronic maps are generally obtained through trajectory clustering. This is especially true for high-precision maps, where trajectories obtained through surveying vehicles equipped with high-precision GPS (Global Positioning System) and / or cameras are clustered. The specific clustering method involves pairwise clustering across multiple trajectories: A point on one trajectory is fixed as a reference point, and each point on another trajectory is traversed sequentially, determining the distance between the reference point and each point on the other trajectory. After the first traversal, another point adjacent to the reference point on the same trajectory is used as the reference point, and the above traversal process is repeated to determine whether any two points belong to the same category, thus completing the trajectory clustering.

[0003] Because surveying vehicles travel continuously during the surveying process, the resulting trajectories are relatively long. Clustering such long trajectories often involves large thresholds, resulting in low accuracy. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for generating road networks, in order to avoid the problem of low route and road network accuracy caused by direct clustering due to long survey trajectories in the prior art.

[0005] In a first aspect, embodiments of this application provide a method for generating a road network, including:

[0006] Acquire at least two surveying trajectories, as well as the orientation and position information of the trajectory points on the surveying trajectories; wherein, the orientation information includes the angle between the orientation of the trajectory point on the surveying trajectories and the preset coordinate axis of the preset coordinate system, and the position information includes the coordinates of the trajectory point in the preset coordinate system;

[0007] The survey trajectory is divided into grid cells of a preset size to obtain a grid trajectory; wherein the grid cells on the grid trajectory are distributed along the survey trajectory, and the grid cells include at least one first trajectory segment;

[0008] Based on the orientation information and the location information, in two adjacent grid cells, any two first trajectory segments with a similarity less than the similarity threshold are clustered into the same trajectory segment to obtain the target route; then a road network is generated based on the target route.

[0009] The method for generating a road network provided in this application rasterizes the surveyed trajectory and clusters trajectory segments between adjacent grids. Essentially, it clusters trajectory segments with similar positions based on similarity, thus effectively improving the accuracy of the target route and road network. This allows for setting more precise similarity thresholds, further enhancing the accuracy of the target route and road network. Furthermore, since clustering only trajectory segments within adjacent grids avoids the inefficiency of determining the target route caused by using a single trajectory point on one surveyed trajectory to traverse all trajectory points on another surveyed trajectory in existing technologies.

[0010] In one possible implementation, the grid cell is rectangular in shape, and each of two adjacent grid cells has one side overlapping.

[0011] One possible implementation, based on the orientation information and the location information, involves clustering any two first trajectory segments with a similarity threshold into the same trajectory segment within two adjacent grid cells to obtain the target route, including:

[0012] In two adjacent grid cells, the first trajectory segment in either grid cell is marked as the target trajectory segment, and the start and end points of the target trajectory segment are determined.

[0013] Based on the similarity between a first key point in another grid cell and the starting point, in the other grid cell, the first trajectory segment whose similarity to the target trajectory segment is less than the similarity threshold is determined as the second trajectory segment, and the first trajectory segment in the other grid cell other than the second trajectory segment is determined as the third trajectory segment; wherein, the first key point is the trajectory point on the first trajectory segment in the other grid cell that is closest to the starting point, and the other grid cell is the grid cell other than the grid cell where the target trajectory segment is located in the two adjacent grid cells;

[0014] Cluster the second trajectory segment and the target trajectory segment into the same trajectory segment;

[0015] Based on the similarity between the second key point in the other grid cell and the endpoint, in the other grid cell, the third trajectory segment whose similarity with the target trajectory segment is less than the similarity threshold is determined as the fourth trajectory segment; wherein, the second key point is the trajectory point on the third trajectory segment in the other grid cell that is closest to the endpoint;

[0016] The fourth trajectory segment and the target trajectory segment are clustered into the same trajectory segment to obtain the target route.

[0017] In one possible implementation, the similarity threshold includes a distance threshold and an orientation threshold; then, based on the similarity between a first keypoint in another grid cell and the starting point, determining the first trajectory segment in the other grid cell whose similarity to the target trajectory segment is less than the similarity threshold as the second trajectory segment includes:

[0018] Based on the location information and orientation information of the starting point, on each of the first trajectory segments in the other grid cell, the first key point that is closest to the starting point is determined respectively;

[0019] Determine the first distance between the starting point and the first key point, and the difference in the included angle;

[0020] In response to the first distance being less than the distance threshold and the difference in the included angle being less than the orientation threshold, the first trajectory segment containing the first key point in the other grid cell is determined to be the second trajectory segment.

