Map processing method, device and equipment
Through map topology map matching processing and trajectory line projection, the two-way matching of trajectory lines and map paths is achieved, solving the problems of map timeliness and low scene labeling accuracy, and improving path matching accuracy and productivity.
Patent Information
- Application Number
- CN202411132966.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-22
AI Technical Summary
In the prior art, the timeliness of maps lead to inaccurate path matching, and the "pipeline" structure of the actual road and the "line" structure of the trajectory lead to low scene labeling accuracy.
By obtaining the trajectory lines to be marked, using the map topology map for matching processing, determining the map path on the trajectory line, and updating the blank scene in the trajectory interval into scene information, realizing bidirectional matching between the trajectory line and the map path, and improving the scene labeling accuracy .
It solves the matching omissions caused by map timeliness, improves the scene labeling accuracy, is highly robust and universal, and can adapt to various map specification data and scene roads, greatly improving production efficiency.
Smart Images

Figure CN119007567A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technology of producing high-precision maps of urban roads, and in particular to a map processing method, device and equipment. Background Art
[0002] At present, in order for users to quickly navigate the required path on ordinary urban roads and highways, map marking is required. Map marking refers to marking the map position consistent with the actual position.
[0003] In the prior art, the map link path matching the trajectory GPS is first obtained based on the existing HMM, and then the first and last nodes of each link are projected to the trajectory, and then the trajectory range corresponding to the link is obtained, and finally the scene information corresponding to the link is assigned to the trajectory.
[0004] However, in the prior art, due to the timeliness of maps, some road changes in the real world have not been updated to the map in a timely manner. The trajectory of the existing solution can only match part of the map link path, resulting in inaccurate path matching; and, since the real road is a "pipeline" structure and the trajectory is a "line" structure, if there is an angle deviation between the geometric direction of the trajectory and the real road, directly taking the projection range of the first and last nodes of the path on the trajectory as the scene range, the scene range will also have deviations, resulting in inaccurate path matching, which in turn leads to low scene annotation accuracy of the map. Summary of the invention
[0005] The present application provides a map processing method, device and equipment to solve the technical problem of low accuracy of map scene annotation.
[0006] In a first aspect, the present application provides a map processing method, comprising:
[0007] Acquire a trajectory line to be marked; wherein the trajectory line is a preset moving route collected from a mobile device when it moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area;
[0008] According to the trajectory collection area, a plurality of trajectory points on the trajectory line are matched with a preset map topology map, a map path matching the trajectory line is determined on the map topology map, and scene information of the map path is determined; wherein the map topology map represents a route map within an area corresponding to the trajectory collection area in a preset map library;
[0009] The trajectory line is projected according to the map path, a trajectory section on the trajectory line that matches the map path is determined, and a preset blank scene of the trajectory section is updated as the scene information.
[0010] Furthermore, the preset map topology diagram includes directed edges, nodes, association relationships between the directed edges and the nodes, and an outer geometric frame where the directed edges are located;
[0011] The directed edges are determined based on the route data in the map library, and the nodes are determined based on the node data in the map library; the outer geometric frame is obtained by expanding the initial geometric frame where the directed edges are located.
[0012] Furthermore, matching a plurality of trajectory points on the trajectory line with a preset map topology map according to the trajectory collection area, and determining a map path matching the trajectory line on the map topology map, comprises:
[0013] Determining the global positioning coordinates of each of the trajectory points;
[0014] For each of the trajectory points, according to the global positioning coordinate value of the trajectory point, in the map topology corresponding to the trajectory collection area, a plurality of the outer geometric boxes associated with the trajectory point are determined, and the directed edges corresponding to the associated outer geometric boxes are determined to be candidate trajectory paths;
[0015] Determining the observation probability and transition probability of each candidate trajectory path;
[0016] According to the observation probability and the transition probability of each trajectory path, a map path matching the trajectory line is determined.
[0017] Further, projecting the trajectory line according to the map path to determine a trajectory section on the trajectory line that matches the map path includes:
[0018] Determine a node in the map path, and determine a corresponding point of the node on the trajectory line; wherein the corresponding point is a point obtained by projecting the node on the trajectory line by a preset projection method;
[0019] Determining the observation probability and the transition probability of each corresponding point in turn;
[0020] According to the observation probability and the transition probability of each corresponding point, a trajectory interval on the trajectory line that matches the map path is determined.
[0021] Further, the trajectory points also include trajectory points located outside the outer geometric frame;
[0022] The method further comprises:
[0023] A newly added scene is determined according to the trajectory points outside the outer geometric frame.
[0024] Furthermore, the determining of the newly added scene according to the trajectory points outside the outer geometric frame includes:
[0025] According to the trajectory line, the trajectory points outside the outer geometric frame are grouped to obtain multiple groups of trajectories to be matched;
[0026] For each track point in the set of to-be-matched tracks, determine the global positioning coordinate value of the track point, and determine multiple candidate track paths of the track point in the map topology map according to the global positioning coordinate value of the track point; determine the observation probability and transition probability of each candidate track path;
[0027] If it is determined that the trajectory to be matched has no matching map path according to the observation probability and the transition probability of the trajectory point in the trajectory to be matched, then the trajectory point in the trajectory to be matched is determined to be a newly added scene.
