Static map construction method and device, equipment, medium and product
By mapping the static points in the multi -frame point cloud data to the initial grid map and updating the grid point value, the problem of error -associated dynamic goals in existing technologies has been solved, and a more accurate static environment determination and dynamic target tracking performance are achieved. promote.
Patent Information
- Application Number
- CN202411370789.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2025-01-21
Smart Images
Figure CN119334334A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of map construction technology, and in particular to a static map construction method, device, equipment, medium and product. Background Art
[0002] Static point filtering of radar point clouds is of great significance in the fields of autonomous driving, robot navigation, intelligent monitoring, etc. It can improve positioning accuracy, avoid false alarms, and enhance user experience. In order to ensure the accuracy of static point filtering, a static map can be built first to determine the static surrounding environment. In the current map construction process, it is easy to mistakenly associate a stopped dynamic target or a low-speed sliding dynamic target with the static surrounding environment, which affects the recognition rate and tracking performance of the dynamic target. Summary of the invention
[0003] The present application provides a static map construction method, device, equipment, medium and product, aiming to effectively solve the above technical problems.
[0004] According to a first aspect of the present application, the present application provides a static map construction method, comprising:
[0005] A data acquisition step, acquiring multiple frames of point cloud data, and obtaining static point information from the point cloud data, wherein the static point information includes first position information of the static point in three-dimensional space;
[0006] a position conversion step, determining second position information of the static point on the initial grid map according to the first position information;
[0007] A map updating step, updating each grid point on the initial grid map according to the second position information to obtain a static map;
[0008] Among them, the initial grid map includes first grid points and second grid points, the update amplitude of the first grid points is greater than the update amplitude of the second grid points, the first grid points correspond to the second position information, and the initial grid map and the point cloud data are obtained based on the same area.
[0009] Furthermore, the map updating step includes:
[0010] Determine the type of the current grid point according to the second position information, where the type includes a first grid point and a second grid point;
[0011] In the case where the current grid point is the first grid point, adding a first update amount to the current grid point value to obtain an updated first grid point value;
[0012] When the current grid point is the second grid point, subtracting the second update amount from the current grid point value to obtain an updated second grid point value;
[0013] Among them, the first update amount is greater than the second update amount.
[0014] Furthermore, after the map updating step, the method further comprises:
[0015] The iterative step repeats the data acquisition step to the map updating step until a preset end condition is reached to obtain a final static map.
[0016] Furthermore, after the iteration step, the method further comprises:
[0017] Static environment points are determined according to the final static map and the grid threshold, and static environment filtering is performed on new point cloud data based on the static environment points.
[0018] Furthermore, the initial grid map is obtained by:
[0019] An initial grid map is determined according to a preset area, radar performance, and a preset resolution.
[0020] Further, the first position information includes a first horizontal coordinate and a first vertical coordinate, the preset resolution includes a horizontal resolution and a vertical resolution, and the initial grid map also includes a horizontal offset and a vertical offset;
[0021] The position conversion step comprises:
[0022] Convert the first lateral coordinate according to the lateral resolution and the lateral offset to obtain a second lateral coordinate;
[0023] The first longitudinal coordinate is transformed according to the longitudinal resolution and the longitudinal offset to obtain a second longitudinal coordinate, and the second position information includes the second transverse coordinate and the second longitudinal coordinate.
[0024] According to a second aspect of the present application, the present application further provides a static map construction device, the device comprising:
[0025] A data acquisition module, used to acquire multiple frames of point cloud data, and obtain static point information from the point cloud data, wherein the static point information includes first position information of the static point in three-dimensional space;
[0026] A position conversion module, used to determine second position information of the static point on the initial grid map according to the first position information;
[0027] A map updating module, configured to update each grid point on the initial grid map according to the second location information to obtain a static map;
[0028] Among them, the initial grid map includes first grid points and second grid points, the update amplitude of the first grid points is greater than the update amplitude of the second grid points, the first grid points correspond to the second position information, and the initial grid map and the point cloud data are obtained based on the same area.
[0029] According to a third aspect of the present application, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the methods described above when executing the program.