[0021] One possible implementation, in response to the first distance being less than the distance threshold and the difference in the included angle being less than the orientation threshold, determining the first trajectory segment containing the first key point in the other grid cell as the second trajectory segment includes:

[0022] In response to the fact that the spatial distance between the starting point and the first key point is less than a spatial distance threshold and the difference in the included angle is less than the orientation threshold, the height distance between the starting point and the first key point is determined; wherein, the spatial distance and the height distance constitute the distance;

[0023] In response to the height distance being less than the height distance threshold, it is determined that the first trajectory segment containing the first key point in the other grid cell and the target trajectory segment satisfy the similarity threshold.

[0024] One possible implementation, before clustering any two first trajectory segments with a similarity less than a similarity threshold in two adjacent grid cells based on the orientation information and the location information to obtain the target route, further includes:

[0025] Determine the number of the first trajectory segments within the grid cell;

[0026] In response to the number of the first trajectory segments being greater than 1, any two of the first trajectory segments with a similarity less than the similarity threshold are clustered within the grid cell to obtain the fifth trajectory segment;

[0027] The step of clustering any two first trajectory segments with a similarity less than a similarity threshold in two adjacent grid cells based on the orientation information and the location information to obtain the target route includes:

[0028] Based on the orientation information and the location information, in two adjacent grid cells, any two fifth trajectory segments with a similarity less than a similarity threshold are clustered to obtain the target route.

[0029] Secondly, embodiments of this application provide an apparatus for generating a road network, comprising:

[0030] Information unit: used to acquire at least two surveying trajectories, as well as orientation information and position information of trajectory points on the surveying trajectories; wherein, the orientation information includes the angle between the orientation of the trajectory point on the surveying trajectories and the preset coordinate axis of the preset coordinate system, and the position information includes the coordinates of the trajectory point in the preset coordinate system;

[0031] Grid unit: used to divide the survey trajectory into grid units of a preset size to obtain a grid trajectory; wherein, the grid units on the grid trajectory are distributed along the survey trajectory, and the grid unit includes at least one first trajectory segment;

[0032] Clustering unit: Based on the orientation information and the location information, it is used to cluster any two first trajectory segments with a similarity less than a similarity threshold into the same trajectory segment in two adjacent grid units to obtain the target route; then, a road network is generated based on the target route.

[0033] In one possible implementation, the grid cell is rectangular in shape, and each of two adjacent grid cells has one side overlapping.

[0034] In one possible implementation, the clustering unit is specifically used to mark the first trajectory segment in any of two adjacent grid cells as a target trajectory segment, and determine the start and end points of the target trajectory segment; based on the similarity between a first key point in another grid cell and the start point, in that other grid cell, determine the first trajectory segment whose similarity to the target trajectory segment is less than the similarity threshold as a second trajectory segment, and the first trajectory segments in that other grid cell, excluding the second trajectory segment, as a third trajectory segment; wherein, the first key point is the trajectory point on the first trajectory segment in the other grid cell that is closest to the start point, and the... Another grid cell is the grid cell other than the grid cell containing the target trajectory segment among the two adjacent grid cells; the second trajectory segment and the target trajectory segment are clustered into the same trajectory segment; based on the similarity between the second key point in the other grid cell and the endpoint, in the other grid cell, the third trajectory segment whose similarity with the target trajectory segment is less than the similarity threshold is determined as the fourth trajectory segment; wherein, the second key point is the trajectory point on the third trajectory segment in the other grid cell that is closest to the endpoint; the fourth trajectory segment and the target trajectory segment are clustered into the same trajectory segment to obtain the target route.

[0035] In one possible implementation, the similarity threshold includes a distance threshold and an orientation threshold; then the clustering unit is further configured to, based on the location information and orientation information of the starting point, determine, on each of the first trajectory segments in the other grid unit, the first key point that is closest to the starting point; determine a first distance and an angle difference between the starting point and the first key point; and, in response to the first distance being less than the distance threshold and the angle difference being less than the orientation threshold, determine the first trajectory segment in the other grid unit where the first key point is located as the second trajectory segment.

[0036] In one possible implementation, the clustering unit is further configured to determine the height distance between the starting point and the first key point in response to the spatial distance between the starting point and the first key point being less than a spatial distance threshold and the difference in the included angle being less than the orientation threshold; wherein the spatial distance and the height distance constitute the distance; and in response to the height distance being less than the height distance threshold, determine that the first trajectory segment in which the first key point in the other grid unit is located and the target trajectory segment satisfy the similarity threshold.