[0028] Furthermore, the method further comprises:
[0029] Taking the first trajectory point in the trajectory line as the starting point, selecting a plurality of downsampled trajectory points according to a preset spacing;
[0030] Determining the global positioning coordinate value of each of the trajectory points includes:
[0031] Determine the global positioning coordinate value of each downsampled trajectory point.
[0032] In a second aspect, the present application provides a map processing device, comprising:
[0033] An acquisition module, used to acquire a trajectory line to be marked; wherein the trajectory line is a preset moving route collected from a mobile device when it moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area;
[0034] A matching module, configured to match a plurality of track points on the track line with a preset map topology map according to the track collection area, and determine a map path matching the track line on the map topology map; wherein the map topology map represents a route map within an area corresponding to the track collection area in a preset map library;
[0035] A first determination module, used to determine the scene information of the map path;
[0036] A projection module, configured to project the trajectory line according to the map path, and determine a trajectory interval on the trajectory line that matches the map path;
[0037] An updating module is used to update the preset blank scene of the trajectory interval to the scene information.
[0038] Furthermore, the preset map topology diagram includes directed edges, nodes, association relationships between the directed edges and the nodes, and an outer geometric frame where the directed edges are located;
[0039] The directed edges are determined based on the route data in the map library, and the nodes are determined based on the node data in the map library; the outer geometric frame is obtained by expanding the initial geometric frame where the directed edges are located.
[0040] Furthermore, the matching module includes:
[0041] A first determining unit, used to determine the global positioning coordinate value of each of the trajectory points;
[0042] a second determining unit, configured to determine, for each of the trajectory points, a plurality of outer geometric boxes associated with the trajectory point in the map topology corresponding to the trajectory collection area according to the global positioning coordinate value of the trajectory point, and determine that all directed edges corresponding to the associated outer geometric boxes are candidate trajectory paths;
[0043] A third determination unit, configured to determine an observation probability and a transition probability of each candidate trajectory path;
[0044] The fourth determining unit is used to determine a map path matching the trajectory line according to the observation probability and the transition probability of each trajectory path.
[0045] Furthermore, the projection module comprises:
[0046] A fifth determination unit, configured to determine a node in the map path, and determine a corresponding point of the node on the trajectory line; wherein the corresponding point is a point obtained by projecting the node on the trajectory line in a preset projection manner;
[0047] A sixth determining unit, used to sequentially determine the observation probability and the transition probability of each corresponding point;
[0048] The seventh determining unit is used to determine a trajectory section on the trajectory line that matches the map path according to the observation probability and the transition probability of each corresponding point.
[0049] Further, the trajectory points also include trajectory points located outside the outer geometric frame;
[0050] The device also includes:
[0051] The eighth determining unit is used to determine a newly added scene according to the trajectory points located outside the outer geometric frame.
[0052] Furthermore, the eighth determining unit includes:
[0053] A grouping subunit, used for grouping the trajectory points outside the outer geometric frame according to the trajectory line to obtain multiple groups of trajectories to be matched;
[0054] An execution subunit is used to determine the global positioning coordinate value of each trajectory point in each group of to-be-matched trajectories, and determine multiple candidate trajectory paths of the trajectory point in the map topology map according to the global positioning coordinate value of the trajectory point; and determine the observation probability and transition probability of each candidate trajectory path;
[0055] The determination subunit is configured to determine that the track point in the track to be matched is a newly added scene if it is determined that the track to be matched has no matching map path according to the observation probability and the transition probability of the track point in the track to be matched.
[0056] Furthermore, the device also includes:
[0057] A downsampling module, used to select a plurality of downsampled trajectory points according to a preset spacing, taking the first trajectory point in the trajectory line as a starting point;
[0058] The first determining unit is specifically used for:
[0059] Determine the global positioning coordinate value of each downsampled trajectory point.
[0060] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.
[0061] 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 described in the first aspect.
[0062] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.
[0063] The present application provides a map processing method, device and equipment, which obtains a trajectory line to be marked; wherein the trajectory line is a preset moving route collected by a mobile device when it moves in an actual scene, and the trajectory line includes multiple trajectory points, and the trajectory line includes a preset trajectory collection area. According to the trajectory collection area, the multiple trajectory points on the trajectory line are matched with the preset map topology map, and the map path matching the trajectory line is determined on the map topology map, and the scene information of the map path is determined; wherein the map topology map represents the route map in the area corresponding to the trajectory collection area in the preset map library. According to the map path, the trajectory line is projected, the trajectory interval matching the map path on the trajectory line is determined, and the preset blank scene of the trajectory interval is updated to the scene information. In this scheme, first, the trajectory collection area of the trajectory line corresponds to a map topology map, and the multiple trajectory points are matched with the map topology map to obtain the matching map path link. The map path link is projected onto the trajectory line, the trajectory interval matching the map path on the trajectory line is determined, and the scene information of the map path link is assigned to the trajectory interval. Therefore, multi-segment path matching can solve the matching omissions caused by map timeliness, and the two-way matching between the trajectory line and the map topology can improve the scene annotation accuracy. In addition, the present application has high robustness and universality, and can be widely adapted to various map specification data and various scene roads, greatly improving production efficiency and solving the technical problem of low scene annotation accuracy of the map. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0065] Figure 1 A flowchart of a map processing method provided in an embodiment of the present application;
[0066] Figure 2 A flowchart of another map processing method provided in an embodiment of the present application;
[0067] Figure 3 A flowchart of another map processing method provided in an embodiment of the present application;
[0068] Figure 4 A structural schematic diagram of a map processing device provided in an embodiment of the present application;
[0069] Figure 5 A schematic diagram of the structure of another map processing device provided in an embodiment of the present application;
[0070] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;
[0071] Figure 7 A block diagram of an electronic device provided in an embodiment of the present application.