[0030] According to a fourth aspect of the present application, the present application further provides a storage medium, wherein a plurality of instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute the steps of the static map construction method as described above.
[0031] According to a fifth aspect of the present application, the present application also provides a computer program product, and when the program code contained in the computer program product is executed by a processor in an electronic device, the steps of the above-mentioned static map construction method are implemented.
[0032] Through one or more of the above embodiments in the present application, at least the following technical effects can be achieved: by mapping the static points accumulated in multiple frames to the initial grid map, and updating the grid point values according to the mapping position information (that is, the second position information), a static map is obtained, wherein the update amplitude of the grid point values corresponding to the static points is greater than the update amplitude of the grid point values corresponding to the non-static points, so that the grid point values corresponding to the flickering and unstable static points can still be slowly updated to widen the gap with the non-static points, which is more conducive to the determination of the static environment. After obtaining the final static map, the static points in the static environment can be better filtered out. When tracking a target running at a low speed or stopping, it can be associated with the correct static point of the target itself, and will not be mistakenly associated with the static point in the static environment, resulting in target position errors, etc. In addition, the static map in the present application can be quickly generated based on multi-frame point cloud data. In the case of an unknown environment or a change in the environment, a static map in the current environment is constructed in time, thereby improving efficiency and the adaptability of the construction. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] The technical solution and other beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.
[0034] Figure 1A flowchart of a static map construction method provided in an embodiment of the present application;
[0035] Figure 2 A schematic diagram of the structure of a static map construction device provided in an embodiment of the present application;
[0036] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0037] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0038] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally indicates that the associated objects before and after are in an "or" relationship.
[0039] The following is an introduction to a static map construction method, device, equipment, medium and product provided by the present application in conjunction with the accompanying drawings.
[0040] Figure 1 FIG. 1 is a flow chart of a static map construction method provided in an embodiment of the present application. Figure 1 As shown, a static map construction method includes the following steps:
[0041] In the data acquisition step S101, multiple frames of point cloud data are acquired, and static point information is obtained from the point cloud data.
[0042] The static point information includes first position information of the static point in three-dimensional space. The first position information is the three-dimensional coordinate information of the static point in three-dimensional space. The static point information may also include information such as the number of static points.
[0043] In this step, after scanning a certain area multiple times by radar, multiple frames of point cloud data are obtained, and static point detection is performed on the multiple frames of point cloud data to obtain static point information. In other words, the static points are obtained based on the detection of different frames of point cloud, which may include multiple static points with the same first position information but different acquisition times.
[0044] Illustratively, whether each point in the point cloud data is a static point or a dynamic point can be determined by a set threshold, or by analyzing the operation information of each category after clustering the points. It can also be determined whether it is a static point or a dynamic point based on the motion information of the previous and next frame points. This application does not impose any restrictions on this.
[0045] It should be noted that in this step, before obtaining the point cloud data, it is also necessary to obtain the initial grid map of the same area corresponding to the point cloud data. The initial grid map is generated based on predefined map size, resolution, grid point initial value and other information.
[0046] The position conversion step S102 is to determine the second position information of the static point on the initial grid map according to the first position information.
[0047] In this step, the three-dimensional static point is mapped to the two-dimensional initial grid map to obtain the position information of the static point mapped on the initial grid map, that is, the second position information is the two-dimensional position information of the static point on the initial grid map, which includes the horizontal coordinate and the vertical coordinate.
[0048] In a map updating step S103, each grid point on the initial grid map is updated according to the second position information to obtain a static map.
[0049] The initial grid map includes a first grid point and a second grid point, the update amplitude of the first grid point is greater than the update amplitude of the second grid point, and the first grid point corresponds to the second position information. The static map is generated based on the above static points, and the static environment is determined by the static map, so as to facilitate subsequent target identification, target tracking and positioning, etc. The grid point with a higher value in the static map can be considered as a static environment, and the grid point with a lower value is a non-static environment. The static environment is filtered out using the static points with a higher grid point value to ensure the accuracy of target positioning, identification, tracking, etc.