[0037] In one possible implementation, the device further includes a counting unit for determining the number of the first trajectory segments within the grid cell; in response to a number greater than 1 within the first trajectory segments, clustering any two first trajectory segments with a similarity less than the similarity threshold within the grid cell to obtain a fifth trajectory segment; then the clustering unit is further configured to, based on the orientation information and the location information, cluster any two fifth trajectory segments with a similarity less than the similarity threshold in two adjacent grid cells to obtain the target route.

[0038] Thirdly, embodiments of this application provide a readable storage medium, including,

[0039] memory,

[0040] The memory is used to store instructions that, when executed by a processor, cause an apparatus including the readable storage medium to perform the method as described in the first aspect and any possible implementation.

[0041] Fourthly, embodiments of this application provide an electronic device, including:

[0042] Memory, used to store computer programs;

[0043] When a processor executes a computer program stored in the memory, it implements the method as described in the first aspect and any possible implementation. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of a method for generating a road network provided in an embodiment of this application;

[0045] Figure 2 A schematic diagram of a grid trajectory provided in an embodiment of this application;

[0046] Figure 3 A schematic diagram of a road network provided for an embodiment of this application;

[0047] Figure 4 A flowchart illustrating a method for clustering trajectory segments in two adjacent grid cells, provided in an embodiment of this application;

[0048] Figure 5 A schematic diagram of a device for generating a road network provided in an embodiment of this application;

[0049] Figure 6 This is a schematic diagram of the structure of an electronic device for generating a road network, provided in an embodiment of this application. Detailed Implementation

[0050] To address the problem of low road network accuracy caused by low route accuracy in existing technologies, this application provides a method for generating a road network: a raster process is applied to the surveyed trajectory, distributing raster cells along the surveyed trajectory; trajectory segments in adjacent raster cells are clustered to obtain the target route; and a high-precision road network is generated based on the orientation and location information of the target route, avoiding the low accuracy problem caused by directly clustering long trajectories in existing technologies.

[0051] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0052] Please refer to Figure 1 This application proposes a method for generating road networks to improve the accuracy and efficiency of road network generation. The method specifically includes the following implementation steps:

[0053] Step 101: Obtain at least two surveying trajectories, as well as the orientation and location information of the trajectory points on the surveying trajectories.

[0054] The mapping trajectory consists of trajectory points. Orientation information includes the angle between the orientation of the trajectory points and the preset coordinate axes of the preset coordinate system. Position information includes the coordinates of the trajectory points in the preset coordinate system.

[0055] The orientation of the aforementioned trajectory points represents the orientation of the surveying trajectory, specifically the direction of travel of the surveying vehicle used to draw the trajectory. In other words, when the surveying trajectory is a straight line, the orientation information of each trajectory point on the trajectory is the same. When the surveying trajectory is a curve, the orientation information of each trajectory point on the trajectory is different.

[0056] The aforementioned preset coordinate system can be a vehicle coordinate system, a lidar coordinate system, a world coordinate system (such as a UTM coordinate system, a WGS84 coordinate system, etc.), etc. Coordinates in different coordinate systems can be converted to each other. In the embodiments of this application, the coordinates are all represented by three-dimensional coordinates (x, y, z).

[0057] Step 102: Divide the survey trajectory into grid cells of preset size to obtain the grid trajectory.

[0058] In this system, the grid cells on the grid trajectory are distributed along the survey trajectory, and each grid cell includes at least one trajectory segment.

[0059] Specifically, each grid unit can be a polygon with the same shape and equal size (all preset dimensions), such as an isosceles trapezoid, rectangle, pentagon, etc. The rectangle can have unequal length and width dimensions, or it can have equal length and width dimensions. In the embodiments of this application, the grid unit is preferably a matrix with equal length and width dimensions; the size is, for example, 1m × 1m, 10m × 10m.

[0060] On the grid trajectory, these grid cells are distributed end-to-end, meaning that adjacent grid cells each have one overlapping edge, which can be partial or complete. When they completely overlap, they share one edge. Please refer to [reference needed]. Figure 2 Continue to refer to Figure 2 It can be obtained that the continuous grids distributed along the surveying trajectory form a grid trajectory that corresponds one-to-one with the surveying trajectory.