[0072] The above drawings show clear embodiments of the present disclosure, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present disclosure in any way, but to illustrate the concepts of the present disclosure to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0073] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present disclosure.
[0074] At present, in order for users to quickly navigate the required path on ordinary urban roads and highways, map marking is required. Map marking refers to marking the map position consistent with the actual position.
[0075] In one example, the map link path matching the trajectory GPS is first obtained based on the existing HMM, and then the first and last nodes of each link are projected to the trajectory, and then the trajectory range corresponding to the link is obtained, and finally the scene information corresponding to the link is assigned to the trajectory. However, in the prior art, due to the timeliness of the map, some road changes in the real world have not been updated to the map in a timely manner. The trajectory of the existing solution can only match part of the map link path, resulting in inaccurate path matching; and because the real road is a "pipeline" structure and the trajectory is a "line" structure, if there is an angle deviation between the geometric direction of the trajectory and the real road, the projection range of the first and last nodes of the path in the trajectory is directly used as the scene range, then the scene range will also have deviations, resulting in inaccurate path matching, which in turn leads to low scene annotation accuracy of the map.
[0076] The present application provides a map processing method, device and equipment, aiming to solve the above technical problems in the prior art.
[0077] 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.
[0078] Figure 1 A flowchart of a map processing method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes:
[0079] Step 101, obtaining a trajectory line to be marked; wherein the trajectory line is a preset moving route collected when the mobile device moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area.
[0080] For example, the execution subject of this embodiment may be an electronic device, or a terminal device, or a map processing device or device, or other devices or equipment that can execute this embodiment, and there is no limitation to this. In this embodiment, the execution subject is described as an electronic device.
[0081] First, when the preset self-moving device is used to move in the actual scene, the moving route, that is, the trajectory line, is collected according to its own moving trajectory, and the trajectory line includes multiple trajectory points. For example, the self-moving device is a device including a global positioning system (GPS). During the movement, multiple GPS coordinates, that is, multiple trajectory points, are collected at preset time intervals to obtain a trajectory line. In addition, the trajectory line includes a preset trajectory collection area around it, for example, the trajectory collection area is rectangular, circular, etc., which is not limited to this.
[0082] Step 102: According to the trajectory collection area, multiple trajectory points on the trajectory line are matched with a preset map topology map, a map path matching the trajectory line is determined on the map topology map, and scene information of the map path is determined; wherein the map topology map represents a route map within an area corresponding to the trajectory collection area in a preset map library.
[0083] Exemplarily, the preset map library includes an existing map constructed based on existing roads. The existing map includes a path and scene information on the path. The scene information refers to the environmental information of each coordinate point on the path, etc. According to the trajectory collection area, the area corresponding to the trajectory collection area can be determined in the preset map library, and a map topology map can be constructed according to the route information in the corresponding area. The map topology map is the route map in the area corresponding to the trajectory collection area in the map library. Specifically, the global positioning coordinate value of the trajectory collection area is determined, and according to the global positioning coordinate value of the trajectory collection area, the map data corresponding to the trajectory collection area is obtained in the map library. The map data includes route data and node data. The route data is link data, and the node data is node data. The node data includes a starting point and an end point. The link data in the map data is used as a directed edge in the graph structure, and the node data in the map data is used as a node in the graph structure. The association relationship between the node and the directed edge is recorded to obtain a preliminary topology map. Furthermore, each directed edge in the preliminary topological map includes an initial geometric frame, and the initial geometric frame of the directed edge is expanded by a preset distance to form an outer geometric frame, and a map topological map, namely, an RTreer tree, is constructed based on the directed edges, nodes, association relationships and outer geometric frames.
[0084] In this step, based on the preset matching model, each track point can be matched with the map topology in turn according to the order of the track points and the global positioning coordinate value of each track point, and a map path matching the track line is determined on the map topology, and the scene information corresponding to the map path is determined. It should be noted that there is no limitation on the type of matching model.
[0085] Step 103: Project the trajectory line according to the map path, determine the trajectory interval on the trajectory line that matches the map path, and update the preset blank scene of the trajectory interval as scene information.
[0086] Exemplarily, in order to further determine the detailed scene of each track point on the track line, the track line is projected according to the starting point and the end point of the map path, and the corresponding point on the track line that matches the starting point of the map path and the corresponding point on the track line that matches the end point of the map path are determined. According to the corresponding point matching the starting point of the map path and the corresponding point matching the end point of the map path, the track interval on the track line that matches the map path is determined, and the preset blank scene of the track interval is updated as the scene information.