[0050] In this step, it is determined whether the current grid point is the first grid point or the second grid point according to the second position information. After determining the type of the current grid point, the value of the current grid point is updated according to the point value update method of the first grid point or the second grid point. After all grid points are updated, a static map is obtained. Compared with the initial grid map, the values of each grid point in the updated static map change. The size difference between the grid point values can show which areas are static environments. Among them, the update amplitude of the first grid point value is greater than the update amplitude of the second grid point value.
[0051] Specifically, if the current grid point is the first grid point corresponding to the static point, the update can be an increase of 10% based on the value of the current grid point. If the current grid point is the second grid point (that is, a grid point that does not correspond to the static point), the update can be a decrease of 5% based on the value of the current grid point, thereby obtaining an updated grid point value.
[0052] During the static environment detection process, static points may flicker unstably. For example, point A is determined as a static point in the first frame, but is determined as a non-static point in the second frame. In order to ensure that these unstable and flickering static points can be finally determined as static environments, the static points in the multi-frame point cloud data are accumulated in the following way:
[0053] When point A is determined as a static point in the first frame, the grid point value corresponding to point A increases by 10%. When point A is determined as a non-static point in the second frame, the grid point value corresponding to point A continues to decrease by 5%. When point A is further determined as a static point in the third frame, the grid point value corresponding to point A continues to increase by 10%, thereby accumulating the grid point values of multiple frames of point A. In this way, the grid point value corresponding to the unstable and flickering static point A can still be slowly accumulated, and the accumulated value can still be well distinguished from the grid point value of the non-static point, so as to determine the static environment according to the final grid point value.
[0054] The static map construction method provided by the embodiment of the present application maps the static points accumulated in multiple frames to the initial grid map, and updates the grid point values according to the mapping position information (that is, the second position information), thereby obtaining a static map, wherein the update amplitude of the grid point values corresponding to the static points is greater than the update amplitude of the grid point values corresponding to the non-static points, so that the grid point values corresponding to the flickering and unstable static points can still be slowly updated to widen the gap with the non-static points, which is more conducive to the determination of the static environment. After obtaining the final static map, the static points in the static environment can be better filtered out. When tracking a target running at a low speed or stopping, it can be associated with the correct static point of the target itself, and will not be mistakenly associated with the static point in the static environment, resulting in target position errors, etc. In addition, the static map in the present application can be quickly generated based on multi-frame point cloud data, and it can timely construct and obtain a static map in the current environment in an unknown environment or when the environment changes, thereby improving efficiency and the adaptability of the construction.
[0055] In some embodiments of the present application, the map updating step includes:
[0056] The type of the current grid point is determined according to the second position information, wherein the type includes a first grid point and a second grid point. That is, if the current grid point is a mapping point of a static point on an initial grid map, then the current grid point is a first grid point; if the current grid point is not a mapping point of a static point on an initial grid map, then the current grid point is a second grid point.
[0057] When the current grid point is the first grid point, the first update amount is added to the current grid point value to obtain the updated first grid point value, that is, the first update amount is added to the original first grid point value to obtain the updated first grid point value.
[0058] When the current grid point is the second grid point, the second update amount is subtracted from the current grid point value to obtain the updated second grid point value, that is, the second update amount is subtracted from the original second grid point value to obtain the updated second grid point value.
[0059] Among them, the first update amount is greater than the second update amount.
[0060] Schematically, the second position information of the static point is (xindex, yindex), where xindex is the second horizontal coordinate and yindex is the second vertical coordinate. On this basis, the update of the grid point value can be:
[0061] First grid point: map(xindex,yindex)=map(xindex,yindex)+m, where m is the first update amount, and map(xindex,yindex) refers to the grid point value corresponding to the second position information, that is, the first grid point value.
[0062] The second grid point: map(~xindex,~yindex)=map(~xindex,~yindex)-n, n is the second update amount, m>n, ~xindex is the horizontal coordinate of the non-static point, ~yindex is the vertical coordinate of the non-static point, map(~xindex,~yindex) refers to the grid point value corresponding to the position of the non-static point, that is, the second grid point value.
[0063] Among them, the first update amount m and the second update amount n are set according to experience, repeated test results, the area of the initial grid map, etc. When the static map includes static environmental information such as isolation belts, guardrails, green belts, etc., m can be set to 2 and n can be set to 1. In other embodiments of the present application, they can also be set to other values, which are not limited to this.