[0061] Step 103: Based on the orientation information and the location information, in two adjacent grid cells, any two first trajectory segments with a similarity less than the similarity threshold are clustered into the same trajectory segment to obtain the target route.

[0062] Then, a road network is generated based on the target routes. For example, if the target routes include route A→B→C and route M→B→A, then the road network generated based on the first and second routes is as follows: Figure 3 As shown, the road network may also include information on signs, buildings, etc., set up along each route by sensors on the surveying vehicle during the surveying process (not shown in the figure).

[0063] In this case, any two first trajectory segments are selected from two adjacent grid cells.

[0064] The two adjacent grid cells mentioned above are not limited to two adjacent grid cells in a certain horizontal or vertical direction. When the grid cell is rectangular, for a grid cell with grid cells distributed around its four sides, the grid cells adjacent to it should be grid cells in its 8-neighborhood; and the neighborhood of a grid cell refers to the grid cells that are connected to the edge of the grid cell, or to the vertex of the grid cell. That is, for the aforementioned grid cell with grid cells distributed around its four sides, the 8 grid cells connected to each of its edges and vertices constitute the 8-neighborhood of the grid cell.

[0065] The aforementioned similarity includes positional similarity and orientation similarity. Correspondingly, the preset similarity thresholds include a distance threshold and an orientation threshold. The following explanation addresses the similarity between the first trajectory segments taken from two different but adjacent raster cells; please refer to [reference needed]. Figure 4 :

[0066] Step 401: In two adjacent grid cells, mark the first trajectory segment in either grid cell as the target trajectory segment, and determine the start and end points of the target trajectory segment.

[0067] Specifically, based on the orientation and location information of trajectory points on the surveyed trajectory, the location and orientation information of the starting point and the location and orientation information of the ending point of the target trajectory segment are determined.

[0068] Step 402: Based on the similarity between the first key point in another grid cell and the starting point of the target trajectory segment, in the other grid cell, the first trajectory segment with a similarity less than the similarity threshold with the target trajectory segment is identified as the second trajectory segment, and the first trajectory segment other than the second trajectory segment in the other grid cell is identified as the third trajectory segment.

[0069] The first key point is the trajectory point on the first trajectory segment in the other grid cell that is closest to the starting point; the other grid cell is the other grid cell among two adjacent grid cells, excluding the grid cell where the target trajectory segment is located.

[0070] The similarity between the aforementioned first key point and the starting point specifically includes positional similarity and orientation similarity, which are obtained based on the positional and orientation information of the first key point and the starting point, respectively. It can be seen that the positional and orientation information in step 402 specifically refers to the positional and orientation information of the trajectory points on the first trajectory segment in another grid cell, and the positional and orientation information of the starting point on the aforementioned target trajectory segment. The following provides a detailed explanation:

[0071] First, based on the location and orientation information of the starting point of the target trajectory segment, in each first trajectory segment in another grid cell, the trajectory point closest to the starting point is determined as the first key point. That is, a first key point is determined on each first trajectory segment in the other grid cell.

[0072] Then, determine the first distance between the starting point and the first key point, as well as the difference in the included angle. This difference in angle is obtained based on the orientation information of the starting point and the first key point.

[0073] Next, in response to the first distance being less than a distance threshold and the angle difference being less than an orientation threshold, the first trajectory segment containing the first key point in another grid cell is determined as the second trajectory segment. That is, when determining the clusterable trajectory segment through the starting point, the first trajectory segment in another grid cell is divided into a second trajectory segment that can be clustered with the target trajectory segment, and a third trajectory segment that cannot be clustered with the target trajectory segment, that is, independent of the target trajectory segment.

[0074] To avoid incorrectly clustering routes such as viaducts that differ only in spatial height, the aforementioned distances include both spatial distance and height distance. For example, if the starting point's coordinates are (X1, Y1, Z1), and the first key point's coordinates are (X... a Y a Z a If the spatial distance is D1, then the spatial distance is D1 = √(X1 - X). a ) 2 +(Y1-Y a ) 2 +(Z1-Z a ) 2 The height distance D2 = |Z1 - Z a |

[0075] To further improve clustering efficiency, when the spatial distance is determined to be no less than the distance threshold, or when the spatial distance is less than the distance threshold but the difference in angle is no less than the aforementioned orientation threshold, the first trajectory segment where the current first key point is located can be directly determined as the third trajectory segment, rather than the second trajectory segment.

[0076] Only when the spatial distance is less than the distance threshold and the difference in angle is less than the orientation threshold, is the height distance further determined. When the height distance is also less than the height distance threshold, the first trajectory segment where the current first key point is located is determined as the second trajectory segment.