[0087] For example, for the starting point of the map path, the trajectory line is projected using a plurality of preset projection methods to determine a plurality of corresponding points on the trajectory line that match the starting point of the map path, wherein each projection method corresponds to a corresponding point. For the end point of the map path, the trajectory line is projected using a plurality of preset projection methods to determine a plurality of corresponding points on the trajectory line that match the end point of the map path, wherein each projection method corresponds to a corresponding point. For the plurality of corresponding points that match the starting point of the map path and the plurality of corresponding points that match the end point of the map path, a chain network can be constructed based on the plurality of corresponding points of the map path, and a preset Viterbi algorithm is used in the chain network to find the sequence with the highest probability. The sequence with the highest probability is the trajectory interval on the trajectory line that matches the map path, and the preset blank scene of the trajectory interval is updated to the scene information, and then the scene of the trajectory interval is the scene information.
[0088] Therefore, after obtaining the scene information of the trajectory interval, this application can update the existing map according to the scene information. For example, it can be applied to the automatic annotation service of high-precision map point cloud lines to improve the annotation efficiency; it can be applied to the automatic difference service of high-precision map point cloud lines to obtain the trajectory collection range and improve the difference accuracy; it can also be applied to the photo and trajectory cutting service of high-precision map point cloud lines to improve the efficiency of subsequent operations.
[0089] In an embodiment of the present application, a trajectory line to be annotated is obtained; wherein the trajectory line is a preset moving route collected from a mobile device when it moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area. According to the trajectory collection area, a plurality of trajectory points on the trajectory line are matched with a preset map topology map, a map path matching the trajectory line is determined on the map topology map, and the scene information of the map path is determined; wherein the map topology map represents a route map in an area corresponding to the trajectory collection area in a preset map library. According to the map path, the trajectory line is projected, a trajectory interval matching the map path on the trajectory line is determined, and the preset blank scene of the trajectory interval is updated to the scene information. In this scheme, first, the trajectory collection area of the trajectory line corresponds to a map topology map, a plurality of trajectory points are matched with the map topology map, and a matching map path link is obtained. The map path link is projected onto the trajectory line, a trajectory interval matching the map path on the trajectory line is determined, and the scene information of the map path link is assigned to the trajectory interval. Therefore, multi-segment path matching can solve the matching omissions caused by map timeliness, and the two-way matching between the trajectory line and the map topology can improve the scene annotation accuracy. In addition, the present application has high robustness and universality, and can be widely adapted to various map specification data and various scene roads, greatly improving production efficiency and solving the technical problem of low scene annotation accuracy of the map.
[0090] Figure 2 A flowchart of another map processing method provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the method includes:
[0091] Step 201, obtaining a trajectory line to be marked; wherein the trajectory line is a preset moving route collected when the mobile device moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area.
[0092] For example, this step can be referred to Figure 1 Step 101 in the above is not described in detail.
[0093] Step 202: Determine the global positioning coordinate value of each trajectory point.
[0094] In one example, step 202 includes: taking the first trajectory point in the trajectory line as the starting point, and selecting a plurality of downsampled trajectory points according to a preset spacing.
[0095] In one example, step 202 includes determining a global positioning coordinate value of each downsampled trajectory point.
[0096] Exemplarily, the electronic device sequentially traverses the track points on the track line, performs equally spaced downsampling on the track points, obtains a plurality of downsampled track points, and determines the global positioning coordinate value of each downsampled track point. Specifically, on the track line, taking the first track point in the track line as the starting point, a track point Ti is selected at every preset interval D, all the selected track points are downsampled track points, and the global positioning coordinate value of each downsampled track point is determined.
[0097] Step 203: for each trajectory point, according to the global positioning coordinate value of the trajectory point, in the map topology corresponding to the trajectory collection area, multiple outer geometric boxes associated with the trajectory point are determined, and the directed edges corresponding to the associated outer geometric boxes are determined to be candidate trajectory paths.
[0098] In one example, a preset map topology diagram includes directed edges, nodes, associations between directed edges and nodes, and an outer geometric frame where the directed edges are located; wherein the directed edges are determined based on route data in a map library, and the nodes are determined based on node data in the map library; and the outer geometric frame is obtained by expanding the initial geometric frame where the directed edges are located.
[0099] Exemplarily, first, the electronic device needs to determine the map topology. Specifically, the electronic device determines the global positioning coordinate value of the trajectory collection area, and according to the global positioning coordinate value of the trajectory collection area, obtains the map data corresponding to the trajectory collection area in the map library, and the map data includes route data and node data, the route data is link data, the node data is node data, and the node data includes the starting point and the end point. Then, the electronic device uses the link data in the map data as the directed edge in the graph structure, and the node data in the map data as the node in the graph structure, and records the association relationship between the node and the directed edge, so as to obtain a preliminary topology. Furthermore, each directed edge in the preliminary topology includes an initial geometric frame, and the electronic device expands the initial geometric frame of the directed edge by a preset distance to form an outer geometric frame, and constructs a map topology based on the directed edge, the node, the association relationship and the outer geometric frame, that is, the RTreer tree, and the map topology represents the association relationship between the directed edge and the node, the outer geometric frame where each directed edge is located, etc.