[0064] The static map construction method provided in the embodiment of the present application updates the grid point values of the static points accumulated in multiple frames through the first update amount and the second update amount to ensure that the grid point values corresponding to the unstable and flickering static points can still be slowly updated, and the gap with the non-static points is continuously widened, which makes it easier to determine the static environment according to the final grid point values in the final static map. In the process of target positioning and tracking, the static points in the static environment can be better filtered out to ensure that low-speed running or tentative targets will not be associated with the static environment, thereby improving the accuracy of target positioning and tracking.
[0065] In some embodiments of the present application, after the map updating step S013, the method further includes:
[0066] Iteration step S104, repeating the data acquisition step to the map update step until a preset end condition is reached to obtain a final static map.
[0067] In this embodiment, in order to improve the robustness of the static map, the above-mentioned data acquisition step S101 to the map update step S103 can be repeated to scan the same area multiple times and update the grid point values, so that the gap between the first grid point value and the second grid point value becomes larger and larger, making the grid points corresponding to the static environment more and more stable.
[0068] It should be noted that the preset end condition may be a preset number of iterations, a preset execution time, or a performance evaluation result of a static map, etc., and there is no limitation on this.
[0069] In some embodiments of the present application, after the iterative step S104, the method further includes:
[0070] S105, determining static environment points according to the final static map and the grid threshold, and performing static environment filtering on the new point cloud data based on the static environment points.
[0071] In this step, the grid point values in the final static map are compared according to the preset grid threshold, and the grid points corresponding to the grid point values greater than the grid threshold are used as static environment points. The locations of all static environment points are the static environment areas. When the radar acquires new point cloud data, the static points can be filtered out through these determined static environment points in the static map, so that the static points corresponding to the slow-running or paused targets can be retained, so that the target will not be associated with the static environment, thereby improving the accuracy of target positioning and tracking.
[0072] Specifically, after acquiring new point cloud data through radar, the new point cloud data is aligned with the final static map. Based on the aligned static map, the points in the point cloud data corresponding to the static environment points are filtered out as static environment areas. The retained points can include points corresponding to slow-moving or paused targets, thereby avoiding the mistaken association of such slow-moving or paused targets with the static environment, and especially improving the accuracy of positioning and tracking of slow-moving or paused targets.
[0073] It should be noted that the current processing methods for static points include:
[0074] 1. All static detection points obtained by signal processing are filtered out to avoid the influence of the static environment on the accuracy of subsequent target positioning and tracking. However, for targets that have stopped or are gliding at low speed, it is impossible to effectively use their static points to continuously track the target and keep it in the correct position.
[0075] 2. Do not adopt the strategy of filtering out all static detection points. All static points are retained to achieve the effect of continuous tracking of the target using static points. However, this method has the problem that when the target is close to a static environment (such as guardrails, green belts, etc.) and is driving at a low speed or stops, there is no way to set a good association threshold so that the target is not associated with static detection points such as guardrails. In other words, this will cause the target to be associated with static environments such as guardrails, thereby causing subsequent applications such as target tracking and positioning to deviate from its true driving trajectory, and even form false targets such as retention.
[0076] In response to the problems existing in the above-mentioned static point processing process, this application first constructs a static map, and then uses the static map to filter out static points related to the static environment, so as to prevent the static points of the target from being associated with the static environment, and improve the accuracy of target tracking and positioning. Among them, the static map is formed by continuously updating the grid point values after raster mapping of the accumulated multi-frame static points, ensuring that the flickering and unstable static points can also be updated slowly.
[0077] In some embodiments of the present application, the initial grid map is obtained by:
[0078] An initial grid map is determined according to a preset area, radar performance, and a preset resolution.
[0079] That is to say, the size of the initial grid map is determined according to the area where the grid map is applied, the radar performance, the preset resolution and other information. Schematically, the horizontal range of the initial grid map is determined according to the area where the grid map is applied, the vertical range of the initial grid map is determined according to the radar performance (i.e., the range that the radar can scan), and then the size of the initial grid map is determined according to the preset horizontal resolution and vertical resolution. And a preset value is assigned to each grid point in the initial grid map, so as to finally obtain the initialized grid map. The grid points in the initial grid map can be uniformly assigned 0 or other values, which are not limited.