[0077] Step 403: Cluster the second trajectory segment and the target trajectory segment into the same trajectory segment.

[0078] Clustering is the process of merging the second trajectory segment and the target trajectory segment. The specific merging method can be to make the second trajectory segment coincide with the target trajectory segment (including information) and delete one of them; or, to determine a trajectory segment (including information) between the second trajectory segment and the target trajectory segment and delete the second trajectory segment and the target trajectory segment.

[0079] Step 404: Based on the similarity between the second key point and the endpoint in the other grid cell, in the other grid cell, determine the third trajectory segment with similarity and similarity threshold with the target trajectory segment as the fourth trajectory segment.

[0080] The second key point is the trajectory point on the third trajectory segment in the other grid cell that has the smallest distance from the endpoint on the target trajectory segment.

[0081] To avoid situations where factors such as turns prevent the complete filtering of trajectory segments on the same route from the starting point, step 404 determines trajectory segments with similarity less than the similarity threshold in another grid cell based on the endpoint of the target trajectory segment.

[0082] Similar to step 402, the similarity between the second keypoint and the endpoint specifically includes positional similarity and orientation similarity. These are obtained based on the positional and orientation information of the second keypoint and the endpoint of the target trajectory segment, respectively. Therefore, the positional and orientation information in step 404 specifically refers to the positional and orientation information of the trajectory points on the third trajectory segment in the other grid cell, and the positional and orientation information of the endpoint of the target trajectory segment. The specific method for determining the similarity is consistent with that described in step 402 and will not be repeated here.

[0083] Step 405: Cluster the fourth trajectory segment and the target trajectory segment into the same trajectory segment to obtain the target route.

[0084] Specifically, after step 404, a fourth trajectory segment that clusters with the target trajectory segment is further selected from the third trajectory segment in another grid cell. The remaining third trajectory segments are independent of the target trajectory segment and belong to different routes.

[0085] That is, the first trajectory segment of another grid cell is ultimately divided into a second trajectory segment, a third trajectory segment, and a fourth trajectory segment. The fourth trajectory segment is selected from the third trajectory segment. After the second and fourth trajectory segments are clustered with the target trajectory segment, a single trajectory segment is obtained: the same trajectory segment. At this time, the trajectory segments in the two adjacent grid cells include the first trajectory segment (from the grid cell where the target trajectory segment is located), the same trajectory segment, and the third trajectory segment.

[0086] Furthermore, the target trajectory segment in step 401 can actually be any one of the first trajectory segments in any of the aforementioned grid cells. Therefore, in the grid cell where the target trajectory segment is located, the remaining first trajectory segments are sequentially taken as the target trajectory segment, and steps 401-405 are repeated to traverse all the first trajectory segments in the grid cell where the target trajectory segment is located, thus completing the clustering of the first trajectory segments between two adjacent grid cells.

[0087] Furthermore, to further improve the efficiency and accuracy of determining the target route and road network, before step 103, i.e., before implementing "based on the orientation information and the location information, clustering any two first trajectory segments with a similarity less than a similarity threshold in two adjacent grid cells to obtain the target route," the first trajectory segments in each grid cell are first clustered. Specifically, firstly, the number of first trajectory segments within the grid cell is determined. In response to a number greater than 1, any two first trajectory segments with a similarity less than a similarity threshold within the grid cell are clustered to obtain a fifth trajectory segment. That is, any two first trajectory segments with a similarity less than a similarity threshold within the grid cell are clustered, while any two first trajectory segments with a similarity greater than or equal to the similarity threshold are not clustered. The resulting fifth trajectory segment includes both the clustered same trajectory segments and the unclustered first trajectory segments. Here, the clustering of first trajectory segments within each grid cell is consistent with the method steps described in steps 401-405. The following explanation is provided: First, within each grid cell, two first trajectory segments are randomly selected, and the start and end points of one of the first trajectory segments are determined. The start point includes the position and orientation information of the starting point of the first trajectory segment, and the end point includes the position and orientation information of the ending point of the first trajectory segment. Then, the trajectory point on the other first trajectory segment closest to the start point of the first trajectory segment is determined, and this closest trajectory point is marked as the first keypoint. The distance between the first keypoint and the aforementioned start point is determined as the positional similarity, and the difference between the angle between the orientation information of the first keypoint and the preset coordinate axis of the preset coordinate system, and the angle between the orientation information of the aforementioned start point and the preset coordinate axis of the preset coordinate system, is determined as the orientation similarity.