[0100] Then, according to the map topology, the candidate trajectory paths of the trajectory line are determined. Specifically, for each downsampled trajectory point T i (i=0,1,…,N), the electronic device determines in which outer geometric frames the trajectory point is located in the map topology according to the global positioning coordinate value of the trajectory point. A trajectory point can be located in multiple outer geometric frames at the same time. The outer geometric frames containing the trajectory point are the associated multiple outer geometric frames. Since each outer geometric frame contains a directed edge, the directed edges corresponding to the associated outer geometric frames are determined to be candidate trajectory paths L j (T i ).
[0101] Step 204: Determine the observation probability and transition probability of each candidate trajectory path.
[0102] Exemplarily, based on the preset HMM model, the electronic device sequentially calculates each candidate trajectory path L j (T i ) o (L j |T i ). Specifically, ① calculate the trajectory point T on the XY plane i To L j Vertical distance D xy (T i ,L j ) and the vertical point Prj(T i ,L j ), vertical point Prj(T i ,L j ) is located on the trajectory path L j ②Calculate the trajectory point Ti The forward direction and Prj(T i ,L j ) where the trajectory path L j The angle Rad(T i ,Prj(T i ,L j )), where the forward direction refers to the driving direction of the mobile device, that is, the extension direction of the trajectory line. i ,Prj(T i ,L j )) is greater than the preset first angle threshold, then L is discarded j (T i ); if Rad(T i ,Prj(T i ,L j )) is less than or equal to the preset first angle threshold, then proceed to the next step; ③ For the trajectory path L that is less than or equal to the first angle threshold j , calculate the trajectory point T i and the vertical point Prj(T i ,L j ) between the Z coordinates D z (T i ,Prj(T i ,L j )); ④ Calculate L according to the preset formula j (T i ) o (L j |T i ):
[0103]
[0104] Among them, 0.35 and 0.3 are both preset coefficients.
[0105] The electronic device calculates each trajectory path L in turn k (T i )’s transition probability P t (L k (T i )|L j (T i-1 )). Specifically, ① calculate the trajectory point T i-1 to T i The distance D(T i-1 ,T i );② Use the preset search algorithm to search the trajectory path L in the map topology j (T i-1 ) to the trajectory path L k (T i) and calculate the path length D(L j (T i-1 ),L k (T i )), if Path is empty, then P t (L k (T i )|L j (T i-1 ))=0, if Path is not empty, go to the next step ③; ③ Calculate the angle Rad(T i-1 T i ,Prj(T i-1 ,L j )Prj(T i ,L k )), where the first line direction is the trajectory point T i-1 to T i The second connection direction is Prj(T i-1 ,L j ) to Prj(T i ,L k ) connection direction. If Rad(T i-1 T i ,Prj(T i-1 ,L j )Prj(T i ,L k )) is greater than the preset second angle threshold, then P t (L k (T i )|L j (T i-1 ))=0,if Rad(T i-1 T i ,Prj(T i-1 ,L j )Prj(T i ,L k )) is less than or equal to the second angle threshold, then enter ④; ④ calculate the trajectory path L k (T i ) t (L k (T i )|L j (T i-1 )):
[0106]
[0107] Among them, 0.5 is the preset coefficient.
[0108] Step 205: Determine a map path that matches the trajectory line according to the observation probability and transition probability of each trajectory path.
[0109] Exemplarily, the electronic device constructs multiple candidate trajectory paths into a chain network based on the trajectory of the trajectory line, and uses a preset Viterbi algorithm in the chain network to find the sequence with the highest probability based on the observation probability and transition probability of each trajectory path. The sequence with the highest probability is the map path link that matches the trajectory line.
[0110] Step 206: Determine the scene information of the map path.
[0111] Exemplarily, based on a map library, the electronic device determines scene information of a map path.
[0112] Step 207: determine the nodes in the map path, and determine the corresponding points of the nodes on the trajectory line; wherein the corresponding points are points obtained by projecting the nodes on the trajectory line by a preset projection method.
[0113] Exemplarily, the electronic device determines the nodes in the map path, and the nodes include the starting point and the end point of the map path. According to the nodes in the map path, the corresponding points of the starting point and the end point of the matching map path link on the trajectory are calculated, that is, the candidate scene demarcation points. Specifically, for the node N in the map path, i , project the trajectory line through a variety of preset projection methods to obtain node N i Multiple corresponding points C on the trajectory line j (N i ). Each projection method corresponds to a corresponding point, and the corresponding point includes the distance node N i The nearest trajectory point, node N i The projection point on the trajectory line, the intersection point of the straight line and the trajectory line, and the straight line passing through node N i and perpendicular to node N i The line of the associated map path link. It should be noted that there is no limit on the number of corresponding points and the selection method.
[0114] Specifically, for the starting point of the map path, the trajectory line is projected using a plurality of preset projection methods to determine a plurality of corresponding points on the trajectory line that match the starting point of the map path, wherein each projection method corresponds to a corresponding point. For the end point of the map path, the trajectory line is projected using a plurality of preset projection methods to determine a plurality of corresponding points on the trajectory line that match the end point of the map path, wherein each projection method corresponds to a corresponding point.
[0115] Step 208: determine the observation probability and transition probability of each corresponding point in turn.