[0080] In some embodiments of the present application, the first position information includes a first horizontal coordinate x and a first vertical coordinate y, the preset resolution includes a horizontal resolution and a vertical resolution, and the initial grid map also includes a horizontal offset and a vertical offset;
[0081] The position conversion step comprises:
[0082] The first horizontal coordinate is transformed according to the horizontal resolution and the horizontal offset to obtain a second horizontal coordinate xindex.
[0083] The first longitudinal coordinate is transformed according to the longitudinal resolution and the longitudinal offset to obtain a second longitudinal coordinate, and the second position information includes the second transverse coordinate and the second longitudinal coordinate yindex.
[0084] Specifically, xindex=x / horizontal resolution-horizontal offset+1; yindex=y / vertical resolution-vertical offset+1.
[0085] In another embodiment of the present application, the static map construction method includes the following steps:
[0086] S201, initializing the grid map.
[0087] Schematically, taking the focus range of -25 to 25 m horizontally and 0 to 300 m vertically as an example, the horizontal resolution is set to 1 m, and the vertical resolution is 1 m, then a 50*300 grid map can be initialized, recorded as map(50,100), with a horizontal offset of -25 and a vertical offset of 0.
[0088] S202, performing static point detection on the multi-frame point cloud data to obtain static points.
[0089] Schematically, 5 to 10 frames of point cloud data can be selected for static point detection to obtain accumulated static point data pointdata(N,3), where N is the number of accumulated static points, and each static point contains (x, y, z) position information.
[0090] It should be noted that there is no fixed order for S201 and S202 and they can be executed simultaneously.
[0091] S203, for each static point in the static point data pointdata, find its corresponding position (xindex, yindex) in the initial grid map, and update each grid point in the initial grid map according to the found position (xindex, yindex) to obtain an updated static map.
[0092] It should be noted that in order to save calculation amount, upper and lower limits of the update are set for the grid point values, that is, the minimum grid point value after update cannot be less than the lowest threshold, and the maximum cannot be greater than the highest threshold. Schematically, the lowest threshold can be set to 0, the highest threshold is set to 100, the first update amount is set to 2, and the second update amount is set to 1.
[0093] S204, repeat the above S202 to S203 to reach a preset number of iterations or a preset time, so as to finally obtain a more robust static map. The final static map is traversed, and the position where the value > thr at map (xindex, yindex) is considered to be a static environment. thr is the grid threshold, which can be set according to needs, experience, etc., and it represents the robustness of the map here. After determining the static environment, the static points of the static environment can be filtered out from the point cloud data obtained by subsequent scanning, thereby improving the accuracy of subsequent target positioning and tracking.
[0094] Illustratively, the preset number of iterations may be 200-500, the preset time may be 3 minutes, and the grid threshold thr may range from 70 to 90.
[0095] It should be noted that the static map construction method provided in this application can perform adaptive background modeling on the map at any time. No matter what external changes occur in the current environment, it can be updated in real time, thereby improving the accuracy of static point filtering and the applicability of the map. The static map has good accuracy.
[0096] On the other hand, the present application also provides a static map construction device, such as Figure 2 As shown, the device comprises:
[0097] The data acquisition module 210 is used to acquire multiple frames of point cloud data and obtain static point information from the point cloud data, where the static point information includes first position information of the static point in three-dimensional space.
[0098] The position conversion module 220 is used to determine the second position information of the static point on the initial grid map according to the first position information.
[0099] The map updating module 230 is used to update each grid point on the initial grid map according to the second position information to obtain a static map.
[0100] Among them, the initial grid map includes a first grid point and a second grid point, the first grid point corresponds to the second position information, the update amplitude of the first grid point is greater than the update amplitude of the second grid point, and the initial grid map and the point cloud data are obtained based on the same area.
[0101] It should be noted that the static map construction device corresponds to the above-mentioned static map construction method, which will not be described in detail here.