[0088] If the positional similarity is less than the distance threshold and the orientation similarity is less than the orientation threshold, then the height difference between the first key point and the starting point can be further determined. If this height difference is also less than the height-distance threshold, then the first trajectory segment containing the first key point and the first trajectory segment containing the starting point satisfy the similarity threshold. These two first trajectory segments are then clustered to obtain the fifth trajectory segment. If the positional similarity is not less than the aforementioned distance threshold, or the orientation similarity is not less than the aforementioned orientation threshold, then the trajectory point closest to the aforementioned endpoint on the other first trajectory segment is determined as the second key point.

[0089] Similarly, determine the positional similarity and orientation similarity between the endpoint and the second keypoint. If the positional similarity is not less than the similarity threshold, or the orientation similarity is not less than the similarity threshold, then these two first trajectory segments are determined to be trajectory segments belonging to different routes within the current grid cell, i.e., these two first trajectory segments are determined not to cluster. If the positional similarity is less than the distance threshold, and the orientation similarity is less than the orientation threshold, then the height difference between the height of the second keypoint and the endpoint can be further determined. When the height difference is less than the height-distance threshold, it can be determined that the first trajectory segment where the second keypoint is located and the first trajectory segment where the endpoint is located satisfy the similarity threshold, then these two first trajectory segments are still determined to cluster, resulting in the fifth trajectory segment.

[0090] When step 103 is executed, based on the aforementioned orientation and location information, any two fifth trajectory segments with a similarity less than a similarity threshold are clustered within two adjacent grid cells to obtain the target route. That is, for a grid cell containing multiple trajectory segments, the trajectory segments meeting the similarity threshold are first clustered within the grid cell. Then, for the grid cell where trajectory segment clustering within the grid cell has been completed, trajectory segments meeting the similarity threshold are clustered between adjacent grid cells to obtain the target route, thereby further improving the accuracy and efficiency of the obtained target route and road network.

[0091] Based on the same inventive concept, this application provides an apparatus for generating a road network, which is similar to the aforementioned apparatus. Figure 1 The method for generating the road network shown corresponds to the specific implementation of this device, which can be found in the description of the aforementioned method embodiments. Repeated descriptions will not be repeated here. Figure 5 The device includes:

[0092] Information unit 501: used to acquire at least two surveying trajectories, as well as the orientation and location information of the trajectory points on the surveying trajectories.

[0093] The orientation information includes the angle between the orientation of the trajectory point on the survey trajectory and the preset coordinate axis of the preset coordinate system, and the position information includes the coordinates of the trajectory point in the preset coordinate system.

[0094] Grid unit 502: used to divide the mapping trajectory into grid units of a preset size to obtain a grid trajectory.

[0095] The grid cells on the grid trajectory are distributed along the mapping trajectory, and each grid cell includes at least one first trajectory segment.

[0096] In one possible implementation, the grid cell is rectangular in shape, and each of two adjacent grid cells has one side overlapping.

[0097] Clustering unit 503: Based on the orientation information and the location information, it clusters any two first trajectory segments with a similarity less than a similarity threshold into the same trajectory segment in two adjacent grid cells to obtain a target route; then it generates a road network based on the target route.

[0098] The clustering unit 503 is specifically used to, in two adjacent grid units, mark the first trajectory segment in any one of the grid units as a target trajectory segment, and determine the start and end points of the target trajectory segment; based on the similarity between a first key point in another grid unit and the start point, in the other grid unit, determine the first trajectory segment in the other grid unit whose similarity to the target trajectory segment is less than the similarity threshold as a second trajectory segment, and the first trajectory segments in the other grid unit other than the second trajectory segment as third trajectory segments; wherein, the first key point is the trajectory point on the first trajectory segment in the other grid unit that is closest to the start point, and the other grid unit... A grid cell is any grid cell other than the one containing the target trajectory segment among two adjacent grid cells; the second trajectory segment and the target trajectory segment are clustered into the same trajectory segment; based on the similarity between the second key point in the other grid cell and the endpoint, in the other grid cell, the third trajectory segment whose similarity to the target trajectory segment is less than the similarity threshold is determined as the fourth trajectory segment; wherein, the second key point is the trajectory point on the third trajectory segment in the other grid cell that is closest to the endpoint; the fourth trajectory segment and the target trajectory segment are clustered into the same trajectory segment to obtain the target route.