[0116] Exemplarily, the electronic device calculates the observation probability of each corresponding point in turn. Specifically, ① calculate N i To the corresponding point C j (N i ) between i ,C j );②Calculate C j (N i ) o (C j |N i ):
[0117]
[0118] The electronic device calculates the transfer probability of each corresponding point in turn. Specifically, ① calculate the trajectory point C j (N i-1 ) to C k (N i ) on the trajectory line D(C j (N i-1 ),C k (N i ));②Compute nodes N i-1 To N i The path length D(N i-1 ,N i );③Calculate C k (N i ) t (C k (N i )|C j (N i-1 )):
[0119]
[0120] Step 209: Determine the trajectory interval on the trajectory line that matches the map path according to the observation probability and the transition probability of each corresponding point.
[0121] Exemplarily, for multiple corresponding points that match the starting point of the map path and multiple corresponding points that match the end point of the map path, the electronic device constructs the matched multiple corresponding points into a chain network along the map path link, and uses a preset Viterbi algorithm in the chain network to find the sequence with the highest probability. The corresponding points contained in the sequence with the highest probability are the optimal scene demarcation points, and the sequence with the highest probability is the trajectory interval on the trajectory line that matches the map path.
[0122] Step 210: The trajectory points also include trajectory points outside the outer geometric frame; and a newly added scene is determined based on the trajectory points outside the outer geometric frame.
[0123] In one example, step 210 includes: grouping trajectory points located outside the outer geometric box according to trajectory lines to obtain multiple groups of trajectories to be matched; determining the global positioning coordinate value of the trajectory point for each group of trajectory points to be matched, and determining multiple candidate trajectory paths of the trajectory point in the map topology map according to the global positioning coordinate value of the trajectory point; determining the observation probability and transition probability of each candidate trajectory path; if it is determined that the trajectory to be matched has no matching map path according to the observation probability and transition probability of the trajectory point in the trajectory to be matched, then determining the trajectory point in the trajectory to be matched as a newly added scene.
[0124] Exemplarily, the track points also include track points outside the outer geometric frame. The track points outside the outer geometric frame are unmatched track points, and it is necessary to further determine whether the track points are newly added scenes. The electronic device groups the unmatched track points based on track continuity to obtain multiple groups of tracks, and repeats steps S204 to S205 for each group of tracks. After execution, the track points that are still not matched to the map path link are considered newly added scenes.
[0125] For example, the track points on the trajectory line can be divided into three sections. Through path matching, it is determined that the middle section has a map path matching the trajectory line in the chain network. For the first section path and the tail end path at both ends, based on the trajectory continuity, the track points on the first section path are divided into the first group, and the track points on the tail end path are divided into the second group. Steps S204 to S205 are repeated for the first group and the second group respectively. After execution, the track points that are still not matched to the map path link are regarded as new scenes.
[0126] Step 211: Update the preset blank scene in the trajectory interval to scene information.
[0127] Exemplarily, the electronic device updates the preset blank scene of the track interval into the scene information.
[0128] In an embodiment of the present application, a trajectory line to be marked is obtained; wherein the trajectory line is a preset moving route collected when the mobile device moves in an actual scene, the trajectory line includes multiple trajectory points, and the trajectory line includes a preset trajectory collection area. The global positioning coordinate value of each trajectory point is determined. For each trajectory point, according to the global positioning coordinate value of the trajectory point, in the map topology corresponding to the trajectory collection area, multiple outer geometric boxes associated with the trajectory point are determined, and the directed edges corresponding to the associated outer geometric boxes are determined to be candidate trajectory paths. The observation probability and transition probability of each candidate trajectory path are determined. According to the observation probability and transition probability of each trajectory path, a map path matching the trajectory line is determined. The scene information of the map path is determined. The nodes in the map path are determined, and the corresponding points of the nodes on the trajectory line are determined; wherein the corresponding points are points obtained by projecting the nodes on the trajectory line by a preset projection method. The observation probability and transition probability of each corresponding point are determined in turn. According to the observation probability and transition probability of each corresponding point, the trajectory interval matching the map path located on the trajectory line is determined. The trajectory points also include trajectory points located outside the outer geometric frame; according to the trajectory points located outside the outer geometric frame, the newly added scene is determined. The preset blank scene of the trajectory interval is updated to the scene information. Therefore, multi-segment path matching can solve the matching omissions caused by the timeliness of the map, and the two-way matching between the trajectory line and the map topology can improve the scene annotation accuracy. In addition, the present application has high robustness and universality, and can be widely adapted to various map specification data and various scene roads, which greatly improves production efficiency and solves the technical problem of low scene annotation accuracy of the map.
[0129] In one example, Figure 3 A flowchart of another map processing method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, it includes: map topology construction; trajectory downsampling; trajectory matching map; node matching trajectory; determining trajectory scene.
[0130] Specifically, map topology construction refers to generating a map topology map; trajectory downsampling refers to downsampling the trajectory points on the trajectory line to obtain multiple downsampled trajectory points; trajectory matching map refers to matching the multiple downsampled trajectory points with the map topology map, and determining the map path that matches the trajectory line on the map topology map; node matching trajectory refers to projecting the trajectory line according to the map path, and determining the trajectory interval that matches the map path on the trajectory line; determining the trajectory scene refers to updating the preset blank scene of the trajectory interval to the scene information, so as to obtain the scene information of the trajectory interval.
[0131] Figure 4 A structural diagram of a map processing device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the device comprises:
[0132] The acquisition module 31 is used to acquire the trajectory line to be marked; wherein the trajectory line is a preset moving route collected when the mobile device moves in the actual scene, the trajectory line includes multiple trajectory points, and the trajectory line includes a preset trajectory collection area.