[0102] On the other hand, Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310 (processor), a communication interface 320 (Communications Interface), a memory 330 (memory) and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the static map construction method provided above, the method comprising: a data acquisition step, acquiring multiple frames of point cloud data, and obtaining static point information from the point cloud data, the static point information including the first position information of the static point in three-dimensional space; a position conversion step, determining the second position information of the static point on the initial grid map according to the first position information; a map update step, updating each grid point on the initial grid map according to the second position information to obtain a static map; wherein the initial grid map includes a first grid point and a second grid point, the update amplitude of the first grid point is greater than the update amplitude of the second grid point, the first grid point corresponds to the second position information, and the initial grid map and the point cloud data are obtained based on the same area.
[0103] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0104] On the other hand, an embodiment of the present application further provides a storage medium on which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor to execute the static map construction method provided in the above embodiments.
[0105] In addition, the logic instructions in the above-mentioned storage medium can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.
[0106] On the other hand, an embodiment of the present application further provides a computer program product, and when the program code contained in the computer program product is executed by a processor in an electronic device, the static map construction method provided in the above embodiments is implemented.
[0107] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0108] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0109] In summary, although the present application has been disclosed as above with preferred embodiments, the above preferred embodiments are not intended to limit the present application. Ordinary technicians in this field can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined in the claims.
Claims
1. A static map construction method, characterized in that: include: A data acquisition step, acquiring multiple frames of point cloud data, and obtaining static point information from the point cloud data, wherein the static point information includes first position information of the static point in three-dimensional space; a position conversion step, determining second position information of the static point on the initial grid map according to the first position information; A map updating step, updating each grid point on the initial grid map according to the second position information to obtain a static map; Among them, the initial grid map includes a first grid point and a second grid point, the first grid point corresponds to the second position information, the update amplitude of the first grid point is greater than the update amplitude of the second grid point, and the initial grid map and the point cloud data are obtained based on the same area.
2. The method according to claim 1, characterized in that The map updating step comprises: Determine the type of the current grid point according to the second position information, where the type includes a first grid point and a second grid point; In the case where the current grid point is the first grid point, adding a first update amount to the current grid point value to obtain an updated first grid point value; When the current grid point is the second grid point, subtracting the second update amount from the current grid point value to obtain an updated second grid point value; Among them, the first update amount is greater than the second update amount.
3. The method according to claim 2, characterized in that After the map updating step, the method further comprises: The iterative step repeats the data acquisition step to the map updating step until a preset end condition is reached to obtain a final static map.
4. The method according to claim 3, characterized in that After the iterating step, the method further comprises: Static environment points are determined according to the final static map and the grid threshold, and static environment filtering is performed on new point cloud data based on the static environment points.
5. The method according to claim 1, characterized in that The initial grid map is obtained by: An initial grid map is determined according to a preset area, radar performance, and a preset resolution.
6. The method according to claim 5, characterized in that The first position information includes a first horizontal coordinate and a first vertical coordinate, the preset resolution includes a horizontal resolution and a vertical resolution, and the initial grid map also includes a horizontal offset and a vertical offset; The position conversion step comprises: Convert the first lateral coordinate according to the lateral resolution and the lateral offset to obtain a second lateral coordinate; The first longitudinal coordinate is transformed according to the longitudinal resolution and the longitudinal offset to obtain a second longitudinal coordinate, and the second position information includes the second transverse coordinate and the second longitudinal coordinate.
7. A static map construction device, characterized in that: The device comprises: A data acquisition module, used to acquire multiple frames of point cloud data, and obtain static point information from the point cloud data, wherein the static point information includes first position information of the static point in three-dimensional space; A position conversion module, used to determine second position information of the static point on the initial grid map according to the first position information; A map updating module, configured to update each grid point on the initial grid map according to the second location information to obtain a static map; Among them, the initial grid map includes first grid points and second grid points, the update amplitude of the first grid points is greater than the update amplitude of the second grid points, the first grid points correspond to the second position information, and the initial grid map and the point cloud data are obtained based on the same area.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A storage medium, characterized in that: The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps of the method according to any one of claims 1 to 6.
10. A computer program product, characterized in that When the program code contained in the computer program product is executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 6 are implemented.