[0099] The similarity threshold includes a distance threshold and an orientation threshold; then the clustering unit 503 is further configured to, based on the location information and orientation information of the starting point, determine the first key point that is closest to the starting point on each of the first trajectory segments in the other grid unit; determine the first distance between the starting point and the first key point, and the difference in the included angle; in response to the first distance being less than the distance threshold and the difference in the included angle being less than the orientation threshold, determine the first trajectory segment where the first key point in the other grid unit is located as the second trajectory segment.

[0100] The device for generating the road network further includes a quantity unit for determining the number of the first trajectory segments within the grid cell; in response to the number of the first trajectory segments being greater than 1, clustering any two first trajectory segments with a similarity less than the similarity threshold within the grid cell to obtain a fifth trajectory segment; then the clustering unit 503 is further configured to, based on the orientation information and the location information, cluster any two fifth trajectory segments with a similarity less than the similarity threshold in two adjacent grid cells to obtain the target route.

[0101] Based on the same inventive concept, embodiments of this application also provide a readable storage medium, including:

[0102] memory,

[0103] The memory is used to store instructions that, when executed by a processor, cause the apparatus including the readable storage medium to perform the method of generating a road network as described above.

[0104] Based on the same inventive concept as the aforementioned method for generating road networks, this application also provides an electronic device that can implement the functions of the aforementioned method for generating road networks. Please refer to [link / reference needed]. Figure 6 The electronic device includes:

[0105] At least one processor 601 and a memory 602 connected to at least one processor 601. In this embodiment, the specific connection medium between the processor 601 and the memory 602 is not limited. Figure 6 The example shown is the connection between processor 601 and memory 602 via bus 600. Bus 600 is... Figure 6 The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. The 600 bus can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 6 The term is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, the processor 601 can also be called a controller; there is no restriction on the name.

[0106] In this embodiment, memory 602 stores instructions executable by at least one processor 601. By executing the instructions stored in memory 602, at least one processor 601 can perform the road network generation method described above. Processor 601 can implement... Figure 5 The functions of each module in the device shown.

[0107] The processor 601 is the control center of the device. It can connect to various parts of the control device through various interfaces and lines. By running or executing instructions stored in memory 602 and calling data stored in memory 602, the processor can perform various functions and process data, thereby monitoring the device as a whole.

[0108] In one possible design, processor 601 may include one or more processing units. Processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 601. In some embodiments, processor 601 and memory 602 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0109] Processor 601 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method for generating a road network disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0110] Memory 602, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 602 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory 602 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 602 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0111] By designing and programming the processor 601, the code corresponding to the road network generation method described in the foregoing embodiments can be embedded into the chip, thereby enabling the chip to execute the code during runtime. Figure 1 The steps of the method for generating the road network are shown. How to design and program the processor 601 is a technique well-known to those skilled in the art and will not be described further here.

[0112] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0113] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as 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 this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes: Universal Serial Bus flash disks, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0117] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for generating a road network, characterized in that, include: Acquire at least two surveying trajectories, as well as the orientation and position information of the trajectory points on the surveying trajectories; wherein, the orientation information includes the angle between the orientation of the trajectory point on the surveying trajectories and the preset coordinate axis of the preset coordinate system, and the position information includes the coordinates of the trajectory point in the preset coordinate system; The mapping trajectory is divided into grid cells of a preset size to obtain a grid trajectory; wherein, the grid cell includes at least one first trajectory segment; In two adjacent grid cells, the first trajectory segment in either grid cell is marked as the target trajectory segment, and the start and end points of the target trajectory segment are determined. Based on the similarity between a first key point in another grid cell and the starting point, in the other grid cell, the first trajectory segment with a similarity less than a similarity threshold to the target trajectory segment is identified as the second trajectory segment, and the first trajectory segment in the other grid cell other than the second trajectory segment is identified as the third trajectory segment; wherein, the first key point is the trajectory point on the first trajectory segment in the other grid cell that is closest to the starting point, and the other grid cell is the grid cell other than the grid cell where the target trajectory segment is located in the two adjacent grid cells; Cluster the second trajectory segment and the target trajectory segment into the same trajectory segment; Based on the similarity between the second key point in the other grid cell and the endpoint, in the other grid cell, the third trajectory segment whose similarity with the target trajectory segment is less than the similarity threshold is determined as the fourth trajectory segment; wherein, the second key point is the trajectory point on the third trajectory segment in the other grid cell that is closest to the endpoint; The second trajectory segment, the fourth trajectory segment, and the target trajectory segment are clustered into the same trajectory segment to obtain the target route; then a road network is generated based on the target route.