[0133] The matching module 32 is used to match multiple trajectory points on the trajectory line with a preset map topology according to the trajectory collection area, and determine a map path matching the trajectory line on the map topology; wherein the map topology represents a route map within an area corresponding to the trajectory collection area in a preset map library.
[0134] The first determination module 33 is used to determine the scene information of the map path.
[0135] The projection module 34 is used to project the trajectory line according to the map path, and determine the trajectory interval on the trajectory line that matches the map path.
[0136] The updating module 35 is used to update the preset blank scene of the track section into the scene information.
[0137] The device of this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principles are the same and will not be repeated here.
[0138] Figure 5 A schematic diagram of the structure of another map processing device provided in an embodiment of the present application, in Figure 4 Based on the embodiment shown, Figure 5 As shown, the preset map topology diagram includes directed edges, nodes, the relationship between directed edges and nodes, and an outer geometric frame where the directed edges are located; wherein the directed edges are determined based on the route data in the map library, and the nodes are determined based on the node data in the map library; the outer geometric frame is obtained by expanding the initial geometric frame where the directed edges are located.
[0139] In one example, the matching module 32 includes:
[0140] The first determining unit 321 is used to determine the global positioning coordinate value of each track point.
[0141] The second determining unit 322 is used to determine, for each trajectory point, multiple outer geometric boxes associated with the trajectory point in a map topology corresponding to the trajectory collection area according to the global positioning coordinate value of the trajectory point, and determine that all directed edges corresponding to the associated outer geometric boxes are candidate trajectory paths.
[0142] The third determining unit 323 is used to determine the observation probability and the transition probability of each candidate trajectory path.
[0143] The fourth determining unit 324 is used to determine a map path matching the trajectory line according to the observation probability and the transition probability of each trajectory path.
[0144] In one example, the projection module 34 includes:
[0145] The fifth determining unit 341 is used to determine the nodes in the map path and determine the corresponding points of the nodes on the trajectory line; wherein the corresponding points are points obtained by projecting the nodes on the trajectory line by a preset projection method.
[0146] The sixth determining unit 342 is used to determine the observation probability and the transition probability of each corresponding point in sequence.
[0147] The seventh determining unit 343 is used to determine the trajectory section on the trajectory line that matches the map path according to the observation probability and the transition probability of each corresponding point.
[0148] In one example, the trajectory points further include trajectory points located outside the outer geometric box; the device further includes:
[0149] The eighth determining unit 325 is used to determine a newly added scene according to the trajectory points located outside the outer geometric frame.
[0150] In one example, the eighth determining unit 325 includes:
[0151] The grouping subunit 3251 is used to group the trajectory points outside the outer geometric box according to the trajectory line to obtain multiple groups of trajectories to be matched.
[0152] The execution subunit 3252 is used to determine the global positioning coordinate value of the trajectory point for each group of trajectory points to be matched, and determine multiple candidate trajectory paths of the trajectory point in the map topology map according to the global positioning coordinate value of the trajectory point; determine the observation probability and transition probability of each candidate trajectory path.
[0153] The determination subunit 3253 is used to determine that the track point in the track to be matched is a newly added scene if it is determined that the track to be matched has no matching map path according to the observation probability and the transition probability of the track point in the track to be matched.
[0154] In one example, the device further includes:
[0155] The downsampling module 41 is used to select a plurality of downsampled trajectory points according to a preset interval, taking the first trajectory point in the trajectory line as a starting point.
[0156] The first determining unit 321 is specifically configured to:
[0157] Determine the global positioning coordinates of each downsampled trajectory point.
[0158] The device of this embodiment can execute the technical solution in the above method. Its specific implementation process and technical principles are the same and will not be repeated here.
[0159] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the electronic device includes: a memory 51 and a processor 52.
[0160] The memory 51 stores a computer program that can be executed on the processor 52 .
[0161] The processor 52 is configured to execute the method provided in the above embodiment.
[0162] The electronic device further includes a receiver 53 and a transmitter 54. The receiver 53 is used to receive instructions and data sent by an external device, and the transmitter 54 is used to send instructions and data to the external device.
[0163] Figure 7 This is a block diagram of an electronic device provided in an embodiment of the present application. The electronic device may be a mobile phone, a computer, a digital broadcast terminal, a message transceiver, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.
[0164] The device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output (I / O) interface 612 , a sensor component 614 , and a communication component 616 .
[0165] The processing component 602 generally controls the overall operation of the device 600, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.
[0166] The memory 604 is configured to store various types of data to support operations on the device 600. Examples of such data include instructions for any application or method operating on the device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 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.
[0167] The power supply component 606 provides power to the various components of the device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 600.
[0168] The multimedia component 608 includes a screen that provides an output interface between the device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
[0169] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the device 600 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.
[0170] I / O interface 612 provides an interface between processing component 602 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.
[0171] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the device 600. For example, the sensor assembly 614 can detect the open / closed state of the device 600, the relative positioning of components, such as the display and keypad of the device 600, the sensor assembly 614 can also detect the position change of the device 600 or a component of the device 600, the presence or absence of user contact with the device 600, the orientation or acceleration / deceleration of the device 600 and the temperature change of the device 600. The sensor assembly 614 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 614 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.