2. The method as described in claim 1, characterized in that, The grid cell is rectangular in shape, and each of the two adjacent grid cells has one side overlapping.

3. The method as described in claim 1, characterized in that, The similarity threshold includes a distance threshold and an orientation threshold; then, based on the similarity between a first keypoint in another grid cell and the starting point, in that other grid cell, determining the first trajectory segment whose similarity to the target trajectory segment is less than the similarity threshold as the second trajectory segment includes: Based on the location information and orientation information of the starting point, on each of the first trajectory segments in the other grid cell, the first key point that is closest to the starting point is determined respectively; Determine the first distance between the starting point and the first key point, and the difference in the included angle; In response to the first distance being less than the distance threshold and the difference in the included angle being less than the orientation threshold, the first trajectory segment containing the first key point in the other grid cell is determined to be the second trajectory segment.

4. The method as described in claim 3, characterized in that, The step of determining the first trajectory segment containing the first key point in the other grid cell as the second trajectory segment in response to the first distance being less than the distance threshold and the difference in the included angle being less than the orientation threshold includes: In response to the fact that the spatial distance between the starting point and the first key point is less than a spatial distance threshold and the difference in the included angle is less than the orientation threshold, the height distance between the starting point and the first key point is determined; wherein, the spatial distance and the height distance constitute the distance; In response to the height distance being less than the height distance threshold, it is determined that the first trajectory segment containing the first key point in the other grid cell and the target trajectory segment satisfy the similarity threshold.

5. The method according to any one of claims 1-4, characterized in that, Before clustering any two first trajectory segments with a similarity less than a similarity threshold in two adjacent grid cells based on the orientation information and the location information to obtain the target route, the method further includes: Determine the number of the first trajectory segments within the grid cell; In response to the number of the first trajectory segments being greater than 1, any two of the first trajectory segments with a similarity less than the similarity threshold are clustered within the grid cell to obtain the fifth trajectory segment; The step of clustering any two first trajectory segments with a similarity less than a similarity threshold in two adjacent grid cells based on the orientation information and the location information to obtain the target route includes: Based on the orientation information and the location information, in two adjacent grid cells, any two fifth trajectory segments with a similarity less than a similarity threshold are clustered to obtain the target route.

6. An apparatus for generating a road network, characterized in that, include: Information unit: used to acquire at least two surveying trajectories, as well as orientation information and position information of trajectory points on the surveying trajectories; wherein, the orientation information includes the angle between the orientation of the trajectory point on the surveying trajectories and the preset coordinate axis of the preset coordinate system, and the position information includes the coordinates of the trajectory point in the preset coordinate system; Grid unit: used to divide the mapping trajectory into grid units of a preset size to obtain a grid trajectory; wherein, the grid unit includes at least one first trajectory segment; Clustering unit: Used to mark the first trajectory segment in any one of two adjacent grid cells as a target trajectory segment, and determine the start and end points of the target trajectory segment; based on the similarity between a first keypoint in another grid cell and the start point, in that other grid cell, determine the first trajectory segment whose similarity to the target trajectory segment is less than a similarity threshold as a second trajectory segment, and the first trajectory segments in that other grid cell, excluding the second trajectory segment, as third trajectory segments; wherein, the first keypoint is the trajectory point on the first trajectory segment in the other grid cell that is closest to the start point, and the other grid cell is the two adjacent grid cells. In the unit, the grid cells other than the grid cell where the target trajectory segment is located; the second trajectory segment and the target trajectory segment are clustered into the same trajectory segment; based on the similarity between the second key point in the other grid cell and the endpoint, in the other grid cell, the third trajectory segment whose similarity with the target trajectory segment is less than the similarity threshold is determined as the fourth trajectory segment; wherein, the second key point is the trajectory point on the third trajectory segment in the other grid cell that is closest to the endpoint; the second trajectory segment, the fourth trajectory segment and the target trajectory segment are clustered into the same trajectory segment to obtain the target route; then a road network is generated based on the target route.

7. A readable storage medium, characterized in that, include, memory, The memory is used to store instructions that, when executed by a processor, cause the apparatus including the readable storage medium to perform the method as described in any one of claims 1-5.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a computer program stored in the memory, implements the method as described in any one of claims 1-5.

Images