[0172] The communication component 616 is configured to facilitate wired or wireless communication between the device 600 and other devices. The device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.
[0173] In an exemplary embodiment, the apparatus 600 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.
[0174] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the instructions can be executed by the processor 620 of the device 600 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.
[0175] An embodiment of the present application also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the method provided by the above embodiment.
[0176] An embodiment of the present application also provides a computer program product, which includes: a computer program, which is stored in a readable storage medium, and at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.
[0177] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.
[0178] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A map processing method, characterized in that: include: Acquire a trajectory line to be marked; wherein the trajectory line is a preset moving route collected from a mobile device when it moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area; According to the trajectory collection area, a plurality of trajectory points on the trajectory line are matched with a preset map topology map, a map path matching the trajectory line is determined on the map topology map, and scene information of the map path is determined; wherein the map topology map represents a route map within an area corresponding to the trajectory collection area in a preset map library; The trajectory line is projected according to the map path, a trajectory section on the trajectory line that matches the map path is determined, and a preset blank scene of the trajectory section is updated as the scene information.
2. The method according to claim 1, characterized in that The preset map topology diagram includes directed edges, nodes, association relationships between the directed edges and the nodes, and an outer geometric frame where the directed edges are located; The directed edges are determined based on the route data in the map library, and the nodes are determined based on the node data in the map library; the outer geometric frame is obtained by expanding the initial geometric frame where the directed edges are located.
3. The method according to claim 2, characterized in that According to the trajectory collection area, matching the plurality of trajectory points on the trajectory line with a preset map topology map, and determining a map path matching the trajectory line on the map topology map, comprises: Determining the global positioning coordinates of each of the trajectory points; For each of the trajectory points, according to the global positioning coordinate value of the trajectory point, in the map topology corresponding to the trajectory collection area, a plurality of the outer geometric boxes associated with the trajectory point are determined, and the directed edges corresponding to the associated outer geometric boxes are determined to be candidate trajectory paths; Determining the observation probability and transition probability of each candidate trajectory path; According to the observation probability and the transition probability of each trajectory path, a map path matching the trajectory line is determined.
4. The method according to claim 3, characterized in that The projecting the trajectory line according to the map path to determine a trajectory section on the trajectory line that matches the map path includes: Determine a node in the map path, and determine a corresponding point of the node on the trajectory line; wherein the corresponding point is a point obtained by projecting the node on the trajectory line by a preset projection method; Determining the observation probability and the transition probability of each corresponding point in turn; According to the observation probability and the transition probability of each corresponding point, a trajectory interval on the trajectory line that matches the map path is determined.
5. The method according to claim 3, characterized in that: The trajectory points also include trajectory points located outside the outer geometric frame; The method further comprises: A newly added scene is determined according to the trajectory points outside the outer geometric frame.
6. The method according to claim 5, characterized in that The step of determining a new scene according to the trajectory points outside the outer geometric frame includes: According to the trajectory line, the trajectory points outside the outer geometric frame are grouped to obtain multiple groups of trajectories to be matched; For each track point in the set of to-be-matched tracks, determine the global positioning coordinate value of the track point, and determine multiple candidate track paths of the track point in the map topology map according to the global positioning coordinate value of the track point; determine the observation probability and transition probability of each candidate track path; If it is determined that the trajectory to be matched has no matching map path according to the observation probability and the transition probability of the trajectory point in the trajectory to be matched, then the trajectory point in the trajectory to be matched is determined to be a newly added scene.
7. The method according to any one of claims 3 to 6, characterized in that: The method further comprises: Taking the first trajectory point in the trajectory line as the starting point, selecting a plurality of downsampled trajectory points according to a preset spacing; Determining the global positioning coordinate value of each of the trajectory points includes: Determine the global positioning coordinate value of each downsampled trajectory point.
8. A map processing device, characterized in that: include: An acquisition module, used to acquire a trajectory line to be marked; wherein the trajectory line is a preset moving route collected from a mobile device when it moves in an actual scene, the trajectory line includes a plurality of trajectory points, and the trajectory line includes a preset trajectory collection area; A matching module, configured to match a plurality of track points on the track line with a preset map topology map according to the track collection area, and determine a map path matching the track line on the map topology map; wherein the map topology map represents a route map within an area corresponding to the track collection area in a preset map library; A first determination module, used to determine the scene information of the map path; A projection module, configured to project the trajectory line according to the map path, and determine a trajectory interval on the trajectory line that matches the map path; An updating module is used to update the preset blank scene of the trajectory interval to the scene information.
9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium / computer program product, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor; and / or, The computer program product comprises a computer program, which implements the method according to any one of claims 1 to 7 when executed by a processor.
Citation Information
Patent Citations
Vehicle GPS data map matching method based on hidden markov model
CN106595680A
GPS (Global Position System) spatio-temporal data increment road network real-time updating and trace matching system
CN106840176A
Improved hidden Markov model map matching method and device
CN114440900A
Method for navigating and positioning battery-replacing AGV (Automatic Guided Vehicle) by using multiple navigation devices
CN115342798A
Map drawing method and device and computer readable storage medium
CN117705081A
Cited By
Train operation control method and device and electronic equipment
CN120756554A
